ianmilligan1 · January 30, 2018 20:58
diff --git a/big-error-log-domains.log b/big-error-log-domains.log
 2018-01-30 16:49:07,894 [main] WARN  NativeCodeLoader - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
 2018-01-30 16:49:07,963 [main] WARN  Utils - Your hostname, indexer resolves to a loopback address: 127.0.0.1; using 192.168.32.19 instead (on interface ens3)
 2018-01-30 16:49:07,963 [main] WARN  Utils - Set SPARK_LOCAL_IP if you need to bind to another address
 2018-01-30 16:49:13,243 [main] WARN  ObjectStore - Failed to get database global_temp, returning NoSuchObjectException
 Spark context Web UI available at http://192.168.32.19:4040
 Spark context available as 'sc' (master = local[12], app id = local-1517330948464).
 Spark session available as 'spark'.
 Loading university-of-alberta-websites.scala...
 import io.archivesunleashed.spark.matchbox.{ExtractDomain, ExtractLinks, RemoveHTML, RecordLoader, WriteGEXF}
 import io.archivesunleashed.spark.rdd.RecordRDD._
 2018-01-30 16:49:15,341 [main] INFO  MemoryStore - Block broadcast_0 stored as values in memory (estimated size 265.5 KB, free 47.8 GB)
 2018-01-30 16:49:15,379 [main] INFO  MemoryStore - Block broadcast_0_piece0 stored as bytes in memory (estimated size 20.2 KB, free 47.8 GB)
 2018-01-30 16:49:15,381 [dispatcher-event-loop-12] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 16:49:15,384 [main] INFO  SparkContext - Created broadcast 0 from newAPIHadoopFile at RecordLoader.scala:34
 2018-01-30 16:49:15,564 [main] INFO  FileInputFormat - Total input paths to process : 3618
 2018-01-30 16:49:15,713 [main] INFO  SparkContext - Starting job: sortBy at RecordRDD.scala:40
 2018-01-30 16:49:15,949 [dag-scheduler-event-loop] INFO  DAGScheduler - Registering RDD 6 (map at RecordRDD.scala:38)
 2018-01-30 16:49:15,952 [dag-scheduler-event-loop] INFO  DAGScheduler - Got job 0 (sortBy at RecordRDD.scala:40) with 3618 output partitions
 2018-01-30 16:49:15,952 [dag-scheduler-event-loop] INFO  DAGScheduler - Final stage: ResultStage 1 (sortBy at RecordRDD.scala:40)
 2018-01-30 16:49:15,952 [dag-scheduler-event-loop] INFO  DAGScheduler - Parents of final stage: List(ShuffleMapStage 0)
 2018-01-30 16:49:15,955 [dag-scheduler-event-loop] INFO  DAGScheduler - Missing parents: List(ShuffleMapStage 0)
 2018-01-30 16:49:15,960 [dag-scheduler-event-loop] INFO  DAGScheduler - Submitting ShuffleMapStage 0 (MapPartitionsRDD[6] at map at RecordRDD.scala:38), which has no missing parents
 2018-01-30 16:49:16,046 [dag-scheduler-event-loop] INFO  MemoryStore - Block broadcast_1 stored as values in memory (estimated size 5.0 KB, free 47.8 GB)
 2018-01-30 16:49:16,050 [dag-scheduler-event-loop] INFO  MemoryStore - Block broadcast_1_piece0 stored as bytes in memory (estimated size 2.9 KB, free 47.8 GB)
 2018-01-30 16:49:16,050 [dispatcher-event-loop-13] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 16:49:16,059 [dag-scheduler-event-loop] INFO  SparkContext - Created broadcast 1 from broadcast at DAGScheduler.scala:996
 2018-01-30 16:49:16,071 [dag-scheduler-event-loop] INFO  DAGScheduler - Submitting 3618 missing tasks from ShuffleMapStage 0 (MapPartitionsRDD[6] at map at RecordRDD.scala:38)
 2018-01-30 16:49:16,075 [dag-scheduler-event-loop] INFO  TaskSchedulerImpl - Adding task set 0.0 with 3618 tasks
 2018-01-30 16:49:16,129 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 0.0 in stage 0.0 (TID 0, localhost, executor driver, partition 0, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,133 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 1.0 in stage 0.0 (TID 1, localhost, executor driver, partition 1, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,135 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 2.0 in stage 0.0 (TID 2, localhost, executor driver, partition 2, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,136 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 3.0 in stage 0.0 (TID 3, localhost, executor driver, partition 3, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:49:16,138 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 4.0 in stage 0.0 (TID 4, localhost, executor driver, partition 4, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,139 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 5.0 in stage 0.0 (TID 5, localhost, executor driver, partition 5, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:49:16,140 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 6.0 in stage 0.0 (TID 6, localhost, executor driver, partition 6, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,141 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 7.0 in stage 0.0 (TID 7, localhost, executor driver, partition 7, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,142 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 8.0 in stage 0.0 (TID 8, localhost, executor driver, partition 8, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:49:16,142 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 9.0 in stage 0.0 (TID 9, localhost, executor driver, partition 9, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 16:49:16,144 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 10.0 in stage 0.0 (TID 10, localhost, executor driver, partition 10, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:49:16,147 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 11.0 in stage 0.0 (TID 11, localhost, executor driver, partition 11, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:16,153 [Executor task launch worker for task 1] INFO  Executor - Running task 1.0 in stage 0.0 (TID 1)
 2018-01-30 16:49:16,153 [Executor task launch worker for task 0] INFO  Executor - Running task 0.0 in stage 0.0 (TID 0)
 2018-01-30 16:49:16,156 [Executor task launch worker for task 6] INFO  Executor - Running task 6.0 in stage 0.0 (TID 6)
 2018-01-30 16:49:16,158 [Executor task launch worker for task 4] INFO  Executor - Running task 4.0 in stage 0.0 (TID 4)
 2018-01-30 16:49:16,158 [Executor task launch worker for task 7] INFO  Executor - Running task 7.0 in stage 0.0 (TID 7)
 2018-01-30 16:49:16,157 [Executor task launch worker for task 5] INFO  Executor - Running task 5.0 in stage 0.0 (TID 5)
 2018-01-30 16:49:16,160 [Executor task launch worker for task 9] INFO  Executor - Running task 9.0 in stage 0.0 (TID 9)
 2018-01-30 16:49:16,162 [Executor task launch worker for task 2] INFO  Executor - Running task 2.0 in stage 0.0 (TID 2)
 2018-01-30 16:49:16,156 [Executor task launch worker for task 3] INFO  Executor - Running task 3.0 in stage 0.0 (TID 3)
 2018-01-30 16:49:16,164 [Executor task launch worker for task 11] INFO  Executor - Running task 11.0 in stage 0.0 (TID 11)
 2018-01-30 16:49:16,167 [Executor task launch worker for task 8] INFO  Executor - Running task 8.0 in stage 0.0 (TID 8)
 2018-01-30 16:49:16,169 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.mojo_animal-sniffer-annotations-1.14.jar with timestamp 1517330948447
 2018-01-30 16:49:16,168 [Executor task launch worker for task 10] INFO  Executor - Running task 10.0 in stage 0.0 (TID 10)
 2018-01-30 16:49:16,533 [Executor task launch worker for task 4] INFO  TransportClientFactory - Successfully created connection to /192.168.32.19:46742 after 24 ms (0 ms spent in bootstraps)
 2018-01-30 16:49:16,539 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.mojo_animal-sniffer-annotations-1.14.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4448432180235018762.tmp
 2018-01-30 16:49:16,586 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.mojo_animal-sniffer-annotations-1.14.jar to class loader
 2018-01-30 16:49:16,586 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scalanlp_breeze-macros_2.11-0.13.1.jar with timestamp 1517330948446
 2018-01-30 16:49:16,587 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scalanlp_breeze-macros_2.11-0.13.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2735297956622596792.tmp
 2018-01-30 16:49:16,605 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scalanlp_breeze-macros_2.11-0.13.1.jar to class loader
 2018-01-30 16:49:16,605 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.sourceforge.jmatio_jmatio-1.0.jar with timestamp 1517330948447
 2018-01-30 16:49:16,605 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.sourceforge.jmatio_jmatio-1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5205947465234484253.tmp
 2018-01-30 16:49:16,627 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.sourceforge.jmatio_jmatio-1.0.jar to class loader
 2018-01-30 16:49:16,627 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/javax.xml.bind_jaxb-api-2.2.7.jar with timestamp 1517330948447
 2018-01-30 16:49:16,627 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/javax.xml.bind_jaxb-api-2.2.7.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1955806234824652418.tmp
 2018-01-30 16:49:16,642 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/javax.xml.bind_jaxb-api-2.2.7.jar to class loader
 2018-01-30 16:49:16,642 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-exec-1.3.jar with timestamp 1517330948448
 2018-01-30 16:49:16,642 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-exec-1.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3009028011953304733.tmp
 2018-01-30 16:49:16,657 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-exec-1.3.jar to class loader
 2018-01-30 16:49:16,657 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scala-lang.modules_scala-xml_2.11-1.0.6.jar with timestamp 1517330948446
 2018-01-30 16:49:16,658 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scala-lang.modules_scala-xml_2.11-1.0.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4440173939055355140.tmp
 2018-01-30 16:49:16,706 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scala-lang.modules_scala-xml_2.11-1.0.6.jar to class loader
 2018-01-30 16:49:16,706 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-core_2.11-3.5.1.jar with timestamp 1517330948446
 2018-01-30 16:49:16,707 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-core_2.11-3.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3407686680056679177.tmp
 2018-01-30 16:49:16,739 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.json4s_json4s-core_2.11-3.5.1.jar to class loader
 2018-01-30 16:49:16,739 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.esotericsoftware_minlog-1.3.0.jar with timestamp 1517330948446
 2018-01-30 16:49:16,739 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.esotericsoftware_minlog-1.3.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5728760172715009475.tmp
 2018-01-30 16:49:16,743 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.esotericsoftware_minlog-1.3.0.jar to class loader
 2018-01-30 16:49:16,743 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-logging_commons-logging-api-1.1.jar with timestamp 1517330948448
 2018-01-30 16:49:16,743 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-logging_commons-logging-api-1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3813956053877948962.tmp
 2018-01-30 16:49:16,756 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-logging_commons-logging-api-1.1.jar to class loader
 2018-01-30 16:49:16,756 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.woodstox_stax2-api-3.1.4.jar with timestamp 1517330948449
 2018-01-30 16:49:16,756 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.woodstox_stax2-api-3.1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7066523785304803669.tmp
 2018-01-30 16:49:16,778 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.woodstox_stax2-api-3.1.4.jar to class loader
 2018-01-30 16:49:16,778 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-utility-0.5.jar with timestamp 1517330948448
 2018-01-30 16:49:16,778 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-utility-0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4296666123593225488.tmp
 2018-01-30 16:49:16,784 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.sis.core_sis-utility-0.5.jar to class loader
 2018-01-30 16:49:16,784 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.healthmarketscience.jackcess_jackcess-2.1.2.jar with timestamp 1517330948447
 2018-01-30 16:49:16,785 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.healthmarketscience.jackcess_jackcess-2.1.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1168638258375664443.tmp
 2018-01-30 16:49:16,790 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.healthmarketscience.jackcess_jackcess-2.1.2.jar to class loader
 2018-01-30 16:49:16,790 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/xalan_xalan-2.7.0.jar with timestamp 1517330948447
 2018-01-30 16:49:16,791 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/xalan_xalan-2.7.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3307953662768685247.tmp
 2018-01-30 16:49:16,838 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/xalan_xalan-2.7.0.jar to class loader
 2018-01-30 16:49:16,838 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-transports-http-3.0.3.jar with timestamp 1517330948449
 2018-01-30 16:49:16,838 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-transports-http-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5085909106112740362.tmp
 2018-01-30 16:49:16,851 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.cxf_cxf-rt-transports-http-3.0.3.jar to class loader
 2018-01-30 16:49:16,851 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.pff_java-libpst-0.8.1.jar with timestamp 1517330948448
 2018-01-30 16:49:16,851 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.pff_java-libpst-0.8.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1238296323462672585.tmp
 2018-01-30 16:49:16,859 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.pff_java-libpst-0.8.1.jar to class loader
 2018-01-30 16:49:16,859 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_grib-4.5.5.jar with timestamp 1517330948448
 2018-01-30 16:49:16,859 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_grib-4.5.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp741118377061281051.tmp
 2018-01-30 16:49:16,959 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_grib-4.5.5.jar to class loader
 2018-01-30 16:49:16,959 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.netpreserve.commons_webarchive-commons-1.1.8.jar with timestamp 1517330948445
 2018-01-30 16:49:16,960 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.netpreserve.commons_webarchive-commons-1.1.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp198893629467860972.tmp
 2018-01-30 16:49:16,986 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.netpreserve.commons_webarchive-commons-1.1.8.jar to class loader
 2018-01-30 16:49:16,986 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-core-4.10.3.jar with timestamp 1517330948447
 2018-01-30 16:49:16,986 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-core-4.10.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8596592399833409256.tmp
 2018-01-30 16:49:17,024 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.lucene_lucene-core-4.10.3.jar to class loader
 2018-01-30 16:49:17,024 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.james_apache-mime4j-dom-0.7.2.jar with timestamp 1517330948447
 2018-01-30 16:49:17,024 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.james_apache-mime4j-dom-0.7.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8938864358290651010.tmp
 2018-01-30 16:49:17,028 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.james_apache-mime4j-dom-0.7.2.jar to class loader
 2018-01-30 16:49:17,028 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.quartz-scheduler_quartz-2.2.0.jar with timestamp 1517330948449
 2018-01-30 16:49:17,029 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.quartz-scheduler_quartz-2.2.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5245227064180928254.tmp
 2018-01-30 16:49:17,051 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.quartz-scheduler_quartz-2.2.0.jar to class loader
 2018-01-30 16:49:17,051 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-queryparser-4.10.3.jar with timestamp 1517330948447
 2018-01-30 16:49:17,052 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-queryparser-4.10.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4434926559106286716.tmp
 2018-01-30 16:49:17,062 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.lucene_lucene-queryparser-4.10.3.jar to class loader
 2018-01-30 16:49:17,062 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-lang_commons-lang-2.5.jar with timestamp 1517330948447
 2018-01-30 16:49:17,063 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-lang_commons-lang-2.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7331476499143520104.tmp
 2018-01-30 16:49:17,074 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-lang_commons-lang-2.5.jar to class loader
 2018-01-30 16:49:17,074 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.github.fommil.netlib_core-1.1.2.jar with timestamp 1517330948446
 2018-01-30 16:49:17,074 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.github.fommil.netlib_core-1.1.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1312839095565007212.tmp
 2018-01-30 16:49:17,079 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.github.fommil.netlib_core-1.1.2.jar to class loader
 2018-01-30 16:49:17,079 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.rometools_rome-1.5.1.jar with timestamp 1517330948448
 2018-01-30 16:49:17,079 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.rometools_rome-1.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp288917754214781785.tmp
 2018-01-30 16:49:17,089 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.rometools_rome-1.5.1.jar to class loader
 2018-01-30 16:49:17,089 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.module_jackson-module-paranamer-2.8.8.jar with timestamp 1517330948446
 2018-01-30 16:49:17,090 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.module_jackson-module-paranamer-2.8.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp9199539086151899857.tmp
 2018-01-30 16:49:17,093 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.fasterxml.jackson.module_jackson-module-paranamer-2.8.8.jar to class loader
 2018-01-30 16:49:17,093 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.typelevel_machinist_2.11-0.6.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,093 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.typelevel_machinist_2.11-0.6.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp650929254218359577.tmp
 2018-01-30 16:49:17,106 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.typelevel_machinist_2.11-0.6.1.jar to class loader
 2018-01-30 16:49:17,106 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.woodstox_woodstox-core-asl-4.4.1.jar with timestamp 1517330948449
 2018-01-30 16:49:17,106 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.woodstox_woodstox-core-asl-4.4.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6361613612741744857.tmp
 2018-01-30 16:49:17,120 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.woodstox_woodstox-core-asl-4.4.1.jar to class loader
 2018-01-30 16:49:17,121 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.glassfish_javax.json-1.0.4.jar with timestamp 1517330948447
 2018-01-30 16:49:17,121 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.glassfish_javax.json-1.0.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2600178285853315861.tmp
 2018-01-30 16:49:17,125 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.glassfish_javax.json-1.0.4.jar to class loader
 2018-01-30 16:49:17,125 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-metadata-0.5.jar with timestamp 1517330948448
 2018-01-30 16:49:17,126 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-metadata-0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8527160983900484863.tmp
 2018-01-30 16:49:17,142 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.sis.core_sis-metadata-0.5.jar to class loader
 2018-01-30 16:49:17,142 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.ccil.cowan.tagsoup_tagsoup-1.2.1.jar with timestamp 1517330948448
 2018-01-30 16:49:17,142 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.ccil.cowan.tagsoup_tagsoup-1.2.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6519050058993989957.tmp
 2018-01-30 16:49:17,145 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.ccil.cowan.tagsoup_tagsoup-1.2.1.jar to class loader
 2018-01-30 16:49:17,145 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-io_commons-io-2.4.jar with timestamp 1517330948447
 2018-01-30 16:49:17,146 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-io_commons-io-2.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6170374856045103245.tmp
 2018-01-30 16:49:17,150 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-io_commons-io-2.4.jar to class loader
 2018-01-30 16:49:17,150 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.esotericsoftware_kryo-shaded-3.0.3.jar with timestamp 1517330948446
 2018-01-30 16:49:17,150 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.esotericsoftware_kryo-shaded-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1597797719857725402.tmp
 2018-01-30 16:49:17,160 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.esotericsoftware_kryo-shaded-3.0.3.jar to class loader
 2018-01-30 16:49:17,160 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.json_json-20140107.jar with timestamp 1517330948446
 2018-01-30 16:49:17,161 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.json_json-20140107.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5897647142135866079.tmp
 2018-01-30 16:49:17,174 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.json_json-20140107.jar to class loader
 2018-01-30 16:49:17,174 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/de.l3s.boilerpipe_boilerpipe-1.1.0.jar with timestamp 1517330948448
 2018-01-30 16:49:17,174 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/de.l3s.boilerpipe_boilerpipe-1.1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7910584269147185381.tmp
 2018-01-30 16:49:17,182 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/de.l3s.boilerpipe_boilerpipe-1.1.0.jar to class loader
 2018-01-30 16:49:17,182 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.sf.jwordnet_jwnl-1.3.3.jar with timestamp 1517330948449
 2018-01-30 16:49:17,183 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.sf.jwordnet_jwnl-1.3.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4573117704135213800.tmp
 2018-01-30 16:49:17,186 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.sf.jwordnet_jwnl-1.3.3.jar to class loader
 2018-01-30 16:49:17,186 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpmime-4.2.6.jar with timestamp 1517330948449
 2018-01-30 16:49:17,187 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpmime-4.2.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8127747077589972096.tmp
 2018-01-30 16:49:17,197 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.httpcomponents_httpmime-4.2.6.jar to class loader
 2018-01-30 16:49:17,197 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/junit_junit-4.8.2.jar with timestamp 1517330948445
 2018-01-30 16:49:17,198 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/junit_junit-4.8.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5568875436567575078.tmp
 2018-01-30 16:49:17,206 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/junit_junit-4.8.2.jar to class loader
 2018-01-30 16:49:17,206 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scalanlp_breeze_2.11-0.13.1.jar with timestamp 1517330948445
 2018-01-30 16:49:17,206 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scalanlp_breeze_2.11-0.13.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp342729549225114337.tmp
 2018-01-30 16:49:17,279 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scalanlp_breeze_2.11-0.13.1.jar to class loader
 2018-01-30 16:49:17,279 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_jempbox-1.8.10.jar with timestamp 1517330948448
 2018-01-30 16:49:17,280 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_jempbox-1.8.10.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp690260360030711689.tmp
 2018-01-30 16:49:17,294 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.pdfbox_jempbox-1.8.10.jar to class loader
 2018-01-30 16:49:17,295 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-rs-client-3.0.3.jar with timestamp 1517330948448
 2018-01-30 16:49:17,295 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-rs-client-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7545291032898054575.tmp
 2018-01-30 16:49:17,300 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.cxf_cxf-rt-rs-client-3.0.3.jar to class loader
 2018-01-30 16:49:17,300 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.martiansoftware_jsap-2.1.jar with timestamp 1517330948447
 2018-01-30 16:49:17,300 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.martiansoftware_jsap-2.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2091960849796533667.tmp
 2018-01-30 16:49:17,303 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.martiansoftware_jsap-2.1.jar to class loader
 2018-01-30 16:49:17,303 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.gagravarr_vorbis-java-tika-0.6.jar with timestamp 1517330948447
 2018-01-30 16:49:17,303 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.gagravarr_vorbis-java-tika-0.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8984193473214238685.tmp
 2018-01-30 16:49:17,316 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.gagravarr_vorbis-java-tika-0.6.jar to class loader
 2018-01-30 16:49:17,316 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/javax.measure_jsr-275-0.9.3.jar with timestamp 1517330948449
 2018-01-30 16:49:17,316 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/javax.measure_jsr-275-0.9.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8120983619172458456.tmp
 2018-01-30 16:49:17,327 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/javax.measure_jsr-275-0.9.3.jar to class loader
 2018-01-30 16:49:17,327 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/de.jollyday_jollyday-0.4.9.jar with timestamp 1517330948447
 2018-01-30 16:49:17,327 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/de.jollyday_jollyday-0.4.9.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7714148207097418587.tmp
 2018-01-30 16:49:17,336 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/de.jollyday_jollyday-0.4.9.jar to class loader
 2018-01-30 16:49:17,336 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.opengis_geoapi-3.0.0.jar with timestamp 1517330948448
 2018-01-30 16:49:17,336 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.opengis_geoapi-3.0.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7801737021472909314.tmp
 2018-01-30 16:49:17,346 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.opengis_geoapi-3.0.0.jar to class loader
 2018-01-30 16:49:17,346 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.jsoup_jsoup-1.7.3.jar with timestamp 1517330948445
 2018-01-30 16:49:17,346 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.jsoup_jsoup-1.7.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4343304798326347161.tmp
 2018-01-30 16:49:17,360 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.jsoup_jsoup-1.7.3.jar to class loader
 2018-01-30 16:49:17,360 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.io7m.xom_xom-1.2.10.jar with timestamp 1517330948447
 2018-01-30 16:49:17,360 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.io7m.xom_xom-1.2.10.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6661397495730281888.tmp
 2018-01-30 16:49:17,369 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.io7m.xom_xom-1.2.10.jar to class loader
 2018-01-30 16:49:17,369 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_udunits-4.5.5.jar with timestamp 1517330948449
 2018-01-30 16:49:17,369 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_udunits-4.5.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8840266856115151181.tmp
 2018-01-30 16:49:17,379 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_udunits-4.5.5.jar to class loader
 2018-01-30 16:49:17,379 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-queries-4.10.3.jar with timestamp 1517330948447
 2018-01-30 16:49:17,379 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-queries-4.10.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5260635062593145883.tmp
 2018-01-30 16:49:17,388 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.lucene_lucene-queries-4.10.3.jar to class loader
 2018-01-30 16:49:17,388 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-provider-svn-commons-1.4.jar with timestamp 1517330948449
 2018-01-30 16:49:17,388 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-provider-svn-commons-1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8467684251244422362.tmp
 2018-01-30 16:49:17,394 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.maven.scm_maven-scm-provider-svn-commons-1.4.jar to class loader
 2018-01-30 16:49:17,394 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-referencing-0.5.jar with timestamp 1517330948449
 2018-01-30 16:49:17,394 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.core_sis-referencing-0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8141760053753382762.tmp
 2018-01-30 16:49:17,397 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.sis.core_sis-referencing-0.5.jar to class loader
 2018-01-30 16:49:17,398 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.ws.xmlschema_xmlschema-core-2.1.0.jar with timestamp 1517330948449
 2018-01-30 16:49:17,398 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.ws.xmlschema_xmlschema-core-2.1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3862655726889541095.tmp
 2018-01-30 16:49:17,401 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.ws.xmlschema_xmlschema-core-2.1.0.jar to class loader
 2018-01-30 16:49:17,401 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.objenesis_objenesis-2.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,401 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.objenesis_objenesis-2.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7170704339531131156.tmp
 2018-01-30 16:49:17,410 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.objenesis_objenesis-2.1.jar to class loader
 2018-01-30 16:49:17,410 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.errorprone_error_prone_annotations-2.0.18.jar with timestamp 1517330948447
 2018-01-30 16:49:17,411 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.errorprone_error_prone_annotations-2.0.18.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5497301723545683447.tmp
 2018-01-30 16:49:17,418 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.errorprone_error_prone_annotations-2.0.18.jar to class loader
 2018-01-30 16:49:17,418 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-math3-3.1.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,418 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-math3-3.1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1230099204147209614.tmp
 2018-01-30 16:49:17,423 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-math3-3.1.1.jar to class loader
 2018-01-30 16:49:17,423 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codelibs_jhighlight-1.0.2.jar with timestamp 1517330948448
 2018-01-30 16:49:17,423 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codelibs_jhighlight-1.0.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1041827414193765848.tmp
 2018-01-30 16:49:17,427 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codelibs_jhighlight-1.0.2.jar to class loader
 2018-01-30 16:49:17,427 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.j2objc_j2objc-annotations-1.1.jar with timestamp 1517330948447
 2018-01-30 16:49:17,427 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.j2objc_j2objc-annotations-1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6014854889316466829.tmp
 2018-01-30 16:49:17,429 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.j2objc_j2objc-annotations-1.1.jar to class loader
 2018-01-30 16:49:17,430 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.xmlbeans_xmlbeans-2.6.0.jar with timestamp 1517330948448
 2018-01-30 16:49:17,430 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.xmlbeans_xmlbeans-2.6.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8942402263585235231.tmp
 2018-01-30 16:49:17,464 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.xmlbeans_xmlbeans-2.6.0.jar to class loader
 2018-01-30 16:49:17,465 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scala-lang_scala-reflect-2.11.8.jar with timestamp 1517330948446
 2018-01-30 16:49:17,465 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scala-lang_scala-reflect-2.11.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3189896774580936482.tmp
 2018-01-30 16:49:17,493 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scala-lang_scala-reflect-2.11.8.jar to class loader
 2018-01-30 16:49:17,493 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-annotations-2.8.8.jar with timestamp 1517330948446
 2018-01-30 16:49:17,493 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-annotations-2.8.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1034499640696646886.tmp
 2018-01-30 16:49:17,515 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.fasterxml.jackson.core_jackson-annotations-2.8.8.jar to class loader
 2018-01-30 16:49:17,516 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.opennlp_opennlp-tools-1.5.3.jar with timestamp 1517330948448
 2018-01-30 16:49:17,516 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.opennlp_opennlp-tools-1.5.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4399871673861353146.tmp
 2018-01-30 16:49:17,520 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.opennlp_opennlp-tools-1.5.3.jar to class loader
 2018-01-30 16:49:17,520 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.code.findbugs_jsr305-1.3.9.jar with timestamp 1517330948446
 2018-01-30 16:49:17,520 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.code.findbugs_jsr305-1.3.9.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8658845671215898116.tmp
 2018-01-30 16:49:17,523 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.code.findbugs_jsr305-1.3.9.jar to class loader
 2018-01-30 16:49:17,523 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.sf.opencsv_opencsv-2.3.jar with timestamp 1517330948446
 2018-01-30 16:49:17,523 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.sf.opencsv_opencsv-2.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1430901650719152142.tmp
 2018-01-30 16:49:17,526 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.sf.opencsv_opencsv-2.3.jar to class loader
 2018-01-30 16:49:17,526 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.twitter_chill-java-0.8.4.jar with timestamp 1517330948446
 2018-01-30 16:49:17,526 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.twitter_chill-java-0.8.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5032480747209445886.tmp
 2018-01-30 16:49:17,530 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.twitter_chill-java-0.8.4.jar to class loader
 2018-01-30 16:49:17,530 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-lang3-3.3.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,531 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-lang3-3.3.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp709857668583776104.tmp
 2018-01-30 16:49:17,542 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-lang3-3.3.1.jar to class loader
 2018-01-30 16:49:17,542 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_netcdf4-4.5.5.jar with timestamp 1517330948448
 2018-01-30 16:49:17,542 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_netcdf4-4.5.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3903682867916260766.tmp
 2018-01-30 16:49:17,545 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_netcdf4-4.5.5.jar to class loader
 2018-01-30 16:49:17,545 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.chuusai_shapeless_2.11-2.3.2.jar with timestamp 1517330948445
 2018-01-30 16:49:17,545 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.chuusai_shapeless_2.11-2.3.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp9155456684243056432.tmp
 2018-01-30 16:49:17,560 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.chuusai_shapeless_2.11-2.3.2.jar to class loader
 2018-01-30 16:49:17,560 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/joda-time_joda-time-2.2.jar with timestamp 1517330948446
 2018-01-30 16:49:17,560 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/joda-time_joda-time-2.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4361878975104720658.tmp
 2018-01-30 16:49:17,564 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/joda-time_joda-time-2.2.jar to class loader
 2018-01-30 16:49:17,564 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.plexus_plexus-utils-1.5.6.jar with timestamp 1517330948449
 2018-01-30 16:49:17,564 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.plexus_plexus-utils-1.5.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5505798450603716027.tmp
 2018-01-30 16:49:17,567 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.plexus_plexus-utils-1.5.6.jar to class loader
 2018-01-30 16:49:17,567 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/regexp_regexp-1.3.jar with timestamp 1517330948449
 2018-01-30 16:49:17,567 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/regexp_regexp-1.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5720054947300466251.tmp
 2018-01-30 16:49:17,578 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/regexp_regexp-1.3.jar to class loader
 2018-01-30 16:49:17,578 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-frontend-jaxrs-3.0.3.jar with timestamp 1517330948449
 2018-01-30 16:49:17,578 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-rt-frontend-jaxrs-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2026278785377082738.tmp
 2018-01-30 16:49:17,606 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.cxf_cxf-rt-frontend-jaxrs-3.0.3.jar to class loader
 2018-01-30 16:49:17,606 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_cdm-4.5.5.jar with timestamp 1517330948448
 2018-01-30 16:49:17,607 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_cdm-4.5.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3231655722166491319.tmp
 2018-01-30 16:49:17,618 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_cdm-4.5.5.jar to class loader
 2018-01-30 16:49:17,618 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.twitter_chill_2.11-0.8.4.jar with timestamp 1517330948445
 2018-01-30 16:49:17,619 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.twitter_chill_2.11-0.8.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6725904376340466418.tmp
 2018-01-30 16:49:17,623 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.twitter_chill_2.11-0.8.4.jar to class loader
 2018-01-30 16:49:17,623 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-core-2.8.8.jar with timestamp 1517330948446
 2018-01-30 16:49:17,623 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-core-2.8.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3131720555275957437.tmp
 2018-01-30 16:49:17,645 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.fasterxml.jackson.core_jackson-core-2.8.8.jar to class loader
 2018-01-30 16:49:17,645 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.spire-math_spire-macros_2.11-0.13.0.jar with timestamp 1517330948446
 2018-01-30 16:49:17,646 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.spire-math_spire-macros_2.11-0.13.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8795896997269315108.tmp
 2018-01-30 16:49:17,648 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.spire-math_spire-macros_2.11-0.13.0.jar to class loader
 2018-01-30 16:49:17,648 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.tika_tika-core-1.12.jar with timestamp 1517330948445
 2018-01-30 16:49:17,649 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.tika_tika-core-1.12.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6644353569335337911.tmp
 2018-01-30 16:49:17,652 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.tika_tika-core-1.12.jar to class loader
 2018-01-30 16:49:17,652 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.storage_sis-storage-0.5.jar with timestamp 1517330948449
 2018-01-30 16:49:17,652 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.storage_sis-storage-0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7963748064824504820.tmp
 2018-01-30 16:49:17,660 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.sis.storage_sis-storage-0.5.jar to class loader
 2018-01-30 16:49:17,660 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scala-lang_scala-parser-combinators-2.11.0-M4.jar with timestamp 1517330948445
 2018-01-30 16:49:17,660 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scala-lang_scala-parser-combinators-2.11.0-M4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5989614506838019515.tmp
 2018-01-30 16:49:17,663 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scala-lang_scala-parser-combinators-2.11.0-M4.jar to class loader
 2018-01-30 16:49:17,663 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-ooxml-3.13.jar with timestamp 1517330948448
 2018-01-30 16:49:17,663 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-ooxml-3.13.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8735145389029191570.tmp
 2018-01-30 16:49:17,668 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.poi_poi-ooxml-3.13.jar to class loader
 2018-01-30 16:49:17,668 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-ast_2.11-3.5.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,669 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-ast_2.11-3.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4028210721205342678.tmp
 2018-01-30 16:49:17,672 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.json4s_json4s-ast_2.11-3.5.1.jar to class loader
 2018-01-30 16:49:17,672 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/javax.servlet_javax.servlet-api-3.0.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,672 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/javax.servlet_javax.servlet-api-3.0.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7844416879077256733.tmp
 2018-01-30 16:49:17,675 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/javax.servlet_javax.servlet-api-3.0.1.jar to class loader
 2018-01-30 16:49:17,675 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/it.unimi.dsi_fastutil-6.5.2.jar with timestamp 1517330948447
 2018-01-30 16:49:17,675 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/it.unimi.dsi_fastutil-6.5.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7072769314611856459.tmp
 2018-01-30 16:49:17,744 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/it.unimi.dsi_fastutil-6.5.2.jar to class loader
 2018-01-30 16:49:17,744 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.code.gson_gson-2.3.1.jar with timestamp 1517330948446
 2018-01-30 16:49:17,744 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.code.gson_gson-2.3.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7162264972765022859.tmp
 2018-01-30 16:49:17,748 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.code.gson_gson-2.3.1.jar to class loader
 2018-01-30 16:49:17,748 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.thoughtworks.paranamer_paranamer-2.8.jar with timestamp 1517330948446
 2018-01-30 16:49:17,748 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.thoughtworks.paranamer_paranamer-2.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4298721335429084236.tmp
 2018-01-30 16:49:17,795 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.thoughtworks.paranamer_paranamer-2.8.jar to class loader
 2018-01-30 16:49:17,795 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.jcip_jcip-annotations-1.0.jar with timestamp 1517330948449
 2018-01-30 16:49:17,795 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.jcip_jcip-annotations-1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7948668663161619497.tmp
 2018-01-30 16:49:17,798 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.jcip_jcip-annotations-1.0.jar to class loader
 2018-01-30 16:49:17,798 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.aspectj_aspectjrt-1.8.0.jar with timestamp 1517330948448
 2018-01-30 16:49:17,798 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.aspectj_aspectjrt-1.8.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5384864249242225835.tmp
 2018-01-30 16:49:17,809 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.aspectj_aspectjrt-1.8.0.jar to class loader
 2018-01-30 16:49:17,809 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_pdfbox-1.8.10.jar with timestamp 1517330948447
 2018-01-30 16:49:17,809 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_pdfbox-1.8.10.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp652166629513070224.tmp
 2018-01-30 16:49:17,931 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.pdfbox_pdfbox-1.8.10.jar to class loader
 2018-01-30 16:49:17,931 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-scratchpad-3.13.jar with timestamp 1517330948448
 2018-01-30 16:49:17,931 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-scratchpad-3.13.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1835773068495467735.tmp
 2018-01-30 16:49:17,974 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.poi_poi-scratchpad-3.13.jar to class loader
 2018-01-30 16:49:17,974 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-jackson_2.11-3.5.1.jar with timestamp 1517330948445
 2018-01-30 16:49:17,974 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-jackson_2.11-3.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7878772696888598500.tmp
 2018-01-30 16:49:17,981 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.json4s_json4s-jackson_2.11-3.5.1.jar to class loader
 2018-01-30 16:49:17,982 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcpkix-jdk15on-1.52.jar with timestamp 1517330948448
 2018-01-30 16:49:17,982 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcpkix-jdk15on-1.52.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5278542463493472612.tmp
 2018-01-30 16:49:17,986 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.bouncycastle_bcpkix-jdk15on-1.52.jar to class loader
 2018-01-30 16:49:17,986 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/c3p0_c3p0-0.9.1.1.jar with timestamp 1517330948449
 2018-01-30 16:49:17,986 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/c3p0_c3p0-0.9.1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5661987132996274906.tmp
 2018-01-30 16:49:17,990 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/c3p0_c3p0-0.9.1.1.jar to class loader
 2018-01-30 16:49:17,991 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.rometools_rome-utils-1.5.1.jar with timestamp 1517330948448
 2018-01-30 16:49:17,991 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.rometools_rome-utils-1.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7813984425649867605.tmp
 2018-01-30 16:49:17,993 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.rometools_rome-utils-1.5.1.jar to class loader
 2018-01-30 16:49:17,993 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.gagravarr_vorbis-java-core-0.6.jar with timestamp 1517330948448
 2018-01-30 16:49:17,993 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.gagravarr_vorbis-java-core-0.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6900314315495751531.tmp
 2018-01-30 16:49:17,997 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.gagravarr_vorbis-java-core-0.6.jar to class loader
 2018-01-30 16:49:17,997 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpclient-4.2.6.jar with timestamp 1517330948449
 2018-01-30 16:49:17,997 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpclient-4.2.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8279773797839492567.tmp
 2018-01-30 16:49:18,000 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.httpcomponents_httpclient-4.2.6.jar to class loader
 2018-01-30 16:49:18,000 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-ooxml-schemas-3.13.jar with timestamp 1517330948448
 2018-01-30 16:49:18,000 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-ooxml-schemas-3.13.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1340302427472514216.tmp
 2018-01-30 16:49:18,052 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.poi_poi-ooxml-schemas-3.13.jar to class loader
 2018-01-30 16:49:18,052 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.storage_sis-netcdf-0.5.jar with timestamp 1517330948448
 2018-01-30 16:49:18,052 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.sis.storage_sis-netcdf-0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3026418598082195434.tmp
 2018-01-30 16:49:18,094 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.sis.storage_sis-netcdf-0.5.jar to class loader
 2018-01-30 16:49:18,094 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/xerces_xercesImpl-2.11.0.jar with timestamp 1517330948446
 2018-01-30 16:49:18,094 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/xerces_xercesImpl-2.11.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7369715246780765885.tmp
 2018-01-30 16:49:18,099 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/xerces_xercesImpl-2.11.0.jar to class loader
 2018-01-30 16:49:18,099 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.protobuf_protobuf-java-3.2.0.jar with timestamp 1517330948447
 2018-01-30 16:49:18,099 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.protobuf_protobuf-java-3.2.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8826929566585164123.tmp
 2018-01-30 16:49:18,142 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.protobuf_protobuf-java-3.2.0.jar to class loader
 2018-01-30 16:49:18,142 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.james_apache-mime4j-core-0.7.2.jar with timestamp 1517330948447
 2018-01-30 16:49:18,142 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.james_apache-mime4j-core-0.7.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1000467896128492964.tmp
 2018-01-30 16:49:18,153 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.james_apache-mime4j-core-0.7.2.jar to class loader
 2018-01-30 16:49:18,153 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.googlecode.juniversalchardet_juniversalchardet-1.0.3.jar with timestamp 1517330948447
 2018-01-30 16:49:18,153 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.googlecode.juniversalchardet_juniversalchardet-1.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2239121057317717413.tmp
 2018-01-30 16:49:18,156 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.googlecode.juniversalchardet_juniversalchardet-1.0.3.jar to class loader
 2018-01-30 16:49:18,156 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_jj2000-5.2.jar with timestamp 1517330948449
 2018-01-30 16:49:18,156 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_jj2000-5.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7900261676563509133.tmp
 2018-01-30 16:49:18,174 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_jj2000-5.2.jar to class loader
 2018-01-30 16:49:18,174 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.spire-math_spire_2.11-0.13.0.jar with timestamp 1517330948446
 2018-01-30 16:49:18,174 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.spire-math_spire_2.11-0.13.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp194104776627385089.tmp
 2018-01-30 16:49:18,249 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.spire-math_spire_2.11-0.13.0.jar to class loader
 2018-01-30 16:49:18,249 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-3.13.jar with timestamp 1517330948448
 2018-01-30 16:49:18,250 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.poi_poi-3.13.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5559450935531405761.tmp
 2018-01-30 16:49:18,266 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.poi_poi-3.13.jar to class loader
 2018-01-30 16:49:18,267 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.healthmarketscience.jackcess_jackcess-encrypt-2.1.1.jar with timestamp 1517330948447
 2018-01-30 16:49:18,267 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.healthmarketscience.jackcess_jackcess-encrypt-2.1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp9076559943332603401.tmp
 2018-01-30 16:49:18,277 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.healthmarketscience.jackcess_jackcess-encrypt-2.1.1.jar to class loader
 2018-01-30 16:49:18,277 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-logging_commons-logging-1.1.3.jar with timestamp 1517330948446
 2018-01-30 16:49:18,277 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-logging_commons-logging-1.1.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4088844120459360114.tmp
 2018-01-30 16:49:18,284 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-logging_commons-logging-1.1.3.jar to class loader
 2018-01-30 16:49:18,284 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/javax.ws.rs_javax.ws.rs-api-2.0.1.jar with timestamp 1517330948449
 2018-01-30 16:49:18,284 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/javax.ws.rs_javax.ws.rs-api-2.0.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2258591923740576893.tmp
 2018-01-30 16:49:18,287 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/javax.ws.rs_javax.ws.rs-api-2.0.1.jar to class loader
 2018-01-30 16:49:18,287 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.java.dev.jets3t_jets3t-0.6.1.jar with timestamp 1517330948446
 2018-01-30 16:49:18,287 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.java.dev.jets3t_jets3t-0.6.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7865543766238339769.tmp
 2018-01-30 16:49:18,392 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.java.dev.jets3t_jets3t-0.6.1.jar to class loader
 2018-01-30 16:49:18,392 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/xml-apis_xml-apis-1.4.01.jar with timestamp 1517330948449
 2018-01-30 16:49:18,393 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/xml-apis_xml-apis-1.4.01.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3444931840995431321.tmp
 2018-01-30 16:49:18,404 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/xml-apis_xml-apis-1.4.01.jar to class loader
 2018-01-30 16:49:18,404 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-vfs2-2.0.jar with timestamp 1517330948448
 2018-01-30 16:49:18,405 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-vfs2-2.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp299266606337651140.tmp
 2018-01-30 16:49:18,421 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-vfs2-2.0.jar to class loader
 2018-01-30 16:49:18,421 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.tukaani_xz-1.5.jar with timestamp 1517330948447
 2018-01-30 16:49:18,421 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.tukaani_xz-1.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6142426372690029465.tmp
 2018-01-30 16:49:18,429 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.tukaani_xz-1.5.jar to class loader
 2018-01-30 16:49:18,429 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-scalap_2.11-3.5.1.jar with timestamp 1517330948446
 2018-01-30 16:49:18,429 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.json4s_json4s-scalap_2.11-3.5.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6880366713553769687.tmp
 2018-01-30 16:49:18,433 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.json4s_json4s-scalap_2.11-3.5.1.jar to class loader
 2018-01-30 16:49:18,433 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.slf4j_slf4j-api-1.7.24.jar with timestamp 1517330948446
 2018-01-30 16:49:18,433 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.slf4j_slf4j-api-1.7.24.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3087783224213837099.tmp
 2018-01-30 16:49:18,436 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.slf4j_slf4j-api-1.7.24.jar to class loader
 2018-01-30 16:49:18,436 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-configuration_commons-configuration-1.8.jar with timestamp 1517330948447
 2018-01-30 16:49:18,436 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-configuration_commons-configuration-1.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5876076927501358941.tmp
 2018-01-30 16:49:18,440 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-configuration_commons-configuration-1.8.jar to class loader
 2018-01-30 16:49:18,440 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.github.junrar_junrar-0.7.jar with timestamp 1517330948448
 2018-01-30 16:49:18,440 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.github.junrar_junrar-0.7.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7072836990988435607.tmp
 2018-01-30 16:49:18,443 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.github.junrar_junrar-0.7.jar to class loader
 2018-01-30 16:49:18,443 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.slf4j_jul-to-slf4j-1.7.24.jar with timestamp 1517330948446
 2018-01-30 16:49:18,443 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.slf4j_jul-to-slf4j-1.7.24.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4752501471641370363.tmp
 2018-01-30 16:49:18,446 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.slf4j_jul-to-slf4j-1.7.24.jar to class loader
 2018-01-30 16:49:18,446 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/io.archivesunleashed_aut-0.12.1.jar with timestamp 1517330948445
 2018-01-30 16:49:18,446 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/io.archivesunleashed_aut-0.12.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8701106715297610068.tmp
 2018-01-30 16:49:18,450 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/io.archivesunleashed_aut-0.12.1.jar to class loader
 2018-01-30 16:49:18,450 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcprov-jdk15on-1.52.jar with timestamp 1517330948447
 2018-01-30 16:49:18,450 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcprov-jdk15on-1.52.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6467577611898868715.tmp
 2018-01-30 16:49:18,481 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.bouncycastle_bcprov-jdk15on-1.52.jar to class loader
 2018-01-30 16:49:18,481 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-net_commons-net-1.4.1.jar with timestamp 1517330948446
 2018-01-30 16:49:18,482 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-net_commons-net-1.4.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4688247884417315001.tmp
 2018-01-30 16:49:18,485 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-net_commons-net-1.4.1.jar to class loader
 2018-01-30 16:49:18,485 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.module_jackson-module-scala_2.11-2.8.8.jar with timestamp 1517330948445
 2018-01-30 16:49:18,485 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.module_jackson-module-scala_2.11-2.8.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp434078340534422037.tmp
 2018-01-30 16:49:18,488 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.fasterxml.jackson.module_jackson-module-scala_2.11-2.8.8.jar to class loader
 2018-01-30 16:49:18,489 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.xerial.snappy_snappy-java-1.1.4.jar with timestamp 1517330948445
 2018-01-30 16:49:18,489 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.xerial.snappy_snappy-java-1.1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7193808435017909726.tmp
 2018-01-30 16:49:18,493 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.xerial.snappy_snappy-java-1.1.4.jar to class loader
 2018-01-30 16:49:18,493 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-api-1.4.jar with timestamp 1517330948448
 2018-01-30 16:49:18,494 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-api-1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5254382541610675742.tmp
 2018-01-30 16:49:18,503 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.maven.scm_maven-scm-api-1.4.jar to class loader
 2018-01-30 16:49:18,503 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.adobe.xmp_xmpcore-5.1.2.jar with timestamp 1517330948448
 2018-01-30 16:49:18,504 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.adobe.xmp_xmpcore-5.1.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5360619949612811070.tmp
 2018-01-30 16:49:18,509 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.adobe.xmp_xmpcore-5.1.2.jar to class loader
 2018-01-30 16:49:18,509 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.scala-lang.modules_scala-parser-combinators_2.11-1.0.5.jar with timestamp 1517330948445
 2018-01-30 16:49:18,509 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.scala-lang.modules_scala-parser-combinators_2.11-1.0.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3888520693073056521.tmp
 2018-01-30 16:49:18,517 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.scala-lang.modules_scala-parser-combinators_2.11-1.0.5.jar to class loader
 2018-01-30 16:49:18,517 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-analyzers-common-4.10.3.jar with timestamp 1517330948447
 2018-01-30 16:49:18,517 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-analyzers-common-4.10.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp986630570950396184.tmp
 2018-01-30 16:49:18,575 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.lucene_lucene-analyzers-common-4.10.3.jar to class loader
 2018-01-30 16:49:18,575 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.stanford.nlp_stanford-corenlp-3.8.0.jar with timestamp 1517330948445
 2018-01-30 16:49:18,575 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.stanford.nlp_stanford-corenlp-3.8.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8251313061375398613.tmp
 2018-01-30 16:49:18,714 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.stanford.nlp_stanford-corenlp-3.8.0.jar to class loader
 2018-01-30 16:49:18,714 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/edu.ucar_httpservices-4.5.5.jar with timestamp 1517330948448
 2018-01-30 16:49:18,715 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/edu.ucar_httpservices-4.5.5.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5199235848119444825.tmp
 2018-01-30 16:49:18,735 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/edu.ucar_httpservices-4.5.5.jar to class loader
 2018-01-30 16:49:18,735 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.jdom_jdom-2.0.2.jar with timestamp 1517330948448
 2018-01-30 16:49:18,735 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.jdom_jdom-2.0.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp9059870591551458456.tmp
 2018-01-30 16:49:18,759 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.jdom_jdom-2.0.2.jar to class loader
 2018-01-30 16:49:18,759 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-core-3.0.3.jar with timestamp 1517330948449
 2018-01-30 16:49:18,759 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.cxf_cxf-core-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2684956739609568791.tmp
 2018-01-30 16:49:18,767 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.cxf_cxf-core-3.0.3.jar to class loader
 2018-01-30 16:49:18,767 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.htmlparser_htmlparser-1.6.jar with timestamp 1517330948447
 2018-01-30 16:49:18,767 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.htmlparser_htmlparser-1.6.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3551323129470816645.tmp
 2018-01-30 16:49:18,789 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.htmlparser_htmlparser-1.6.jar to class loader
 2018-01-30 16:49:18,789 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-codec_commons-codec-1.9.jar with timestamp 1517330948447
 2018-01-30 16:49:18,790 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-codec_commons-codec-1.9.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8536210705933503431.tmp
 2018-01-30 16:49:18,793 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-codec_commons-codec-1.9.jar to class loader
 2018-01-30 16:49:18,793 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.sf.ehcache_ehcache-core-2.6.2.jar with timestamp 1517330948449
 2018-01-30 16:49:18,793 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.sf.ehcache_ehcache-core-2.6.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8415671262123709687.tmp
 2018-01-30 16:49:18,798 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.sf.ehcache_ehcache-core-2.6.2.jar to class loader
 2018-01-30 16:49:18,798 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.googlecode.efficient-java-matrix-library_ejml-0.23.jar with timestamp 1517330948447
 2018-01-30 16:49:18,798 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.googlecode.efficient-java-matrix-library_ejml-0.23.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6756159679995873505.tmp
 2018-01-30 16:49:18,802 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.googlecode.efficient-java-matrix-library_ejml-0.23.jar to class loader
 2018-01-30 16:49:18,802 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.beust_jcommander-1.35.jar with timestamp 1517330948449
 2018-01-30 16:49:18,802 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.beust_jcommander-1.35.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5307362518449092245.tmp
 2018-01-30 16:49:18,805 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.beust_jcommander-1.35.jar to class loader
 2018-01-30 16:49:18,805 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.drewnoakes_metadata-extractor-2.8.0.jar with timestamp 1517330948448
 2018-01-30 16:49:18,805 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.drewnoakes_metadata-extractor-2.8.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6654389457623050845.tmp
 2018-01-30 16:49:18,847 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.drewnoakes_metadata-extractor-2.8.0.jar to class loader
 2018-01-30 16:49:18,847 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-compress-1.10.jar with timestamp 1517330948447
 2018-01-30 16:49:18,847 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-compress-1.10.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7248529224091625882.tmp
 2018-01-30 16:49:18,850 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-compress-1.10.jar to class loader
 2018-01-30 16:49:18,850 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpcore-4.3.jar with timestamp 1517330948447
 2018-01-30 16:49:18,851 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.httpcomponents_httpcore-4.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7726489711191866412.tmp
 2018-01-30 16:49:18,854 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.httpcomponents_httpcore-4.3.jar to class loader
 2018-01-30 16:49:18,854 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.slf4j_jcl-over-slf4j-1.7.24.jar with timestamp 1517330948446
 2018-01-30 16:49:18,854 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.slf4j_jcl-over-slf4j-1.7.24.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5125464374237486573.tmp
 2018-01-30 16:49:18,866 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.slf4j_jcl-over-slf4j-1.7.24.jar to class loader
 2018-01-30 16:49:18,867 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.jackson_jackson-core-asl-1.5.2.jar with timestamp 1517330948449
 2018-01-30 16:49:18,867 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.jackson_jackson-core-asl-1.5.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3011843356690289631.tmp
 2018-01-30 16:49:18,870 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.jackson_jackson-core-asl-1.5.2.jar to class loader
 2018-01-30 16:49:18,870 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/tl.lin_lintools-datatypes-1.0.0.jar with timestamp 1517330948446
 2018-01-30 16:49:18,870 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/tl.lin_lintools-datatypes-1.0.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5122482278066721931.tmp
 2018-01-30 16:49:18,887 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/tl.lin_lintools-datatypes-1.0.0.jar to class loader
 2018-01-30 16:49:18,887 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-sandbox-4.10.3.jar with timestamp 1517330948447
 2018-01-30 16:49:18,887 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.lucene_lucene-sandbox-4.10.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1571120638052346901.tmp
 2018-01-30 16:49:18,890 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.lucene_lucene-sandbox-4.10.3.jar to class loader
 2018-01-30 16:49:18,890 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.github.rwl_jtransforms-2.4.0.jar with timestamp 1517330948446
 2018-01-30 16:49:18,891 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.github.rwl_jtransforms-2.4.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5848160702649195226.tmp
 2018-01-30 16:49:18,894 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.github.rwl_jtransforms-2.4.0.jar to class loader
 2018-01-30 16:49:18,894 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.jdom_jdom2-2.0.4.jar with timestamp 1517330948449
 2018-01-30 16:49:18,894 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.jdom_jdom2-2.0.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2027731653252533578.tmp
 2018-01-30 16:49:18,898 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.jdom_jdom2-2.0.4.jar to class loader
 2018-01-30 16:49:18,898 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/it.unimi.dsi_dsiutils-2.0.12.jar with timestamp 1517330948447
 2018-01-30 16:49:18,898 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/it.unimi.dsi_dsiutils-2.0.12.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp585254655513573083.tmp
 2018-01-30 16:49:18,902 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/it.unimi.dsi_dsiutils-2.0.12.jar to class loader
 2018-01-30 16:49:18,902 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/oro_oro-2.0.8.jar with timestamp 1517330948449
 2018-01-30 16:49:18,902 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/oro_oro-2.0.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3615307465207301984.tmp
 2018-01-30 16:49:18,909 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/oro_oro-2.0.8.jar to class loader
 2018-01-30 16:49:18,909 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.java.dev.jna_jna-4.1.0.jar with timestamp 1517330948449
 2018-01-30 16:49:18,909 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.java.dev.jna_jna-4.1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8697221257781573646.tmp
 2018-01-30 16:49:18,913 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.java.dev.jna_jna-4.1.0.jar to class loader
 2018-01-30 16:49:18,913 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_fontbox-1.8.10.jar with timestamp 1517330948448
 2018-01-30 16:49:18,914 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.pdfbox_fontbox-1.8.10.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2094068932929509630.tmp
 2018-01-30 16:49:19,006 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.pdfbox_fontbox-1.8.10.jar to class loader
 2018-01-30 16:49:19,006 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.ow2.asm_asm-5.0.4.jar with timestamp 1517330948448
 2018-01-30 16:49:19,006 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.ow2.asm_asm-5.0.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5867021759786154949.tmp
 2018-01-30 16:49:19,009 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.ow2.asm_asm-5.0.4.jar to class loader
 2018-01-30 16:49:19,009 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-csv-1.0.jar with timestamp 1517330948448
 2018-01-30 16:49:19,009 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.commons_commons-csv-1.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5558970157676178699.tmp
 2018-01-30 16:49:19,037 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.commons_commons-csv-1.0.jar to class loader
 2018-01-30 16:49:19,037 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.syncthemall_boilerpipe-1.2.2.jar with timestamp 1517330948446
 2018-01-30 16:49:19,037 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.syncthemall_boilerpipe-1.2.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8915387310335677306.tmp
 2018-01-30 16:49:19,040 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.syncthemall_boilerpipe-1.2.2.jar to class loader
 2018-01-30 16:49:19,041 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.google.guava_guava-23.0.jar with timestamp 1517330948445
 2018-01-30 16:49:19,041 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.google.guava_guava-23.0.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1156862189594712010.tmp
 2018-01-30 16:49:19,048 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.google.guava_guava-23.0.jar to class loader
 2018-01-30 16:49:19,048 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/javax.annotation_javax.annotation-api-1.2.jar with timestamp 1517330948449
 2018-01-30 16:49:19,048 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/javax.annotation_javax.annotation-api-1.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp5833347987461101935.tmp
 2018-01-30 16:49:19,050 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/javax.annotation_javax.annotation-api-1.2.jar to class loader
 2018-01-30 16:49:19,051 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.googlecode.mp4parser_isoparser-1.0.2.jar with timestamp 1517330948448
 2018-01-30 16:49:19,051 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.googlecode.mp4parser_isoparser-1.0.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8464521891873002022.tmp
 2018-01-30 16:49:19,054 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.googlecode.mp4parser_isoparser-1.0.2.jar to class loader
 2018-01-30 16:49:19,054 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.tika_tika-parsers-1.12.jar with timestamp 1517330948445
 2018-01-30 16:49:19,055 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.tika_tika-parsers-1.12.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3427366540997694145.tmp
 2018-01-30 16:49:19,058 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.tika_tika-parsers-1.12.jar to class loader
 2018-01-30 16:49:19,058 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcmail-jdk15on-1.52.jar with timestamp 1517330948447
 2018-01-30 16:49:19,058 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.bouncycastle_bcmail-jdk15on-1.52.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp155514426502071646.tmp
 2018-01-30 16:49:19,061 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.bouncycastle_bcmail-jdk15on-1.52.jar to class loader
 2018-01-30 16:49:19,062 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/log4j_log4j-1.2.17.jar with timestamp 1517330948447
 2018-01-30 16:49:19,062 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/log4j_log4j-1.2.17.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7455913246465938309.tmp
 2018-01-30 16:49:19,066 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/log4j_log4j-1.2.17.jar to class loader
 2018-01-30 16:49:19,066 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-collections_commons-collections-3.2.1.jar with timestamp 1517330948447
 2018-01-30 16:49:19,066 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-collections_commons-collections-3.2.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6379122139199541596.tmp
 2018-01-30 16:49:19,070 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-collections_commons-collections-3.2.1.jar to class loader
 2018-01-30 16:49:19,070 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.gnu.inet_libidn-1.15.jar with timestamp 1517330948447
 2018-01-30 16:49:19,070 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.gnu.inet_libidn-1.15.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp552521674749334989.tmp
 2018-01-30 16:49:19,073 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.gnu.inet_libidn-1.15.jar to class loader
 2018-01-30 16:49:19,073 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.googlecode.json-simple_json-simple-1.1.1.jar with timestamp 1517330948448
 2018-01-30 16:49:19,073 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.googlecode.json-simple_json-simple-1.1.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp2441293880655961205.tmp
 2018-01-30 16:49:19,083 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.googlecode.json-simple_json-simple-1.1.1.jar to class loader
 2018-01-30 16:49:19,083 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.apple_AppleJavaExtensions-1.4.jar with timestamp 1517330948447
 2018-01-30 16:49:19,083 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.apple_AppleJavaExtensions-1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp6560238227739937897.tmp
 2018-01-30 16:49:19,093 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.apple_AppleJavaExtensions-1.4.jar to class loader
 2018-01-30 16:49:19,093 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/commons-httpclient_commons-httpclient-3.1.jar with timestamp 1517330948447
 2018-01-30 16:49:19,093 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/commons-httpclient_commons-httpclient-3.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4992263360021554390.tmp
 2018-01-30 16:49:19,097 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/commons-httpclient_commons-httpclient-3.1.jar to class loader
 2018-01-30 16:49:19,097 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.opennlp_opennlp-maxent-3.0.3.jar with timestamp 1517330948449
 2018-01-30 16:49:19,097 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.opennlp_opennlp-maxent-3.0.3.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp3238295319958305936.tmp
 2018-01-30 16:49:19,116 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.opennlp_opennlp-maxent-3.0.3.jar to class loader
 2018-01-30 16:49:19,116 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/net.sourceforge.nekohtml_nekohtml-1.9.20.jar with timestamp 1517330948449
 2018-01-30 16:49:19,116 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/net.sourceforge.nekohtml_nekohtml-1.9.20.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4023524855235225188.tmp
 2018-01-30 16:49:19,149 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/net.sourceforge.nekohtml_nekohtml-1.9.20.jar to class loader
 2018-01-30 16:49:19,149 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.codehaus.jackson_jackson-mapper-asl-1.5.2.jar with timestamp 1517330948446
 2018-01-30 16:49:19,150 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.codehaus.jackson_jackson-mapper-asl-1.5.2.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp4272812581646085030.tmp
 2018-01-30 16:49:19,153 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.codehaus.jackson_jackson-mapper-asl-1.5.2.jar to class loader
 2018-01-30 16:49:19,153 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-databind-2.8.8.jar with timestamp 1517330948446
 2018-01-30 16:49:19,153 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/com.fasterxml.jackson.core_jackson-databind-2.8.8.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp8688548516688993994.tmp
 2018-01-30 16:49:19,158 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/com.fasterxml.jackson.core_jackson-databind-2.8.8.jar to class loader
 2018-01-30 16:49:19,158 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-provider-svnexe-1.4.jar with timestamp 1517330948448
 2018-01-30 16:49:19,158 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.apache.maven.scm_maven-scm-provider-svnexe-1.4.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp7454115836944181709.tmp
 2018-01-30 16:49:19,161 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.apache.maven.scm_maven-scm-provider-svnexe-1.4.jar to class loader
 2018-01-30 16:49:19,161 [Executor task launch worker for task 4] INFO  Executor - Fetching spark://192.168.32.19:46742/jars/org.itadaki_bzip2-0.9.1.jar with timestamp 1517330948449
 2018-01-30 16:49:19,161 [Executor task launch worker for task 4] INFO  Utils - Fetching spark://192.168.32.19:46742/jars/org.itadaki_bzip2-0.9.1.jar to /tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/fetchFileTemp1890152517137375004.tmp
 2018-01-30 16:49:19,175 [Executor task launch worker for task 4] INFO  Executor - Adding file:/tmp/spark-c84bbbe0-9654-4f63-9aa7-720e34b5f9e7/userFiles-c04ca5a2-9ff9-43ad-81e6-11d32da08992/org.itadaki_bzip2-0.9.1.jar to class loader
 2018-01-30 16:49:19,266 [Executor task launch worker for task 5] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126043216115-00105.warc.gz:0+1000072016
 2018-01-30 16:49:19,266 [Executor task launch worker for task 2] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406021046-00012-crawling200.us.archive.org-6682.warc.gz:0+100161336
 2018-01-30 16:49:19,266 [Executor task launch worker for task 7] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003003618-00498-crawling209.us.archive.org-6681.warc.gz:0+118797619
 2018-01-30 16:49:19,266 [Executor task launch worker for task 4] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002205352-00447-crawling209.us.archive.org-6681.warc.gz:0+118748738
 2018-01-30 16:49:19,266 [Executor task launch worker for task 9] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-RHYTNI-20120724183026-00000-crawling202.us.archive.org-6680.warc.gz:0+2183668
 2018-01-30 16:49:19,266 [Executor task launch worker for task 3] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-18963-20131227213014370-00000-wbgrp-crawl060.us.archive.org-6444.warc.gz:0+1000058145
 2018-01-30 16:49:19,266 [Executor task launch worker for task 1] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006114843-00052-crawling205.us.archive.org-6681.warc.gz:0+100531482
 2018-01-30 16:49:19,266 [Executor task launch worker for task 0] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930090055-00131-crawling202.us.archive.org-6681.warc.gz:0+108693245
 2018-01-30 16:49:19,266 [Executor task launch worker for task 11] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008213436-00052-crawling208.us.archive.org-6683.warc.gz:0+147494192
 2018-01-30 16:49:19,267 [Executor task launch worker for task 6] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002120719-00327-crawling209.us.archive.org-6681.warc.gz:0+101894447
 2018-01-30 16:49:19,267 [Executor task launch worker for task 10] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224221504411-00052.warc.gz:0+1000016538
 2018-01-30 16:49:19,267 [Executor task launch worker for task 8] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929014318-00049-crawling113.us.archive.org-6683.warc.gz:0+115944929
 2018-01-30 16:49:19,963 [Executor task launch worker for task 9] INFO  Executor - Finished task 9.0 in stage 0.0 (TID 9). 1850 bytes result sent to driver
 2018-01-30 16:49:19,969 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 12.0 in stage 0.0 (TID 12, localhost, executor driver, partition 12, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:49:19,970 [Executor task launch worker for task 12] INFO  Executor - Running task 12.0 in stage 0.0 (TID 12)
 2018-01-30 16:49:19,972 [Executor task launch worker for task 12] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB198318-20160227160336248-00001.warc.gz:0+281139119
 2018-01-30 16:49:19,977 [task-result-getter-0] INFO  TaskSetManager - Finished task 9.0 in stage 0.0 (TID 9) in 3833 ms on localhost (executor driver) (1/3618)
 2018-01-30 16:49:22,526 [Executor task launch worker for task 4] INFO  Executor - Finished task 4.0 in stage 0.0 (TID 4). 1759 bytes result sent to driver
 2018-01-30 16:49:22,533 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 13.0 in stage 0.0 (TID 13, localhost, executor driver, partition 13, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:49:22,534 [Executor task launch worker for task 13] INFO  Executor - Running task 13.0 in stage 0.0 (TID 13)
 2018-01-30 16:49:22,534 [task-result-getter-1] INFO  TaskSetManager - Finished task 4.0 in stage 0.0 (TID 4) in 6398 ms on localhost (executor driver) (2/3618)
 2018-01-30 16:49:22,537 [Executor task launch worker for task 13] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-21899-20130515200059301-00003-wbgrp-crawl101.us.archive.org-6443.warc.gz:0+937335351
 2018-01-30 16:49:22,795 [Executor task launch worker for task 7] INFO  Executor - Finished task 7.0 in stage 0.0 (TID 7). 1759 bytes result sent to driver
 2018-01-30 16:49:22,797 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 14.0 in stage 0.0 (TID 14, localhost, executor driver, partition 14, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:49:22,797 [Executor task launch worker for task 14] INFO  Executor - Running task 14.0 in stage 0.0 (TID 14)
 2018-01-30 16:49:22,799 [Executor task launch worker for task 14] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-ANNUAL-11312-20150127030045330-00000-wbgrp-crawl053.us.archive.org-6441.warc.gz:0+230782
 2018-01-30 16:49:22,803 [task-result-getter-2] INFO  TaskSetManager - Finished task 7.0 in stage 0.0 (TID 7) in 6663 ms on localhost (executor driver) (3/3618)
 2018-01-30 16:49:22,837 [Executor task launch worker for task 14] INFO  Executor - Finished task 14.0 in stage 0.0 (TID 14). 1698 bytes result sent to driver
 2018-01-30 16:49:22,839 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 15.0 in stage 0.0 (TID 15, localhost, executor driver, partition 15, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:49:22,839 [Executor task launch worker for task 15] INFO  Executor - Running task 15.0 in stage 0.0 (TID 15)
 2018-01-30 16:49:22,839 [task-result-getter-3] INFO  TaskSetManager - Finished task 14.0 in stage 0.0 (TID 14) in 43 ms on localhost (executor driver) (4/3618)
 2018-01-30 16:49:22,842 [Executor task launch worker for task 15] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120928030615-00006-crawling113.us.archive.org-6683.warc.gz:0+106407496
 2018-01-30 16:49:44,053 [Executor task launch worker for task 6] INFO  Executor - Finished task 6.0 in stage 0.0 (TID 6). 1763 bytes result sent to driver
 2018-01-30 16:49:44,055 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 16.0 in stage 0.0 (TID 16, localhost, executor driver, partition 16, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:49:44,055 [Executor task launch worker for task 16] INFO  Executor - Running task 16.0 in stage 0.0 (TID 16)
 2018-01-30 16:49:44,055 [task-result-getter-0] INFO  TaskSetManager - Finished task 6.0 in stage 0.0 (TID 6) in 27915 ms on localhost (executor driver) (5/3618)
 2018-01-30 16:49:44,057 [Executor task launch worker for task 16] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB245654-20161029221927250-00002.warc.gz:0+351548160
 2018-01-30 16:49:45,558 [Executor task launch worker for task 12] INFO  Executor - Finished task 12.0 in stage 0.0 (TID 12). 1846 bytes result sent to driver
 2018-01-30 16:49:45,560 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 17.0 in stage 0.0 (TID 17, localhost, executor driver, partition 17, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:49:45,561 [Executor task launch worker for task 17] INFO  Executor - Running task 17.0 in stage 0.0 (TID 17)
 2018-01-30 16:49:45,561 [task-result-getter-1] INFO  TaskSetManager - Finished task 12.0 in stage 0.0 (TID 12) in 25596 ms on localhost (executor driver) (6/3618)
 2018-01-30 16:49:45,562 [Executor task launch worker for task 17] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-SMFGXK-20121009182602-00000-wbgrp-crawl058.us.archive.org-6680.warc.gz:0+1890859
 2018-01-30 16:49:45,891 [Executor task launch worker for task 17] INFO  Executor - Finished task 17.0 in stage 0.0 (TID 17). 1694 bytes result sent to driver
 2018-01-30 16:49:45,902 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 18.0 in stage 0.0 (TID 18, localhost, executor driver, partition 18, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:45,902 [Executor task launch worker for task 18] INFO  Executor - Running task 18.0 in stage 0.0 (TID 18)
 2018-01-30 16:49:45,902 [task-result-getter-2] INFO  TaskSetManager - Finished task 17.0 in stage 0.0 (TID 17) in 344 ms on localhost (executor driver) (7/3618)
 2018-01-30 16:49:45,904 [Executor task launch worker for task 18] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003030502-00527-crawling209.us.archive.org-6681.warc.gz:0+102322852
 2018-01-30 16:49:50,750 [Executor task launch worker for task 2] INFO  Executor - Finished task 2.0 in stage 0.0 (TID 2). 1763 bytes result sent to driver
 2018-01-30 16:49:50,752 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 19.0 in stage 0.0 (TID 19, localhost, executor driver, partition 19, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:49:50,752 [Executor task launch worker for task 19] INFO  Executor - Running task 19.0 in stage 0.0 (TID 19)
 2018-01-30 16:49:50,752 [task-result-getter-3] INFO  TaskSetManager - Finished task 2.0 in stage 0.0 (TID 2) in 34619 ms on localhost (executor driver) (8/3618)
 2018-01-30 16:49:50,755 [Executor task launch worker for task 19] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003001721-00495-crawling209.us.archive.org-6681.warc.gz:0+112991279
 2018-01-30 16:49:57,422 [Executor task launch worker for task 8] INFO  Executor - Finished task 8.0 in stage 0.0 (TID 8). 1573 bytes result sent to driver
 2018-01-30 16:49:57,423 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 20.0 in stage 0.0 (TID 20, localhost, executor driver, partition 20, PROCESS_LOCAL, 19523 bytes)
 2018-01-30 16:49:57,423 [Executor task launch worker for task 20] INFO  Executor - Running task 20.0 in stage 0.0 (TID 20)
 2018-01-30 16:49:57,423 [task-result-getter-0] INFO  TaskSetManager - Finished task 8.0 in stage 0.0 (TID 8) in 41282 ms on localhost (executor driver) (9/3618)
 2018-01-30 16:49:57,425 [Executor task launch worker for task 20] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-TEST-JOB225705-20160716151400740-00002.warc.gz:0+299996403
 2018-01-30 16:49:57,531 [Executor task launch worker for task 1] INFO  Executor - Finished task 1.0 in stage 0.0 (TID 1). 1846 bytes result sent to driver
 2018-01-30 16:49:57,533 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 21.0 in stage 0.0 (TID 21, localhost, executor driver, partition 21, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 16:49:57,533 [Executor task launch worker for task 21] INFO  Executor - Running task 21.0 in stage 0.0 (TID 21)
 2018-01-30 16:49:57,533 [task-result-getter-1] INFO  TaskSetManager - Finished task 1.0 in stage 0.0 (TID 1) in 41402 ms on localhost (executor driver) (10/3618)
 2018-01-30 16:49:57,535 [Executor task launch worker for task 21] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-3218-20150331000539034-00000-wbgrp-crawl065.us.archive.org-6441.warc.gz:0+84216601
 2018-01-30 16:50:00,385 [Executor task launch worker for task 0] INFO  Executor - Finished task 0.0 in stage 0.0 (TID 0). 1783 bytes result sent to driver
 2018-01-30 16:50:00,386 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 22.0 in stage 0.0 (TID 22, localhost, executor driver, partition 22, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:00,386 [task-result-getter-2] INFO  TaskSetManager - Finished task 0.0 in stage 0.0 (TID 0) in 44286 ms on localhost (executor driver) (11/3618)
 2018-01-30 16:50:00,386 [Executor task launch worker for task 22] INFO  Executor - Running task 22.0 in stage 0.0 (TID 22)
 2018-01-30 16:50:00,388 [Executor task launch worker for task 22] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002202933-00441-crawling209.us.archive.org-6681.warc.gz:0+116145704
 2018-01-30 16:50:01,449 [Executor task launch worker for task 15] INFO  Executor - Finished task 15.0 in stage 0.0 (TID 15). 1573 bytes result sent to driver
 2018-01-30 16:50:01,450 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 23.0 in stage 0.0 (TID 23, localhost, executor driver, partition 23, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:50:01,451 [Executor task launch worker for task 23] INFO  Executor - Running task 23.0 in stage 0.0 (TID 23)
 2018-01-30 16:50:01,451 [task-result-getter-3] INFO  TaskSetManager - Finished task 15.0 in stage 0.0 (TID 15) in 38614 ms on localhost (executor driver) (12/3618)
 2018-01-30 16:50:01,452 [Executor task launch worker for task 23] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB292442-20170424054936326-00004.warc.gz:0+116727838
 2018-01-30 16:50:03,887 [Executor task launch worker for task 22] INFO  Executor - Finished task 22.0 in stage 0.0 (TID 22). 1759 bytes result sent to driver
 2018-01-30 16:50:03,895 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 24.0 in stage 0.0 (TID 24, localhost, executor driver, partition 24, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:50:03,895 [task-result-getter-0] INFO  TaskSetManager - Finished task 22.0 in stage 0.0 (TID 22) in 3510 ms on localhost (executor driver) (13/3618)
 2018-01-30 16:50:03,895 [Executor task launch worker for task 24] INFO  Executor - Running task 24.0 in stage 0.0 (TID 24)
 2018-01-30 16:50:03,902 [Executor task launch worker for task 24] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-DSYXLF-20121213221715-00010-wbgrp-crawl056.us.archive.org-6680.warc.gz:0+29650621
 2018-01-30 16:50:05,480 [Executor task launch worker for task 21] INFO  Executor - Finished task 21.0 in stage 0.0 (TID 21). 1771 bytes result sent to driver
 2018-01-30 16:50:05,481 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 25.0 in stage 0.0 (TID 25, localhost, executor driver, partition 25, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:05,481 [Executor task launch worker for task 25] INFO  Executor - Running task 25.0 in stage 0.0 (TID 25)
 2018-01-30 16:50:05,481 [task-result-getter-1] INFO  TaskSetManager - Finished task 21.0 in stage 0.0 (TID 21) in 7949 ms on localhost (executor driver) (14/3618)
 2018-01-30 16:50:05,482 [Executor task launch worker for task 25] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EQSHTS-20120317095404-00003-crawling200.us.archive.org-6681.warc.gz:0+7090617
 2018-01-30 16:50:05,794 [Executor task launch worker for task 23] INFO  Executor - Finished task 23.0 in stage 0.0 (TID 23). 1759 bytes result sent to driver
 2018-01-30 16:50:05,795 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 26.0 in stage 0.0 (TID 26, localhost, executor driver, partition 26, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:05,795 [task-result-getter-2] INFO  TaskSetManager - Finished task 23.0 in stage 0.0 (TID 23) in 4346 ms on localhost (executor driver) (15/3618)
 2018-01-30 16:50:05,795 [Executor task launch worker for task 26] INFO  Executor - Running task 26.0 in stage 0.0 (TID 26)
 2018-01-30 16:50:05,796 [Executor task launch worker for task 26] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002035209-00180-crawling209.us.archive.org-6681.warc.gz:0+102744154
 2018-01-30 16:50:06,253 [Executor task launch worker for task 25] INFO  Executor - Finished task 25.0 in stage 0.0 (TID 25). 1686 bytes result sent to driver
 2018-01-30 16:50:06,254 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 27.0 in stage 0.0 (TID 27, localhost, executor driver, partition 27, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:06,254 [Executor task launch worker for task 27] INFO  Executor - Running task 27.0 in stage 0.0 (TID 27)
 2018-01-30 16:50:06,255 [task-result-getter-3] INFO  TaskSetManager - Finished task 25.0 in stage 0.0 (TID 25) in 775 ms on localhost (executor driver) (16/3618)
 2018-01-30 16:50:06,256 [Executor task launch worker for task 27] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002130042-00340-crawling209.us.archive.org-6681.warc.gz:0+106985516
 2018-01-30 16:50:06,296 [Executor task launch worker for task 11] INFO  Executor - Finished task 11.0 in stage 0.0 (TID 11). 1573 bytes result sent to driver
 2018-01-30 16:50:06,297 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 28.0 in stage 0.0 (TID 28, localhost, executor driver, partition 28, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:06,298 [task-result-getter-0] INFO  TaskSetManager - Finished task 11.0 in stage 0.0 (TID 11) in 50154 ms on localhost (executor driver) (17/3618)
 2018-01-30 16:50:06,304 [Executor task launch worker for task 28] INFO  Executor - Running task 28.0 in stage 0.0 (TID 28)
 2018-01-30 16:50:06,306 [Executor task launch worker for task 28] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-VPDVIH-20111220121156-00006-crawling114.us.archive.org-6680.warc.gz:0+100808116
 2018-01-30 16:50:07,737 [Executor task launch worker for task 18] INFO  Executor - Finished task 18.0 in stage 0.0 (TID 18). 1759 bytes result sent to driver
 2018-01-30 16:50:07,738 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 29.0 in stage 0.0 (TID 29, localhost, executor driver, partition 29, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 16:50:07,738 [Executor task launch worker for task 29] INFO  Executor - Running task 29.0 in stage 0.0 (TID 29)
 2018-01-30 16:50:07,738 [task-result-getter-1] INFO  TaskSetManager - Finished task 18.0 in stage 0.0 (TID 18) in 21837 ms on localhost (executor driver) (18/3618)
 2018-01-30 16:50:07,740 [Executor task launch worker for task 29] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120612203852-00001-crawling200.us.archive.org-6681.warc.gz:0+100004615
 2018-01-30 16:50:08,742 [Executor task launch worker for task 24] INFO  Executor - Finished task 24.0 in stage 0.0 (TID 24). 1763 bytes result sent to driver
 2018-01-30 16:50:08,743 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 30.0 in stage 0.0 (TID 30, localhost, executor driver, partition 30, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:50:08,743 [Executor task launch worker for task 30] INFO  Executor - Running task 30.0 in stage 0.0 (TID 30)
 2018-01-30 16:50:08,743 [task-result-getter-2] INFO  TaskSetManager - Finished task 24.0 in stage 0.0 (TID 24) in 4849 ms on localhost (executor driver) (19/3618)
 2018-01-30 16:50:08,745 [Executor task launch worker for task 30] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171125045600139-00062.warc.gz:0+1000055861
 2018-01-30 16:50:11,369 [Executor task launch worker for task 19] INFO  Executor - Finished task 19.0 in stage 0.0 (TID 19). 1846 bytes result sent to driver
 2018-01-30 16:50:11,370 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 31.0 in stage 0.0 (TID 31, localhost, executor driver, partition 31, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:50:11,370 [Executor task launch worker for task 31] INFO  Executor - Running task 31.0 in stage 0.0 (TID 31)
 2018-01-30 16:50:11,370 [task-result-getter-3] INFO  TaskSetManager - Finished task 19.0 in stage 0.0 (TID 19) in 20619 ms on localhost (executor driver) (20/3618)
 2018-01-30 16:50:11,372 [Executor task launch worker for task 31] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-5908-20131115213018103-00000-wbgrp-crawl101.us.archive.org-6443.warc.gz:0+167490011
 2018-01-30 16:50:15,887 [Executor task launch worker for task 16] INFO  Executor - Finished task 16.0 in stage 0.0 (TID 16). 1759 bytes result sent to driver
 2018-01-30 16:50:15,888 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 32.0 in stage 0.0 (TID 32, localhost, executor driver, partition 32, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:15,888 [Executor task launch worker for task 32] INFO  Executor - Running task 32.0 in stage 0.0 (TID 32)
 2018-01-30 16:50:15,889 [task-result-getter-0] INFO  TaskSetManager - Finished task 16.0 in stage 0.0 (TID 16) in 31834 ms on localhost (executor driver) (21/3618)
 2018-01-30 16:50:15,890 [Executor task launch worker for task 32] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-JWRICE-20111205180709-00007-crawling210.us.archive.org-6682.warc.gz:0+135607136
 2018-01-30 16:50:21,432 [Executor task launch worker for task 10] INFO  Executor - Finished task 10.0 in stage 0.0 (TID 10). 1918 bytes result sent to driver
 2018-01-30 16:50:21,433 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 33.0 in stage 0.0 (TID 33, localhost, executor driver, partition 33, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:21,433 [Executor task launch worker for task 33] INFO  Executor - Running task 33.0 in stage 0.0 (TID 33)
 2018-01-30 16:50:21,433 [task-result-getter-1] INFO  TaskSetManager - Finished task 10.0 in stage 0.0 (TID 10) in 65291 ms on localhost (executor driver) (22/3618)
 2018-01-30 16:50:21,435 [Executor task launch worker for task 33] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002075050-00260-crawling209.us.archive.org-6681.warc.gz:0+113824413
 2018-01-30 16:50:24,006 [Executor task launch worker for task 31] INFO  Executor - Finished task 31.0 in stage 0.0 (TID 31). 1867 bytes result sent to driver
 2018-01-30 16:50:24,008 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 34.0 in stage 0.0 (TID 34, localhost, executor driver, partition 34, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:24,008 [Executor task launch worker for task 34] INFO  Executor - Running task 34.0 in stage 0.0 (TID 34)
 2018-01-30 16:50:24,009 [task-result-getter-2] INFO  TaskSetManager - Finished task 31.0 in stage 0.0 (TID 31) in 12640 ms on localhost (executor driver) (23/3618)
 2018-01-30 16:50:24,010 [Executor task launch worker for task 34] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301121736-00153-crawling211.us.archive.org-6682.warc.gz:0+102529586
 2018-01-30 16:50:29,978 [Executor task launch worker for task 29] INFO  Executor - Finished task 29.0 in stage 0.0 (TID 29). 1839 bytes result sent to driver
 2018-01-30 16:50:29,979 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 35.0 in stage 0.0 (TID 35, localhost, executor driver, partition 35, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 16:50:29,980 [task-result-getter-3] INFO  TaskSetManager - Finished task 29.0 in stage 0.0 (TID 29) in 22243 ms on localhost (executor driver) (24/3618)
 2018-01-30 16:50:29,980 [Executor task launch worker for task 35] INFO  Executor - Running task 35.0 in stage 0.0 (TID 35)
 2018-01-30 16:50:29,982 [Executor task launch worker for task 35] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QAOHFF-20120412221353-00011-crawling201.us.archive.org-6682.warc.gz:0+100001046
 2018-01-30 16:50:30,048 [Executor task launch worker for task 34] INFO  Executor - Finished task 34.0 in stage 0.0 (TID 34). 1573 bytes result sent to driver
 2018-01-30 16:50:30,049 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 36.0 in stage 0.0 (TID 36, localhost, executor driver, partition 36, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:30,049 [Executor task launch worker for task 36] INFO  Executor - Running task 36.0 in stage 0.0 (TID 36)
 2018-01-30 16:50:30,049 [task-result-getter-0] INFO  TaskSetManager - Finished task 34.0 in stage 0.0 (TID 34) in 6042 ms on localhost (executor driver) (25/3618)
 2018-01-30 16:50:30,052 [Executor task launch worker for task 36] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002115511-00325-crawling209.us.archive.org-6681.warc.gz:0+102722005
 2018-01-30 16:50:31,710 [Executor task launch worker for task 27] INFO  Executor - Finished task 27.0 in stage 0.0 (TID 27). 1763 bytes result sent to driver
 2018-01-30 16:50:31,711 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 37.0 in stage 0.0 (TID 37, localhost, executor driver, partition 37, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:31,711 [Executor task launch worker for task 37] INFO  Executor - Running task 37.0 in stage 0.0 (TID 37)
 2018-01-30 16:50:31,711 [task-result-getter-1] INFO  TaskSetManager - Finished task 27.0 in stage 0.0 (TID 27) in 25457 ms on localhost (executor driver) (26/3618)
 2018-01-30 16:50:31,713 [Executor task launch worker for task 37] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930054551-00087-crawling202.us.archive.org-6681.warc.gz:0+100087253
 2018-01-30 16:50:32,929 [Executor task launch worker for task 5] INFO  Executor - Finished task 5.0 in stage 0.0 (TID 5). 2565 bytes result sent to driver
 2018-01-30 16:50:32,930 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 38.0 in stage 0.0 (TID 38, localhost, executor driver, partition 38, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:50:32,931 [Executor task launch worker for task 38] INFO  Executor - Running task 38.0 in stage 0.0 (TID 38)
 2018-01-30 16:50:32,931 [task-result-getter-2] INFO  TaskSetManager - Finished task 5.0 in stage 0.0 (TID 5) in 76793 ms on localhost (executor driver) (27/3618)
 2018-01-30 16:50:32,933 [Executor task launch worker for task 38] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003135839-00629-crawling209.us.archive.org-6681.warc.gz:0+102073756
 2018-01-30 16:50:34,634 [Executor task launch worker for task 26] INFO  Executor - Finished task 26.0 in stage 0.0 (TID 26). 1767 bytes result sent to driver
 2018-01-30 16:50:34,635 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 39.0 in stage 0.0 (TID 39, localhost, executor driver, partition 39, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:50:34,636 [Executor task launch worker for task 39] INFO  Executor - Running task 39.0 in stage 0.0 (TID 39)
 2018-01-30 16:50:34,637 [Executor task launch worker for task 39] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121012215347-00006-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+101119086
 2018-01-30 16:50:34,638 [task-result-getter-3] INFO  TaskSetManager - Finished task 26.0 in stage 0.0 (TID 26) in 28844 ms on localhost (executor driver) (28/3618)
 2018-01-30 16:50:34,694 [Executor task launch worker for task 28] INFO  Executor - Finished task 28.0 in stage 0.0 (TID 28). 1759 bytes result sent to driver
 2018-01-30 16:50:34,696 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 40.0 in stage 0.0 (TID 40, localhost, executor driver, partition 40, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 16:50:34,696 [Executor task launch worker for task 40] INFO  Executor - Running task 40.0 in stage 0.0 (TID 40)
 2018-01-30 16:50:34,696 [task-result-getter-0] INFO  TaskSetManager - Finished task 28.0 in stage 0.0 (TID 28) in 28399 ms on localhost (executor driver) (29/3618)
 2018-01-30 16:50:34,698 [Executor task launch worker for task 40] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727232757659-00038.warc.gz:0+1000478611
 2018-01-30 16:50:46,963 [Executor task launch worker for task 33] INFO  Executor - Finished task 33.0 in stage 0.0 (TID 33). 1763 bytes result sent to driver
 2018-01-30 16:50:46,968 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 41.0 in stage 0.0 (TID 41, localhost, executor driver, partition 41, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:50:46,969 [Executor task launch worker for task 41] INFO  Executor - Running task 41.0 in stage 0.0 (TID 41)
 2018-01-30 16:50:46,972 [task-result-getter-1] INFO  TaskSetManager - Finished task 33.0 in stage 0.0 (TID 33) in 25540 ms on localhost (executor driver) (30/3618)
 2018-01-30 16:50:46,977 [Executor task launch worker for task 41] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628033357-00015-crawling212.us.archive.org-6682.warc.gz:0+110323495
 2018-01-30 16:50:48,357 [Executor task launch worker for task 36] INFO  Executor - Finished task 36.0 in stage 0.0 (TID 36). 1763 bytes result sent to driver
 2018-01-30 16:50:48,358 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 42.0 in stage 0.0 (TID 42, localhost, executor driver, partition 42, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:50:48,358 [Executor task launch worker for task 42] INFO  Executor - Running task 42.0 in stage 0.0 (TID 42)
 2018-01-30 16:50:48,358 [task-result-getter-2] INFO  TaskSetManager - Finished task 36.0 in stage 0.0 (TID 36) in 18309 ms on localhost (executor driver) (31/3618)
 2018-01-30 16:50:48,359 [Executor task launch worker for task 42] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924165426945-00038.warc.gz:0+1000048481
 2018-01-30 16:51:02,078 [Executor task launch worker for task 32] INFO  Executor - Finished task 32.0 in stage 0.0 (TID 32). 1573 bytes result sent to driver
 2018-01-30 16:51:02,080 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 43.0 in stage 0.0 (TID 43, localhost, executor driver, partition 43, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:51:02,081 [Executor task launch worker for task 43] INFO  Executor - Running task 43.0 in stage 0.0 (TID 43)
 2018-01-30 16:51:02,081 [task-result-getter-3] INFO  TaskSetManager - Finished task 32.0 in stage 0.0 (TID 32) in 46193 ms on localhost (executor driver) (32/3618)
 2018-01-30 16:51:02,084 [Executor task launch worker for task 43] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB263823-20170128001409414-00000.warc.gz:0+56347756
 2018-01-30 16:51:02,503 [Executor task launch worker for task 20] INFO  Executor - Finished task 20.0 in stage 0.0 (TID 20). 1871 bytes result sent to driver
 2018-01-30 16:51:02,504 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 44.0 in stage 0.0 (TID 44, localhost, executor driver, partition 44, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:51:02,504 [Executor task launch worker for task 44] INFO  Executor - Running task 44.0 in stage 0.0 (TID 44)
 2018-01-30 16:51:02,505 [task-result-getter-0] INFO  TaskSetManager - Finished task 20.0 in stage 0.0 (TID 20) in 65083 ms on localhost (executor driver) (33/3618)
 2018-01-30 16:51:02,506 [Executor task launch worker for task 44] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226221209226-00167.warc.gz:0+1000020129
 2018-01-30 16:51:06,664 [Executor task launch worker for task 35] INFO  Executor - Finished task 35.0 in stage 0.0 (TID 35). 1771 bytes result sent to driver
 2018-01-30 16:51:06,665 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 45.0 in stage 0.0 (TID 45, localhost, executor driver, partition 45, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:06,665 [Executor task launch worker for task 45] INFO  Executor - Running task 45.0 in stage 0.0 (TID 45)
 2018-01-30 16:51:06,665 [task-result-getter-1] INFO  TaskSetManager - Finished task 35.0 in stage 0.0 (TID 35) in 36686 ms on localhost (executor driver) (34/3618)
 2018-01-30 16:51:06,669 [Executor task launch worker for task 45] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929210011-00002-crawling202.us.archive.org-6681.warc.gz:0+100115615
 2018-01-30 16:51:08,478 [Executor task launch worker for task 43] INFO  Executor - Finished task 43.0 in stage 0.0 (TID 43). 1835 bytes result sent to driver
 2018-01-30 16:51:08,479 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 46.0 in stage 0.0 (TID 46, localhost, executor driver, partition 46, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 16:51:08,479 [Executor task launch worker for task 46] INFO  Executor - Running task 46.0 in stage 0.0 (TID 46)
 2018-01-30 16:51:08,479 [task-result-getter-2] INFO  TaskSetManager - Finished task 43.0 in stage 0.0 (TID 43) in 6399 ms on localhost (executor driver) (35/3618)
 2018-01-30 16:51:08,487 [Executor task launch worker for task 46] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121229151541-00031-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+122704917
 2018-01-30 16:51:08,624 [Executor task launch worker for task 39] INFO  Executor - Finished task 39.0 in stage 0.0 (TID 39). 1692 bytes result sent to driver
 2018-01-30 16:51:08,625 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 47.0 in stage 0.0 (TID 47, localhost, executor driver, partition 47, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:08,625 [Executor task launch worker for task 47] INFO  Executor - Running task 47.0 in stage 0.0 (TID 47)
 2018-01-30 16:51:08,625 [task-result-getter-3] INFO  TaskSetManager - Finished task 39.0 in stage 0.0 (TID 39) in 33990 ms on localhost (executor driver) (36/3618)
 2018-01-30 16:51:08,626 [Executor task launch worker for task 47] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-XXHVTJ-20120222060537-00002-crawling206.us.archive.org-6683.warc.gz:0+34139034
 2018-01-30 16:51:09,273 [Executor task launch worker for task 37] INFO  Executor - Finished task 37.0 in stage 0.0 (TID 37). 1787 bytes result sent to driver
 2018-01-30 16:51:09,274 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 48.0 in stage 0.0 (TID 48, localhost, executor driver, partition 48, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:09,274 [Executor task launch worker for task 48] INFO  Executor - Running task 48.0 in stage 0.0 (TID 48)
 2018-01-30 16:51:09,274 [task-result-getter-0] INFO  TaskSetManager - Finished task 37.0 in stage 0.0 (TID 37) in 37564 ms on localhost (executor driver) (37/3618)
 2018-01-30 16:51:09,276 [Executor task launch worker for task 48] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930121939-00163-crawling202.us.archive.org-6681.warc.gz:0+100096367
 2018-01-30 16:51:10,478 [Executor task launch worker for task 38] INFO  Executor - Finished task 38.0 in stage 0.0 (TID 38). 1846 bytes result sent to driver
 2018-01-30 16:51:10,480 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 49.0 in stage 0.0 (TID 49, localhost, executor driver, partition 49, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:51:10,481 [Executor task launch worker for task 49] INFO  Executor - Running task 49.0 in stage 0.0 (TID 49)
 2018-01-30 16:51:10,481 [task-result-getter-1] INFO  TaskSetManager - Finished task 38.0 in stage 0.0 (TID 38) in 37551 ms on localhost (executor driver) (38/3618)
 2018-01-30 16:51:10,483 [Executor task launch worker for task 49] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB169816-20150821213040949-00000.warc.gz:0+256418500
 2018-01-30 16:51:13,213 [Executor task launch worker for task 30] INFO  Executor - Finished task 30.0 in stage 0.0 (TID 30). 2041 bytes result sent to driver
 2018-01-30 16:51:13,214 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 50.0 in stage 0.0 (TID 50, localhost, executor driver, partition 50, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:51:13,215 [Executor task launch worker for task 50] INFO  Executor - Running task 50.0 in stage 0.0 (TID 50)
 2018-01-30 16:51:13,215 [task-result-getter-2] INFO  TaskSetManager - Finished task 30.0 in stage 0.0 (TID 30) in 64472 ms on localhost (executor driver) (39/3618)
 2018-01-30 16:51:13,217 [Executor task launch worker for task 50] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224014305664-00005.warc.gz:0+1000006966
 2018-01-30 16:51:14,382 [Executor task launch worker for task 47] INFO  Executor - Finished task 47.0 in stage 0.0 (TID 47). 2129 bytes result sent to driver
 2018-01-30 16:51:14,384 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 51.0 in stage 0.0 (TID 51, localhost, executor driver, partition 51, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:14,384 [Executor task launch worker for task 51] INFO  Executor - Running task 51.0 in stage 0.0 (TID 51)
 2018-01-30 16:51:14,384 [task-result-getter-3] INFO  TaskSetManager - Finished task 47.0 in stage 0.0 (TID 47) in 5760 ms on localhost (executor driver) (40/3618)
 2018-01-30 16:51:14,387 [Executor task launch worker for task 51] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110911185824-00033-crawling211.us.archive.org-6681.warc.gz:0+100976372
 2018-01-30 16:51:30,184 [Executor task launch worker for task 41] INFO  Executor - Finished task 41.0 in stage 0.0 (TID 41). 1660 bytes result sent to driver
 2018-01-30 16:51:30,187 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 52.0 in stage 0.0 (TID 52, localhost, executor driver, partition 52, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:30,188 [task-result-getter-0] INFO  TaskSetManager - Finished task 41.0 in stage 0.0 (TID 41) in 43221 ms on localhost (executor driver) (41/3618)
 2018-01-30 16:51:30,188 [Executor task launch worker for task 52] INFO  Executor - Running task 52.0 in stage 0.0 (TID 52)
 2018-01-30 16:51:30,192 [Executor task launch worker for task 52] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930054403-00086-crawling202.us.archive.org-6681.warc.gz:0+107962956
 2018-01-30 16:51:31,184 [Executor task launch worker for task 49] INFO  Executor - Finished task 49.0 in stage 0.0 (TID 49). 1969 bytes result sent to driver
 2018-01-30 16:51:31,189 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 53.0 in stage 0.0 (TID 53, localhost, executor driver, partition 53, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:51:31,189 [task-result-getter-1] INFO  TaskSetManager - Finished task 49.0 in stage 0.0 (TID 49) in 20709 ms on localhost (executor driver) (42/3618)
 2018-01-30 16:51:31,190 [Executor task launch worker for task 53] INFO  Executor - Running task 53.0 in stage 0.0 (TID 53)
 2018-01-30 16:51:31,193 [Executor task launch worker for task 53] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224085852182-00022.warc.gz:0+1000014976
 2018-01-30 16:51:36,527 [Executor task launch worker for task 45] INFO  Executor - Finished task 45.0 in stage 0.0 (TID 45). 1855 bytes result sent to driver
 2018-01-30 16:51:36,529 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 54.0 in stage 0.0 (TID 54, localhost, executor driver, partition 54, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:36,530 [task-result-getter-2] INFO  TaskSetManager - Finished task 45.0 in stage 0.0 (TID 45) in 29866 ms on localhost (executor driver) (43/3618)
 2018-01-30 16:51:36,544 [Executor task launch worker for task 54] INFO  Executor - Running task 54.0 in stage 0.0 (TID 54)
 2018-01-30 16:51:36,547 [Executor task launch worker for task 54] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003131613-00621-crawling209.us.archive.org-6681.warc.gz:0+104923333
 2018-01-30 16:51:41,226 [Executor task launch worker for task 48] INFO  Executor - Finished task 48.0 in stage 0.0 (TID 48). 1783 bytes result sent to driver
 2018-01-30 16:51:41,229 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 55.0 in stage 0.0 (TID 55, localhost, executor driver, partition 55, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:51:41,229 [Executor task launch worker for task 55] INFO  Executor - Running task 55.0 in stage 0.0 (TID 55)
 2018-01-30 16:51:41,230 [task-result-getter-3] INFO  TaskSetManager - Finished task 48.0 in stage 0.0 (TID 48) in 31955 ms on localhost (executor driver) (44/3618)
 2018-01-30 16:51:41,233 [Executor task launch worker for task 55] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025105605830-00072.warc.gz:0+1000012125
 2018-01-30 16:51:44,465 [Executor task launch worker for task 51] INFO  Executor - Finished task 51.0 in stage 0.0 (TID 51). 1846 bytes result sent to driver
 2018-01-30 16:51:44,467 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 56.0 in stage 0.0 (TID 56, localhost, executor driver, partition 56, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:44,467 [Executor task launch worker for task 56] INFO  Executor - Running task 56.0 in stage 0.0 (TID 56)
 2018-01-30 16:51:44,467 [task-result-getter-0] INFO  TaskSetManager - Finished task 51.0 in stage 0.0 (TID 51) in 30084 ms on localhost (executor driver) (45/3618)
 2018-01-30 16:51:44,469 [Executor task launch worker for task 56] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-XQIAVS-20111129005529-00013-crawling212.us.archive.org-6683.warc.gz:0+100171397
 2018-01-30 16:51:44,649 [Executor task launch worker for task 54] INFO  Executor - Finished task 54.0 in stage 0.0 (TID 54). 1759 bytes result sent to driver
 2018-01-30 16:51:44,651 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 57.0 in stage 0.0 (TID 57, localhost, executor driver, partition 57, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:51:44,651 [Executor task launch worker for task 57] INFO  Executor - Running task 57.0 in stage 0.0 (TID 57)
 2018-01-30 16:51:44,651 [task-result-getter-1] INFO  TaskSetManager - Finished task 54.0 in stage 0.0 (TID 54) in 8122 ms on localhost (executor driver) (46/3618)
 2018-01-30 16:51:44,652 [Executor task launch worker for task 57] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-8609-20141003213025464-00000-wbgrp-crawl057.us.archive.org-6444.warc.gz:0+183536776
 2018-01-30 16:51:47,586 [Executor task launch worker for task 46] INFO  Executor - Finished task 46.0 in stage 0.0 (TID 46). 1573 bytes result sent to driver
 2018-01-30 16:51:47,588 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 58.0 in stage 0.0 (TID 58, localhost, executor driver, partition 58, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:51:47,589 [task-result-getter-2] INFO  TaskSetManager - Finished task 46.0 in stage 0.0 (TID 46) in 39110 ms on localhost (executor driver) (47/3618)
 2018-01-30 16:51:47,589 [Executor task launch worker for task 58] INFO  Executor - Running task 58.0 in stage 0.0 (TID 58)
 2018-01-30 16:51:47,591 [Executor task launch worker for task 58] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB310054-20170623210417177-00001.warc.gz:0+1000114905
 2018-01-30 16:51:53,819 [Executor task launch worker for task 42] INFO  Executor - Finished task 42.0 in stage 0.0 (TID 42). 1954 bytes result sent to driver
 2018-01-30 16:51:53,823 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 59.0 in stage 0.0 (TID 59, localhost, executor driver, partition 59, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:51:53,823 [Executor task launch worker for task 59] INFO  Executor - Running task 59.0 in stage 0.0 (TID 59)
 2018-01-30 16:51:53,824 [task-result-getter-3] INFO  TaskSetManager - Finished task 42.0 in stage 0.0 (TID 42) in 65466 ms on localhost (executor driver) (48/3618)
 2018-01-30 16:51:53,829 [Executor task launch worker for task 59] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-YDUKWP-20111130195517-00008-crawling203.us.archive.org-6680.warc.gz:0+100112975
 2018-01-30 16:52:00,078 [Executor task launch worker for task 57] INFO  Executor - Finished task 57.0 in stage 0.0 (TID 57). 1780 bytes result sent to driver
 2018-01-30 16:52:00,080 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 60.0 in stage 0.0 (TID 60, localhost, executor driver, partition 60, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:52:00,080 [task-result-getter-0] INFO  TaskSetManager - Finished task 57.0 in stage 0.0 (TID 57) in 15430 ms on localhost (executor driver) (49/3618)
 2018-01-30 16:52:00,080 [Executor task launch worker for task 60] INFO  Executor - Running task 60.0 in stage 0.0 (TID 60)
 2018-01-30 16:52:00,083 [Executor task launch worker for task 60] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-6291-20140919214910351-00000-wbgrp-crawl056.us.archive.org-6442.warc.gz:0+116877625
 2018-01-30 16:52:00,481 [Executor task launch worker for task 52] INFO  Executor - Finished task 52.0 in stage 0.0 (TID 52). 1783 bytes result sent to driver
 2018-01-30 16:52:00,482 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 61.0 in stage 0.0 (TID 61, localhost, executor driver, partition 61, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:52:00,482 [Executor task launch worker for task 61] INFO  Executor - Running task 61.0 in stage 0.0 (TID 61)
 2018-01-30 16:52:00,484 [task-result-getter-1] INFO  TaskSetManager - Finished task 52.0 in stage 0.0 (TID 52) in 30298 ms on localhost (executor driver) (50/3618)
 2018-01-30 16:52:00,484 [Executor task launch worker for task 61] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-25116-20130614205208335-00000-wbgrp-crawl051.us.archive.org-6440.warc.gz:0+1169176028
 2018-01-30 16:52:04,279 [Executor task launch worker for task 56] INFO  Executor - Finished task 56.0 in stage 0.0 (TID 56). 1767 bytes result sent to driver
 2018-01-30 16:52:04,280 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 62.0 in stage 0.0 (TID 62, localhost, executor driver, partition 62, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 16:52:04,284 [Executor task launch worker for task 62] INFO  Executor - Running task 62.0 in stage 0.0 (TID 62)
 2018-01-30 16:52:04,284 [task-result-getter-2] INFO  TaskSetManager - Finished task 56.0 in stage 0.0 (TID 56) in 19818 ms on localhost (executor driver) (51/3618)
 2018-01-30 16:52:04,287 [Executor task launch worker for task 62] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-XUHQKQ-20120501182907-00000-crawling212.us.archive.org-6683.warc.gz:0+1898200
 2018-01-30 16:52:04,669 [Executor task launch worker for task 62] INFO  Executor - Finished task 62.0 in stage 0.0 (TID 62). 1690 bytes result sent to driver
 2018-01-30 16:52:04,670 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 63.0 in stage 0.0 (TID 63, localhost, executor driver, partition 63, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:52:04,670 [Executor task launch worker for task 63] INFO  Executor - Running task 63.0 in stage 0.0 (TID 63)
 2018-01-30 16:52:04,670 [task-result-getter-3] INFO  TaskSetManager - Finished task 62.0 in stage 0.0 (TID 62) in 390 ms on localhost (executor driver) (52/3618)
 2018-01-30 16:52:04,672 [Executor task launch worker for task 63] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003033612-00530-crawling209.us.archive.org-6681.warc.gz:0+101514684
 2018-01-30 16:52:08,678 [Executor task launch worker for task 59] INFO  Executor - Finished task 59.0 in stage 0.0 (TID 59). 1759 bytes result sent to driver
 2018-01-30 16:52:08,679 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 64.0 in stage 0.0 (TID 64, localhost, executor driver, partition 64, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:52:08,679 [Executor task launch worker for task 64] INFO  Executor - Running task 64.0 in stage 0.0 (TID 64)
 2018-01-30 16:52:08,679 [task-result-getter-0] INFO  TaskSetManager - Finished task 59.0 in stage 0.0 (TID 59) in 14858 ms on localhost (executor driver) (53/3618)
 2018-01-30 16:52:08,680 [Executor task launch worker for task 64] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-25116-20130616160804290-00008-wbgrp-crawl051.us.archive.org-6440.warc.gz:0+1000139971
 2018-01-30 16:52:11,569 [Executor task launch worker for task 44] INFO  Executor - Finished task 44.0 in stage 0.0 (TID 44). 1839 bytes result sent to driver
 2018-01-30 16:52:11,571 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 65.0 in stage 0.0 (TID 65, localhost, executor driver, partition 65, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:52:11,571 [Executor task launch worker for task 65] INFO  Executor - Running task 65.0 in stage 0.0 (TID 65)
 2018-01-30 16:52:11,572 [task-result-getter-1] INFO  TaskSetManager - Finished task 44.0 in stage 0.0 (TID 44) in 69068 ms on localhost (executor driver) (54/3618)
 2018-01-30 16:52:11,573 [Executor task launch worker for task 65] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB207545-20160416193001255-00001.warc.gz:0+261804550
 2018-01-30 16:52:12,309 [Executor task launch worker for task 63] INFO  Executor - Finished task 63.0 in stage 0.0 (TID 63). 1759 bytes result sent to driver
 2018-01-30 16:52:12,309 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 66.0 in stage 0.0 (TID 66, localhost, executor driver, partition 66, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:52:12,309 [Executor task launch worker for task 66] INFO  Executor - Running task 66.0 in stage 0.0 (TID 66)
 2018-01-30 16:52:12,311 [Executor task launch worker for task 66] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002002330-00124-crawling209.us.archive.org-6681.warc.gz:0+100617284
 2018-01-30 16:52:12,312 [task-result-getter-2] INFO  TaskSetManager - Finished task 63.0 in stage 0.0 (TID 63) in 7642 ms on localhost (executor driver) (55/3618)
 2018-01-30 16:52:19,040 [Executor task launch worker for task 60] INFO  Executor - Finished task 60.0 in stage 0.0 (TID 60). 1875 bytes result sent to driver
 2018-01-30 16:52:19,041 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 67.0 in stage 0.0 (TID 67, localhost, executor driver, partition 67, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:52:19,041 [Executor task launch worker for task 67] INFO  Executor - Running task 67.0 in stage 0.0 (TID 67)
 2018-01-30 16:52:19,041 [task-result-getter-3] INFO  TaskSetManager - Finished task 60.0 in stage 0.0 (TID 60) in 18962 ms on localhost (executor driver) (56/3618)
 2018-01-30 16:52:19,042 [Executor task launch worker for task 67] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002065230-00238-crawling209.us.archive.org-6681.warc.gz:0+105499756
 2018-01-30 16:52:21,701 [Executor task launch worker for task 66] INFO  Executor - Finished task 66.0 in stage 0.0 (TID 66). 1767 bytes result sent to driver
 2018-01-30 16:52:21,702 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 68.0 in stage 0.0 (TID 68, localhost, executor driver, partition 68, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 16:52:21,702 [task-result-getter-0] INFO  TaskSetManager - Finished task 66.0 in stage 0.0 (TID 66) in 9393 ms on localhost (executor driver) (57/3618)
 2018-01-30 16:52:21,702 [Executor task launch worker for task 68] INFO  Executor - Running task 68.0 in stage 0.0 (TID 68)
 2018-01-30 16:52:21,703 [Executor task launch worker for task 68] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150728235905978-00047.warc.gz:0+1000008162
 2018-01-30 16:52:26,036 [Executor task launch worker for task 50] INFO  Executor - Finished task 50.0 in stage 0.0 (TID 50). 1902 bytes result sent to driver
 2018-01-30 16:52:26,037 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 69.0 in stage 0.0 (TID 69, localhost, executor driver, partition 69, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 16:52:26,037 [Executor task launch worker for task 69] INFO  Executor - Running task 69.0 in stage 0.0 (TID 69)
 2018-01-30 16:52:26,039 [Executor task launch worker for task 69] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB193236-20160127072905010-00005.warc.gz:0+1000006891
 2018-01-30 16:52:26,070 [task-result-getter-1] INFO  TaskSetManager - Finished task 50.0 in stage 0.0 (TID 50) in 72835 ms on localhost (executor driver) (58/3618)
 2018-01-30 16:52:28,289 [Executor task launch worker for task 67] INFO  Executor - Finished task 67.0 in stage 0.0 (TID 67). 1676 bytes result sent to driver
 2018-01-30 16:52:28,290 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 70.0 in stage 0.0 (TID 70, localhost, executor driver, partition 70, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:52:28,290 [Executor task launch worker for task 70] INFO  Executor - Running task 70.0 in stage 0.0 (TID 70)
 2018-01-30 16:52:28,293 [task-result-getter-2] INFO  TaskSetManager - Finished task 67.0 in stage 0.0 (TID 67) in 9253 ms on localhost (executor driver) (59/3618)
 2018-01-30 16:52:28,294 [Executor task launch worker for task 70] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024174305252-00041.warc.gz:0+1000026942
 2018-01-30 16:52:40,181 [Executor task launch worker for task 65] INFO  Executor - Finished task 65.0 in stage 0.0 (TID 65). 1759 bytes result sent to driver
 2018-01-30 16:52:40,182 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 71.0 in stage 0.0 (TID 71, localhost, executor driver, partition 71, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:52:40,182 [Executor task launch worker for task 71] INFO  Executor - Running task 71.0 in stage 0.0 (TID 71)
 2018-01-30 16:52:40,183 [task-result-getter-3] INFO  TaskSetManager - Finished task 65.0 in stage 0.0 (TID 65) in 28613 ms on localhost (executor driver) (60/3618)
 2018-01-30 16:52:40,184 [Executor task launch worker for task 71] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002041006-00190-crawling209.us.archive.org-6681.warc.gz:0+100167764
 2018-01-30 16:52:47,380 [Executor task launch worker for task 53] INFO  Executor - Finished task 53.0 in stage 0.0 (TID 53). 1831 bytes result sent to driver
 2018-01-30 16:52:47,381 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 72.0 in stage 0.0 (TID 72, localhost, executor driver, partition 72, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:52:47,381 [Executor task launch worker for task 72] INFO  Executor - Running task 72.0 in stage 0.0 (TID 72)
 2018-01-30 16:52:47,381 [task-result-getter-0] INFO  TaskSetManager - Finished task 53.0 in stage 0.0 (TID 53) in 76192 ms on localhost (executor driver) (61/3618)
 2018-01-30 16:52:47,383 [Executor task launch worker for task 72] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-18963-20131228002448746-00001-wbgrp-crawl060.us.archive.org-6444.warc.gz:0+51641412
 2018-01-30 16:52:49,491 [Executor task launch worker for task 58] INFO  Executor - Finished task 58.0 in stage 0.0 (TID 58). 1759 bytes result sent to driver
 2018-01-30 16:52:49,492 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 73.0 in stage 0.0 (TID 73, localhost, executor driver, partition 73, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:52:49,492 [Executor task launch worker for task 73] INFO  Executor - Running task 73.0 in stage 0.0 (TID 73)
 2018-01-30 16:52:49,494 [Executor task launch worker for task 73] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126144430334-00124.warc.gz:0+1000028762
 2018-01-30 16:52:49,505 [task-result-getter-1] INFO  TaskSetManager - Finished task 58.0 in stage 0.0 (TID 58) in 61918 ms on localhost (executor driver) (62/3618)
 2018-01-30 16:52:51,409 [Executor task launch worker for task 72] INFO  Executor - Finished task 72.0 in stage 0.0 (TID 72). 1759 bytes result sent to driver
 2018-01-30 16:52:51,410 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 74.0 in stage 0.0 (TID 74, localhost, executor driver, partition 74, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:52:51,410 [Executor task launch worker for task 74] INFO  Executor - Running task 74.0 in stage 0.0 (TID 74)
 2018-01-30 16:52:51,411 [task-result-getter-2] INFO  TaskSetManager - Finished task 72.0 in stage 0.0 (TID 72) in 4031 ms on localhost (executor driver) (63/3618)
 2018-01-30 16:52:51,412 [Executor task launch worker for task 74] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628025452-00010-crawling212.us.archive.org-6682.warc.gz:0+114303482
 2018-01-30 16:53:07,962 [Executor task launch worker for task 55] INFO  Executor - Finished task 55.0 in stage 0.0 (TID 55). 2173 bytes result sent to driver
 2018-01-30 16:53:07,963 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 75.0 in stage 0.0 (TID 75, localhost, executor driver, partition 75, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:53:07,963 [Executor task launch worker for task 75] INFO  Executor - Running task 75.0 in stage 0.0 (TID 75)
 2018-01-30 16:53:07,964 [task-result-getter-3] INFO  TaskSetManager - Finished task 55.0 in stage 0.0 (TID 55) in 86736 ms on localhost (executor driver) (64/3618)
 2018-01-30 16:53:07,965 [Executor task launch worker for task 75] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224060645351-00015.warc.gz:0+1000007166
 2018-01-30 16:53:12,604 [Executor task launch worker for task 71] INFO  Executor - Finished task 71.0 in stage 0.0 (TID 71). 1767 bytes result sent to driver
 2018-01-30 16:53:12,605 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 76.0 in stage 0.0 (TID 76, localhost, executor driver, partition 76, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 16:53:12,605 [task-result-getter-0] INFO  TaskSetManager - Finished task 71.0 in stage 0.0 (TID 71) in 32423 ms on localhost (executor driver) (65/3618)
 2018-01-30 16:53:12,605 [Executor task launch worker for task 76] INFO  Executor - Running task 76.0 in stage 0.0 (TID 76)
 2018-01-30 16:53:12,607 [Executor task launch worker for task 76] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121228025148-00003-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+107247666
 2018-01-30 16:53:36,589 [Executor task launch worker for task 70] INFO  Executor - Finished task 70.0 in stage 0.0 (TID 70). 2241 bytes result sent to driver
 2018-01-30 16:53:36,591 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 77.0 in stage 0.0 (TID 77, localhost, executor driver, partition 77, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:53:36,591 [Executor task launch worker for task 77] INFO  Executor - Running task 77.0 in stage 0.0 (TID 77)
 2018-01-30 16:53:36,591 [task-result-getter-1] INFO  TaskSetManager - Finished task 70.0 in stage 0.0 (TID 70) in 68302 ms on localhost (executor driver) (66/3618)
 2018-01-30 16:53:36,592 [Executor task launch worker for task 77] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924092507271-00025.warc.gz:0+1000070362
 2018-01-30 16:53:38,585 [Executor task launch worker for task 74] INFO  Executor - Finished task 74.0 in stage 0.0 (TID 74). 1573 bytes result sent to driver
 2018-01-30 16:53:38,586 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 78.0 in stage 0.0 (TID 78, localhost, executor driver, partition 78, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:53:38,586 [Executor task launch worker for task 78] INFO  Executor - Running task 78.0 in stage 0.0 (TID 78)
 2018-01-30 16:53:38,586 [task-result-getter-2] INFO  TaskSetManager - Finished task 74.0 in stage 0.0 (TID 74) in 47177 ms on localhost (executor driver) (67/3618)
 2018-01-30 16:53:38,587 [Executor task launch worker for task 78] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-KOINAK-20121113001146-00011-wbgrp-crawl057.us.archive.org-6681.warc.gz:0+100002457
 2018-01-30 16:53:40,226 [Executor task launch worker for task 13] INFO  Executor - Finished task 13.0 in stage 0.0 (TID 13). 1811 bytes result sent to driver
 2018-01-30 16:53:40,227 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 79.0 in stage 0.0 (TID 79, localhost, executor driver, partition 79, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 16:53:40,227 [Executor task launch worker for task 79] INFO  Executor - Running task 79.0 in stage 0.0 (TID 79)
 2018-01-30 16:53:40,227 [task-result-getter-3] INFO  TaskSetManager - Finished task 13.0 in stage 0.0 (TID 13) in 257694 ms on localhost (executor driver) (68/3618)
 2018-01-30 16:53:40,228 [Executor task launch worker for task 79] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121229092113-00028-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+229770645
 2018-01-30 16:53:50,602 [Executor task launch worker for task 76] INFO  Executor - Finished task 76.0 in stage 0.0 (TID 76). 1573 bytes result sent to driver
 2018-01-30 16:53:50,603 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 80.0 in stage 0.0 (TID 80, localhost, executor driver, partition 80, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:53:50,604 [task-result-getter-0] INFO  TaskSetManager - Finished task 76.0 in stage 0.0 (TID 76) in 38000 ms on localhost (executor driver) (69/3618)
 2018-01-30 16:53:50,604 [Executor task launch worker for task 80] INFO  Executor - Running task 80.0 in stage 0.0 (TID 80)
 2018-01-30 16:53:50,606 [Executor task launch worker for task 80] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB188217-20151218213029686-00000.warc.gz:0+1000016562
 2018-01-30 16:53:55,746 [Executor task launch worker for task 73] INFO  Executor - Finished task 73.0 in stage 0.0 (TID 73). 2041 bytes result sent to driver
 2018-01-30 16:53:55,746 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 81.0 in stage 0.0 (TID 81, localhost, executor driver, partition 81, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:53:55,747 [Executor task launch worker for task 81] INFO  Executor - Running task 81.0 in stage 0.0 (TID 81)
 2018-01-30 16:53:55,747 [task-result-getter-1] INFO  TaskSetManager - Finished task 73.0 in stage 0.0 (TID 73) in 66256 ms on localhost (executor driver) (70/3618)
 2018-01-30 16:53:55,749 [Executor task launch worker for task 81] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924014451452-00012.warc.gz:0+1000075778
 2018-01-30 16:53:56,647 [Executor task launch worker for task 78] INFO  Executor - Finished task 78.0 in stage 0.0 (TID 78). 1894 bytes result sent to driver
 2018-01-30 16:53:56,647 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 82.0 in stage 0.0 (TID 82, localhost, executor driver, partition 82, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:53:56,648 [Executor task launch worker for task 82] INFO  Executor - Running task 82.0 in stage 0.0 (TID 82)
 2018-01-30 16:53:56,648 [task-result-getter-2] INFO  TaskSetManager - Finished task 78.0 in stage 0.0 (TID 78) in 18063 ms on localhost (executor driver) (71/3618)
 2018-01-30 16:53:56,649 [Executor task launch worker for task 82] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171123191430717-00000.warc.gz:0+1344617494
 2018-01-30 16:54:12,683 [Executor task launch worker for task 75] INFO  Executor - Finished task 75.0 in stage 0.0 (TID 75). 2341 bytes result sent to driver
 2018-01-30 16:54:12,685 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 83.0 in stage 0.0 (TID 83, localhost, executor driver, partition 83, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:54:12,686 [Executor task launch worker for task 83] INFO  Executor - Running task 83.0 in stage 0.0 (TID 83)
 2018-01-30 16:54:12,687 [task-result-getter-3] INFO  TaskSetManager - Finished task 75.0 in stage 0.0 (TID 75) in 64725 ms on localhost (executor driver) (72/3618)
 2018-01-30 16:54:12,688 [Executor task launch worker for task 83] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124010937352-00012.warc.gz:0+1000000847
 2018-01-30 16:54:22,001 [Executor task launch worker for task 3] INFO  Executor - Finished task 3.0 in stage 0.0 (TID 3). 1934 bytes result sent to driver
 2018-01-30 16:54:22,005 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 84.0 in stage 0.0 (TID 84, localhost, executor driver, partition 84, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:22,005 [task-result-getter-0] INFO  TaskSetManager - Finished task 3.0 in stage 0.0 (TID 3) in 305870 ms on localhost (executor driver) (73/3618)
 2018-01-30 16:54:22,005 [Executor task launch worker for task 84] INFO  Executor - Running task 84.0 in stage 0.0 (TID 84)
 2018-01-30 16:54:22,008 [Executor task launch worker for task 84] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003111355-00591-crawling209.us.archive.org-6681.warc.gz:0+103145676
 2018-01-30 16:54:25,558 [Executor task launch worker for task 79] INFO  Executor - Finished task 79.0 in stage 0.0 (TID 79). 1573 bytes result sent to driver
 2018-01-30 16:54:25,559 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 85.0 in stage 0.0 (TID 85, localhost, executor driver, partition 85, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:25,559 [Executor task launch worker for task 85] INFO  Executor - Running task 85.0 in stage 0.0 (TID 85)
 2018-01-30 16:54:25,561 [Executor task launch worker for task 85] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001222154-00095-crawling209.us.archive.org-6681.warc.gz:0+107968505
 2018-01-30 16:54:25,569 [task-result-getter-1] INFO  TaskSetManager - Finished task 79.0 in stage 0.0 (TID 79) in 45343 ms on localhost (executor driver) (74/3618)
 2018-01-30 16:54:27,708 [Executor task launch worker for task 84] INFO  Executor - Finished task 84.0 in stage 0.0 (TID 84). 1759 bytes result sent to driver
 2018-01-30 16:54:27,709 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 86.0 in stage 0.0 (TID 86, localhost, executor driver, partition 86, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:27,709 [Executor task launch worker for task 86] INFO  Executor - Running task 86.0 in stage 0.0 (TID 86)
 2018-01-30 16:54:27,710 [task-result-getter-2] INFO  TaskSetManager - Finished task 84.0 in stage 0.0 (TID 84) in 5705 ms on localhost (executor driver) (75/3618)
 2018-01-30 16:54:27,711 [Executor task launch worker for task 86] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301083426-00097-crawling211.us.archive.org-6682.warc.gz:0+100796632
 2018-01-30 16:54:32,611 [Executor task launch worker for task 85] INFO  Executor - Finished task 85.0 in stage 0.0 (TID 85). 1854 bytes result sent to driver
 2018-01-30 16:54:32,612 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 87.0 in stage 0.0 (TID 87, localhost, executor driver, partition 87, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 16:54:32,613 [Executor task launch worker for task 87] INFO  Executor - Running task 87.0 in stage 0.0 (TID 87)
 2018-01-30 16:54:32,615 [Executor task launch worker for task 87] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120613174023-00014-crawling200.us.archive.org-6681.warc.gz:0+100001699
 2018-01-30 16:54:32,616 [task-result-getter-3] INFO  TaskSetManager - Finished task 85.0 in stage 0.0 (TID 85) in 7058 ms on localhost (executor driver) (76/3618)
 2018-01-30 16:54:45,449 [Executor task launch worker for task 40] INFO  Executor - Finished task 40.0 in stage 0.0 (TID 40). 1882 bytes result sent to driver
 2018-01-30 16:54:45,451 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 88.0 in stage 0.0 (TID 88, localhost, executor driver, partition 88, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 16:54:45,452 [task-result-getter-0] INFO  TaskSetManager - Finished task 40.0 in stage 0.0 (TID 40) in 250757 ms on localhost (executor driver) (77/3618)
 2018-01-30 16:54:45,461 [Executor task launch worker for task 88] INFO  Executor - Running task 88.0 in stage 0.0 (TID 88)
 2018-01-30 16:54:45,463 [Executor task launch worker for task 88] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB184570-20151124131408660-00002.warc.gz:0+1000000528
 2018-01-30 16:54:47,952 [Executor task launch worker for task 87] INFO  Executor - Finished task 87.0 in stage 0.0 (TID 87). 1854 bytes result sent to driver
 2018-01-30 16:54:47,954 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 89.0 in stage 0.0 (TID 89, localhost, executor driver, partition 89, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:47,954 [Executor task launch worker for task 89] INFO  Executor - Running task 89.0 in stage 0.0 (TID 89)
 2018-01-30 16:54:47,955 [task-result-getter-1] INFO  TaskSetManager - Finished task 87.0 in stage 0.0 (TID 87) in 15343 ms on localhost (executor driver) (78/3618)
 2018-01-30 16:54:47,969 [Executor task launch worker for task 89] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002190349-00421-crawling209.us.archive.org-6681.warc.gz:0+109369019
 2018-01-30 16:54:48,383 [Executor task launch worker for task 86] INFO  Executor - Finished task 86.0 in stage 0.0 (TID 86). 1573 bytes result sent to driver
 2018-01-30 16:54:48,384 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 90.0 in stage 0.0 (TID 90, localhost, executor driver, partition 90, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:48,384 [Executor task launch worker for task 90] INFO  Executor - Running task 90.0 in stage 0.0 (TID 90)
 2018-01-30 16:54:48,384 [task-result-getter-2] INFO  TaskSetManager - Finished task 86.0 in stage 0.0 (TID 86) in 20675 ms on localhost (executor driver) (79/3618)
 2018-01-30 16:54:48,385 [Executor task launch worker for task 90] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001194807-00060-crawling209.us.archive.org-6681.warc.gz:0+112972325
 2018-01-30 16:54:56,725 [Executor task launch worker for task 89] INFO  Executor - Finished task 89.0 in stage 0.0 (TID 89). 1759 bytes result sent to driver
 2018-01-30 16:54:56,726 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 91.0 in stage 0.0 (TID 91, localhost, executor driver, partition 91, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:54:56,726 [Executor task launch worker for task 91] INFO  Executor - Running task 91.0 in stage 0.0 (TID 91)
 2018-01-30 16:54:56,726 [task-result-getter-3] INFO  TaskSetManager - Finished task 89.0 in stage 0.0 (TID 89) in 8773 ms on localhost (executor driver) (80/3618)
 2018-01-30 16:54:56,728 [Executor task launch worker for task 91] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB286387-20170325001430891-00000.warc.gz:0+47542123
 2018-01-30 16:54:57,307 [Executor task launch worker for task 90] INFO  Executor - Finished task 90.0 in stage 0.0 (TID 90). 1767 bytes result sent to driver
 2018-01-30 16:54:57,308 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 92.0 in stage 0.0 (TID 92, localhost, executor driver, partition 92, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:57,311 [Executor task launch worker for task 92] INFO  Executor - Running task 92.0 in stage 0.0 (TID 92)
 2018-01-30 16:54:57,311 [task-result-getter-0] INFO  TaskSetManager - Finished task 90.0 in stage 0.0 (TID 90) in 8928 ms on localhost (executor driver) (81/3618)
 2018-01-30 16:54:57,312 [Executor task launch worker for task 92] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002173510-00402-crawling209.us.archive.org-6681.warc.gz:0+103761156
 2018-01-30 16:54:59,532 [Executor task launch worker for task 77] INFO  Executor - Finished task 77.0 in stage 0.0 (TID 77). 1973 bytes result sent to driver
 2018-01-30 16:54:59,533 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 93.0 in stage 0.0 (TID 93, localhost, executor driver, partition 93, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:54:59,534 [task-result-getter-1] INFO  TaskSetManager - Finished task 77.0 in stage 0.0 (TID 77) in 82944 ms on localhost (executor driver) (82/3618)
 2018-01-30 16:54:59,534 [Executor task launch worker for task 93] INFO  Executor - Running task 93.0 in stage 0.0 (TID 93)
 2018-01-30 16:54:59,536 [Executor task launch worker for task 93] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002094845-00295-crawling209.us.archive.org-6681.warc.gz:0+102662502
 2018-01-30 16:55:03,315 [Executor task launch worker for task 91] INFO  Executor - Finished task 91.0 in stage 0.0 (TID 91). 1807 bytes result sent to driver
 2018-01-30 16:55:03,316 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 94.0 in stage 0.0 (TID 94, localhost, executor driver, partition 94, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:55:03,316 [task-result-getter-2] INFO  TaskSetManager - Finished task 91.0 in stage 0.0 (TID 91) in 6591 ms on localhost (executor driver) (83/3618)
 2018-01-30 16:55:03,316 [Executor task launch worker for task 94] INFO  Executor - Running task 94.0 in stage 0.0 (TID 94)
 2018-01-30 16:55:03,319 [Executor task launch worker for task 94] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB306384-20170610001524455-00000.warc.gz:0+54725226
 2018-01-30 16:55:07,109 [Executor task launch worker for task 92] INFO  Executor - Finished task 92.0 in stage 0.0 (TID 92). 1759 bytes result sent to driver
 2018-01-30 16:55:07,111 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 95.0 in stage 0.0 (TID 95, localhost, executor driver, partition 95, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:07,111 [Executor task launch worker for task 95] INFO  Executor - Running task 95.0 in stage 0.0 (TID 95)
 2018-01-30 16:55:07,112 [Executor task launch worker for task 95] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001054110-00006-crawling209.us.archive.org-6681.warc.gz:0+100284215
 2018-01-30 16:55:07,113 [task-result-getter-3] INFO  TaskSetManager - Finished task 92.0 in stage 0.0 (TID 92) in 9805 ms on localhost (executor driver) (84/3618)
 2018-01-30 16:55:07,995 [Executor task launch worker for task 93] INFO  Executor - Finished task 93.0 in stage 0.0 (TID 93). 1763 bytes result sent to driver
 2018-01-30 16:55:07,996 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 96.0 in stage 0.0 (TID 96, localhost, executor driver, partition 96, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 16:55:07,996 [Executor task launch worker for task 96] INFO  Executor - Running task 96.0 in stage 0.0 (TID 96)
 2018-01-30 16:55:07,997 [task-result-getter-0] INFO  TaskSetManager - Finished task 93.0 in stage 0.0 (TID 93) in 8464 ms on localhost (executor driver) (85/3618)
 2018-01-30 16:55:07,998 [Executor task launch worker for task 96] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-JOB165910-20150723191750192-00000.warc.gz:0+1000105212
 2018-01-30 16:55:09,480 [Executor task launch worker for task 81] INFO  Executor - Finished task 81.0 in stage 0.0 (TID 81). 1962 bytes result sent to driver
 2018-01-30 16:55:09,481 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 97.0 in stage 0.0 (TID 97, localhost, executor driver, partition 97, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:55:09,481 [Executor task launch worker for task 97] INFO  Executor - Running task 97.0 in stage 0.0 (TID 97)
 2018-01-30 16:55:09,482 [task-result-getter-1] INFO  TaskSetManager - Finished task 81.0 in stage 0.0 (TID 81) in 73735 ms on localhost (executor driver) (86/3618)
 2018-01-30 16:55:09,483 [Executor task launch worker for task 97] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171123194722917-00002.warc.gz:0+1000030577
 2018-01-30 16:55:10,696 [Executor task launch worker for task 94] INFO  Executor - Finished task 94.0 in stage 0.0 (TID 94). 1799 bytes result sent to driver
 2018-01-30 16:55:10,697 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 98.0 in stage 0.0 (TID 98, localhost, executor driver, partition 98, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:10,697 [Executor task launch worker for task 98] INFO  Executor - Running task 98.0 in stage 0.0 (TID 98)
 2018-01-30 16:55:10,697 [task-result-getter-2] INFO  TaskSetManager - Finished task 94.0 in stage 0.0 (TID 94) in 7381 ms on localhost (executor driver) (87/3618)
 2018-01-30 16:55:10,698 [Executor task launch worker for task 98] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002134552-00350-crawling209.us.archive.org-6681.warc.gz:0+100434293
 2018-01-30 16:55:25,019 [Executor task launch worker for task 95] INFO  Executor - Finished task 95.0 in stage 0.0 (TID 95). 1783 bytes result sent to driver
 2018-01-30 16:55:25,024 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 99.0 in stage 0.0 (TID 99, localhost, executor driver, partition 99, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:25,025 [Executor task launch worker for task 99] INFO  Executor - Running task 99.0 in stage 0.0 (TID 99)
 2018-01-30 16:55:25,025 [task-result-getter-3] INFO  TaskSetManager - Finished task 95.0 in stage 0.0 (TID 95) in 17915 ms on localhost (executor driver) (88/3618)
 2018-01-30 16:55:25,028 [Executor task launch worker for task 99] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001193751-00057-crawling209.us.archive.org-6681.warc.gz:0+101756377
 2018-01-30 16:55:25,635 [Executor task launch worker for task 80] INFO  Executor - Finished task 80.0 in stage 0.0 (TID 80). 1914 bytes result sent to driver
 2018-01-30 16:55:25,636 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 100.0 in stage 0.0 (TID 100, localhost, executor driver, partition 100, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:55:25,636 [Executor task launch worker for task 100] INFO  Executor - Running task 100.0 in stage 0.0 (TID 100)
 2018-01-30 16:55:25,636 [task-result-getter-0] INFO  TaskSetManager - Finished task 80.0 in stage 0.0 (TID 80) in 95033 ms on localhost (executor driver) (89/3618)
 2018-01-30 16:55:25,637 [Executor task launch worker for task 100] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB172599-20150911214236460-00000.warc.gz:0+26846279
 2018-01-30 16:55:28,328 [Executor task launch worker for task 100] INFO  Executor - Finished task 100.0 in stage 0.0 (TID 100). 1778 bytes result sent to driver
 2018-01-30 16:55:28,329 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 101.0 in stage 0.0 (TID 101, localhost, executor driver, partition 101, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 16:55:28,329 [Executor task launch worker for task 101] INFO  Executor - Running task 101.0 in stage 0.0 (TID 101)
 2018-01-30 16:55:28,329 [task-result-getter-1] INFO  TaskSetManager - Finished task 100.0 in stage 0.0 (TID 100) in 2694 ms on localhost (executor driver) (90/3618)
 2018-01-30 16:55:28,331 [Executor task launch worker for task 101] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-RJOMJP-20120103182751-00000-crawling212.us.archive.org-6680.warc.gz:0+1227385
 2018-01-30 16:55:28,528 [Executor task launch worker for task 101] INFO  Executor - Finished task 101.0 in stage 0.0 (TID 101). 1690 bytes result sent to driver
 2018-01-30 16:55:28,529 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 102.0 in stage 0.0 (TID 102, localhost, executor driver, partition 102, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:55:28,529 [Executor task launch worker for task 102] INFO  Executor - Running task 102.0 in stage 0.0 (TID 102)
 2018-01-30 16:55:28,529 [task-result-getter-2] INFO  TaskSetManager - Finished task 101.0 in stage 0.0 (TID 101) in 200 ms on localhost (executor driver) (91/3618)
 2018-01-30 16:55:28,530 [Executor task launch worker for task 102] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-KOINAK-20121112204235-00005-wbgrp-crawl057.us.archive.org-6681.warc.gz:0+114377271
 2018-01-30 16:55:29,160 [Executor task launch worker for task 99] INFO  Executor - Finished task 99.0 in stage 0.0 (TID 99). 1694 bytes result sent to driver
 2018-01-30 16:55:29,161 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 103.0 in stage 0.0 (TID 103, localhost, executor driver, partition 103, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:29,161 [task-result-getter-3] INFO  TaskSetManager - Finished task 99.0 in stage 0.0 (TID 99) in 4138 ms on localhost (executor driver) (92/3618)
 2018-01-30 16:55:29,165 [Executor task launch worker for task 103] INFO  Executor - Running task 103.0 in stage 0.0 (TID 103)
 2018-01-30 16:55:29,167 [Executor task launch worker for task 103] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003081156-00549-crawling209.us.archive.org-6681.warc.gz:0+104891840
 2018-01-30 16:55:30,560 [Executor task launch worker for task 98] INFO  Executor - Finished task 98.0 in stage 0.0 (TID 98). 1763 bytes result sent to driver
 2018-01-30 16:55:30,561 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 104.0 in stage 0.0 (TID 104, localhost, executor driver, partition 104, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:55:30,561 [Executor task launch worker for task 104] INFO  Executor - Running task 104.0 in stage 0.0 (TID 104)
 2018-01-30 16:55:30,561 [task-result-getter-0] INFO  TaskSetManager - Finished task 98.0 in stage 0.0 (TID 98) in 19865 ms on localhost (executor driver) (93/3618)
 2018-01-30 16:55:30,563 [Executor task launch worker for task 104] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120930180437-00111-crawling113.us.archive.org-6683.warc.gz:0+100000094
 2018-01-30 16:55:32,821 [Executor task launch worker for task 83] INFO  Executor - Finished task 83.0 in stage 0.0 (TID 83). 2469 bytes result sent to driver
 2018-01-30 16:55:32,822 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 105.0 in stage 0.0 (TID 105, localhost, executor driver, partition 105, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 16:55:32,822 [task-result-getter-1] INFO  TaskSetManager - Finished task 83.0 in stage 0.0 (TID 83) in 80138 ms on localhost (executor driver) (94/3618)
 2018-01-30 16:55:32,822 [Executor task launch worker for task 105] INFO  Executor - Running task 105.0 in stage 0.0 (TID 105)
 2018-01-30 16:55:32,824 [Executor task launch worker for task 105] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121230155003-00037-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+100000914
 2018-01-30 16:55:38,041 [Executor task launch worker for task 104] INFO  Executor - Finished task 104.0 in stage 0.0 (TID 104). 1573 bytes result sent to driver
 2018-01-30 16:55:38,043 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 106.0 in stage 0.0 (TID 106, localhost, executor driver, partition 106, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:38,043 [Executor task launch worker for task 106] INFO  Executor - Running task 106.0 in stage 0.0 (TID 106)
 2018-01-30 16:55:38,043 [task-result-getter-2] INFO  TaskSetManager - Finished task 104.0 in stage 0.0 (TID 104) in 7482 ms on localhost (executor driver) (95/3618)
 2018-01-30 16:55:38,045 [Executor task launch worker for task 106] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930164718-00211-crawling202.us.archive.org-6681.warc.gz:0+101702887
 2018-01-30 16:55:42,669 [Executor task launch worker for task 68] INFO  Executor - Finished task 68.0 in stage 0.0 (TID 68). 1803 bytes result sent to driver
 2018-01-30 16:55:42,670 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 107.0 in stage 0.0 (TID 107, localhost, executor driver, partition 107, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:42,670 [Executor task launch worker for task 107] INFO  Executor - Running task 107.0 in stage 0.0 (TID 107)
 2018-01-30 16:55:42,671 [task-result-getter-3] INFO  TaskSetManager - Finished task 68.0 in stage 0.0 (TID 68) in 200970 ms on localhost (executor driver) (96/3618)
 2018-01-30 16:55:42,672 [Executor task launch worker for task 107] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003001238-00494-crawling209.us.archive.org-6681.warc.gz:0+102699770
 2018-01-30 16:55:50,517 [Executor task launch worker for task 64] INFO  Executor - Finished task 64.0 in stage 0.0 (TID 64). 1759 bytes result sent to driver
 2018-01-30 16:55:50,519 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 108.0 in stage 0.0 (TID 108, localhost, executor driver, partition 108, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:55:50,519 [task-result-getter-0] INFO  TaskSetManager - Finished task 64.0 in stage 0.0 (TID 64) in 221841 ms on localhost (executor driver) (97/3618)
 2018-01-30 16:55:50,519 [Executor task launch worker for task 108] INFO  Executor - Running task 108.0 in stage 0.0 (TID 108)
 2018-01-30 16:55:50,521 [Executor task launch worker for task 108] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629134224-00066-crawling212.us.archive.org-6682.warc.gz:0+248751109
 2018-01-30 16:55:52,310 [Executor task launch worker for task 105] INFO  Executor - Finished task 105.0 in stage 0.0 (TID 105). 1573 bytes result sent to driver
 2018-01-30 16:55:52,311 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 109.0 in stage 0.0 (TID 109, localhost, executor driver, partition 109, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:55:52,312 [Executor task launch worker for task 109] INFO  Executor - Running task 109.0 in stage 0.0 (TID 109)
 2018-01-30 16:55:52,312 [task-result-getter-1] INFO  TaskSetManager - Finished task 105.0 in stage 0.0 (TID 105) in 19490 ms on localhost (executor driver) (98/3618)
 2018-01-30 16:55:52,313 [Executor task launch worker for task 109] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003022757-00523-crawling209.us.archive.org-6681.warc.gz:0+103665476
 2018-01-30 16:56:00,994 [Executor task launch worker for task 107] INFO  Executor - Finished task 107.0 in stage 0.0 (TID 107). 1759 bytes result sent to driver
 2018-01-30 16:56:00,995 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 110.0 in stage 0.0 (TID 110, localhost, executor driver, partition 110, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:00,996 [Executor task launch worker for task 110] INFO  Executor - Running task 110.0 in stage 0.0 (TID 110)
 2018-01-30 16:56:00,996 [task-result-getter-2] INFO  TaskSetManager - Finished task 107.0 in stage 0.0 (TID 107) in 18326 ms on localhost (executor driver) (99/3618)
 2018-01-30 16:56:00,997 [Executor task launch worker for task 110] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002155800-00379-crawling209.us.archive.org-6681.warc.gz:0+104443242
 2018-01-30 16:56:05,285 [Executor task launch worker for task 103] INFO  Executor - Finished task 103.0 in stage 0.0 (TID 103). 1759 bytes result sent to driver
 2018-01-30 16:56:05,287 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 111.0 in stage 0.0 (TID 111, localhost, executor driver, partition 111, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:05,287 [Executor task launch worker for task 111] INFO  Executor - Running task 111.0 in stage 0.0 (TID 111)
 2018-01-30 16:56:05,287 [task-result-getter-3] INFO  TaskSetManager - Finished task 103.0 in stage 0.0 (TID 103) in 36126 ms on localhost (executor driver) (100/3618)
 2018-01-30 16:56:05,289 [Executor task launch worker for task 111] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301110548-00134-crawling211.us.archive.org-6682.warc.gz:0+105447720
 2018-01-30 16:56:05,806 [Executor task launch worker for task 110] INFO  Executor - Finished task 110.0 in stage 0.0 (TID 110). 1690 bytes result sent to driver
 2018-01-30 16:56:05,807 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 112.0 in stage 0.0 (TID 112, localhost, executor driver, partition 112, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 16:56:05,808 [task-result-getter-0] INFO  TaskSetManager - Finished task 110.0 in stage 0.0 (TID 110) in 4813 ms on localhost (executor driver) (101/3618)
 2018-01-30 16:56:05,808 [Executor task launch worker for task 112] INFO  Executor - Running task 112.0 in stage 0.0 (TID 112)
 2018-01-30 16:56:05,809 [Executor task launch worker for task 112] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-ANNUAL-9747-20131007182526486-00012-wbgrp-crawl058.us.archive.org-6442.warc.gz:0+72752
 2018-01-30 16:56:05,830 [Executor task launch worker for task 112] INFO  Executor - Finished task 112.0 in stage 0.0 (TID 112). 1500 bytes result sent to driver
 2018-01-30 16:56:05,831 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 113.0 in stage 0.0 (TID 113, localhost, executor driver, partition 113, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:56:05,831 [Executor task launch worker for task 113] INFO  Executor - Running task 113.0 in stage 0.0 (TID 113)
 2018-01-30 16:56:05,831 [task-result-getter-1] INFO  TaskSetManager - Finished task 112.0 in stage 0.0 (TID 112) in 24 ms on localhost (executor driver) (102/3618)
 2018-01-30 16:56:05,832 [Executor task launch worker for task 113] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924110959895-00028.warc.gz:0+1000052528
 2018-01-30 16:56:07,662 [Executor task launch worker for task 102] INFO  Executor - Finished task 102.0 in stage 0.0 (TID 102). 1807 bytes result sent to driver
 2018-01-30 16:56:07,663 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 114.0 in stage 0.0 (TID 114, localhost, executor driver, partition 114, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:07,663 [task-result-getter-2] INFO  TaskSetManager - Finished task 102.0 in stage 0.0 (TID 102) in 39135 ms on localhost (executor driver) (103/3618)
 2018-01-30 16:56:07,663 [Executor task launch worker for task 114] INFO  Executor - Running task 114.0 in stage 0.0 (TID 114)
 2018-01-30 16:56:07,665 [Executor task launch worker for task 114] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930143909-00193-crawling202.us.archive.org-6681.warc.gz:0+116389253
 2018-01-30 16:56:08,792 [Executor task launch worker for task 111] INFO  Executor - Finished task 111.0 in stage 0.0 (TID 111). 1500 bytes result sent to driver
 2018-01-30 16:56:08,794 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 115.0 in stage 0.0 (TID 115, localhost, executor driver, partition 115, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:56:08,794 [task-result-getter-3] INFO  TaskSetManager - Finished task 111.0 in stage 0.0 (TID 111) in 3508 ms on localhost (executor driver) (104/3618)
 2018-01-30 16:56:08,794 [Executor task launch worker for task 115] INFO  Executor - Running task 115.0 in stage 0.0 (TID 115)
 2018-01-30 16:56:08,796 [Executor task launch worker for task 115] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-17160-20140529172613336-00001-wbgrp-crawl067.us.archive.org-6443.warc.gz:0+1291891576
 2018-01-30 16:56:12,875 [Executor task launch worker for task 69] INFO  Executor - Finished task 69.0 in stage 0.0 (TID 69). 2025 bytes result sent to driver
 2018-01-30 16:56:12,877 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 116.0 in stage 0.0 (TID 116, localhost, executor driver, partition 116, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:56:12,877 [Executor task launch worker for task 116] INFO  Executor - Running task 116.0 in stage 0.0 (TID 116)
 2018-01-30 16:56:12,877 [task-result-getter-0] INFO  TaskSetManager - Finished task 69.0 in stage 0.0 (TID 69) in 226841 ms on localhost (executor driver) (105/3618)
 2018-01-30 16:56:12,879 [Executor task launch worker for task 116] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226055917357-00129.warc.gz:0+1000038668
 2018-01-30 16:56:15,186 [Executor task launch worker for task 114] INFO  Executor - Finished task 114.0 in stage 0.0 (TID 114). 1870 bytes result sent to driver
 2018-01-30 16:56:15,188 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 117.0 in stage 0.0 (TID 117, localhost, executor driver, partition 117, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:15,188 [task-result-getter-1] INFO  TaskSetManager - Finished task 114.0 in stage 0.0 (TID 114) in 7525 ms on localhost (executor driver) (106/3618)
 2018-01-30 16:56:15,188 [Executor task launch worker for task 117] INFO  Executor - Running task 117.0 in stage 0.0 (TID 117)
 2018-01-30 16:56:15,191 [Executor task launch worker for task 117] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301071039-00076-crawling211.us.archive.org-6682.warc.gz:0+105370312
 2018-01-30 16:56:16,470 [Executor task launch worker for task 106] INFO  Executor - Finished task 106.0 in stage 0.0 (TID 106). 1787 bytes result sent to driver
 2018-01-30 16:56:16,471 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 118.0 in stage 0.0 (TID 118, localhost, executor driver, partition 118, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:16,472 [task-result-getter-2] INFO  TaskSetManager - Finished task 106.0 in stage 0.0 (TID 106) in 38430 ms on localhost (executor driver) (107/3618)
 2018-01-30 16:56:16,472 [Executor task launch worker for task 118] INFO  Executor - Running task 118.0 in stage 0.0 (TID 118)
 2018-01-30 16:56:16,474 [Executor task launch worker for task 118] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301134813-00176-crawling211.us.archive.org-6682.warc.gz:0+100111029
 2018-01-30 16:56:24,210 [Executor task launch worker for task 109] INFO  Executor - Finished task 109.0 in stage 0.0 (TID 109). 1759 bytes result sent to driver
 2018-01-30 16:56:24,213 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 119.0 in stage 0.0 (TID 119, localhost, executor driver, partition 119, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:56:24,214 [Executor task launch worker for task 119] INFO  Executor - Running task 119.0 in stage 0.0 (TID 119)
 2018-01-30 16:56:24,214 [task-result-getter-3] INFO  TaskSetManager - Finished task 109.0 in stage 0.0 (TID 109) in 31903 ms on localhost (executor driver) (108/3618)
 2018-01-30 16:56:24,219 [Executor task launch worker for task 119] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-TWXJWC-20120120153347-00000-crawling114.us.archive.org-6681.warc.gz:0+7905191
 2018-01-30 16:56:25,394 [Executor task launch worker for task 119] INFO  Executor - Finished task 119.0 in stage 0.0 (TID 119). 1706 bytes result sent to driver
 2018-01-30 16:56:25,395 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 120.0 in stage 0.0 (TID 120, localhost, executor driver, partition 120, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:56:25,395 [Executor task launch worker for task 120] INFO  Executor - Running task 120.0 in stage 0.0 (TID 120)
 2018-01-30 16:56:25,396 [task-result-getter-0] INFO  TaskSetManager - Finished task 119.0 in stage 0.0 (TID 119) in 1183 ms on localhost (executor driver) (109/3618)
 2018-01-30 16:56:25,397 [Executor task launch worker for task 120] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629175409-00083-crawling212.us.archive.org-6682.warc.gz:0+108108826
 2018-01-30 16:56:25,659 [Executor task launch worker for task 118] INFO  Executor - Finished task 118.0 in stage 0.0 (TID 118). 1573 bytes result sent to driver
 2018-01-30 16:56:25,660 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 121.0 in stage 0.0 (TID 121, localhost, executor driver, partition 121, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:56:25,660 [Executor task launch worker for task 121] INFO  Executor - Running task 121.0 in stage 0.0 (TID 121)
 2018-01-30 16:56:25,660 [task-result-getter-1] INFO  TaskSetManager - Finished task 118.0 in stage 0.0 (TID 118) in 9189 ms on localhost (executor driver) (110/3618)
 2018-01-30 16:56:25,662 [Executor task launch worker for task 121] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025001839242-00053.warc.gz:0+1000004885
 2018-01-30 16:56:32,668 [Executor task launch worker for task 117] INFO  Executor - Finished task 117.0 in stage 0.0 (TID 117). 1573 bytes result sent to driver
 2018-01-30 16:56:32,669 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 122.0 in stage 0.0 (TID 122, localhost, executor driver, partition 122, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:56:32,669 [Executor task launch worker for task 122] INFO  Executor - Running task 122.0 in stage 0.0 (TID 122)
 2018-01-30 16:56:32,669 [task-result-getter-2] INFO  TaskSetManager - Finished task 117.0 in stage 0.0 (TID 117) in 17482 ms on localhost (executor driver) (111/3618)
 2018-01-30 16:56:32,671 [Executor task launch worker for task 122] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-25116-20130615080818366-00003-wbgrp-crawl051.us.archive.org-6440.warc.gz:0+1001555020
 2018-01-30 16:57:00,233 [Executor task launch worker for task 88] INFO  Executor - Finished task 88.0 in stage 0.0 (TID 88). 1807 bytes result sent to driver
 2018-01-30 16:57:00,234 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 123.0 in stage 0.0 (TID 123, localhost, executor driver, partition 123, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:57:00,234 [task-result-getter-3] INFO  TaskSetManager - Finished task 88.0 in stage 0.0 (TID 88) in 134784 ms on localhost (executor driver) (112/3618)
 2018-01-30 16:57:00,234 [Executor task launch worker for task 123] INFO  Executor - Running task 123.0 in stage 0.0 (TID 123)
 2018-01-30 16:57:00,237 [Executor task launch worker for task 123] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB201053-20160313041251921-00001.warc.gz:0+291508941
 2018-01-30 16:57:02,662 [Executor task launch worker for task 120] INFO  Executor - Finished task 120.0 in stage 0.0 (TID 120). 1573 bytes result sent to driver
 2018-01-30 16:57:02,664 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 124.0 in stage 0.0 (TID 124, localhost, executor driver, partition 124, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:57:02,664 [Executor task launch worker for task 124] INFO  Executor - Running task 124.0 in stage 0.0 (TID 124)
 2018-01-30 16:57:02,664 [task-result-getter-0] INFO  TaskSetManager - Finished task 120.0 in stage 0.0 (TID 120) in 37269 ms on localhost (executor driver) (113/3618)
 2018-01-30 16:57:02,665 [Executor task launch worker for task 124] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB247169-20161105090004840-00001.warc.gz:0+1000019839
 2018-01-30 16:57:10,870 [Executor task launch worker for task 108] INFO  Executor - Finished task 108.0 in stage 0.0 (TID 108). 1573 bytes result sent to driver
 2018-01-30 16:57:10,871 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 125.0 in stage 0.0 (TID 125, localhost, executor driver, partition 125, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:57:10,871 [Executor task launch worker for task 125] INFO  Executor - Running task 125.0 in stage 0.0 (TID 125)
 2018-01-30 16:57:10,871 [task-result-getter-1] INFO  TaskSetManager - Finished task 108.0 in stage 0.0 (TID 108) in 80353 ms on localhost (executor driver) (114/3618)
 2018-01-30 16:57:10,873 [Executor task launch worker for task 125] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-JWRICE-20111205180401-00006-crawling210.us.archive.org-6682.warc.gz:0+114162509
 2018-01-30 16:57:13,495 [Executor task launch worker for task 113] INFO  Executor - Finished task 113.0 in stage 0.0 (TID 113). 2056 bytes result sent to driver
 2018-01-30 16:57:13,496 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 126.0 in stage 0.0 (TID 126, localhost, executor driver, partition 126, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 16:57:13,496 [task-result-getter-2] INFO  TaskSetManager - Finished task 113.0 in stage 0.0 (TID 113) in 67666 ms on localhost (executor driver) (115/3618)
 2018-01-30 16:57:13,497 [Executor task launch worker for task 126] INFO  Executor - Running task 126.0 in stage 0.0 (TID 126)
 2018-01-30 16:57:13,498 [Executor task launch worker for task 126] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB214113-20160524140450606-00001.warc.gz:0+1000006377
 2018-01-30 16:57:19,519 [Executor task launch worker for task 61] INFO  Executor - Finished task 61.0 in stage 0.0 (TID 61). 1942 bytes result sent to driver
 2018-01-30 16:57:19,520 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 127.0 in stage 0.0 (TID 127, localhost, executor driver, partition 127, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:57:19,520 [task-result-getter-3] INFO  TaskSetManager - Finished task 61.0 in stage 0.0 (TID 61) in 319038 ms on localhost (executor driver) (116/3618)
 2018-01-30 16:57:19,524 [Executor task launch worker for task 127] INFO  Executor - Running task 127.0 in stage 0.0 (TID 127)
 2018-01-30 16:57:19,535 [Executor task launch worker for task 127] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171125081756012-00068.warc.gz:0+1000029784
 2018-01-30 16:57:21,114 [Executor task launch worker for task 97] INFO  Executor - Finished task 97.0 in stage 0.0 (TID 97). 3399 bytes result sent to driver
 2018-01-30 16:57:21,114 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 128.0 in stage 0.0 (TID 128, localhost, executor driver, partition 128, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:57:21,114 [Executor task launch worker for task 128] INFO  Executor - Running task 128.0 in stage 0.0 (TID 128)
 2018-01-30 16:57:21,115 [task-result-getter-0] INFO  TaskSetManager - Finished task 97.0 in stage 0.0 (TID 97) in 131634 ms on localhost (executor driver) (117/3618)
 2018-01-30 16:57:21,116 [Executor task launch worker for task 128] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124003645397-00011.warc.gz:0+1000072024
 2018-01-30 16:57:24,981 [Executor task launch worker for task 116] INFO  Executor - Finished task 116.0 in stage 0.0 (TID 116). 1835 bytes result sent to driver
 2018-01-30 16:57:24,982 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 129.0 in stage 0.0 (TID 129, localhost, executor driver, partition 129, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:57:24,983 [task-result-getter-1] INFO  TaskSetManager - Finished task 116.0 in stage 0.0 (TID 116) in 72107 ms on localhost (executor driver) (118/3618)
 2018-01-30 16:57:24,983 [Executor task launch worker for task 129] INFO  Executor - Running task 129.0 in stage 0.0 (TID 129)
 2018-01-30 16:57:24,984 [Executor task launch worker for task 129] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406015032-00010-crawling200.us.archive.org-6682.warc.gz:0+100519235
 2018-01-30 16:57:29,389 [Executor task launch worker for task 123] INFO  Executor - Finished task 123.0 in stage 0.0 (TID 123). 1759 bytes result sent to driver
 2018-01-30 16:57:29,390 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 130.0 in stage 0.0 (TID 130, localhost, executor driver, partition 130, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:57:29,390 [Executor task launch worker for task 130] INFO  Executor - Running task 130.0 in stage 0.0 (TID 130)
 2018-01-30 16:57:29,390 [task-result-getter-2] INFO  TaskSetManager - Finished task 123.0 in stage 0.0 (TID 123) in 29157 ms on localhost (executor driver) (119/3618)
 2018-01-30 16:57:29,392 [Executor task launch worker for task 130] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002121437-00329-crawling209.us.archive.org-6681.warc.gz:0+105475133
 2018-01-30 16:57:32,849 [Executor task launch worker for task 130] INFO  Executor - Finished task 130.0 in stage 0.0 (TID 130). 1690 bytes result sent to driver
 2018-01-30 16:57:32,850 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 131.0 in stage 0.0 (TID 131, localhost, executor driver, partition 131, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:57:32,850 [Executor task launch worker for task 131] INFO  Executor - Running task 131.0 in stage 0.0 (TID 131)
 2018-01-30 16:57:32,850 [task-result-getter-3] INFO  TaskSetManager - Finished task 130.0 in stage 0.0 (TID 130) in 3460 ms on localhost (executor driver) (120/3618)
 2018-01-30 16:57:32,851 [Executor task launch worker for task 131] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-ANNUAL-22707-20130919192400115-00001-wbgrp-crawl064.us.archive.org-6441.warc.gz:0+492650009
 2018-01-30 16:57:34,501 [Executor task launch worker for task 121] INFO  Executor - Finished task 121.0 in stage 0.0 (TID 121). 2033 bytes result sent to driver
 2018-01-30 16:57:34,502 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 132.0 in stage 0.0 (TID 132, localhost, executor driver, partition 132, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:57:34,502 [Executor task launch worker for task 132] INFO  Executor - Running task 132.0 in stage 0.0 (TID 132)
 2018-01-30 16:57:34,502 [task-result-getter-0] INFO  TaskSetManager - Finished task 121.0 in stage 0.0 (TID 121) in 68842 ms on localhost (executor driver) (121/3618)
 2018-01-30 16:57:34,503 [Executor task launch worker for task 132] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225041639153-00065.warc.gz:0+1000013087
 2018-01-30 16:57:41,775 [Executor task launch worker for task 125] INFO  Executor - Finished task 125.0 in stage 0.0 (TID 125). 1573 bytes result sent to driver
 2018-01-30 16:57:41,776 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 133.0 in stage 0.0 (TID 133, localhost, executor driver, partition 133, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:57:41,776 [Executor task launch worker for task 133] INFO  Executor - Running task 133.0 in stage 0.0 (TID 133)
 2018-01-30 16:57:41,776 [task-result-getter-1] INFO  TaskSetManager - Finished task 125.0 in stage 0.0 (TID 125) in 30905 ms on localhost (executor driver) (122/3618)
 2018-01-30 16:57:41,777 [Executor task launch worker for task 133] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-22548-20140411213021265-00000-wbgrp-crawl102.us.archive.org-6444.warc.gz:0+343122273
 2018-01-30 16:57:53,222 [Executor task launch worker for task 129] INFO  Executor - Finished task 129.0 in stage 0.0 (TID 129). 1759 bytes result sent to driver
 2018-01-30 16:57:53,223 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 134.0 in stage 0.0 (TID 134, localhost, executor driver, partition 134, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:57:53,223 [task-result-getter-2] INFO  TaskSetManager - Finished task 129.0 in stage 0.0 (TID 129) in 28241 ms on localhost (executor driver) (123/3618)
 2018-01-30 16:57:53,223 [Executor task launch worker for task 134] INFO  Executor - Running task 134.0 in stage 0.0 (TID 134)
 2018-01-30 16:57:53,224 [Executor task launch worker for task 134] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301113801-00142-crawling211.us.archive.org-6682.warc.gz:0+110431561
 2018-01-30 16:58:23,987 [Executor task launch worker for task 134] INFO  Executor - Finished task 134.0 in stage 0.0 (TID 134). 1573 bytes result sent to driver
 2018-01-30 16:58:23,995 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 135.0 in stage 0.0 (TID 135, localhost, executor driver, partition 135, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:58:23,995 [task-result-getter-3] INFO  TaskSetManager - Finished task 134.0 in stage 0.0 (TID 134) in 30773 ms on localhost (executor driver) (124/3618)
 2018-01-30 16:58:23,995 [Executor task launch worker for task 135] INFO  Executor - Running task 135.0 in stage 0.0 (TID 135)
 2018-01-30 16:58:23,998 [Executor task launch worker for task 135] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-11748-20150109213419318-00000-wbgrp-crawl105.us.archive.org-6446.warc.gz:0+191562104
 2018-01-30 16:58:30,426 [Executor task launch worker for task 128] INFO  Executor - Finished task 128.0 in stage 0.0 (TID 128). 2533 bytes result sent to driver
 2018-01-30 16:58:30,428 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 136.0 in stage 0.0 (TID 136, localhost, executor driver, partition 136, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:58:30,428 [Executor task launch worker for task 136] INFO  Executor - Running task 136.0 in stage 0.0 (TID 136)
 2018-01-30 16:58:30,429 [task-result-getter-0] INFO  TaskSetManager - Finished task 128.0 in stage 0.0 (TID 128) in 69315 ms on localhost (executor driver) (125/3618)
 2018-01-30 16:58:30,431 [Executor task launch worker for task 136] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006053007-00030-crawling205.us.archive.org-6681.warc.gz:0+100118948
 2018-01-30 16:58:31,356 [Executor task launch worker for task 124] INFO  Executor - Finished task 124.0 in stage 0.0 (TID 124). 1759 bytes result sent to driver
 2018-01-30 16:58:31,358 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 137.0 in stage 0.0 (TID 137, localhost, executor driver, partition 137, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:58:31,358 [Executor task launch worker for task 137] INFO  Executor - Running task 137.0 in stage 0.0 (TID 137)
 2018-01-30 16:58:31,358 [task-result-getter-1] INFO  TaskSetManager - Finished task 124.0 in stage 0.0 (TID 124) in 88695 ms on localhost (executor driver) (126/3618)
 2018-01-30 16:58:31,359 [Executor task launch worker for task 137] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002021405-00151-crawling209.us.archive.org-6681.warc.gz:0+103492371
 2018-01-30 16:58:36,356 [Executor task launch worker for task 137] INFO  Executor - Finished task 137.0 in stage 0.0 (TID 137). 1694 bytes result sent to driver
 2018-01-30 16:58:36,357 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 138.0 in stage 0.0 (TID 138, localhost, executor driver, partition 138, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:58:36,358 [Executor task launch worker for task 138] INFO  Executor - Running task 138.0 in stage 0.0 (TID 138)
 2018-01-30 16:58:36,358 [task-result-getter-2] INFO  TaskSetManager - Finished task 137.0 in stage 0.0 (TID 137) in 5001 ms on localhost (executor driver) (127/3618)
 2018-01-30 16:58:36,361 [Executor task launch worker for task 138] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002200117-00435-crawling209.us.archive.org-6681.warc.gz:0+109580308
 2018-01-30 16:58:37,047 [Executor task launch worker for task 127] INFO  Executor - Finished task 127.0 in stage 0.0 (TID 127). 2337 bytes result sent to driver
 2018-01-30 16:58:37,048 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 139.0 in stage 0.0 (TID 139, localhost, executor driver, partition 139, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 16:58:37,049 [Executor task launch worker for task 139] INFO  Executor - Running task 139.0 in stage 0.0 (TID 139)
 2018-01-30 16:58:37,049 [task-result-getter-3] INFO  TaskSetManager - Finished task 127.0 in stage 0.0 (TID 127) in 77530 ms on localhost (executor driver) (128/3618)
 2018-01-30 16:58:37,050 [Executor task launch worker for task 139] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QAOHFF-20120412223839-00013-crawling201.us.archive.org-6682.warc.gz:0+100799830
 2018-01-30 16:58:39,230 [Executor task launch worker for task 135] INFO  Executor - Finished task 135.0 in stage 0.0 (TID 135). 1859 bytes result sent to driver
 2018-01-30 16:58:39,231 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 140.0 in stage 0.0 (TID 140, localhost, executor driver, partition 140, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:58:39,231 [Executor task launch worker for task 140] INFO  Executor - Running task 140.0 in stage 0.0 (TID 140)
 2018-01-30 16:58:39,231 [task-result-getter-0] INFO  TaskSetManager - Finished task 135.0 in stage 0.0 (TID 135) in 15237 ms on localhost (executor driver) (129/3618)
 2018-01-30 16:58:39,232 [Executor task launch worker for task 140] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629155109-00076-crawling212.us.archive.org-6682.warc.gz:0+100536461
 2018-01-30 16:58:40,355 [Executor task launch worker for task 138] INFO  Executor - Finished task 138.0 in stage 0.0 (TID 138). 1759 bytes result sent to driver
 2018-01-30 16:58:40,356 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 141.0 in stage 0.0 (TID 141, localhost, executor driver, partition 141, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:58:40,356 [Executor task launch worker for task 141] INFO  Executor - Running task 141.0 in stage 0.0 (TID 141)
 2018-01-30 16:58:40,356 [task-result-getter-1] INFO  TaskSetManager - Finished task 138.0 in stage 0.0 (TID 138) in 4000 ms on localhost (executor driver) (130/3618)
 2018-01-30 16:58:40,357 [Executor task launch worker for task 141] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002115037-00324-crawling209.us.archive.org-6681.warc.gz:0+100419003
 2018-01-30 16:58:40,414 [Executor task launch worker for task 132] INFO  Executor - Finished task 132.0 in stage 0.0 (TID 132). 1827 bytes result sent to driver
 2018-01-30 16:58:40,415 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 142.0 in stage 0.0 (TID 142, localhost, executor driver, partition 142, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:58:40,415 [task-result-getter-2] INFO  TaskSetManager - Finished task 132.0 in stage 0.0 (TID 132) in 65914 ms on localhost (executor driver) (131/3618)
 2018-01-30 16:58:40,416 [Executor task launch worker for task 142] INFO  Executor - Running task 142.0 in stage 0.0 (TID 142)
 2018-01-30 16:58:40,417 [Executor task launch worker for task 142] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025200024684-00088.warc.gz:0+1000056341
 2018-01-30 16:58:43,483 [Executor task launch worker for task 133] INFO  Executor - Finished task 133.0 in stage 0.0 (TID 133). 1894 bytes result sent to driver
 2018-01-30 16:58:43,484 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 143.0 in stage 0.0 (TID 143, localhost, executor driver, partition 143, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:58:43,485 [Executor task launch worker for task 143] INFO  Executor - Running task 143.0 in stage 0.0 (TID 143)
 2018-01-30 16:58:43,485 [task-result-getter-3] INFO  TaskSetManager - Finished task 133.0 in stage 0.0 (TID 133) in 61710 ms on localhost (executor driver) (132/3618)
 2018-01-30 16:58:43,486 [Executor task launch worker for task 143] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131005001521473-00033-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+5212729
 2018-01-30 16:58:43,785 [Executor task launch worker for task 143] INFO  Executor - Finished task 143.0 in stage 0.0 (TID 143). 1686 bytes result sent to driver
 2018-01-30 16:58:43,786 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 144.0 in stage 0.0 (TID 144, localhost, executor driver, partition 144, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:58:43,786 [Executor task launch worker for task 144] INFO  Executor - Running task 144.0 in stage 0.0 (TID 144)
 2018-01-30 16:58:43,786 [task-result-getter-0] INFO  TaskSetManager - Finished task 143.0 in stage 0.0 (TID 143) in 302 ms on localhost (executor driver) (133/3618)
 2018-01-30 16:58:43,787 [Executor task launch worker for task 144] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124131950003-00034.warc.gz:0+1000027221
 2018-01-30 16:59:08,875 [Executor task launch worker for task 136] INFO  Executor - Finished task 136.0 in stage 0.0 (TID 136). 1759 bytes result sent to driver
 2018-01-30 16:59:08,876 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 145.0 in stage 0.0 (TID 145, localhost, executor driver, partition 145, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 16:59:08,876 [task-result-getter-1] INFO  TaskSetManager - Finished task 136.0 in stage 0.0 (TID 136) in 38449 ms on localhost (executor driver) (134/3618)
 2018-01-30 16:59:08,876 [Executor task launch worker for task 145] INFO  Executor - Running task 145.0 in stage 0.0 (TID 145)
 2018-01-30 16:59:08,878 [Executor task launch worker for task 145] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QRDYRH-20120312213641-00016-crawling113.us.archive.org-6681.warc.gz:0+100004710
 2018-01-30 16:59:09,044 [Executor task launch worker for task 141] INFO  Executor - Finished task 141.0 in stage 0.0 (TID 141). 1763 bytes result sent to driver
 2018-01-30 16:59:09,045 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 146.0 in stage 0.0 (TID 146, localhost, executor driver, partition 146, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:59:09,045 [task-result-getter-2] INFO  TaskSetManager - Finished task 141.0 in stage 0.0 (TID 141) in 28690 ms on localhost (executor driver) (135/3618)
 2018-01-30 16:59:09,045 [Executor task launch worker for task 146] INFO  Executor - Running task 146.0 in stage 0.0 (TID 146)
 2018-01-30 16:59:09,046 [Executor task launch worker for task 146] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126172218403-00129.warc.gz:0+1000060242
 2018-01-30 16:59:13,477 [Executor task launch worker for task 139] INFO  Executor - Finished task 139.0 in stage 0.0 (TID 139). 1767 bytes result sent to driver
 2018-01-30 16:59:13,488 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 147.0 in stage 0.0 (TID 147, localhost, executor driver, partition 147, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:59:13,488 [Executor task launch worker for task 147] INFO  Executor - Running task 147.0 in stage 0.0 (TID 147)
 2018-01-30 16:59:13,509 [task-result-getter-3] INFO  TaskSetManager - Finished task 139.0 in stage 0.0 (TID 139) in 36461 ms on localhost (executor driver) (136/3618)
 2018-01-30 16:59:13,511 [Executor task launch worker for task 147] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-11952-20140606213357739-00000-wbgrp-crawl056.us.archive.org-6441.warc.gz:0+559311373
 2018-01-30 16:59:16,177 [Executor task launch worker for task 140] INFO  Executor - Finished task 140.0 in stage 0.0 (TID 140). 1573 bytes result sent to driver
 2018-01-30 16:59:16,178 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 148.0 in stage 0.0 (TID 148, localhost, executor driver, partition 148, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 16:59:16,179 [task-result-getter-0] INFO  TaskSetManager - Finished task 140.0 in stage 0.0 (TID 140) in 36949 ms on localhost (executor driver) (137/3618)
 2018-01-30 16:59:16,188 [Executor task launch worker for task 148] INFO  Executor - Running task 148.0 in stage 0.0 (TID 148)
 2018-01-30 16:59:16,190 [Executor task launch worker for task 148] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-13149-20131025213017266-00000-wbgrp-crawl057.us.archive.org-6444.warc.gz:0+171172401
 2018-01-30 16:59:26,324 [Executor task launch worker for task 96] INFO  Executor - Finished task 96.0 in stage 0.0 (TID 96). 2148 bytes result sent to driver
 2018-01-30 16:59:26,327 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 149.0 in stage 0.0 (TID 149, localhost, executor driver, partition 149, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 16:59:26,327 [Executor task launch worker for task 149] INFO  Executor - Running task 149.0 in stage 0.0 (TID 149)
 2018-01-30 16:59:26,327 [task-result-getter-1] INFO  TaskSetManager - Finished task 96.0 in stage 0.0 (TID 96) in 258331 ms on localhost (executor driver) (138/3618)
 2018-01-30 16:59:26,330 [Executor task launch worker for task 149] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB203433-20160325213127585-00000.warc.gz:0+1000044785
 2018-01-30 16:59:30,895 [Executor task launch worker for task 148] INFO  Executor - Finished task 148.0 in stage 0.0 (TID 148). 1950 bytes result sent to driver
 2018-01-30 16:59:30,897 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 150.0 in stage 0.0 (TID 150, localhost, executor driver, partition 150, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:59:30,897 [task-result-getter-2] INFO  TaskSetManager - Finished task 148.0 in stage 0.0 (TID 148) in 14720 ms on localhost (executor driver) (139/3618)
 2018-01-30 16:59:30,897 [Executor task launch worker for task 150] INFO  Executor - Running task 150.0 in stage 0.0 (TID 150)
 2018-01-30 16:59:30,901 [Executor task launch worker for task 150] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120630012631-00108-crawling212.us.archive.org-6682.warc.gz:0+100000042
 2018-01-30 16:59:35,913 [Executor task launch worker for task 145] INFO  Executor - Finished task 145.0 in stage 0.0 (TID 145). 1807 bytes result sent to driver
 2018-01-30 16:59:35,915 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 151.0 in stage 0.0 (TID 151, localhost, executor driver, partition 151, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:59:35,915 [Executor task launch worker for task 151] INFO  Executor - Running task 151.0 in stage 0.0 (TID 151)
 2018-01-30 16:59:35,915 [task-result-getter-3] INFO  TaskSetManager - Finished task 145.0 in stage 0.0 (TID 145) in 27039 ms on localhost (executor driver) (140/3618)
 2018-01-30 16:59:35,917 [Executor task launch worker for task 151] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225032629723-00063.warc.gz:0+1000020640
 2018-01-30 16:59:45,380 [Executor task launch worker for task 144] INFO  Executor - Finished task 144.0 in stage 0.0 (TID 144). 1969 bytes result sent to driver
 2018-01-30 16:59:45,382 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 152.0 in stage 0.0 (TID 152, localhost, executor driver, partition 152, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:59:45,383 [Executor task launch worker for task 152] INFO  Executor - Running task 152.0 in stage 0.0 (TID 152)
 2018-01-30 16:59:45,383 [task-result-getter-0] INFO  TaskSetManager - Finished task 144.0 in stage 0.0 (TID 144) in 61598 ms on localhost (executor driver) (141/3618)
 2018-01-30 16:59:45,385 [Executor task launch worker for task 152] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008172643-00003-crawling208.us.archive.org-6683.warc.gz:0+100477468
 2018-01-30 16:59:48,021 [Executor task launch worker for task 142] INFO  Executor - Finished task 142.0 in stage 0.0 (TID 142). 1973 bytes result sent to driver
 2018-01-30 16:59:48,022 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 153.0 in stage 0.0 (TID 153, localhost, executor driver, partition 153, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 16:59:48,022 [Executor task launch worker for task 153] INFO  Executor - Running task 153.0 in stage 0.0 (TID 153)
 2018-01-30 16:59:48,022 [task-result-getter-1] INFO  TaskSetManager - Finished task 142.0 in stage 0.0 (TID 142) in 67608 ms on localhost (executor driver) (142/3618)
 2018-01-30 16:59:48,024 [Executor task launch worker for task 153] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002164506-00390-crawling209.us.archive.org-6681.warc.gz:0+103182255
 2018-01-30 16:59:53,938 [Executor task launch worker for task 150] INFO  Executor - Finished task 150.0 in stage 0.0 (TID 150). 1759 bytes result sent to driver
 2018-01-30 16:59:53,940 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 154.0 in stage 0.0 (TID 154, localhost, executor driver, partition 154, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 16:59:53,940 [Executor task launch worker for task 154] INFO  Executor - Running task 154.0 in stage 0.0 (TID 154)
 2018-01-30 16:59:53,940 [task-result-getter-2] INFO  TaskSetManager - Finished task 150.0 in stage 0.0 (TID 150) in 23044 ms on localhost (executor driver) (143/3618)
 2018-01-30 16:59:53,942 [Executor task launch worker for task 154] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924033454493-00015.warc.gz:0+1000033727
 2018-01-30 16:59:54,379 [Executor task launch worker for task 126] INFO  Executor - Finished task 126.0 in stage 0.0 (TID 126). 1835 bytes result sent to driver
 2018-01-30 16:59:54,380 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 155.0 in stage 0.0 (TID 155, localhost, executor driver, partition 155, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 16:59:54,380 [Executor task launch worker for task 155] INFO  Executor - Running task 155.0 in stage 0.0 (TID 155)
 2018-01-30 16:59:54,381 [task-result-getter-3] INFO  TaskSetManager - Finished task 126.0 in stage 0.0 (TID 126) in 160886 ms on localhost (executor driver) (144/3618)
 2018-01-30 16:59:54,382 [Executor task launch worker for task 155] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120630144014-00109-crawling212.us.archive.org-6682.warc.gz:0+20560145
 2018-01-30 16:59:57,015 [Executor task launch worker for task 155] INFO  Executor - Finished task 155.0 in stage 0.0 (TID 155). 1500 bytes result sent to driver
 2018-01-30 16:59:57,016 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 156.0 in stage 0.0 (TID 156, localhost, executor driver, partition 156, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 16:59:57,016 [Executor task launch worker for task 156] INFO  Executor - Running task 156.0 in stage 0.0 (TID 156)
 2018-01-30 16:59:57,016 [task-result-getter-0] INFO  TaskSetManager - Finished task 155.0 in stage 0.0 (TID 155) in 2636 ms on localhost (executor driver) (145/3618)
 2018-01-30 16:59:57,018 [Executor task launch worker for task 156] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727191240180-00027.warc.gz:0+1002378272
 2018-01-30 17:00:02,087 [Executor task launch worker for task 82] INFO  Executor - Finished task 82.0 in stage 0.0 (TID 82). 2537 bytes result sent to driver
 2018-01-30 17:00:02,089 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 157.0 in stage 0.0 (TID 157, localhost, executor driver, partition 157, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:00:02,089 [task-result-getter-1] INFO  TaskSetManager - Finished task 82.0 in stage 0.0 (TID 82) in 365442 ms on localhost (executor driver) (146/3618)
 2018-01-30 17:00:02,134 [Executor task launch worker for task 157] INFO  Executor - Running task 157.0 in stage 0.0 (TID 157)
 2018-01-30 17:00:02,146 [Executor task launch worker for task 157] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927234016493-00026-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+8216794
 2018-01-30 17:00:02,871 [Executor task launch worker for task 157] INFO  Executor - Finished task 157.0 in stage 0.0 (TID 157). 1686 bytes result sent to driver
 2018-01-30 17:00:02,873 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 158.0 in stage 0.0 (TID 158, localhost, executor driver, partition 158, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:02,873 [Executor task launch worker for task 158] INFO  Executor - Running task 158.0 in stage 0.0 (TID 158)
 2018-01-30 17:00:02,873 [task-result-getter-2] INFO  TaskSetManager - Finished task 157.0 in stage 0.0 (TID 157) in 785 ms on localhost (executor driver) (147/3618)
 2018-01-30 17:00:02,875 [Executor task launch worker for task 158] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930195037-00260-crawling202.us.archive.org-6681.warc.gz:0+109151913
 2018-01-30 17:00:11,458 [Executor task launch worker for task 158] INFO  Executor - Finished task 158.0 in stage 0.0 (TID 158). 1771 bytes result sent to driver
 2018-01-30 17:00:11,460 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 159.0 in stage 0.0 (TID 159, localhost, executor driver, partition 159, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:11,460 [Executor task launch worker for task 159] INFO  Executor - Running task 159.0 in stage 0.0 (TID 159)
 2018-01-30 17:00:11,460 [task-result-getter-3] INFO  TaskSetManager - Finished task 158.0 in stage 0.0 (TID 158) in 8588 ms on localhost (executor driver) (148/3618)
 2018-01-30 17:00:11,462 [Executor task launch worker for task 159] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930193536-00256-crawling202.us.archive.org-6681.warc.gz:0+100189426
 2018-01-30 17:00:14,698 [Executor task launch worker for task 153] INFO  Executor - Finished task 153.0 in stage 0.0 (TID 153). 1763 bytes result sent to driver
 2018-01-30 17:00:14,699 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 160.0 in stage 0.0 (TID 160, localhost, executor driver, partition 160, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:00:14,699 [Executor task launch worker for task 160] INFO  Executor - Running task 160.0 in stage 0.0 (TID 160)
 2018-01-30 17:00:14,699 [task-result-getter-0] INFO  TaskSetManager - Finished task 153.0 in stage 0.0 (TID 153) in 26677 ms on localhost (executor driver) (149/3618)
 2018-01-30 17:00:14,701 [Executor task launch worker for task 160] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929103529-00067-crawling113.us.archive.org-6683.warc.gz:0+293321724
 2018-01-30 17:00:14,991 [Executor task launch worker for task 146] INFO  Executor - Finished task 146.0 in stage 0.0 (TID 146). 1958 bytes result sent to driver
 2018-01-30 17:00:14,991 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 161.0 in stage 0.0 (TID 161, localhost, executor driver, partition 161, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:00:14,991 [Executor task launch worker for task 161] INFO  Executor - Running task 161.0 in stage 0.0 (TID 161)
 2018-01-30 17:00:14,992 [task-result-getter-1] INFO  TaskSetManager - Finished task 146.0 in stage 0.0 (TID 146) in 65947 ms on localhost (executor driver) (150/3618)
 2018-01-30 17:00:14,993 [Executor task launch worker for task 161] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120615153150-00023-crawling200.us.archive.org-6681.warc.gz:0+79365311
 2018-01-30 17:00:16,310 [Executor task launch worker for task 152] INFO  Executor - Finished task 152.0 in stage 0.0 (TID 152). 1763 bytes result sent to driver
 2018-01-30 17:00:16,311 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 162.0 in stage 0.0 (TID 162, localhost, executor driver, partition 162, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:00:16,311 [Executor task launch worker for task 162] INFO  Executor - Running task 162.0 in stage 0.0 (TID 162)
 2018-01-30 17:00:16,311 [task-result-getter-2] INFO  TaskSetManager - Finished task 152.0 in stage 0.0 (TID 152) in 30929 ms on localhost (executor driver) (151/3618)
 2018-01-30 17:00:16,312 [Executor task launch worker for task 162] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-3381-20140905213318595-00000-wbgrp-svc113.us.archive.org-6440.warc.gz:0+181030
 2018-01-30 17:00:16,328 [Executor task launch worker for task 162] INFO  Executor - Finished task 162.0 in stage 0.0 (TID 162). 1500 bytes result sent to driver
 2018-01-30 17:00:16,329 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 163.0 in stage 0.0 (TID 163, localhost, executor driver, partition 163, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:16,329 [task-result-getter-3] INFO  TaskSetManager - Finished task 162.0 in stage 0.0 (TID 162) in 19 ms on localhost (executor driver) (152/3618)
 2018-01-30 17:00:16,329 [Executor task launch worker for task 163] INFO  Executor - Running task 163.0 in stage 0.0 (TID 163)
 2018-01-30 17:00:16,330 [Executor task launch worker for task 163] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301095052-00115-crawling211.us.archive.org-6682.warc.gz:0+101345064
 2018-01-30 17:00:18,254 [Executor task launch worker for task 131] INFO  Executor - Finished task 131.0 in stage 0.0 (TID 131). 1759 bytes result sent to driver
 2018-01-30 17:00:18,255 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 164.0 in stage 0.0 (TID 164, localhost, executor driver, partition 164, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:00:18,256 [Executor task launch worker for task 164] INFO  Executor - Running task 164.0 in stage 0.0 (TID 164)
 2018-01-30 17:00:18,256 [task-result-getter-0] INFO  TaskSetManager - Finished task 131.0 in stage 0.0 (TID 131) in 165406 ms on localhost (executor driver) (153/3618)
 2018-01-30 17:00:18,257 [Executor task launch worker for task 164] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB173656-20150918214439824-00000.warc.gz:0+1000003135
 2018-01-30 17:00:22,930 [Executor task launch worker for task 159] INFO  Executor - Finished task 159.0 in stage 0.0 (TID 159). 1771 bytes result sent to driver
 2018-01-30 17:00:22,932 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 165.0 in stage 0.0 (TID 165, localhost, executor driver, partition 165, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:00:22,932 [task-result-getter-1] INFO  TaskSetManager - Finished task 159.0 in stage 0.0 (TID 159) in 11473 ms on localhost (executor driver) (154/3618)
 2018-01-30 17:00:22,933 [Executor task launch worker for task 165] INFO  Executor - Running task 165.0 in stage 0.0 (TID 165)
 2018-01-30 17:00:22,935 [Executor task launch worker for task 165] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB224318-20160708213100686-00000.warc.gz:0+1000009921
 2018-01-30 17:00:23,903 [Executor task launch worker for task 161] INFO  Executor - Finished task 161.0 in stage 0.0 (TID 161). 1759 bytes result sent to driver
 2018-01-30 17:00:23,904 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 166.0 in stage 0.0 (TID 166, localhost, executor driver, partition 166, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:00:23,904 [Executor task launch worker for task 166] INFO  Executor - Running task 166.0 in stage 0.0 (TID 166)
 2018-01-30 17:00:23,904 [task-result-getter-2] INFO  TaskSetManager - Finished task 161.0 in stage 0.0 (TID 161) in 8913 ms on localhost (executor driver) (155/3618)
 2018-01-30 17:00:23,905 [Executor task launch worker for task 166] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-LFALIS-20120925182725-00000-wbgrp-crawl066.us.archive.org-6682.warc.gz:0+2347725
 2018-01-30 17:00:24,428 [Executor task launch worker for task 166] INFO  Executor - Finished task 166.0 in stage 0.0 (TID 166). 1690 bytes result sent to driver
 2018-01-30 17:00:24,430 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 167.0 in stage 0.0 (TID 167, localhost, executor driver, partition 167, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:00:24,430 [Executor task launch worker for task 167] INFO  Executor - Running task 167.0 in stage 0.0 (TID 167)
 2018-01-30 17:00:24,431 [task-result-getter-3] INFO  TaskSetManager - Finished task 166.0 in stage 0.0 (TID 166) in 528 ms on localhost (executor driver) (156/3618)
 2018-01-30 17:00:24,432 [Executor task launch worker for task 167] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120928135611-00022-crawling113.us.archive.org-6683.warc.gz:0+143208939
 2018-01-30 17:00:41,973 [Executor task launch worker for task 163] INFO  Executor - Finished task 163.0 in stage 0.0 (TID 163). 1573 bytes result sent to driver
 2018-01-30 17:00:41,976 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 168.0 in stage 0.0 (TID 168, localhost, executor driver, partition 168, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:41,976 [Executor task launch worker for task 168] INFO  Executor - Running task 168.0 in stage 0.0 (TID 168)
 2018-01-30 17:00:41,976 [task-result-getter-0] INFO  TaskSetManager - Finished task 163.0 in stage 0.0 (TID 163) in 25647 ms on localhost (executor driver) (157/3618)
 2018-01-30 17:00:41,982 [Executor task launch worker for task 168] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-TTKOLV-20110812145907-00000-crawling204.us.archive.org-6682.warc.gz:0+5301466
 2018-01-30 17:00:42,983 [Executor task launch worker for task 168] INFO  Executor - Finished task 168.0 in stage 0.0 (TID 168). 1774 bytes result sent to driver
 2018-01-30 17:00:42,984 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 169.0 in stage 0.0 (TID 169, localhost, executor driver, partition 169, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:00:42,984 [Executor task launch worker for task 169] INFO  Executor - Running task 169.0 in stage 0.0 (TID 169)
 2018-01-30 17:00:42,984 [task-result-getter-1] INFO  TaskSetManager - Finished task 168.0 in stage 0.0 (TID 168) in 1009 ms on localhost (executor driver) (158/3618)
 2018-01-30 17:00:42,986 [Executor task launch worker for task 169] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB322516-20170819001420528-00000.warc.gz:0+57970439
 2018-01-30 17:00:46,346 [Executor task launch worker for task 151] INFO  Executor - Finished task 151.0 in stage 0.0 (TID 151). 2249 bytes result sent to driver
 2018-01-30 17:00:46,347 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 170.0 in stage 0.0 (TID 170, localhost, executor driver, partition 170, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:46,347 [Executor task launch worker for task 170] INFO  Executor - Running task 170.0 in stage 0.0 (TID 170)
 2018-01-30 17:00:46,347 [task-result-getter-2] INFO  TaskSetManager - Finished task 151.0 in stage 0.0 (TID 151) in 70433 ms on localhost (executor driver) (159/3618)
 2018-01-30 17:00:46,348 [Executor task launch worker for task 170] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008184529-00016-crawling208.us.archive.org-6683.warc.gz:0+103178228
 2018-01-30 17:00:51,591 [Executor task launch worker for task 169] INFO  Executor - Finished task 169.0 in stage 0.0 (TID 169). 1819 bytes result sent to driver
 2018-01-30 17:00:51,592 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 171.0 in stage 0.0 (TID 171, localhost, executor driver, partition 171, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:00:51,592 [Executor task launch worker for task 171] INFO  Executor - Running task 171.0 in stage 0.0 (TID 171)
 2018-01-30 17:00:51,592 [task-result-getter-3] INFO  TaskSetManager - Finished task 169.0 in stage 0.0 (TID 169) in 8608 ms on localhost (executor driver) (160/3618)
 2018-01-30 17:00:51,593 [Executor task launch worker for task 171] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002035305-00181-crawling209.us.archive.org-6681.warc.gz:0+102425474
 2018-01-30 17:00:57,160 [Executor task launch worker for task 149] INFO  Executor - Finished task 149.0 in stage 0.0 (TID 149). 1910 bytes result sent to driver
 2018-01-30 17:00:57,160 [task-result-getter-0] INFO  TaskSetManager - Finished task 149.0 in stage 0.0 (TID 149) in 90834 ms on localhost (executor driver) (161/3618)
 2018-01-30 17:00:57,161 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 172.0 in stage 0.0 (TID 172, localhost, executor driver, partition 172, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:00:57,161 [Executor task launch worker for task 172] INFO  Executor - Running task 172.0 in stage 0.0 (TID 172)
 2018-01-30 17:00:57,162 [Executor task launch worker for task 172] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929192430-00092-crawling113.us.archive.org-6683.warc.gz:0+131088338
 2018-01-30 17:01:00,513 [Executor task launch worker for task 154] INFO  Executor - Finished task 154.0 in stage 0.0 (TID 154). 1969 bytes result sent to driver
 2018-01-30 17:01:00,514 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 173.0 in stage 0.0 (TID 173, localhost, executor driver, partition 173, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:01:00,514 [Executor task launch worker for task 173] INFO  Executor - Running task 173.0 in stage 0.0 (TID 173)
 2018-01-30 17:01:00,514 [task-result-getter-1] INFO  TaskSetManager - Finished task 154.0 in stage 0.0 (TID 154) in 66575 ms on localhost (executor driver) (162/3618)
 2018-01-30 17:01:00,515 [Executor task launch worker for task 173] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929165556-00089-crawling113.us.archive.org-6683.warc.gz:0+112817717
 2018-01-30 17:01:09,850 [Executor task launch worker for task 147] INFO  Executor - Finished task 147.0 in stage 0.0 (TID 147). 1910 bytes result sent to driver
 2018-01-30 17:01:09,851 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 174.0 in stage 0.0 (TID 174, localhost, executor driver, partition 174, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:01:09,851 [Executor task launch worker for task 174] INFO  Executor - Running task 174.0 in stage 0.0 (TID 174)
 2018-01-30 17:01:09,851 [task-result-getter-2] INFO  TaskSetManager - Finished task 147.0 in stage 0.0 (TID 147) in 116374 ms on localhost (executor driver) (163/3618)
 2018-01-30 17:01:09,852 [Executor task launch worker for task 174] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224174625864-00042.warc.gz:0+1000032476
 2018-01-30 17:01:14,068 [Executor task launch worker for task 167] INFO  Executor - Finished task 167.0 in stage 0.0 (TID 167). 1573 bytes result sent to driver
 2018-01-30 17:01:14,069 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 175.0 in stage 0.0 (TID 175, localhost, executor driver, partition 175, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:01:14,069 [Executor task launch worker for task 175] INFO  Executor - Running task 175.0 in stage 0.0 (TID 175)
 2018-01-30 17:01:14,069 [task-result-getter-3] INFO  TaskSetManager - Finished task 167.0 in stage 0.0 (TID 167) in 49640 ms on localhost (executor driver) (164/3618)
 2018-01-30 17:01:14,070 [Executor task launch worker for task 175] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927215516404-00005-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+7818923
 2018-01-30 17:01:14,704 [Executor task launch worker for task 175] INFO  Executor - Finished task 175.0 in stage 0.0 (TID 175). 1690 bytes result sent to driver
 2018-01-30 17:01:14,704 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 176.0 in stage 0.0 (TID 176, localhost, executor driver, partition 176, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:14,704 [Executor task launch worker for task 176] INFO  Executor - Running task 176.0 in stage 0.0 (TID 176)
 2018-01-30 17:01:14,704 [task-result-getter-0] INFO  TaskSetManager - Finished task 175.0 in stage 0.0 (TID 175) in 636 ms on localhost (executor driver) (165/3618)
 2018-01-30 17:01:14,706 [Executor task launch worker for task 176] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003091126-00563-crawling209.us.archive.org-6681.warc.gz:0+105372344
 2018-01-30 17:01:15,950 [Executor task launch worker for task 170] INFO  Executor - Finished task 170.0 in stage 0.0 (TID 170). 1573 bytes result sent to driver
 2018-01-30 17:01:15,951 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 177.0 in stage 0.0 (TID 177, localhost, executor driver, partition 177, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:15,951 [task-result-getter-1] INFO  TaskSetManager - Finished task 170.0 in stage 0.0 (TID 170) in 29604 ms on localhost (executor driver) (166/3618)
 2018-01-30 17:01:15,951 [Executor task launch worker for task 177] INFO  Executor - Running task 177.0 in stage 0.0 (TID 177)
 2018-01-30 17:01:15,952 [Executor task launch worker for task 177] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-MFKVIC-20110729185745-00000-crawling203.us.archive.org-6684.warc.gz:0+7958599
 2018-01-30 17:01:16,874 [Executor task launch worker for task 176] INFO  Executor - Finished task 176.0 in stage 0.0 (TID 176). 1686 bytes result sent to driver
 2018-01-30 17:01:16,874 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 178.0 in stage 0.0 (TID 178, localhost, executor driver, partition 178, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:01:16,874 [task-result-getter-2] INFO  TaskSetManager - Finished task 176.0 in stage 0.0 (TID 176) in 2170 ms on localhost (executor driver) (167/3618)
 2018-01-30 17:01:16,874 [Executor task launch worker for task 178] INFO  Executor - Running task 178.0 in stage 0.0 (TID 178)
 2018-01-30 17:01:16,875 [Executor task launch worker for task 178] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025052259606-00062.warc.gz:0+1000058801
 2018-01-30 17:01:17,531 [Executor task launch worker for task 177] INFO  Executor - Finished task 177.0 in stage 0.0 (TID 177). 1849 bytes result sent to driver
 2018-01-30 17:01:17,532 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 179.0 in stage 0.0 (TID 179, localhost, executor driver, partition 179, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:17,532 [Executor task launch worker for task 179] INFO  Executor - Running task 179.0 in stage 0.0 (TID 179)
 2018-01-30 17:01:17,532 [task-result-getter-3] INFO  TaskSetManager - Finished task 177.0 in stage 0.0 (TID 177) in 1581 ms on localhost (executor driver) (168/3618)
 2018-01-30 17:01:17,533 [Executor task launch worker for task 179] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301171620-00233-crawling211.us.archive.org-6682.warc.gz:0+104755893
 2018-01-30 17:01:21,821 [Executor task launch worker for task 179] INFO  Executor - Finished task 179.0 in stage 0.0 (TID 179). 1573 bytes result sent to driver
 2018-01-30 17:01:21,822 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 180.0 in stage 0.0 (TID 180, localhost, executor driver, partition 180, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:01:21,822 [Executor task launch worker for task 180] INFO  Executor - Running task 180.0 in stage 0.0 (TID 180)
 2018-01-30 17:01:21,822 [task-result-getter-0] INFO  TaskSetManager - Finished task 179.0 in stage 0.0 (TID 179) in 4291 ms on localhost (executor driver) (169/3618)
 2018-01-30 17:01:21,823 [Executor task launch worker for task 180] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927215016254-00004-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+6350062
 2018-01-30 17:01:21,998 [Executor task launch worker for task 171] INFO  Executor - Finished task 171.0 in stage 0.0 (TID 171). 1763 bytes result sent to driver
 2018-01-30 17:01:21,998 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 181.0 in stage 0.0 (TID 181, localhost, executor driver, partition 181, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:01:21,998 [Executor task launch worker for task 181] INFO  Executor - Running task 181.0 in stage 0.0 (TID 181)
 2018-01-30 17:01:21,999 [task-result-getter-1] INFO  TaskSetManager - Finished task 171.0 in stage 0.0 (TID 171) in 30408 ms on localhost (executor driver) (170/3618)
 2018-01-30 17:01:21,999 [Executor task launch worker for task 181] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025152304247-00080.warc.gz:0+1000779046
 2018-01-30 17:01:22,224 [Executor task launch worker for task 180] INFO  Executor - Finished task 180.0 in stage 0.0 (TID 180). 1690 bytes result sent to driver
 2018-01-30 17:01:22,227 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 182.0 in stage 0.0 (TID 182, localhost, executor driver, partition 182, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:22,228 [task-result-getter-2] INFO  TaskSetManager - Finished task 180.0 in stage 0.0 (TID 180) in 407 ms on localhost (executor driver) (171/3618)
 2018-01-30 17:01:22,228 [Executor task launch worker for task 182] INFO  Executor - Running task 182.0 in stage 0.0 (TID 182)
 2018-01-30 17:01:22,229 [Executor task launch worker for task 182] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-XQIAVS-20111129011155-00014-crawling212.us.archive.org-6683.warc.gz:0+118360650
 2018-01-30 17:01:31,407 [Executor task launch worker for task 122] INFO  Executor - Finished task 122.0 in stage 0.0 (TID 122). 1795 bytes result sent to driver
 2018-01-30 17:01:31,408 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 183.0 in stage 0.0 (TID 183, localhost, executor driver, partition 183, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:31,408 [Executor task launch worker for task 183] INFO  Executor - Running task 183.0 in stage 0.0 (TID 183)
 2018-01-30 17:01:31,408 [task-result-getter-3] INFO  TaskSetManager - Finished task 122.0 in stage 0.0 (TID 122) in 298739 ms on localhost (executor driver) (172/3618)
 2018-01-30 17:01:31,409 [Executor task launch worker for task 183] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301130748-00165-crawling211.us.archive.org-6682.warc.gz:0+107127787
 2018-01-30 17:01:33,753 [Executor task launch worker for task 173] INFO  Executor - Finished task 173.0 in stage 0.0 (TID 173). 1573 bytes result sent to driver
 2018-01-30 17:01:33,754 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 184.0 in stage 0.0 (TID 184, localhost, executor driver, partition 184, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:33,754 [Executor task launch worker for task 184] INFO  Executor - Running task 184.0 in stage 0.0 (TID 184)
 2018-01-30 17:01:33,754 [task-result-getter-0] INFO  TaskSetManager - Finished task 173.0 in stage 0.0 (TID 173) in 33240 ms on localhost (executor driver) (173/3618)
 2018-01-30 17:01:33,755 [Executor task launch worker for task 184] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301154107-00206-crawling211.us.archive.org-6682.warc.gz:0+101765378
 2018-01-30 17:01:33,904 [Executor task launch worker for task 183] INFO  Executor - Finished task 183.0 in stage 0.0 (TID 183). 1500 bytes result sent to driver
 2018-01-30 17:01:33,905 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 185.0 in stage 0.0 (TID 185, localhost, executor driver, partition 185, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:33,905 [Executor task launch worker for task 185] INFO  Executor - Running task 185.0 in stage 0.0 (TID 185)
 2018-01-30 17:01:33,905 [task-result-getter-1] INFO  TaskSetManager - Finished task 183.0 in stage 0.0 (TID 183) in 2498 ms on localhost (executor driver) (174/3618)
 2018-01-30 17:01:33,907 [Executor task launch worker for task 185] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301074336-00086-crawling211.us.archive.org-6682.warc.gz:0+111101282
 2018-01-30 17:01:37,474 [Executor task launch worker for task 172] INFO  Executor - Finished task 172.0 in stage 0.0 (TID 172). 1573 bytes result sent to driver
 2018-01-30 17:01:37,475 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 186.0 in stage 0.0 (TID 186, localhost, executor driver, partition 186, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:37,475 [task-result-getter-2] INFO  TaskSetManager - Finished task 172.0 in stage 0.0 (TID 172) in 40314 ms on localhost (executor driver) (175/3618)
 2018-01-30 17:01:37,475 [Executor task launch worker for task 186] INFO  Executor - Running task 186.0 in stage 0.0 (TID 186)
 2018-01-30 17:01:37,476 [Executor task launch worker for task 186] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301081321-00092-crawling211.us.archive.org-6682.warc.gz:0+100214847
 2018-01-30 17:01:38,725 [Executor task launch worker for task 185] INFO  Executor - Finished task 185.0 in stage 0.0 (TID 185). 1573 bytes result sent to driver
 2018-01-30 17:01:38,726 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 187.0 in stage 0.0 (TID 187, localhost, executor driver, partition 187, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:01:38,726 [Executor task launch worker for task 187] INFO  Executor - Running task 187.0 in stage 0.0 (TID 187)
 2018-01-30 17:01:38,726 [task-result-getter-3] INFO  TaskSetManager - Finished task 185.0 in stage 0.0 (TID 185) in 4821 ms on localhost (executor driver) (176/3618)
 2018-01-30 17:01:38,727 [Executor task launch worker for task 187] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-CSRYZP-20120815152431-00018-crawling208.us.archive.org-6681.warc.gz:0+76705443
 2018-01-30 17:01:41,033 [Executor task launch worker for task 160] INFO  Executor - Finished task 160.0 in stage 0.0 (TID 160). 1573 bytes result sent to driver
 2018-01-30 17:01:41,034 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 188.0 in stage 0.0 (TID 188, localhost, executor driver, partition 188, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:01:41,034 [Executor task launch worker for task 188] INFO  Executor - Running task 188.0 in stage 0.0 (TID 188)
 2018-01-30 17:01:41,034 [task-result-getter-0] INFO  TaskSetManager - Finished task 160.0 in stage 0.0 (TID 160) in 86335 ms on localhost (executor driver) (177/3618)
 2018-01-30 17:01:41,035 [Executor task launch worker for task 188] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-QVRPOA-20121113180904-00000-wbgrp-crawl066.us.archive.org-6680.warc.gz:0+2332191
 2018-01-30 17:01:41,457 [Executor task launch worker for task 188] INFO  Executor - Finished task 188.0 in stage 0.0 (TID 188). 1694 bytes result sent to driver
 2018-01-30 17:01:41,458 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 189.0 in stage 0.0 (TID 189, localhost, executor driver, partition 189, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:01:41,460 [Executor task launch worker for task 189] INFO  Executor - Running task 189.0 in stage 0.0 (TID 189)
 2018-01-30 17:01:41,460 [task-result-getter-1] INFO  TaskSetManager - Finished task 188.0 in stage 0.0 (TID 188) in 426 ms on localhost (executor driver) (178/3618)
 2018-01-30 17:01:41,461 [Executor task launch worker for task 189] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-4758-20140912213130333-00000-wbgrp-crawl068.us.archive.org-6444.warc.gz:0+179101996
 2018-01-30 17:01:41,590 [Executor task launch worker for task 184] INFO  Executor - Finished task 184.0 in stage 0.0 (TID 184). 1573 bytes result sent to driver
 2018-01-30 17:01:41,591 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 190.0 in stage 0.0 (TID 190, localhost, executor driver, partition 190, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:41,591 [Executor task launch worker for task 190] INFO  Executor - Running task 190.0 in stage 0.0 (TID 190)
 2018-01-30 17:01:41,591 [task-result-getter-2] INFO  TaskSetManager - Finished task 184.0 in stage 0.0 (TID 184) in 7838 ms on localhost (executor driver) (179/3618)
 2018-01-30 17:01:41,592 [Executor task launch worker for task 190] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930150043-00199-crawling202.us.archive.org-6681.warc.gz:0+100028122
 2018-01-30 17:01:42,847 [Executor task launch worker for task 186] INFO  Executor - Finished task 186.0 in stage 0.0 (TID 186). 1500 bytes result sent to driver
 2018-01-30 17:01:42,849 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 191.0 in stage 0.0 (TID 191, localhost, executor driver, partition 191, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:42,849 [Executor task launch worker for task 191] INFO  Executor - Running task 191.0 in stage 0.0 (TID 191)
 2018-01-30 17:01:42,850 [Executor task launch worker for task 191] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006010838-00015-crawling205.us.archive.org-6681.warc.gz:0+101151905
 2018-01-30 17:01:42,857 [task-result-getter-3] INFO  TaskSetManager - Finished task 186.0 in stage 0.0 (TID 186) in 5382 ms on localhost (executor driver) (180/3618)
 2018-01-30 17:01:47,310 [Executor task launch worker for task 187] INFO  Executor - Finished task 187.0 in stage 0.0 (TID 187). 1759 bytes result sent to driver
 2018-01-30 17:01:47,311 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 192.0 in stage 0.0 (TID 192, localhost, executor driver, partition 192, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:47,312 [Executor task launch worker for task 192] INFO  Executor - Running task 192.0 in stage 0.0 (TID 192)
 2018-01-30 17:01:47,312 [task-result-getter-0] INFO  TaskSetManager - Finished task 187.0 in stage 0.0 (TID 187) in 8586 ms on localhost (executor driver) (181/3618)
 2018-01-30 17:01:47,313 [Executor task launch worker for task 192] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929222536-00034-crawling202.us.archive.org-6681.warc.gz:0+100418881
 2018-01-30 17:01:49,166 [Executor task launch worker for task 182] INFO  Executor - Finished task 182.0 in stage 0.0 (TID 182). 1763 bytes result sent to driver
 2018-01-30 17:01:49,167 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 193.0 in stage 0.0 (TID 193, localhost, executor driver, partition 193, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:49,167 [Executor task launch worker for task 193] INFO  Executor - Running task 193.0 in stage 0.0 (TID 193)
 2018-01-30 17:01:49,168 [task-result-getter-1] INFO  TaskSetManager - Finished task 182.0 in stage 0.0 (TID 182) in 26940 ms on localhost (executor driver) (182/3618)
 2018-01-30 17:01:49,168 [Executor task launch worker for task 193] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930113804-00159-crawling202.us.archive.org-6681.warc.gz:0+100042525
 2018-01-30 17:01:50,869 [Executor task launch worker for task 164] INFO  Executor - Finished task 164.0 in stage 0.0 (TID 164). 1950 bytes result sent to driver
 2018-01-30 17:01:50,870 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 194.0 in stage 0.0 (TID 194, localhost, executor driver, partition 194, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:50,870 [Executor task launch worker for task 194] INFO  Executor - Running task 194.0 in stage 0.0 (TID 194)
 2018-01-30 17:01:50,870 [task-result-getter-2] INFO  TaskSetManager - Finished task 164.0 in stage 0.0 (TID 164) in 92615 ms on localhost (executor driver) (183/3618)
 2018-01-30 17:01:50,871 [Executor task launch worker for task 194] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002025027-00158-crawling209.us.archive.org-6681.warc.gz:0+100000556
 2018-01-30 17:01:54,927 [Executor task launch worker for task 189] INFO  Executor - Finished task 189.0 in stage 0.0 (TID 189). 1847 bytes result sent to driver
 2018-01-30 17:01:54,928 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 195.0 in stage 0.0 (TID 195, localhost, executor driver, partition 195, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:01:54,928 [task-result-getter-3] INFO  TaskSetManager - Finished task 189.0 in stage 0.0 (TID 189) in 13471 ms on localhost (executor driver) (184/3618)
 2018-01-30 17:01:54,928 [Executor task launch worker for task 195] INFO  Executor - Running task 195.0 in stage 0.0 (TID 195)
 2018-01-30 17:01:54,929 [Executor task launch worker for task 195] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QAOHFF-20120412230230-00016-crawling201.us.archive.org-6682.warc.gz:0+113485609
 2018-01-30 17:01:55,463 [Executor task launch worker for task 115] INFO  Executor - Finished task 115.0 in stage 0.0 (TID 115). 1759 bytes result sent to driver
 2018-01-30 17:01:55,464 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 196.0 in stage 0.0 (TID 196, localhost, executor driver, partition 196, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:01:55,464 [Executor task launch worker for task 196] INFO  Executor - Running task 196.0 in stage 0.0 (TID 196)
 2018-01-30 17:01:55,464 [task-result-getter-0] INFO  TaskSetManager - Finished task 115.0 in stage 0.0 (TID 115) in 346671 ms on localhost (executor driver) (185/3618)
 2018-01-30 17:01:55,465 [Executor task launch worker for task 196] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925115100280-00070.warc.gz:0+1000007786
 2018-01-30 17:01:55,713 [Executor task launch worker for task 165] INFO  Executor - Finished task 165.0 in stage 0.0 (TID 165). 1950 bytes result sent to driver
 2018-01-30 17:01:55,714 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 197.0 in stage 0.0 (TID 197, localhost, executor driver, partition 197, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:55,714 [Executor task launch worker for task 197] INFO  Executor - Running task 197.0 in stage 0.0 (TID 197)
 2018-01-30 17:01:55,714 [task-result-getter-1] INFO  TaskSetManager - Finished task 165.0 in stage 0.0 (TID 165) in 92783 ms on localhost (executor driver) (186/3618)
 2018-01-30 17:01:55,716 [Executor task launch worker for task 197] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930135233-00180-crawling202.us.archive.org-6681.warc.gz:0+101512079
 2018-01-30 17:01:56,623 [Executor task launch worker for task 194] INFO  Executor - Finished task 194.0 in stage 0.0 (TID 194). 1767 bytes result sent to driver
 2018-01-30 17:01:56,624 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 198.0 in stage 0.0 (TID 198, localhost, executor driver, partition 198, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:01:56,624 [Executor task launch worker for task 198] INFO  Executor - Running task 198.0 in stage 0.0 (TID 198)
 2018-01-30 17:01:56,624 [task-result-getter-2] INFO  TaskSetManager - Finished task 194.0 in stage 0.0 (TID 194) in 5755 ms on localhost (executor driver) (187/3618)
 2018-01-30 17:01:56,625 [Executor task launch worker for task 198] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002211934-00454-crawling209.us.archive.org-6681.warc.gz:0+100631624
 2018-01-30 17:02:00,697 [Executor task launch worker for task 190] INFO  Executor - Finished task 190.0 in stage 0.0 (TID 190). 1787 bytes result sent to driver
 2018-01-30 17:02:00,698 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 199.0 in stage 0.0 (TID 199, localhost, executor driver, partition 199, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:02:00,698 [Executor task launch worker for task 199] INFO  Executor - Running task 199.0 in stage 0.0 (TID 199)
 2018-01-30 17:02:00,698 [task-result-getter-3] INFO  TaskSetManager - Finished task 190.0 in stage 0.0 (TID 190) in 19107 ms on localhost (executor driver) (188/3618)
 2018-01-30 17:02:00,699 [Executor task launch worker for task 199] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120928031423-00007-crawling113.us.archive.org-6683.warc.gz:0+186021119
 2018-01-30 17:02:01,601 [Executor task launch worker for task 197] INFO  Executor - Finished task 197.0 in stage 0.0 (TID 197). 1779 bytes result sent to driver
 2018-01-30 17:02:01,602 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 200.0 in stage 0.0 (TID 200, localhost, executor driver, partition 200, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:01,602 [Executor task launch worker for task 200] INFO  Executor - Running task 200.0 in stage 0.0 (TID 200)
 2018-01-30 17:02:01,602 [task-result-getter-0] INFO  TaskSetManager - Finished task 197.0 in stage 0.0 (TID 197) in 5889 ms on localhost (executor driver) (189/3618)
 2018-01-30 17:02:01,603 [Executor task launch worker for task 200] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126004857306-00098.warc.gz:0+1000050007
 2018-01-30 17:02:02,795 [Executor task launch worker for task 198] INFO  Executor - Finished task 198.0 in stage 0.0 (TID 198). 1759 bytes result sent to driver
 2018-01-30 17:02:02,799 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 201.0 in stage 0.0 (TID 201, localhost, executor driver, partition 201, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:02,799 [Executor task launch worker for task 201] INFO  Executor - Running task 201.0 in stage 0.0 (TID 201)
 2018-01-30 17:02:02,799 [task-result-getter-1] INFO  TaskSetManager - Finished task 198.0 in stage 0.0 (TID 198) in 6176 ms on localhost (executor driver) (190/3618)
 2018-01-30 17:02:02,800 [Executor task launch worker for task 201] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003052903-00541-crawling209.us.archive.org-6681.warc.gz:0+101487514
 2018-01-30 17:02:03,417 [Executor task launch worker for task 191] INFO  Executor - Finished task 191.0 in stage 0.0 (TID 191). 1767 bytes result sent to driver
 2018-01-30 17:02:03,417 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 202.0 in stage 0.0 (TID 202, localhost, executor driver, partition 202, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:03,417 [Executor task launch worker for task 202] INFO  Executor - Running task 202.0 in stage 0.0 (TID 202)
 2018-01-30 17:02:03,418 [task-result-getter-2] INFO  TaskSetManager - Finished task 191.0 in stage 0.0 (TID 191) in 20570 ms on localhost (executor driver) (191/3618)
 2018-01-30 17:02:03,418 [Executor task launch worker for task 202] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-LJUPFF-20111220163944-00002-crawling205.us.archive.org-6681.warc.gz:0+100269555
 2018-01-30 17:02:06,287 [Executor task launch worker for task 201] INFO  Executor - Finished task 201.0 in stage 0.0 (TID 201). 1686 bytes result sent to driver
 2018-01-30 17:02:06,291 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 203.0 in stage 0.0 (TID 203, localhost, executor driver, partition 203, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:06,291 [Executor task launch worker for task 203] INFO  Executor - Running task 203.0 in stage 0.0 (TID 203)
 2018-01-30 17:02:06,291 [task-result-getter-3] INFO  TaskSetManager - Finished task 201.0 in stage 0.0 (TID 201) in 3493 ms on localhost (executor driver) (192/3618)
 2018-01-30 17:02:06,292 [Executor task launch worker for task 203] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110909160035-00001-crawling211.us.archive.org-6681.warc.gz:0+100658991
 2018-01-30 17:02:06,407 [Executor task launch worker for task 192] INFO  Executor - Finished task 192.0 in stage 0.0 (TID 192). 1799 bytes result sent to driver
 2018-01-30 17:02:06,408 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 204.0 in stage 0.0 (TID 204, localhost, executor driver, partition 204, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:06,408 [Executor task launch worker for task 204] INFO  Executor - Running task 204.0 in stage 0.0 (TID 204)
 2018-01-30 17:02:06,408 [task-result-getter-0] INFO  TaskSetManager - Finished task 192.0 in stage 0.0 (TID 192) in 19097 ms on localhost (executor driver) (193/3618)
 2018-01-30 17:02:06,409 [Executor task launch worker for task 204] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171125231414545-00095.warc.gz:0+1000001987
 2018-01-30 17:02:10,751 [Executor task launch worker for task 193] INFO  Executor - Finished task 193.0 in stage 0.0 (TID 193). 1811 bytes result sent to driver
 2018-01-30 17:02:10,752 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 205.0 in stage 0.0 (TID 205, localhost, executor driver, partition 205, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:10,752 [Executor task launch worker for task 205] INFO  Executor - Running task 205.0 in stage 0.0 (TID 205)
 2018-01-30 17:02:10,752 [task-result-getter-1] INFO  TaskSetManager - Finished task 193.0 in stage 0.0 (TID 193) in 21585 ms on localhost (executor driver) (194/3618)
 2018-01-30 17:02:10,753 [Executor task launch worker for task 205] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002151816-00370-crawling209.us.archive.org-6681.warc.gz:0+107571918
 2018-01-30 17:02:17,960 [Executor task launch worker for task 174] INFO  Executor - Finished task 174.0 in stage 0.0 (TID 174). 1835 bytes result sent to driver
 2018-01-30 17:02:17,961 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 206.0 in stage 0.0 (TID 206, localhost, executor driver, partition 206, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:17,962 [Executor task launch worker for task 206] INFO  Executor - Running task 206.0 in stage 0.0 (TID 206)
 2018-01-30 17:02:17,962 [task-result-getter-2] INFO  TaskSetManager - Finished task 174.0 in stage 0.0 (TID 174) in 68112 ms on localhost (executor driver) (195/3618)
 2018-01-30 17:02:17,963 [Executor task launch worker for task 206] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224214600222-00051.warc.gz:0+1000014298
 2018-01-30 17:02:19,629 [Executor task launch worker for task 205] INFO  Executor - Finished task 205.0 in stage 0.0 (TID 205). 1763 bytes result sent to driver
 2018-01-30 17:02:19,630 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 207.0 in stage 0.0 (TID 207, localhost, executor driver, partition 207, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:19,630 [Executor task launch worker for task 207] INFO  Executor - Running task 207.0 in stage 0.0 (TID 207)
 2018-01-30 17:02:19,630 [task-result-getter-3] INFO  TaskSetManager - Finished task 205.0 in stage 0.0 (TID 205) in 8879 ms on localhost (executor driver) (196/3618)
 2018-01-30 17:02:19,631 [Executor task launch worker for task 207] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226005129030-00116.warc.gz:0+1000005106
 2018-01-30 17:02:19,920 [Executor task launch worker for task 195] INFO  Executor - Finished task 195.0 in stage 0.0 (TID 195). 1767 bytes result sent to driver
 2018-01-30 17:02:19,921 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 208.0 in stage 0.0 (TID 208, localhost, executor driver, partition 208, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:19,921 [Executor task launch worker for task 208] INFO  Executor - Running task 208.0 in stage 0.0 (TID 208)
 2018-01-30 17:02:19,922 [Executor task launch worker for task 208] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001201454-00067-crawling209.us.archive.org-6681.warc.gz:0+100020590
 2018-01-30 17:02:19,923 [task-result-getter-0] INFO  TaskSetManager - Finished task 195.0 in stage 0.0 (TID 195) in 24995 ms on localhost (executor driver) (197/3618)
 2018-01-30 17:02:23,059 [Executor task launch worker for task 202] INFO  Executor - Finished task 202.0 in stage 0.0 (TID 202). 1759 bytes result sent to driver
 2018-01-30 17:02:23,061 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 209.0 in stage 0.0 (TID 209, localhost, executor driver, partition 209, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:02:23,061 [Executor task launch worker for task 209] INFO  Executor - Running task 209.0 in stage 0.0 (TID 209)
 2018-01-30 17:02:23,062 [task-result-getter-1] INFO  TaskSetManager - Finished task 202.0 in stage 0.0 (TID 202) in 19645 ms on localhost (executor driver) (198/3618)
 2018-01-30 17:02:23,062 [Executor task launch worker for task 209] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629173110-00079-crawling212.us.archive.org-6682.warc.gz:0+108868973
 2018-01-30 17:02:23,280 [Executor task launch worker for task 203] INFO  Executor - Finished task 203.0 in stage 0.0 (TID 203). 1767 bytes result sent to driver
 2018-01-30 17:02:23,281 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 210.0 in stage 0.0 (TID 210, localhost, executor driver, partition 210, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:02:23,281 [Executor task launch worker for task 210] INFO  Executor - Running task 210.0 in stage 0.0 (TID 210)
 2018-01-30 17:02:23,281 [task-result-getter-2] INFO  TaskSetManager - Finished task 203.0 in stage 0.0 (TID 203) in 16991 ms on localhost (executor driver) (199/3618)
 2018-01-30 17:02:23,282 [Executor task launch worker for task 210] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004235036314-00028-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+3090849
 2018-01-30 17:02:23,673 [Executor task launch worker for task 210] INFO  Executor - Finished task 210.0 in stage 0.0 (TID 210). 1603 bytes result sent to driver
 2018-01-30 17:02:23,674 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 211.0 in stage 0.0 (TID 211, localhost, executor driver, partition 211, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:23,674 [Executor task launch worker for task 211] INFO  Executor - Running task 211.0 in stage 0.0 (TID 211)
 2018-01-30 17:02:23,674 [task-result-getter-3] INFO  TaskSetManager - Finished task 210.0 in stage 0.0 (TID 210) in 394 ms on localhost (executor driver) (200/3618)
 2018-01-30 17:02:23,675 [Executor task launch worker for task 211] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925010139195-00052.warc.gz:0+1000036058
 2018-01-30 17:02:28,899 [Executor task launch worker for task 208] INFO  Executor - Finished task 208.0 in stage 0.0 (TID 208). 1767 bytes result sent to driver
 2018-01-30 17:02:28,900 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 212.0 in stage 0.0 (TID 212, localhost, executor driver, partition 212, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:02:28,900 [task-result-getter-0] INFO  TaskSetManager - Finished task 208.0 in stage 0.0 (TID 208) in 8980 ms on localhost (executor driver) (201/3618)
 2018-01-30 17:02:28,901 [Executor task launch worker for task 212] INFO  Executor - Running task 212.0 in stage 0.0 (TID 212)
 2018-01-30 17:02:28,902 [Executor task launch worker for task 212] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727184836408-00026.warc.gz:0+1002446424
 2018-01-30 17:02:34,345 [Executor task launch worker for task 178] INFO  Executor - Finished task 178.0 in stage 0.0 (TID 178). 1958 bytes result sent to driver
 2018-01-30 17:02:34,346 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 213.0 in stage 0.0 (TID 213, localhost, executor driver, partition 213, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:34,347 [Executor task launch worker for task 213] INFO  Executor - Running task 213.0 in stage 0.0 (TID 213)
 2018-01-30 17:02:34,347 [task-result-getter-1] INFO  TaskSetManager - Finished task 178.0 in stage 0.0 (TID 178) in 77473 ms on localhost (executor driver) (202/3618)
 2018-01-30 17:02:34,349 [Executor task launch worker for task 213] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925073655824-00063.warc.gz:0+1000020850
 2018-01-30 17:02:35,661 [Executor task launch worker for task 199] INFO  Executor - Finished task 199.0 in stage 0.0 (TID 199). 1573 bytes result sent to driver
 2018-01-30 17:02:35,662 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 214.0 in stage 0.0 (TID 214, localhost, executor driver, partition 214, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:35,662 [Executor task launch worker for task 214] INFO  Executor - Running task 214.0 in stage 0.0 (TID 214)
 2018-01-30 17:02:35,663 [task-result-getter-2] INFO  TaskSetManager - Finished task 199.0 in stage 0.0 (TID 199) in 34965 ms on localhost (executor driver) (203/3618)
 2018-01-30 17:02:35,664 [Executor task launch worker for task 214] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226163147105-00153.warc.gz:0+1000060004
 2018-01-30 17:02:37,637 [Executor task launch worker for task 209] INFO  Executor - Finished task 209.0 in stage 0.0 (TID 209). 1573 bytes result sent to driver
 2018-01-30 17:02:37,638 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 215.0 in stage 0.0 (TID 215, localhost, executor driver, partition 215, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:37,638 [task-result-getter-3] INFO  TaskSetManager - Finished task 209.0 in stage 0.0 (TID 209) in 14577 ms on localhost (executor driver) (204/3618)
 2018-01-30 17:02:37,638 [Executor task launch worker for task 215] INFO  Executor - Running task 215.0 in stage 0.0 (TID 215)
 2018-01-30 17:02:37,639 [Executor task launch worker for task 215] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301074524-00087-crawling211.us.archive.org-6682.warc.gz:0+116317128
 2018-01-30 17:02:39,468 [Executor task launch worker for task 181] INFO  Executor - Finished task 181.0 in stage 0.0 (TID 181). 2667 bytes result sent to driver
 2018-01-30 17:02:39,472 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 216.0 in stage 0.0 (TID 216, localhost, executor driver, partition 216, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:02:39,472 [Executor task launch worker for task 216] INFO  Executor - Running task 216.0 in stage 0.0 (TID 216)
 2018-01-30 17:02:39,473 [task-result-getter-0] INFO  TaskSetManager - Finished task 181.0 in stage 0.0 (TID 181) in 77475 ms on localhost (executor driver) (205/3618)
 2018-01-30 17:02:39,474 [Executor task launch worker for task 216] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301122009-00154-crawling211.us.archive.org-6682.warc.gz:0+105456566
 2018-01-30 17:02:47,353 [Executor task launch worker for task 215] INFO  Executor - Finished task 215.0 in stage 0.0 (TID 215). 1573 bytes result sent to driver
 2018-01-30 17:02:47,355 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 217.0 in stage 0.0 (TID 217, localhost, executor driver, partition 217, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:02:47,355 [Executor task launch worker for task 217] INFO  Executor - Running task 217.0 in stage 0.0 (TID 217)
 2018-01-30 17:02:47,355 [task-result-getter-1] INFO  TaskSetManager - Finished task 215.0 in stage 0.0 (TID 215) in 9717 ms on localhost (executor driver) (206/3618)
 2018-01-30 17:02:47,357 [Executor task launch worker for task 217] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-16000-20131113153824094-00000-wbgrp-crawl058.us.archive.org-6443.warc.gz:0+130988143
 2018-01-30 17:02:49,171 [Executor task launch worker for task 216] INFO  Executor - Finished task 216.0 in stage 0.0 (TID 216). 1573 bytes result sent to driver
 2018-01-30 17:02:49,172 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 218.0 in stage 0.0 (TID 218, localhost, executor driver, partition 218, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:02:49,172 [Executor task launch worker for task 218] INFO  Executor - Running task 218.0 in stage 0.0 (TID 218)
 2018-01-30 17:02:49,172 [task-result-getter-2] INFO  TaskSetManager - Finished task 216.0 in stage 0.0 (TID 216) in 9701 ms on localhost (executor driver) (207/3618)
 2018-01-30 17:02:49,174 [Executor task launch worker for task 218] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB316806-20170723194617507-00001.warc.gz:0+1000037720
 2018-01-30 17:03:13,962 [Executor task launch worker for task 217] INFO  Executor - Finished task 217.0 in stage 0.0 (TID 217). 1763 bytes result sent to driver
 2018-01-30 17:03:13,966 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 219.0 in stage 0.0 (TID 219, localhost, executor driver, partition 219, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:03:13,966 [Executor task launch worker for task 219] INFO  Executor - Running task 219.0 in stage 0.0 (TID 219)
 2018-01-30 17:03:13,966 [task-result-getter-3] INFO  TaskSetManager - Finished task 217.0 in stage 0.0 (TID 217) in 26612 ms on localhost (executor driver) (208/3618)
 2018-01-30 17:03:13,971 [Executor task launch worker for task 219] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927222024985-00010-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+1519361
 2018-01-30 17:03:14,248 [Executor task launch worker for task 219] INFO  Executor - Finished task 219.0 in stage 0.0 (TID 219). 1706 bytes result sent to driver
 2018-01-30 17:03:14,249 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 220.0 in stage 0.0 (TID 220, localhost, executor driver, partition 220, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:03:14,249 [Executor task launch worker for task 220] INFO  Executor - Running task 220.0 in stage 0.0 (TID 220)
 2018-01-30 17:03:14,249 [task-result-getter-0] INFO  TaskSetManager - Finished task 219.0 in stage 0.0 (TID 219) in 286 ms on localhost (executor driver) (209/3618)
 2018-01-30 17:03:14,250 [Executor task launch worker for task 220] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929013531-00048-crawling113.us.archive.org-6683.warc.gz:0+101200145
 2018-01-30 17:03:17,267 [Executor task launch worker for task 156] INFO  Executor - Finished task 156.0 in stage 0.0 (TID 156). 1862 bytes result sent to driver
 2018-01-30 17:03:17,270 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 221.0 in stage 0.0 (TID 221, localhost, executor driver, partition 221, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:03:17,270 [Executor task launch worker for task 221] INFO  Executor - Running task 221.0 in stage 0.0 (TID 221)
 2018-01-30 17:03:17,270 [task-result-getter-1] INFO  TaskSetManager - Finished task 156.0 in stage 0.0 (TID 156) in 200254 ms on localhost (executor driver) (210/3618)
 2018-01-30 17:03:17,272 [Executor task launch worker for task 221] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629180508-00085-crawling212.us.archive.org-6682.warc.gz:0+109732813
 2018-01-30 17:03:24,634 [Executor task launch worker for task 196] INFO  Executor - Finished task 196.0 in stage 0.0 (TID 196). 2233 bytes result sent to driver
 2018-01-30 17:03:24,637 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 222.0 in stage 0.0 (TID 222, localhost, executor driver, partition 222, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:03:24,638 [Executor task launch worker for task 222] INFO  Executor - Running task 222.0 in stage 0.0 (TID 222)
 2018-01-30 17:03:24,639 [task-result-getter-2] INFO  TaskSetManager - Finished task 196.0 in stage 0.0 (TID 196) in 89175 ms on localhost (executor driver) (211/3618)
 2018-01-30 17:03:24,643 [Executor task launch worker for task 222] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927213016234-00000-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+16637918
 2018-01-30 17:03:26,548 [Executor task launch worker for task 222] INFO  Executor - Finished task 222.0 in stage 0.0 (TID 222). 1807 bytes result sent to driver
 2018-01-30 17:03:26,550 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 223.0 in stage 0.0 (TID 223, localhost, executor driver, partition 223, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:03:26,550 [task-result-getter-3] INFO  TaskSetManager - Finished task 222.0 in stage 0.0 (TID 222) in 1914 ms on localhost (executor driver) (212/3618)
 2018-01-30 17:03:26,550 [Executor task launch worker for task 223] INFO  Executor - Running task 223.0 in stage 0.0 (TID 223)
 2018-01-30 17:03:26,552 [Executor task launch worker for task 223] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912032147-00048-crawling211.us.archive.org-6681.warc.gz:0+106261862
 2018-01-30 17:03:27,009 [Executor task launch worker for task 220] INFO  Executor - Finished task 220.0 in stage 0.0 (TID 220). 1486 bytes result sent to driver
 2018-01-30 17:03:27,010 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 224.0 in stage 0.0 (TID 224, localhost, executor driver, partition 224, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:03:27,010 [Executor task launch worker for task 224] INFO  Executor - Running task 224.0 in stage 0.0 (TID 224)
 2018-01-30 17:03:27,010 [task-result-getter-0] INFO  TaskSetManager - Finished task 220.0 in stage 0.0 (TID 220) in 12762 ms on localhost (executor driver) (213/3618)
 2018-01-30 17:03:27,011 [Executor task launch worker for task 224] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171026202943912-00126.warc.gz:0+1000004886
 2018-01-30 17:03:30,530 [Executor task launch worker for task 221] INFO  Executor - Finished task 221.0 in stage 0.0 (TID 221). 1573 bytes result sent to driver
 2018-01-30 17:03:30,532 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 225.0 in stage 0.0 (TID 225, localhost, executor driver, partition 225, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:03:30,532 [Executor task launch worker for task 225] INFO  Executor - Running task 225.0 in stage 0.0 (TID 225)
 2018-01-30 17:03:30,532 [task-result-getter-1] INFO  TaskSetManager - Finished task 221.0 in stage 0.0 (TID 221) in 13263 ms on localhost (executor driver) (214/3618)
 2018-01-30 17:03:30,535 [Executor task launch worker for task 225] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926093742303-00106.warc.gz:0+1000010519
 2018-01-30 17:03:30,967 [Executor task launch worker for task 200] INFO  Executor - Finished task 200.0 in stage 0.0 (TID 200). 1942 bytes result sent to driver
 2018-01-30 17:03:30,968 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 226.0 in stage 0.0 (TID 226, localhost, executor driver, partition 226, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:03:30,969 [Executor task launch worker for task 226] INFO  Executor - Running task 226.0 in stage 0.0 (TID 226)
 2018-01-30 17:03:30,969 [task-result-getter-2] INFO  TaskSetManager - Finished task 200.0 in stage 0.0 (TID 200) in 89367 ms on localhost (executor driver) (215/3618)
 2018-01-30 17:03:30,970 [Executor task launch worker for task 226] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150728165153717-00046.warc.gz:0+1000191219
 2018-01-30 17:03:37,478 [Executor task launch worker for task 204] INFO  Executor - Finished task 204.0 in stage 0.0 (TID 204). 2201 bytes result sent to driver
 2018-01-30 17:03:37,480 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 227.0 in stage 0.0 (TID 227, localhost, executor driver, partition 227, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:03:37,480 [Executor task launch worker for task 227] INFO  Executor - Running task 227.0 in stage 0.0 (TID 227)
 2018-01-30 17:03:37,481 [task-result-getter-3] INFO  TaskSetManager - Finished task 204.0 in stage 0.0 (TID 204) in 91072 ms on localhost (executor driver) (216/3618)
 2018-01-30 17:03:37,483 [Executor task launch worker for task 227] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JILQTV-20111206182840-00000-crawling202.us.archive.org-6680.warc.gz:0+1656944
 2018-01-30 17:03:37,781 [Executor task launch worker for task 227] INFO  Executor - Finished task 227.0 in stage 0.0 (TID 227). 1690 bytes result sent to driver
 2018-01-30 17:03:37,782 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 228.0 in stage 0.0 (TID 228, localhost, executor driver, partition 228, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:03:37,782 [Executor task launch worker for task 228] INFO  Executor - Running task 228.0 in stage 0.0 (TID 228)
 2018-01-30 17:03:37,782 [task-result-getter-0] INFO  TaskSetManager - Finished task 227.0 in stage 0.0 (TID 227) in 303 ms on localhost (executor driver) (217/3618)
 2018-01-30 17:03:37,784 [Executor task launch worker for task 228] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120614014512-00016-crawling200.us.archive.org-6681.warc.gz:0+100001489
 2018-01-30 17:03:39,517 [Executor task launch worker for task 223] INFO  Executor - Finished task 223.0 in stage 0.0 (TID 223). 1573 bytes result sent to driver
 2018-01-30 17:03:39,519 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 229.0 in stage 0.0 (TID 229, localhost, executor driver, partition 229, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:03:39,519 [Executor task launch worker for task 229] INFO  Executor - Running task 229.0 in stage 0.0 (TID 229)
 2018-01-30 17:03:39,519 [task-result-getter-1] INFO  TaskSetManager - Finished task 223.0 in stage 0.0 (TID 223) in 12970 ms on localhost (executor driver) (218/3618)
 2018-01-30 17:03:39,521 [Executor task launch worker for task 229] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-YDUKWP-20111130205352-00015-crawling203.us.archive.org-6680.warc.gz:0+109103650
 2018-01-30 17:03:48,958 [Executor task launch worker for task 228] INFO  Executor - Finished task 228.0 in stage 0.0 (TID 228). 1763 bytes result sent to driver
 2018-01-30 17:03:48,961 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 230.0 in stage 0.0 (TID 230, localhost, executor driver, partition 230, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:03:48,961 [Executor task launch worker for task 230] INFO  Executor - Running task 230.0 in stage 0.0 (TID 230)
 2018-01-30 17:03:48,963 [task-result-getter-2] INFO  TaskSetManager - Finished task 228.0 in stage 0.0 (TID 228) in 11182 ms on localhost (executor driver) (219/3618)
 2018-01-30 17:03:48,975 [Executor task launch worker for task 230] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-ANNUAL-9747-20131007173029353-00001-wbgrp-crawl058.us.archive.org-6442.warc.gz:0+140482
 2018-01-30 17:03:49,036 [Executor task launch worker for task 230] INFO  Executor - Finished task 230.0 in stage 0.0 (TID 230). 1500 bytes result sent to driver
 2018-01-30 17:03:49,038 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 231.0 in stage 0.0 (TID 231, localhost, executor driver, partition 231, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:03:49,038 [task-result-getter-3] INFO  TaskSetManager - Finished task 230.0 in stage 0.0 (TID 230) in 78 ms on localhost (executor driver) (220/3618)
 2018-01-30 17:03:49,043 [Executor task launch worker for task 231] INFO  Executor - Running task 231.0 in stage 0.0 (TID 231)
 2018-01-30 17:03:49,046 [Executor task launch worker for task 231] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226114757032-00142.warc.gz:0+1000033984
 2018-01-30 17:03:51,684 [Executor task launch worker for task 206] INFO  Executor - Finished task 206.0 in stage 0.0 (TID 206). 1835 bytes result sent to driver
 2018-01-30 17:03:51,685 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 232.0 in stage 0.0 (TID 232, localhost, executor driver, partition 232, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:03:51,685 [Executor task launch worker for task 232] INFO  Executor - Running task 232.0 in stage 0.0 (TID 232)
 2018-01-30 17:03:51,686 [task-result-getter-0] INFO  TaskSetManager - Finished task 206.0 in stage 0.0 (TID 206) in 93725 ms on localhost (executor driver) (221/3618)
 2018-01-30 17:03:51,687 [Executor task launch worker for task 232] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406051022-00022-crawling200.us.archive.org-6682.warc.gz:0+107402953
 2018-01-30 17:03:52,269 [Executor task launch worker for task 229] INFO  Executor - Finished task 229.0 in stage 0.0 (TID 229). 1573 bytes result sent to driver
 2018-01-30 17:03:52,270 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 233.0 in stage 0.0 (TID 233, localhost, executor driver, partition 233, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:03:52,270 [task-result-getter-1] INFO  TaskSetManager - Finished task 229.0 in stage 0.0 (TID 229) in 12752 ms on localhost (executor driver) (222/3618)
 2018-01-30 17:03:52,270 [Executor task launch worker for task 233] INFO  Executor - Running task 233.0 in stage 0.0 (TID 233)
 2018-01-30 17:03:52,271 [Executor task launch worker for task 233] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110910013535-00008-crawling211.us.archive.org-6681.warc.gz:0+100351887
 2018-01-30 17:03:55,301 [Executor task launch worker for task 207] INFO  Executor - Finished task 207.0 in stage 0.0 (TID 207). 1835 bytes result sent to driver
 2018-01-30 17:03:55,303 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 234.0 in stage 0.0 (TID 234, localhost, executor driver, partition 234, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:03:55,303 [task-result-getter-2] INFO  TaskSetManager - Finished task 207.0 in stage 0.0 (TID 207) in 95673 ms on localhost (executor driver) (223/3618)
 2018-01-30 17:03:55,303 [Executor task launch worker for task 234] INFO  Executor - Running task 234.0 in stage 0.0 (TID 234)
 2018-01-30 17:03:55,305 [Executor task launch worker for task 234] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002173116-00401-crawling209.us.archive.org-6681.warc.gz:0+100001371
 2018-01-30 17:04:00,665 [Executor task launch worker for task 211] INFO  Executor - Finished task 211.0 in stage 0.0 (TID 211). 2057 bytes result sent to driver
 2018-01-30 17:04:00,667 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 235.0 in stage 0.0 (TID 235, localhost, executor driver, partition 235, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:04:00,667 [Executor task launch worker for task 235] INFO  Executor - Running task 235.0 in stage 0.0 (TID 235)
 2018-01-30 17:04:00,667 [task-result-getter-3] INFO  TaskSetManager - Finished task 211.0 in stage 0.0 (TID 211) in 96993 ms on localhost (executor driver) (224/3618)
 2018-01-30 17:04:00,670 [Executor task launch worker for task 235] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004230019031-00018-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+1018609
 2018-01-30 17:04:00,827 [Executor task launch worker for task 235] INFO  Executor - Finished task 235.0 in stage 0.0 (TID 235). 1690 bytes result sent to driver
 2018-01-30 17:04:00,828 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 236.0 in stage 0.0 (TID 236, localhost, executor driver, partition 236, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 17:04:00,828 [Executor task launch worker for task 236] INFO  Executor - Running task 236.0 in stage 0.0 (TID 236)
 2018-01-30 17:04:00,828 [task-result-getter-0] INFO  TaskSetManager - Finished task 235.0 in stage 0.0 (TID 235) in 162 ms on localhost (executor driver) (225/3618)
 2018-01-30 17:04:00,829 [Executor task launch worker for task 236] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB184570-20151124003902116-00001.warc.gz:0+1000573966
 2018-01-30 17:04:03,335 [Executor task launch worker for task 234] INFO  Executor - Finished task 234.0 in stage 0.0 (TID 234). 1759 bytes result sent to driver
 2018-01-30 17:04:03,337 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 237.0 in stage 0.0 (TID 237, localhost, executor driver, partition 237, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:03,337 [Executor task launch worker for task 237] INFO  Executor - Running task 237.0 in stage 0.0 (TID 237)
 2018-01-30 17:04:03,337 [task-result-getter-1] INFO  TaskSetManager - Finished task 234.0 in stage 0.0 (TID 234) in 8035 ms on localhost (executor driver) (226/3618)
 2018-01-30 17:04:03,340 [Executor task launch worker for task 237] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930113330-00158-crawling202.us.archive.org-6681.warc.gz:0+100486732
 2018-01-30 17:04:06,869 [Executor task launch worker for task 213] INFO  Executor - Finished task 213.0 in stage 0.0 (TID 213). 2049 bytes result sent to driver
 2018-01-30 17:04:06,872 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 238.0 in stage 0.0 (TID 238, localhost, executor driver, partition 238, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:04:06,873 [Executor task launch worker for task 238] INFO  Executor - Running task 238.0 in stage 0.0 (TID 238)
 2018-01-30 17:04:06,873 [task-result-getter-2] INFO  TaskSetManager - Finished task 213.0 in stage 0.0 (TID 213) in 92527 ms on localhost (executor driver) (227/3618)
 2018-01-30 17:04:06,875 [Executor task launch worker for task 238] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225211812325-00107.warc.gz:0+1000048488
 2018-01-30 17:04:08,183 [Executor task launch worker for task 232] INFO  Executor - Finished task 232.0 in stage 0.0 (TID 232). 1759 bytes result sent to driver
 2018-01-30 17:04:08,185 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 239.0 in stage 0.0 (TID 239, localhost, executor driver, partition 239, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:08,185 [task-result-getter-3] INFO  TaskSetManager - Finished task 232.0 in stage 0.0 (TID 232) in 16500 ms on localhost (executor driver) (228/3618)
 2018-01-30 17:04:08,185 [Executor task launch worker for task 239] INFO  Executor - Running task 239.0 in stage 0.0 (TID 239)
 2018-01-30 17:04:08,189 [Executor task launch worker for task 239] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301160302-00213-crawling211.us.archive.org-6682.warc.gz:0+108051770
 2018-01-30 17:04:08,741 [Executor task launch worker for task 233] INFO  Executor - Finished task 233.0 in stage 0.0 (TID 233). 1573 bytes result sent to driver
 2018-01-30 17:04:08,787 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 240.0 in stage 0.0 (TID 240, localhost, executor driver, partition 240, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:04:08,788 [Executor task launch worker for task 240] INFO  Executor - Running task 240.0 in stage 0.0 (TID 240)
 2018-01-30 17:04:08,788 [task-result-getter-0] INFO  TaskSetManager - Finished task 233.0 in stage 0.0 (TID 233) in 16519 ms on localhost (executor driver) (229/3618)
 2018-01-30 17:04:08,789 [Executor task launch worker for task 240] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925025335728-00055.warc.gz:0+1000051678
 2018-01-30 17:04:16,169 [Executor task launch worker for task 239] INFO  Executor - Finished task 239.0 in stage 0.0 (TID 239). 1573 bytes result sent to driver
 2018-01-30 17:04:16,175 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 241.0 in stage 0.0 (TID 241, localhost, executor driver, partition 241, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:04:16,176 [Executor task launch worker for task 241] INFO  Executor - Running task 241.0 in stage 0.0 (TID 241)
 2018-01-30 17:04:16,177 [task-result-getter-1] INFO  TaskSetManager - Finished task 239.0 in stage 0.0 (TID 239) in 7993 ms on localhost (executor driver) (230/3618)
 2018-01-30 17:04:16,184 [Executor task launch worker for task 241] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QAOHFF-20120413034105-00024-crawling201.us.archive.org-6682.warc.gz:0+100000049
 2018-01-30 17:04:18,725 [Executor task launch worker for task 237] INFO  Executor - Finished task 237.0 in stage 0.0 (TID 237). 1878 bytes result sent to driver
 2018-01-30 17:04:18,727 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 242.0 in stage 0.0 (TID 242, localhost, executor driver, partition 242, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:04:18,728 [task-result-getter-2] INFO  TaskSetManager - Finished task 237.0 in stage 0.0 (TID 237) in 15392 ms on localhost (executor driver) (231/3618)
 2018-01-30 17:04:18,728 [Executor task launch worker for task 242] INFO  Executor - Running task 242.0 in stage 0.0 (TID 242)
 2018-01-30 17:04:18,731 [Executor task launch worker for task 242] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-12562-20150612213258547-00000-wbgrp-crawl051.us.archive.org-6443.warc.gz:0+254423417
 2018-01-30 17:04:19,381 [Executor task launch worker for task 218] INFO  Executor - Finished task 218.0 in stage 0.0 (TID 218). 1863 bytes result sent to driver
 2018-01-30 17:04:19,383 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 243.0 in stage 0.0 (TID 243, localhost, executor driver, partition 243, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:19,383 [Executor task launch worker for task 243] INFO  Executor - Running task 243.0 in stage 0.0 (TID 243)
 2018-01-30 17:04:19,383 [task-result-getter-3] INFO  TaskSetManager - Finished task 218.0 in stage 0.0 (TID 218) in 90211 ms on localhost (executor driver) (232/3618)
 2018-01-30 17:04:19,385 [Executor task launch worker for task 243] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001212522-00080-crawling209.us.archive.org-6681.warc.gz:0+103800711
 2018-01-30 17:04:26,881 [Executor task launch worker for task 214] INFO  Executor - Finished task 214.0 in stage 0.0 (TID 214). 1843 bytes result sent to driver
 2018-01-30 17:04:26,883 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 244.0 in stage 0.0 (TID 244, localhost, executor driver, partition 244, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:26,883 [task-result-getter-0] INFO  TaskSetManager - Finished task 214.0 in stage 0.0 (TID 214) in 111221 ms on localhost (executor driver) (233/3618)
 2018-01-30 17:04:26,884 [Executor task launch worker for task 244] INFO  Executor - Running task 244.0 in stage 0.0 (TID 244)
 2018-01-30 17:04:26,885 [Executor task launch worker for task 244] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912032957-00050-crawling211.us.archive.org-6681.warc.gz:0+173552518
 2018-01-30 17:04:27,777 [Executor task launch worker for task 243] INFO  Executor - Finished task 243.0 in stage 0.0 (TID 243). 1763 bytes result sent to driver
 2018-01-30 17:04:27,778 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 245.0 in stage 0.0 (TID 245, localhost, executor driver, partition 245, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:04:27,778 [Executor task launch worker for task 245] INFO  Executor - Running task 245.0 in stage 0.0 (TID 245)
 2018-01-30 17:04:27,778 [task-result-getter-1] INFO  TaskSetManager - Finished task 243.0 in stage 0.0 (TID 243) in 8396 ms on localhost (executor driver) (234/3618)
 2018-01-30 17:04:27,779 [Executor task launch worker for task 245] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121013004923-00009-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+234248530
 2018-01-30 17:04:32,331 [Executor task launch worker for task 241] INFO  Executor - Finished task 241.0 in stage 0.0 (TID 241). 1827 bytes result sent to driver
 2018-01-30 17:04:32,332 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 246.0 in stage 0.0 (TID 246, localhost, executor driver, partition 246, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:04:32,332 [Executor task launch worker for task 246] INFO  Executor - Running task 246.0 in stage 0.0 (TID 246)
 2018-01-30 17:04:32,332 [task-result-getter-2] INFO  TaskSetManager - Finished task 241.0 in stage 0.0 (TID 241) in 16159 ms on localhost (executor driver) (235/3618)
 2018-01-30 17:04:32,334 [Executor task launch worker for task 246] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226103311174-00140.warc.gz:0+1000072893
 2018-01-30 17:04:38,218 [Executor task launch worker for task 212] INFO  Executor - Finished task 212.0 in stage 0.0 (TID 212). 1771 bytes result sent to driver
 2018-01-30 17:04:38,219 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 247.0 in stage 0.0 (TID 247, localhost, executor driver, partition 247, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:04:38,219 [Executor task launch worker for task 247] INFO  Executor - Running task 247.0 in stage 0.0 (TID 247)
 2018-01-30 17:04:38,219 [task-result-getter-3] INFO  TaskSetManager - Finished task 212.0 in stage 0.0 (TID 212) in 129319 ms on localhost (executor driver) (236/3618)
 2018-01-30 17:04:38,221 [Executor task launch worker for task 247] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB206270-20160408213022986-00000.warc.gz:0+1000040693
 2018-01-30 17:04:44,095 [Executor task launch worker for task 242] INFO  Executor - Finished task 242.0 in stage 0.0 (TID 242). 1882 bytes result sent to driver
 2018-01-30 17:04:44,096 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 248.0 in stage 0.0 (TID 248, localhost, executor driver, partition 248, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:44,096 [Executor task launch worker for task 248] INFO  Executor - Running task 248.0 in stage 0.0 (TID 248)
 2018-01-30 17:04:44,096 [task-result-getter-0] INFO  TaskSetManager - Finished task 242.0 in stage 0.0 (TID 242) in 25370 ms on localhost (executor driver) (237/3618)
 2018-01-30 17:04:44,097 [Executor task launch worker for task 248] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301041745-00038-crawling211.us.archive.org-6682.warc.gz:0+101523332
 2018-01-30 17:04:49,654 [Executor task launch worker for task 244] INFO  Executor - Finished task 244.0 in stage 0.0 (TID 244). 1573 bytes result sent to driver
 2018-01-30 17:04:49,655 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 249.0 in stage 0.0 (TID 249, localhost, executor driver, partition 249, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:49,655 [Executor task launch worker for task 249] INFO  Executor - Running task 249.0 in stage 0.0 (TID 249)
 2018-01-30 17:04:49,656 [task-result-getter-1] INFO  TaskSetManager - Finished task 244.0 in stage 0.0 (TID 244) in 22774 ms on localhost (executor driver) (238/3618)
 2018-01-30 17:04:49,656 [Executor task launch worker for task 249] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912025654-00042-crawling211.us.archive.org-6681.warc.gz:0+100064573
 2018-01-30 17:04:52,255 [Executor task launch worker for task 248] INFO  Executor - Finished task 248.0 in stage 0.0 (TID 248). 1500 bytes result sent to driver
 2018-01-30 17:04:52,256 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 250.0 in stage 0.0 (TID 250, localhost, executor driver, partition 250, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:04:52,256 [Executor task launch worker for task 250] INFO  Executor - Running task 250.0 in stage 0.0 (TID 250)
 2018-01-30 17:04:52,256 [task-result-getter-2] INFO  TaskSetManager - Finished task 248.0 in stage 0.0 (TID 248) in 8161 ms on localhost (executor driver) (239/3618)
 2018-01-30 17:04:52,258 [Executor task launch worker for task 250] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110910033207-00012-crawling211.us.archive.org-6681.warc.gz:0+116783004
 2018-01-30 17:04:58,058 [Executor task launch worker for task 224] INFO  Executor - Finished task 224.0 in stage 0.0 (TID 224). 2081 bytes result sent to driver
 2018-01-30 17:04:58,058 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 251.0 in stage 0.0 (TID 251, localhost, executor driver, partition 251, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:04:58,059 [Executor task launch worker for task 251] INFO  Executor - Running task 251.0 in stage 0.0 (TID 251)
 2018-01-30 17:04:58,059 [task-result-getter-3] INFO  TaskSetManager - Finished task 224.0 in stage 0.0 (TID 224) in 91049 ms on localhost (executor driver) (240/3618)
 2018-01-30 17:04:58,060 [Executor task launch worker for task 251] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120928133145-00020-crawling113.us.archive.org-6683.warc.gz:0+193245241
 2018-01-30 17:05:03,547 [Executor task launch worker for task 225] INFO  Executor - Finished task 225.0 in stage 0.0 (TID 225). 2617 bytes result sent to driver
 2018-01-30 17:05:03,547 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 252.0 in stage 0.0 (TID 252, localhost, executor driver, partition 252, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:03,547 [Executor task launch worker for task 252] INFO  Executor - Running task 252.0 in stage 0.0 (TID 252)
 2018-01-30 17:05:03,547 [task-result-getter-0] INFO  TaskSetManager - Finished task 225.0 in stage 0.0 (TID 225) in 93016 ms on localhost (executor driver) (241/3618)
 2018-01-30 17:05:03,548 [Executor task launch worker for task 252] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008185327-00020-crawling208.us.archive.org-6683.warc.gz:0+100111609
 2018-01-30 17:05:13,373 [Executor task launch worker for task 245] INFO  Executor - Finished task 245.0 in stage 0.0 (TID 245). 1787 bytes result sent to driver
 2018-01-30 17:05:13,374 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 253.0 in stage 0.0 (TID 253, localhost, executor driver, partition 253, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 17:05:13,374 [task-result-getter-1] INFO  TaskSetManager - Finished task 245.0 in stage 0.0 (TID 245) in 45596 ms on localhost (executor driver) (242/3618)
 2018-01-30 17:05:13,374 [Executor task launch worker for task 253] INFO  Executor - Running task 253.0 in stage 0.0 (TID 253)
 2018-01-30 17:05:13,375 [Executor task launch worker for task 253] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121230154016-00035-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+104207236
 2018-01-30 17:05:15,669 [Executor task launch worker for task 231] INFO  Executor - Finished task 231.0 in stage 0.0 (TID 231). 1831 bytes result sent to driver
 2018-01-30 17:05:15,669 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 254.0 in stage 0.0 (TID 254, localhost, executor driver, partition 254, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:05:15,669 [task-result-getter-2] INFO  TaskSetManager - Finished task 231.0 in stage 0.0 (TID 231) in 86632 ms on localhost (executor driver) (243/3618)
 2018-01-30 17:05:15,673 [Executor task launch worker for task 254] INFO  Executor - Running task 254.0 in stage 0.0 (TID 254)
 2018-01-30 17:05:15,677 [Executor task launch worker for task 254] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QDPLNZ-20120712204931-00001-crawling105.us.archive.org-6681.warc.gz:0+100000798
 2018-01-30 17:05:20,982 [Executor task launch worker for task 250] INFO  Executor - Finished task 250.0 in stage 0.0 (TID 250). 1573 bytes result sent to driver
 2018-01-30 17:05:20,983 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 255.0 in stage 0.0 (TID 255, localhost, executor driver, partition 255, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:05:20,983 [Executor task launch worker for task 255] INFO  Executor - Running task 255.0 in stage 0.0 (TID 255)
 2018-01-30 17:05:20,985 [task-result-getter-3] INFO  TaskSetManager - Finished task 250.0 in stage 0.0 (TID 250) in 28729 ms on localhost (executor driver) (244/3618)
 2018-01-30 17:05:20,989 [Executor task launch worker for task 255] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-PNQTNO-20121023181750-00000-wbgrp-crawl066.us.archive.org-6682.warc.gz:0+3306389
 2018-01-30 17:05:21,761 [Executor task launch worker for task 255] INFO  Executor - Finished task 255.0 in stage 0.0 (TID 255). 1698 bytes result sent to driver
 2018-01-30 17:05:21,762 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 256.0 in stage 0.0 (TID 256, localhost, executor driver, partition 256, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:21,762 [Executor task launch worker for task 256] INFO  Executor - Running task 256.0 in stage 0.0 (TID 256)
 2018-01-30 17:05:21,762 [task-result-getter-0] INFO  TaskSetManager - Finished task 255.0 in stage 0.0 (TID 255) in 780 ms on localhost (executor driver) (245/3618)
 2018-01-30 17:05:21,763 [Executor task launch worker for task 256] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301175518-00245-crawling211.us.archive.org-6682.warc.gz:0+103519999
 2018-01-30 17:05:23,989 [Executor task launch worker for task 256] INFO  Executor - Finished task 256.0 in stage 0.0 (TID 256). 1500 bytes result sent to driver
 2018-01-30 17:05:23,990 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 257.0 in stage 0.0 (TID 257, localhost, executor driver, partition 257, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:23,990 [Executor task launch worker for task 257] INFO  Executor - Running task 257.0 in stage 0.0 (TID 257)
 2018-01-30 17:05:23,990 [task-result-getter-1] INFO  TaskSetManager - Finished task 256.0 in stage 0.0 (TID 256) in 2228 ms on localhost (executor driver) (246/3618)
 2018-01-30 17:05:23,991 [Executor task launch worker for task 257] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003013415-00514-crawling209.us.archive.org-6681.warc.gz:0+104638800
 2018-01-30 17:05:28,326 [Executor task launch worker for task 257] INFO  Executor - Finished task 257.0 in stage 0.0 (TID 257). 1500 bytes result sent to driver
 2018-01-30 17:05:28,327 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 258.0 in stage 0.0 (TID 258, localhost, executor driver, partition 258, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:28,327 [Executor task launch worker for task 258] INFO  Executor - Running task 258.0 in stage 0.0 (TID 258)
 2018-01-30 17:05:28,327 [task-result-getter-2] INFO  TaskSetManager - Finished task 257.0 in stage 0.0 (TID 257) in 4337 ms on localhost (executor driver) (247/3618)
 2018-01-30 17:05:28,329 [Executor task launch worker for task 258] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301082358-00095-crawling211.us.archive.org-6682.warc.gz:0+100606705
 2018-01-30 17:05:29,001 [Executor task launch worker for task 240] INFO  Executor - Finished task 240.0 in stage 0.0 (TID 240). 1985 bytes result sent to driver
 2018-01-30 17:05:29,002 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 259.0 in stage 0.0 (TID 259, localhost, executor driver, partition 259, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 17:05:29,002 [Executor task launch worker for task 259] INFO  Executor - Running task 259.0 in stage 0.0 (TID 259)
 2018-01-30 17:05:29,002 [task-result-getter-3] INFO  TaskSetManager - Finished task 240.0 in stage 0.0 (TID 240) in 80259 ms on localhost (executor driver) (248/3618)
 2018-01-30 17:05:29,003 [Executor task launch worker for task 259] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB302702-20170523201419723-00000.warc.gz:0+152922230
 2018-01-30 17:05:29,087 [Executor task launch worker for task 252] INFO  Executor - Finished task 252.0 in stage 0.0 (TID 252). 1759 bytes result sent to driver
 2018-01-30 17:05:29,087 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 260.0 in stage 0.0 (TID 260, localhost, executor driver, partition 260, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 17:05:29,087 [Executor task launch worker for task 260] INFO  Executor - Running task 260.0 in stage 0.0 (TID 260)
 2018-01-30 17:05:29,087 [task-result-getter-0] INFO  TaskSetManager - Finished task 252.0 in stage 0.0 (TID 252) in 25540 ms on localhost (executor driver) (249/3618)
 2018-01-30 17:05:29,088 [Executor task launch worker for task 260] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB250776-20161126044151535-00001.warc.gz:0+238316715
 2018-01-30 17:05:30,004 [Executor task launch worker for task 238] INFO  Executor - Finished task 238.0 in stage 0.0 (TID 238). 1863 bytes result sent to driver
 2018-01-30 17:05:30,004 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 261.0 in stage 0.0 (TID 261, localhost, executor driver, partition 261, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:05:30,004 [task-result-getter-1] INFO  TaskSetManager - Finished task 238.0 in stage 0.0 (TID 238) in 83133 ms on localhost (executor driver) (250/3618)
 2018-01-30 17:05:30,004 [Executor task launch worker for task 261] INFO  Executor - Running task 261.0 in stage 0.0 (TID 261)
 2018-01-30 17:05:30,005 [Executor task launch worker for task 261] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB181191-20151030213441006-00000.warc.gz:0+1000003164
 2018-01-30 17:05:33,249 [Executor task launch worker for task 249] INFO  Executor - Finished task 249.0 in stage 0.0 (TID 249). 1573 bytes result sent to driver
 2018-01-30 17:05:33,250 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 262.0 in stage 0.0 (TID 262, localhost, executor driver, partition 262, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:05:33,250 [task-result-getter-2] INFO  TaskSetManager - Finished task 249.0 in stage 0.0 (TID 249) in 43596 ms on localhost (executor driver) (251/3618)
 2018-01-30 17:05:33,250 [Executor task launch worker for task 262] INFO  Executor - Running task 262.0 in stage 0.0 (TID 262)
 2018-01-30 17:05:33,252 [Executor task launch worker for task 262] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-6115-20140214213017237-00000-wbgrp-crawl051.us.archive.org-6443.warc.gz:0+172204334
 2018-01-30 17:05:38,660 [Executor task launch worker for task 254] INFO  Executor - Finished task 254.0 in stage 0.0 (TID 254). 1835 bytes result sent to driver
 2018-01-30 17:05:38,662 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 263.0 in stage 0.0 (TID 263, localhost, executor driver, partition 263, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 17:05:38,662 [task-result-getter-3] INFO  TaskSetManager - Finished task 254.0 in stage 0.0 (TID 254) in 22993 ms on localhost (executor driver) (252/3618)
 2018-01-30 17:05:38,662 [Executor task launch worker for task 263] INFO  Executor - Running task 263.0 in stage 0.0 (TID 263)
 2018-01-30 17:05:38,663 [Executor task launch worker for task 263] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-BIMONTHLY-JOB192760-20160125204349610-00002.warc.gz:0+572580891
 2018-01-30 17:05:39,262 [Executor task launch worker for task 253] INFO  Executor - Finished task 253.0 in stage 0.0 (TID 253). 1573 bytes result sent to driver
 2018-01-30 17:05:39,263 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 264.0 in stage 0.0 (TID 264, localhost, executor driver, partition 264, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:39,263 [Executor task launch worker for task 264] INFO  Executor - Running task 264.0 in stage 0.0 (TID 264)
 2018-01-30 17:05:39,263 [task-result-getter-0] INFO  TaskSetManager - Finished task 253.0 in stage 0.0 (TID 253) in 25889 ms on localhost (executor driver) (253/3618)
 2018-01-30 17:05:39,264 [Executor task launch worker for task 264] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930152238-00201-crawling202.us.archive.org-6681.warc.gz:0+100168745
 2018-01-30 17:05:46,719 [Executor task launch worker for task 262] INFO  Executor - Finished task 262.0 in stage 0.0 (TID 262). 1863 bytes result sent to driver
 2018-01-30 17:05:46,725 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 265.0 in stage 0.0 (TID 265, localhost, executor driver, partition 265, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:05:46,725 [Executor task launch worker for task 265] INFO  Executor - Running task 265.0 in stage 0.0 (TID 265)
 2018-01-30 17:05:46,725 [task-result-getter-1] INFO  TaskSetManager - Finished task 262.0 in stage 0.0 (TID 262) in 13476 ms on localhost (executor driver) (254/3618)
 2018-01-30 17:05:46,727 [Executor task launch worker for task 265] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224183643550-00044.warc.gz:0+1000043594
 2018-01-30 17:05:48,662 [Executor task launch worker for task 246] INFO  Executor - Finished task 246.0 in stage 0.0 (TID 246). 1827 bytes result sent to driver
 2018-01-30 17:05:48,663 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 266.0 in stage 0.0 (TID 266, localhost, executor driver, partition 266, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:48,663 [Executor task launch worker for task 266] INFO  Executor - Running task 266.0 in stage 0.0 (TID 266)
 2018-01-30 17:05:48,663 [task-result-getter-2] INFO  TaskSetManager - Finished task 246.0 in stage 0.0 (TID 246) in 76331 ms on localhost (executor driver) (255/3618)
 2018-01-30 17:05:48,664 [Executor task launch worker for task 266] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301100330-00118-crawling211.us.archive.org-6682.warc.gz:0+101523756
 2018-01-30 17:05:48,757 [Executor task launch worker for task 258] INFO  Executor - Finished task 258.0 in stage 0.0 (TID 258). 1660 bytes result sent to driver
 2018-01-30 17:05:48,758 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 267.0 in stage 0.0 (TID 267, localhost, executor driver, partition 267, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:48,758 [Executor task launch worker for task 267] INFO  Executor - Running task 267.0 in stage 0.0 (TID 267)
 2018-01-30 17:05:48,758 [task-result-getter-3] INFO  TaskSetManager - Finished task 258.0 in stage 0.0 (TID 258) in 20431 ms on localhost (executor driver) (256/3618)
 2018-01-30 17:05:48,760 [Executor task launch worker for task 267] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003122750-00609-crawling209.us.archive.org-6681.warc.gz:0+110940239
 2018-01-30 17:05:49,359 [Executor task launch worker for task 251] INFO  Executor - Finished task 251.0 in stage 0.0 (TID 251). 1573 bytes result sent to driver
 2018-01-30 17:05:49,360 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 268.0 in stage 0.0 (TID 268, localhost, executor driver, partition 268, PROCESS_LOCAL, 19558 bytes)
 2018-01-30 17:05:49,360 [Executor task launch worker for task 268] INFO  Executor - Running task 268.0 in stage 0.0 (TID 268)
 2018-01-30 17:05:49,360 [task-result-getter-0] INFO  TaskSetManager - Finished task 251.0 in stage 0.0 (TID 251) in 51302 ms on localhost (executor driver) (257/3618)
 2018-01-30 17:05:49,361 [Executor task launch worker for task 268] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-9084-20130529011914452-00000-wbgrp-crawl052.us.archive.org-6442.warc.gz:0+1000008279
 2018-01-30 17:05:53,481 [Executor task launch worker for task 264] INFO  Executor - Finished task 264.0 in stage 0.0 (TID 264). 1783 bytes result sent to driver
 2018-01-30 17:05:53,482 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 269.0 in stage 0.0 (TID 269, localhost, executor driver, partition 269, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:05:53,483 [Executor task launch worker for task 269] INFO  Executor - Running task 269.0 in stage 0.0 (TID 269)
 2018-01-30 17:05:53,483 [task-result-getter-1] INFO  TaskSetManager - Finished task 264.0 in stage 0.0 (TID 264) in 14221 ms on localhost (executor driver) (258/3618)
 2018-01-30 17:05:53,484 [Executor task launch worker for task 269] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003013654-00515-crawling209.us.archive.org-6681.warc.gz:0+101085275
 2018-01-30 17:05:53,719 [Executor task launch worker for task 260] INFO  Executor - Finished task 260.0 in stage 0.0 (TID 260). 1759 bytes result sent to driver
 2018-01-30 17:05:53,720 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 270.0 in stage 0.0 (TID 270, localhost, executor driver, partition 270, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:05:53,720 [Executor task launch worker for task 270] INFO  Executor - Running task 270.0 in stage 0.0 (TID 270)
 2018-01-30 17:05:53,720 [task-result-getter-2] INFO  TaskSetManager - Finished task 260.0 in stage 0.0 (TID 260) in 24633 ms on localhost (executor driver) (259/3618)
 2018-01-30 17:05:53,721 [Executor task launch worker for task 270] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124232032509-00052.warc.gz:0+1000010164
 2018-01-30 17:05:54,056 [Executor task launch worker for task 259] INFO  Executor - Finished task 259.0 in stage 0.0 (TID 259). 2261 bytes result sent to driver
 2018-01-30 17:05:54,057 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 271.0 in stage 0.0 (TID 271, localhost, executor driver, partition 271, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:05:54,057 [task-result-getter-3] INFO  TaskSetManager - Finished task 259.0 in stage 0.0 (TID 259) in 25055 ms on localhost (executor driver) (260/3618)
 2018-01-30 17:05:54,058 [Executor task launch worker for task 271] INFO  Executor - Running task 271.0 in stage 0.0 (TID 271)
 2018-01-30 17:05:54,061 [Executor task launch worker for task 271] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925232046447-00089.warc.gz:0+1000064800
 2018-01-30 17:05:56,083 [Executor task launch worker for task 267] INFO  Executor - Finished task 267.0 in stage 0.0 (TID 267). 1759 bytes result sent to driver
 2018-01-30 17:05:56,084 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 272.0 in stage 0.0 (TID 272, localhost, executor driver, partition 272, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:05:56,084 [Executor task launch worker for task 272] INFO  Executor - Running task 272.0 in stage 0.0 (TID 272)
 2018-01-30 17:05:56,084 [task-result-getter-0] INFO  TaskSetManager - Finished task 267.0 in stage 0.0 (TID 267) in 7326 ms on localhost (executor driver) (261/3618)
 2018-01-30 17:05:56,086 [Executor task launch worker for task 272] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-27251-20130722170517663-00000-wbgrp-crawl066.us.archive.org-6441.warc.gz:0+1085591606
 2018-01-30 17:06:00,637 [Executor task launch worker for task 269] INFO  Executor - Finished task 269.0 in stage 0.0 (TID 269). 1759 bytes result sent to driver
 2018-01-30 17:06:00,638 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 273.0 in stage 0.0 (TID 273, localhost, executor driver, partition 273, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:06:00,639 [Executor task launch worker for task 273] INFO  Executor - Running task 273.0 in stage 0.0 (TID 273)
 2018-01-30 17:06:00,639 [task-result-getter-1] INFO  TaskSetManager - Finished task 269.0 in stage 0.0 (TID 269) in 7157 ms on localhost (executor driver) (262/3618)
 2018-01-30 17:06:00,640 [Executor task launch worker for task 273] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-2540-20140603145904065-00000-wbgrp-crawl104.us.archive.org-6445.warc.gz:0+7530
 2018-01-30 17:06:00,665 [Executor task launch worker for task 273] INFO  Executor - Finished task 273.0 in stage 0.0 (TID 273). 1500 bytes result sent to driver
 2018-01-30 17:06:00,665 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 274.0 in stage 0.0 (TID 274, localhost, executor driver, partition 274, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:00,665 [Executor task launch worker for task 274] INFO  Executor - Running task 274.0 in stage 0.0 (TID 274)
 2018-01-30 17:06:00,665 [task-result-getter-2] INFO  TaskSetManager - Finished task 273.0 in stage 0.0 (TID 273) in 27 ms on localhost (executor driver) (263/3618)
 2018-01-30 17:06:00,666 [Executor task launch worker for task 274] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301073132-00082-crawling211.us.archive.org-6682.warc.gz:0+101831238
 2018-01-30 17:06:03,635 [Executor task launch worker for task 266] INFO  Executor - Finished task 266.0 in stage 0.0 (TID 266). 1573 bytes result sent to driver
 2018-01-30 17:06:03,637 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 275.0 in stage 0.0 (TID 275, localhost, executor driver, partition 275, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:03,637 [Executor task launch worker for task 275] INFO  Executor - Running task 275.0 in stage 0.0 (TID 275)
 2018-01-30 17:06:03,638 [task-result-getter-3] INFO  TaskSetManager - Finished task 266.0 in stage 0.0 (TID 266) in 14975 ms on localhost (executor driver) (264/3618)
 2018-01-30 17:06:03,639 [Executor task launch worker for task 275] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930072526-00108-crawling202.us.archive.org-6681.warc.gz:0+100083639
 2018-01-30 17:06:07,338 [Executor task launch worker for task 274] INFO  Executor - Finished task 274.0 in stage 0.0 (TID 274). 1573 bytes result sent to driver
 2018-01-30 17:06:07,340 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 276.0 in stage 0.0 (TID 276, localhost, executor driver, partition 276, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:06:07,340 [Executor task launch worker for task 276] INFO  Executor - Running task 276.0 in stage 0.0 (TID 276)
 2018-01-30 17:06:07,340 [task-result-getter-0] INFO  TaskSetManager - Finished task 274.0 in stage 0.0 (TID 274) in 6675 ms on localhost (executor driver) (265/3618)
 2018-01-30 17:06:07,342 [Executor task launch worker for task 276] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB316806-20170724015813667-00004.warc.gz:0+1000135137
 2018-01-30 17:06:12,179 [Executor task launch worker for task 247] INFO  Executor - Finished task 247.0 in stage 0.0 (TID 247). 1934 bytes result sent to driver
 2018-01-30 17:06:12,181 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 277.0 in stage 0.0 (TID 277, localhost, executor driver, partition 277, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:06:12,181 [Executor task launch worker for task 277] INFO  Executor - Running task 277.0 in stage 0.0 (TID 277)
 2018-01-30 17:06:12,181 [task-result-getter-1] INFO  TaskSetManager - Finished task 247.0 in stage 0.0 (TID 247) in 93963 ms on localhost (executor driver) (266/3618)
 2018-01-30 17:06:12,183 [Executor task launch worker for task 277] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-9788-20140612173807814-00005-wbgrp-crawl065.us.archive.org-6442.warc.gz:0+5662
 2018-01-30 17:06:12,204 [Executor task launch worker for task 277] INFO  Executor - Finished task 277.0 in stage 0.0 (TID 277). 1500 bytes result sent to driver
 2018-01-30 17:06:12,204 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 278.0 in stage 0.0 (TID 278, localhost, executor driver, partition 278, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:06:12,204 [Executor task launch worker for task 278] INFO  Executor - Running task 278.0 in stage 0.0 (TID 278)
 2018-01-30 17:06:12,205 [task-result-getter-2] INFO  TaskSetManager - Finished task 277.0 in stage 0.0 (TID 277) in 24 ms on localhost (executor driver) (267/3618)
 2018-01-30 17:06:12,205 [Executor task launch worker for task 278] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925152853907-00076.warc.gz:0+1000050941
 2018-01-30 17:06:14,187 [Executor task launch worker for task 226] INFO  Executor - Finished task 226.0 in stage 0.0 (TID 226). 1859 bytes result sent to driver
 2018-01-30 17:06:14,188 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 279.0 in stage 0.0 (TID 279, localhost, executor driver, partition 279, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:14,188 [Executor task launch worker for task 279] INFO  Executor - Running task 279.0 in stage 0.0 (TID 279)
 2018-01-30 17:06:14,188 [task-result-getter-3] INFO  TaskSetManager - Finished task 226.0 in stage 0.0 (TID 226) in 163220 ms on localhost (executor driver) (268/3618)
 2018-01-30 17:06:14,189 [Executor task launch worker for task 279] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930074718-00112-crawling202.us.archive.org-6681.warc.gz:0+100039499
 2018-01-30 17:06:15,391 [Executor task launch worker for task 275] INFO  Executor - Finished task 275.0 in stage 0.0 (TID 275). 1795 bytes result sent to driver
 2018-01-30 17:06:15,392 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 280.0 in stage 0.0 (TID 280, localhost, executor driver, partition 280, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:06:15,392 [Executor task launch worker for task 280] INFO  Executor - Running task 280.0 in stage 0.0 (TID 280)
 2018-01-30 17:06:15,392 [task-result-getter-0] INFO  TaskSetManager - Finished task 275.0 in stage 0.0 (TID 275) in 11756 ms on localhost (executor driver) (269/3618)
 2018-01-30 17:06:15,393 [Executor task launch worker for task 280] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-OMAKFV-20120207182728-00000-crawling203.us.archive.org-6680.warc.gz:0+1878395
 2018-01-30 17:06:15,684 [Executor task launch worker for task 280] INFO  Executor - Finished task 280.0 in stage 0.0 (TID 280). 1694 bytes result sent to driver
 2018-01-30 17:06:15,685 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 281.0 in stage 0.0 (TID 281, localhost, executor driver, partition 281, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:15,685 [Executor task launch worker for task 281] INFO  Executor - Running task 281.0 in stage 0.0 (TID 281)
 2018-01-30 17:06:15,685 [task-result-getter-1] INFO  TaskSetManager - Finished task 280.0 in stage 0.0 (TID 280) in 294 ms on localhost (executor driver) (270/3618)
 2018-01-30 17:06:15,686 [Executor task launch worker for task 281] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301111451-00136-crawling211.us.archive.org-6682.warc.gz:0+104765615
 2018-01-30 17:06:23,257 [Executor task launch worker for task 281] INFO  Executor - Finished task 281.0 in stage 0.0 (TID 281). 1573 bytes result sent to driver
 2018-01-30 17:06:23,258 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 282.0 in stage 0.0 (TID 282, localhost, executor driver, partition 282, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:06:23,258 [Executor task launch worker for task 282] INFO  Executor - Running task 282.0 in stage 0.0 (TID 282)
 2018-01-30 17:06:23,259 [task-result-getter-2] INFO  TaskSetManager - Finished task 281.0 in stage 0.0 (TID 281) in 7574 ms on localhost (executor driver) (271/3618)
 2018-01-30 17:06:23,261 [Executor task launch worker for task 282] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-KOINAK-20121112223035-00009-wbgrp-crawl057.us.archive.org-6681.warc.gz:0+100308687
 2018-01-30 17:06:25,602 [Executor task launch worker for task 279] INFO  Executor - Finished task 279.0 in stage 0.0 (TID 279). 1791 bytes result sent to driver
 2018-01-30 17:06:25,603 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 283.0 in stage 0.0 (TID 283, localhost, executor driver, partition 283, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:25,604 [Executor task launch worker for task 283] INFO  Executor - Running task 283.0 in stage 0.0 (TID 283)
 2018-01-30 17:06:25,605 [Executor task launch worker for task 283] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301101207-00120-crawling211.us.archive.org-6682.warc.gz:0+104266104
 2018-01-30 17:06:25,609 [task-result-getter-3] INFO  TaskSetManager - Finished task 279.0 in stage 0.0 (TID 279) in 11422 ms on localhost (executor driver) (272/3618)
 2018-01-30 17:06:32,270 [Executor task launch worker for task 236] INFO  Executor - Finished task 236.0 in stage 0.0 (TID 236). 1914 bytes result sent to driver
 2018-01-30 17:06:32,271 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 284.0 in stage 0.0 (TID 284, localhost, executor driver, partition 284, PROCESS_LOCAL, 19533 bytes)
 2018-01-30 17:06:32,271 [task-result-getter-0] INFO  TaskSetManager - Finished task 236.0 in stage 0.0 (TID 236) in 151443 ms on localhost (executor driver) (273/3618)
 2018-01-30 17:06:32,272 [Executor task launch worker for task 284] INFO  Executor - Running task 284.0 in stage 0.0 (TID 284)
 2018-01-30 17:06:32,274 [Executor task launch worker for task 284] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QA_PATCH_CRAWL-JOB182453-20151109160015084-00000.warc.gz:0+567317
 2018-01-30 17:06:32,409 [Executor task launch worker for task 284] INFO  Executor - Finished task 284.0 in stage 0.0 (TID 284). 1698 bytes result sent to driver
 2018-01-30 17:06:32,410 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 285.0 in stage 0.0 (TID 285, localhost, executor driver, partition 285, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:32,410 [Executor task launch worker for task 285] INFO  Executor - Running task 285.0 in stage 0.0 (TID 285)
 2018-01-30 17:06:32,410 [task-result-getter-1] INFO  TaskSetManager - Finished task 284.0 in stage 0.0 (TID 284) in 140 ms on localhost (executor driver) (274/3618)
 2018-01-30 17:06:32,411 [Executor task launch worker for task 285] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930094715-00144-crawling202.us.archive.org-6681.warc.gz:0+101312664
 2018-01-30 17:06:36,266 [Executor task launch worker for task 282] INFO  Executor - Finished task 282.0 in stage 0.0 (TID 282). 1894 bytes result sent to driver
 2018-01-30 17:06:36,268 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 286.0 in stage 0.0 (TID 286, localhost, executor driver, partition 286, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:06:36,268 [Executor task launch worker for task 286] INFO  Executor - Running task 286.0 in stage 0.0 (TID 286)
 2018-01-30 17:06:36,268 [task-result-getter-2] INFO  TaskSetManager - Finished task 282.0 in stage 0.0 (TID 282) in 13010 ms on localhost (executor driver) (275/3618)
 2018-01-30 17:06:36,272 [Executor task launch worker for task 286] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-9788-20140612170708957-00003-wbgrp-crawl065.us.archive.org-6442.warc.gz:0+1493833686
 2018-01-30 17:06:38,792 [Executor task launch worker for task 283] INFO  Executor - Finished task 283.0 in stage 0.0 (TID 283). 1573 bytes result sent to driver
 2018-01-30 17:06:38,793 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 287.0 in stage 0.0 (TID 287, localhost, executor driver, partition 287, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:06:38,793 [Executor task launch worker for task 287] INFO  Executor - Running task 287.0 in stage 0.0 (TID 287)
 2018-01-30 17:06:38,794 [task-result-getter-3] INFO  TaskSetManager - Finished task 283.0 in stage 0.0 (TID 283) in 13191 ms on localhost (executor driver) (276/3618)
 2018-01-30 17:06:38,795 [Executor task launch worker for task 287] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226145214879-00149.warc.gz:0+1000078037
 2018-01-30 17:06:44,540 [Executor task launch worker for task 285] INFO  Executor - Finished task 285.0 in stage 0.0 (TID 285). 1787 bytes result sent to driver
 2018-01-30 17:06:44,543 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 288.0 in stage 0.0 (TID 288, localhost, executor driver, partition 288, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:44,543 [Executor task launch worker for task 288] INFO  Executor - Running task 288.0 in stage 0.0 (TID 288)
 2018-01-30 17:06:44,544 [task-result-getter-0] INFO  TaskSetManager - Finished task 285.0 in stage 0.0 (TID 285) in 12134 ms on localhost (executor driver) (277/3618)
 2018-01-30 17:06:44,546 [Executor task launch worker for task 288] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301050316-00049-crawling211.us.archive.org-6682.warc.gz:0+102617948
 2018-01-30 17:06:48,000 [Executor task launch worker for task 263] INFO  Executor - Finished task 263.0 in stage 0.0 (TID 263). 1763 bytes result sent to driver
 2018-01-30 17:06:48,002 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 289.0 in stage 0.0 (TID 289, localhost, executor driver, partition 289, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:48,002 [task-result-getter-1] INFO  TaskSetManager - Finished task 263.0 in stage 0.0 (TID 263) in 69341 ms on localhost (executor driver) (278/3618)
 2018-01-30 17:06:48,002 [Executor task launch worker for task 289] INFO  Executor - Running task 289.0 in stage 0.0 (TID 289)
 2018-01-30 17:06:48,007 [Executor task launch worker for task 289] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003024415-00525-crawling209.us.archive.org-6681.warc.gz:0+101832997
 2018-01-30 17:06:56,878 [Executor task launch worker for task 288] INFO  Executor - Finished task 288.0 in stage 0.0 (TID 288). 1573 bytes result sent to driver
 2018-01-30 17:06:56,882 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 290.0 in stage 0.0 (TID 290, localhost, executor driver, partition 290, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:06:56,882 [task-result-getter-2] INFO  TaskSetManager - Finished task 288.0 in stage 0.0 (TID 288) in 12340 ms on localhost (executor driver) (279/3618)
 2018-01-30 17:06:56,882 [Executor task launch worker for task 290] INFO  Executor - Running task 290.0 in stage 0.0 (TID 290)
 2018-01-30 17:06:56,888 [Executor task launch worker for task 290] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QRDYRH-20120313232306-00031-crawling113.us.archive.org-6681.warc.gz:0+100269931
 2018-01-30 17:06:56,930 [Executor task launch worker for task 289] INFO  Executor - Finished task 289.0 in stage 0.0 (TID 289). 1759 bytes result sent to driver
 2018-01-30 17:06:56,931 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 291.0 in stage 0.0 (TID 291, localhost, executor driver, partition 291, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:06:56,931 [Executor task launch worker for task 291] INFO  Executor - Running task 291.0 in stage 0.0 (TID 291)
 2018-01-30 17:06:56,931 [task-result-getter-3] INFO  TaskSetManager - Finished task 289.0 in stage 0.0 (TID 289) in 8930 ms on localhost (executor driver) (280/3618)
 2018-01-30 17:06:56,932 [Executor task launch worker for task 291] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002181324-00409-crawling209.us.archive.org-6681.warc.gz:0+102230987
 2018-01-30 17:07:11,478 [Executor task launch worker for task 290] INFO  Executor - Finished task 290.0 in stage 0.0 (TID 290). 1763 bytes result sent to driver
 2018-01-30 17:07:11,483 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 292.0 in stage 0.0 (TID 292, localhost, executor driver, partition 292, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:11,484 [task-result-getter-0] INFO  TaskSetManager - Finished task 290.0 in stage 0.0 (TID 290) in 14603 ms on localhost (executor driver) (281/3618)
 2018-01-30 17:07:11,485 [Executor task launch worker for task 292] INFO  Executor - Running task 292.0 in stage 0.0 (TID 292)
 2018-01-30 17:07:11,489 [Executor task launch worker for task 292] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930051103-00073-crawling202.us.archive.org-6681.warc.gz:0+100335654
 2018-01-30 17:07:12,391 [Executor task launch worker for task 291] INFO  Executor - Finished task 291.0 in stage 0.0 (TID 291). 1759 bytes result sent to driver
 2018-01-30 17:07:12,393 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 293.0 in stage 0.0 (TID 293, localhost, executor driver, partition 293, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:12,393 [task-result-getter-1] INFO  TaskSetManager - Finished task 291.0 in stage 0.0 (TID 291) in 15462 ms on localhost (executor driver) (282/3618)
 2018-01-30 17:07:12,394 [Executor task launch worker for task 293] INFO  Executor - Running task 293.0 in stage 0.0 (TID 293)
 2018-01-30 17:07:12,396 [Executor task launch worker for task 293] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301062327-00068-crawling211.us.archive.org-6682.warc.gz:0+106090534
 2018-01-30 17:07:16,481 [Executor task launch worker for task 261] INFO  Executor - Finished task 261.0 in stage 0.0 (TID 261). 1962 bytes result sent to driver
 2018-01-30 17:07:16,483 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 294.0 in stage 0.0 (TID 294, localhost, executor driver, partition 294, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:16,483 [task-result-getter-2] INFO  TaskSetManager - Finished task 261.0 in stage 0.0 (TID 261) in 106479 ms on localhost (executor driver) (283/3618)
 2018-01-30 17:07:16,483 [Executor task launch worker for task 294] INFO  Executor - Running task 294.0 in stage 0.0 (TID 294)
 2018-01-30 17:07:16,486 [Executor task launch worker for task 294] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406050107-00021-crawling200.us.archive.org-6682.warc.gz:0+118883394
 2018-01-30 17:07:18,066 [Executor task launch worker for task 265] INFO  Executor - Finished task 265.0 in stage 0.0 (TID 265). 2425 bytes result sent to driver
 2018-01-30 17:07:18,068 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 295.0 in stage 0.0 (TID 295, localhost, executor driver, partition 295, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:18,068 [Executor task launch worker for task 295] INFO  Executor - Running task 295.0 in stage 0.0 (TID 295)
 2018-01-30 17:07:18,068 [task-result-getter-3] INFO  TaskSetManager - Finished task 265.0 in stage 0.0 (TID 265) in 91343 ms on localhost (executor driver) (284/3618)
 2018-01-30 17:07:18,070 [Executor task launch worker for task 295] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301132950-00170-crawling211.us.archive.org-6682.warc.gz:0+103368154
 2018-01-30 17:07:24,690 [Executor task launch worker for task 270] INFO  Executor - Finished task 270.0 in stage 0.0 (TID 270). 2025 bytes result sent to driver
 2018-01-30 17:07:24,693 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 296.0 in stage 0.0 (TID 296, localhost, executor driver, partition 296, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:24,693 [Executor task launch worker for task 296] INFO  Executor - Running task 296.0 in stage 0.0 (TID 296)
 2018-01-30 17:07:24,695 [task-result-getter-0] INFO  TaskSetManager - Finished task 270.0 in stage 0.0 (TID 270) in 90974 ms on localhost (executor driver) (285/3618)
 2018-01-30 17:07:24,696 [Executor task launch worker for task 296] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301182723-00253-crawling211.us.archive.org-6682.warc.gz:0+25167335
 2018-01-30 17:07:26,395 [Executor task launch worker for task 296] INFO  Executor - Finished task 296.0 in stage 0.0 (TID 296). 1587 bytes result sent to driver
 2018-01-30 17:07:26,396 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 297.0 in stage 0.0 (TID 297, localhost, executor driver, partition 297, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:07:26,397 [Executor task launch worker for task 297] INFO  Executor - Running task 297.0 in stage 0.0 (TID 297)
 2018-01-30 17:07:26,397 [task-result-getter-1] INFO  TaskSetManager - Finished task 296.0 in stage 0.0 (TID 296) in 1705 ms on localhost (executor driver) (286/3618)
 2018-01-30 17:07:26,398 [Executor task launch worker for task 297] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925085011755-00065.warc.gz:0+1000051448
 2018-01-30 17:07:26,838 [Executor task launch worker for task 292] INFO  Executor - Finished task 292.0 in stage 0.0 (TID 292). 1791 bytes result sent to driver
 2018-01-30 17:07:26,839 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 298.0 in stage 0.0 (TID 298, localhost, executor driver, partition 298, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:26,839 [Executor task launch worker for task 298] INFO  Executor - Running task 298.0 in stage 0.0 (TID 298)
 2018-01-30 17:07:26,839 [task-result-getter-2] INFO  TaskSetManager - Finished task 292.0 in stage 0.0 (TID 292) in 15358 ms on localhost (executor driver) (287/3618)
 2018-01-30 17:07:26,840 [Executor task launch worker for task 298] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301054024-00057-crawling211.us.archive.org-6682.warc.gz:0+108652077
 2018-01-30 17:07:27,635 [Executor task launch worker for task 295] INFO  Executor - Finished task 295.0 in stage 0.0 (TID 295). 1573 bytes result sent to driver
 2018-01-30 17:07:27,637 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 299.0 in stage 0.0 (TID 299, localhost, executor driver, partition 299, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:07:27,637 [Executor task launch worker for task 299] INFO  Executor - Running task 299.0 in stage 0.0 (TID 299)
 2018-01-30 17:07:27,637 [task-result-getter-3] INFO  TaskSetManager - Finished task 295.0 in stage 0.0 (TID 295) in 9570 ms on localhost (executor driver) (288/3618)
 2018-01-30 17:07:27,638 [Executor task launch worker for task 299] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225231818236-00112.warc.gz:0+1000077554
 2018-01-30 17:07:28,679 [Executor task launch worker for task 293] INFO  Executor - Finished task 293.0 in stage 0.0 (TID 293). 1573 bytes result sent to driver
 2018-01-30 17:07:28,681 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 300.0 in stage 0.0 (TID 300, localhost, executor driver, partition 300, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:28,682 [Executor task launch worker for task 300] INFO  Executor - Running task 300.0 in stage 0.0 (TID 300)
 2018-01-30 17:07:28,682 [task-result-getter-0] INFO  TaskSetManager - Finished task 293.0 in stage 0.0 (TID 293) in 16290 ms on localhost (executor driver) (289/3618)
 2018-01-30 17:07:28,683 [Executor task launch worker for task 300] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-QXKIYS-20110919205657-00000-crawling206.us.archive.org-6682.warc.gz:0+35822
 2018-01-30 17:07:28,711 [Executor task launch worker for task 300] INFO  Executor - Finished task 300.0 in stage 0.0 (TID 300). 1690 bytes result sent to driver
 2018-01-30 17:07:28,712 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 301.0 in stage 0.0 (TID 301, localhost, executor driver, partition 301, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:28,712 [Executor task launch worker for task 301] INFO  Executor - Running task 301.0 in stage 0.0 (TID 301)
 2018-01-30 17:07:28,712 [task-result-getter-1] INFO  TaskSetManager - Finished task 300.0 in stage 0.0 (TID 300) in 31 ms on localhost (executor driver) (290/3618)
 2018-01-30 17:07:28,713 [Executor task launch worker for task 301] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002081045-00267-crawling209.us.archive.org-6681.warc.gz:0+105146970
 2018-01-30 17:07:31,378 [Executor task launch worker for task 276] INFO  Executor - Finished task 276.0 in stage 0.0 (TID 276). 1771 bytes result sent to driver
 2018-01-30 17:07:31,380 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 302.0 in stage 0.0 (TID 302, localhost, executor driver, partition 302, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:07:31,380 [task-result-getter-2] INFO  TaskSetManager - Finished task 276.0 in stage 0.0 (TID 276) in 84041 ms on localhost (executor driver) (291/3618)
 2018-01-30 17:07:31,381 [Executor task launch worker for task 302] INFO  Executor - Running task 302.0 in stage 0.0 (TID 302)
 2018-01-30 17:07:31,383 [Executor task launch worker for task 302] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727112437633-00015.warc.gz:0+1024425205
 2018-01-30 17:07:35,679 [Executor task launch worker for task 271] INFO  Executor - Finished task 271.0 in stage 0.0 (TID 271). 2041 bytes result sent to driver
 2018-01-30 17:07:35,683 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 303.0 in stage 0.0 (TID 303, localhost, executor driver, partition 303, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:07:35,683 [Executor task launch worker for task 303] INFO  Executor - Running task 303.0 in stage 0.0 (TID 303)
 2018-01-30 17:07:35,683 [task-result-getter-3] INFO  TaskSetManager - Finished task 271.0 in stage 0.0 (TID 271) in 101627 ms on localhost (executor driver) (292/3618)
 2018-01-30 17:07:35,689 [Executor task launch worker for task 303] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-3193-20150410213021323-00000-wbgrp-crawl066.us.archive.org-6441.warc.gz:0+280507939
 2018-01-30 17:07:37,692 [Executor task launch worker for task 298] INFO  Executor - Finished task 298.0 in stage 0.0 (TID 298). 1573 bytes result sent to driver
 2018-01-30 17:07:37,693 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 304.0 in stage 0.0 (TID 304, localhost, executor driver, partition 304, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:37,693 [Executor task launch worker for task 304] INFO  Executor - Running task 304.0 in stage 0.0 (TID 304)
 2018-01-30 17:07:37,693 [task-result-getter-0] INFO  TaskSetManager - Finished task 298.0 in stage 0.0 (TID 298) in 10855 ms on localhost (executor driver) (293/3618)
 2018-01-30 17:07:37,695 [Executor task launch worker for task 304] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301040528-00035-crawling211.us.archive.org-6682.warc.gz:0+104487267
 2018-01-30 17:07:39,041 [Executor task launch worker for task 294] INFO  Executor - Finished task 294.0 in stage 0.0 (TID 294). 1759 bytes result sent to driver
 2018-01-30 17:07:39,042 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 305.0 in stage 0.0 (TID 305, localhost, executor driver, partition 305, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:39,042 [Executor task launch worker for task 305] INFO  Executor - Running task 305.0 in stage 0.0 (TID 305)
 2018-01-30 17:07:39,042 [task-result-getter-1] INFO  TaskSetManager - Finished task 294.0 in stage 0.0 (TID 294) in 22560 ms on localhost (executor driver) (294/3618)
 2018-01-30 17:07:39,044 [Executor task launch worker for task 305] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930053330-00082-crawling202.us.archive.org-6681.warc.gz:0+103589621
 2018-01-30 17:07:42,775 [Executor task launch worker for task 304] INFO  Executor - Finished task 304.0 in stage 0.0 (TID 304). 1573 bytes result sent to driver
 2018-01-30 17:07:42,777 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 306.0 in stage 0.0 (TID 306, localhost, executor driver, partition 306, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:42,777 [Executor task launch worker for task 306] INFO  Executor - Running task 306.0 in stage 0.0 (TID 306)
 2018-01-30 17:07:42,778 [task-result-getter-2] INFO  TaskSetManager - Finished task 304.0 in stage 0.0 (TID 304) in 5086 ms on localhost (executor driver) (295/3618)
 2018-01-30 17:07:42,780 [Executor task launch worker for task 306] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006100045-00046-crawling205.us.archive.org-6681.warc.gz:0+105777215
 2018-01-30 17:07:49,631 [Executor task launch worker for task 278] INFO  Executor - Finished task 278.0 in stage 0.0 (TID 278). 1946 bytes result sent to driver
 2018-01-30 17:07:49,632 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 307.0 in stage 0.0 (TID 307, localhost, executor driver, partition 307, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:07:49,632 [task-result-getter-3] INFO  TaskSetManager - Finished task 278.0 in stage 0.0 (TID 278) in 97428 ms on localhost (executor driver) (296/3618)
 2018-01-30 17:07:49,632 [Executor task launch worker for task 307] INFO  Executor - Running task 307.0 in stage 0.0 (TID 307)
 2018-01-30 17:07:49,633 [Executor task launch worker for task 307] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929211943-00010-crawling202.us.archive.org-6681.warc.gz:0+101389978
 2018-01-30 17:07:56,462 [Executor task launch worker for task 301] INFO  Executor - Finished task 301.0 in stage 0.0 (TID 301). 1846 bytes result sent to driver
 2018-01-30 17:07:56,462 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 308.0 in stage 0.0 (TID 308, localhost, executor driver, partition 308, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:07:56,463 [task-result-getter-0] INFO  TaskSetManager - Finished task 301.0 in stage 0.0 (TID 301) in 27751 ms on localhost (executor driver) (297/3618)
 2018-01-30 17:07:56,463 [Executor task launch worker for task 308] INFO  Executor - Running task 308.0 in stage 0.0 (TID 308)
 2018-01-30 17:07:56,464 [Executor task launch worker for task 308] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20121001074600-00112-crawling113.us.archive.org-6683.warc.gz:0+103758743
 2018-01-30 17:08:02,877 [Executor task launch worker for task 287] INFO  Executor - Finished task 287.0 in stage 0.0 (TID 287). 1926 bytes result sent to driver
 2018-01-30 17:08:02,878 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 309.0 in stage 0.0 (TID 309, localhost, executor driver, partition 309, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:08:02,878 [task-result-getter-1] INFO  TaskSetManager - Finished task 287.0 in stage 0.0 (TID 287) in 84085 ms on localhost (executor driver) (298/3618)
 2018-01-30 17:08:02,888 [Executor task launch worker for task 309] INFO  Executor - Running task 309.0 in stage 0.0 (TID 309)
 2018-01-30 17:08:02,889 [Executor task launch worker for task 309] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB224318-20160709124043419-00001.warc.gz:0+132370811
 2018-01-30 17:08:08,910 [Executor task launch worker for task 308] INFO  Executor - Finished task 308.0 in stage 0.0 (TID 308). 1759 bytes result sent to driver
 2018-01-30 17:08:08,911 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 310.0 in stage 0.0 (TID 310, localhost, executor driver, partition 310, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:08:08,911 [Executor task launch worker for task 310] INFO  Executor - Running task 310.0 in stage 0.0 (TID 310)
 2018-01-30 17:08:08,911 [task-result-getter-2] INFO  TaskSetManager - Finished task 308.0 in stage 0.0 (TID 308) in 12449 ms on localhost (executor driver) (299/3618)
 2018-01-30 17:08:08,912 [Executor task launch worker for task 310] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-25116-20130616092150044-00006-wbgrp-crawl051.us.archive.org-6440.warc.gz:0+1001279649
 2018-01-30 17:08:09,190 [Executor task launch worker for task 305] INFO  Executor - Finished task 305.0 in stage 0.0 (TID 305). 1787 bytes result sent to driver
 2018-01-30 17:08:09,191 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 311.0 in stage 0.0 (TID 311, localhost, executor driver, partition 311, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:09,191 [task-result-getter-3] INFO  TaskSetManager - Finished task 305.0 in stage 0.0 (TID 305) in 30149 ms on localhost (executor driver) (300/3618)
 2018-01-30 17:08:09,191 [Executor task launch worker for task 311] INFO  Executor - Running task 311.0 in stage 0.0 (TID 311)
 2018-01-30 17:08:09,192 [Executor task launch worker for task 311] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003115805-00602-crawling209.us.archive.org-6681.warc.gz:0+100289091
 2018-01-30 17:08:10,543 [Executor task launch worker for task 303] INFO  Executor - Finished task 303.0 in stage 0.0 (TID 303). 1969 bytes result sent to driver
 2018-01-30 17:08:10,543 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 312.0 in stage 0.0 (TID 312, localhost, executor driver, partition 312, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:08:10,543 [Executor task launch worker for task 312] INFO  Executor - Running task 312.0 in stage 0.0 (TID 312)
 2018-01-30 17:08:10,543 [task-result-getter-0] INFO  TaskSetManager - Finished task 303.0 in stage 0.0 (TID 303) in 34862 ms on localhost (executor driver) (301/3618)
 2018-01-30 17:08:10,544 [Executor task launch worker for task 312] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225222949443-00110.warc.gz:0+1000056925
 2018-01-30 17:08:15,050 [Executor task launch worker for task 309] INFO  Executor - Finished task 309.0 in stage 0.0 (TID 309). 1759 bytes result sent to driver
 2018-01-30 17:08:15,050 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 313.0 in stage 0.0 (TID 313, localhost, executor driver, partition 313, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:08:15,050 [Executor task launch worker for task 313] INFO  Executor - Running task 313.0 in stage 0.0 (TID 313)
 2018-01-30 17:08:15,050 [task-result-getter-1] INFO  TaskSetManager - Finished task 309.0 in stage 0.0 (TID 309) in 12172 ms on localhost (executor driver) (302/3618)
 2018-01-30 17:08:15,051 [Executor task launch worker for task 313] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024220216424-00049.warc.gz:0+1000038929
 2018-01-30 17:08:16,829 [Executor task launch worker for task 306] INFO  Executor - Finished task 306.0 in stage 0.0 (TID 306). 1759 bytes result sent to driver
 2018-01-30 17:08:16,829 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 314.0 in stage 0.0 (TID 314, localhost, executor driver, partition 314, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:16,829 [Executor task launch worker for task 314] INFO  Executor - Running task 314.0 in stage 0.0 (TID 314)
 2018-01-30 17:08:16,830 [task-result-getter-2] INFO  TaskSetManager - Finished task 306.0 in stage 0.0 (TID 306) in 34052 ms on localhost (executor driver) (303/3618)
 2018-01-30 17:08:16,830 [Executor task launch worker for task 314] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006080518-00042-crawling205.us.archive.org-6681.warc.gz:0+114660748
 2018-01-30 17:08:20,608 [Executor task launch worker for task 307] INFO  Executor - Finished task 307.0 in stage 0.0 (TID 307). 1831 bytes result sent to driver
 2018-01-30 17:08:20,609 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 315.0 in stage 0.0 (TID 315, localhost, executor driver, partition 315, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:08:20,609 [Executor task launch worker for task 315] INFO  Executor - Running task 315.0 in stage 0.0 (TID 315)
 2018-01-30 17:08:20,609 [task-result-getter-3] INFO  TaskSetManager - Finished task 307.0 in stage 0.0 (TID 307) in 30978 ms on localhost (executor driver) (304/3618)
 2018-01-30 17:08:20,610 [Executor task launch worker for task 315] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-EULQOG-20121204182815-00000-wbgrp-crawl058.us.archive.org-6682.warc.gz:0+2477892
 2018-01-30 17:08:21,182 [Executor task launch worker for task 315] INFO  Executor - Finished task 315.0 in stage 0.0 (TID 315). 1694 bytes result sent to driver
 2018-01-30 17:08:21,183 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 316.0 in stage 0.0 (TID 316, localhost, executor driver, partition 316, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:08:21,183 [Executor task launch worker for task 316] INFO  Executor - Running task 316.0 in stage 0.0 (TID 316)
 2018-01-30 17:08:21,183 [task-result-getter-0] INFO  TaskSetManager - Finished task 315.0 in stage 0.0 (TID 315) in 575 ms on localhost (executor driver) (305/3618)
 2018-01-30 17:08:21,184 [Executor task launch worker for task 316] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727030613390-00001.warc.gz:0+1003701700
 2018-01-30 17:08:24,758 [Executor task launch worker for task 268] INFO  Executor - Finished task 268.0 in stage 0.0 (TID 268). 1946 bytes result sent to driver
 2018-01-30 17:08:24,758 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 317.0 in stage 0.0 (TID 317, localhost, executor driver, partition 317, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:24,758 [Executor task launch worker for task 317] INFO  Executor - Running task 317.0 in stage 0.0 (TID 317)
 2018-01-30 17:08:24,758 [task-result-getter-1] INFO  TaskSetManager - Finished task 268.0 in stage 0.0 (TID 268) in 155398 ms on localhost (executor driver) (306/3618)
 2018-01-30 17:08:24,759 [Executor task launch worker for task 317] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929222307-00033-crawling202.us.archive.org-6681.warc.gz:0+100057085
 2018-01-30 17:08:26,065 [Executor task launch worker for task 311] INFO  Executor - Finished task 311.0 in stage 0.0 (TID 311). 1759 bytes result sent to driver
 2018-01-30 17:08:26,066 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 318.0 in stage 0.0 (TID 318, localhost, executor driver, partition 318, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:26,066 [task-result-getter-2] INFO  TaskSetManager - Finished task 311.0 in stage 0.0 (TID 311) in 16876 ms on localhost (executor driver) (307/3618)
 2018-01-30 17:08:26,066 [Executor task launch worker for task 318] INFO  Executor - Running task 318.0 in stage 0.0 (TID 318)
 2018-01-30 17:08:26,067 [Executor task launch worker for task 318] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002202416-00440-crawling209.us.archive.org-6681.warc.gz:0+100002822
 2018-01-30 17:08:30,401 [Executor task launch worker for task 318] INFO  Executor - Finished task 318.0 in stage 0.0 (TID 318). 1773 bytes result sent to driver
 2018-01-30 17:08:30,401 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 319.0 in stage 0.0 (TID 319, localhost, executor driver, partition 319, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:30,401 [Executor task launch worker for task 319] INFO  Executor - Running task 319.0 in stage 0.0 (TID 319)
 2018-01-30 17:08:30,401 [task-result-getter-3] INFO  TaskSetManager - Finished task 318.0 in stage 0.0 (TID 318) in 4336 ms on localhost (executor driver) (308/3618)
 2018-01-30 17:08:30,402 [Executor task launch worker for task 319] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003043149-00535-crawling209.us.archive.org-6681.warc.gz:0+108176283
 2018-01-30 17:08:34,208 [Executor task launch worker for task 319] INFO  Executor - Finished task 319.0 in stage 0.0 (TID 319). 1759 bytes result sent to driver
 2018-01-30 17:08:34,209 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 320.0 in stage 0.0 (TID 320, localhost, executor driver, partition 320, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:08:34,209 [Executor task launch worker for task 320] INFO  Executor - Running task 320.0 in stage 0.0 (TID 320)
 2018-01-30 17:08:34,209 [task-result-getter-0] INFO  TaskSetManager - Finished task 319.0 in stage 0.0 (TID 319) in 3808 ms on localhost (executor driver) (309/3618)
 2018-01-30 17:08:34,210 [Executor task launch worker for task 320] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-8983-20140228213510144-00000-wbgrp-crawl066.us.archive.org-6440.warc.gz:0+172904689
 2018-01-30 17:08:37,754 [Executor task launch worker for task 297] INFO  Executor - Finished task 297.0 in stage 0.0 (TID 297). 1962 bytes result sent to driver
 2018-01-30 17:08:37,754 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 321.0 in stage 0.0 (TID 321, localhost, executor driver, partition 321, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:08:37,754 [Executor task launch worker for task 321] INFO  Executor - Running task 321.0 in stage 0.0 (TID 321)
 2018-01-30 17:08:37,754 [task-result-getter-1] INFO  TaskSetManager - Finished task 297.0 in stage 0.0 (TID 297) in 71358 ms on localhost (executor driver) (310/3618)
 2018-01-30 17:08:37,755 [Executor task launch worker for task 321] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171023203633630-00002.warc.gz:0+1000053792
 2018-01-30 17:08:47,282 [Executor task launch worker for task 320] INFO  Executor - Finished task 320.0 in stage 0.0 (TID 320). 1906 bytes result sent to driver
 2018-01-30 17:08:47,282 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 322.0 in stage 0.0 (TID 322, localhost, executor driver, partition 322, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:08:47,283 [task-result-getter-2] INFO  TaskSetManager - Finished task 320.0 in stage 0.0 (TID 320) in 13074 ms on localhost (executor driver) (311/3618)
 2018-01-30 17:08:47,283 [Executor task launch worker for task 322] INFO  Executor - Running task 322.0 in stage 0.0 (TID 322)
 2018-01-30 17:08:47,284 [Executor task launch worker for task 322] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926123719897-00111.warc.gz:0+1000049791
 2018-01-30 17:08:49,577 [Executor task launch worker for task 299] INFO  Executor - Finished task 299.0 in stage 0.0 (TID 299). 2405 bytes result sent to driver
 2018-01-30 17:08:49,578 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 323.0 in stage 0.0 (TID 323, localhost, executor driver, partition 323, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:08:49,578 [Executor task launch worker for task 323] INFO  Executor - Running task 323.0 in stage 0.0 (TID 323)
 2018-01-30 17:08:49,578 [task-result-getter-3] INFO  TaskSetManager - Finished task 299.0 in stage 0.0 (TID 299) in 81942 ms on localhost (executor driver) (312/3618)
 2018-01-30 17:08:49,579 [Executor task launch worker for task 323] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004220519498-00007-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+4280066
 2018-01-30 17:08:49,830 [Executor task launch worker for task 323] INFO  Executor - Finished task 323.0 in stage 0.0 (TID 323). 1690 bytes result sent to driver
 2018-01-30 17:08:49,831 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 324.0 in stage 0.0 (TID 324, localhost, executor driver, partition 324, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:08:49,831 [Executor task launch worker for task 324] INFO  Executor - Running task 324.0 in stage 0.0 (TID 324)
 2018-01-30 17:08:49,831 [task-result-getter-0] INFO  TaskSetManager - Finished task 323.0 in stage 0.0 (TID 323) in 253 ms on localhost (executor driver) (313/3618)
 2018-01-30 17:08:49,832 [Executor task launch worker for task 324] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QRDYRH-20120313024749-00018-crawling113.us.archive.org-6681.warc.gz:0+820925057
 2018-01-30 17:08:52,324 [Executor task launch worker for task 314] INFO  Executor - Finished task 314.0 in stage 0.0 (TID 314). 1573 bytes result sent to driver
 2018-01-30 17:08:52,324 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 325.0 in stage 0.0 (TID 325, localhost, executor driver, partition 325, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:08:52,324 [Executor task launch worker for task 325] INFO  Executor - Running task 325.0 in stage 0.0 (TID 325)
 2018-01-30 17:08:52,324 [task-result-getter-1] INFO  TaskSetManager - Finished task 314.0 in stage 0.0 (TID 314) in 35495 ms on localhost (executor driver) (314/3618)
 2018-01-30 17:08:52,325 [Executor task launch worker for task 325] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120615025506-00021-crawling200.us.archive.org-6681.warc.gz:0+100002896
 2018-01-30 17:08:55,020 [Executor task launch worker for task 317] INFO  Executor - Finished task 317.0 in stage 0.0 (TID 317). 1882 bytes result sent to driver
 2018-01-30 17:08:55,020 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 326.0 in stage 0.0 (TID 326, localhost, executor driver, partition 326, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:08:55,020 [task-result-getter-2] INFO  TaskSetManager - Finished task 317.0 in stage 0.0 (TID 317) in 30262 ms on localhost (executor driver) (315/3618)
 2018-01-30 17:08:55,021 [Executor task launch worker for task 326] INFO  Executor - Running task 326.0 in stage 0.0 (TID 326)
 2018-01-30 17:08:55,022 [Executor task launch worker for task 326] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002220145-00463-crawling209.us.archive.org-6681.warc.gz:0+104816031
 2018-01-30 17:09:02,844 [Executor task launch worker for task 326] INFO  Executor - Finished task 326.0 in stage 0.0 (TID 326). 1672 bytes result sent to driver
 2018-01-30 17:09:02,845 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 327.0 in stage 0.0 (TID 327, localhost, executor driver, partition 327, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:09:02,845 [task-result-getter-3] INFO  TaskSetManager - Finished task 326.0 in stage 0.0 (TID 326) in 7825 ms on localhost (executor driver) (316/3618)
 2018-01-30 17:09:02,846 [Executor task launch worker for task 327] INFO  Executor - Running task 327.0 in stage 0.0 (TID 327)
 2018-01-30 17:09:02,847 [Executor task launch worker for task 327] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB231501-20160820105536608-00001.warc.gz:0+732194633
 2018-01-30 17:09:04,671 [Executor task launch worker for task 325] INFO  Executor - Finished task 325.0 in stage 0.0 (TID 325). 1759 bytes result sent to driver
 2018-01-30 17:09:04,672 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 328.0 in stage 0.0 (TID 328, localhost, executor driver, partition 328, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:09:04,672 [Executor task launch worker for task 328] INFO  Executor - Running task 328.0 in stage 0.0 (TID 328)
 2018-01-30 17:09:04,672 [task-result-getter-0] INFO  TaskSetManager - Finished task 325.0 in stage 0.0 (TID 325) in 12348 ms on localhost (executor driver) (317/3618)
 2018-01-30 17:09:04,673 [Executor task launch worker for task 328] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224113130580-00028.warc.gz:0+1000064458
 2018-01-30 17:09:29,647 [Executor task launch worker for task 312] INFO  Executor - Finished task 312.0 in stage 0.0 (TID 312). 1819 bytes result sent to driver
 2018-01-30 17:09:29,648 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 329.0 in stage 0.0 (TID 329, localhost, executor driver, partition 329, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:09:29,648 [Executor task launch worker for task 329] INFO  Executor - Running task 329.0 in stage 0.0 (TID 329)
 2018-01-30 17:09:29,648 [task-result-getter-1] INFO  TaskSetManager - Finished task 312.0 in stage 0.0 (TID 312) in 79105 ms on localhost (executor driver) (318/3618)
 2018-01-30 17:09:29,650 [Executor task launch worker for task 329] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926022513541-00094.warc.gz:0+1000061638
 2018-01-30 17:09:31,570 [Executor task launch worker for task 313] INFO  Executor - Finished task 313.0 in stage 0.0 (TID 313). 1969 bytes result sent to driver
 2018-01-30 17:09:31,571 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 330.0 in stage 0.0 (TID 330, localhost, executor driver, partition 330, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:09:31,571 [Executor task launch worker for task 330] INFO  Executor - Running task 330.0 in stage 0.0 (TID 330)
 2018-01-30 17:09:31,571 [task-result-getter-2] INFO  TaskSetManager - Finished task 313.0 in stage 0.0 (TID 313) in 76521 ms on localhost (executor driver) (319/3618)
 2018-01-30 17:09:31,572 [Executor task launch worker for task 330] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628224410-00035-crawling212.us.archive.org-6682.warc.gz:0+102716986
 2018-01-30 17:09:55,712 [Executor task launch worker for task 272] INFO  Executor - Finished task 272.0 in stage 0.0 (TID 272). 2037 bytes result sent to driver
 2018-01-30 17:09:55,714 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 331.0 in stage 0.0 (TID 331, localhost, executor driver, partition 331, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:09:55,714 [Executor task launch worker for task 331] INFO  Executor - Running task 331.0 in stage 0.0 (TID 331)
 2018-01-30 17:09:55,715 [Executor task launch worker for task 331] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301105934-00132-crawling211.us.archive.org-6682.warc.gz:0+102492357
 2018-01-30 17:09:55,717 [task-result-getter-3] INFO  TaskSetManager - Finished task 272.0 in stage 0.0 (TID 272) in 239633 ms on localhost (executor driver) (320/3618)
 2018-01-30 17:09:59,863 [Executor task launch worker for task 331] INFO  Executor - Finished task 331.0 in stage 0.0 (TID 331). 1413 bytes result sent to driver
 2018-01-30 17:09:59,865 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 332.0 in stage 0.0 (TID 332, localhost, executor driver, partition 332, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:09:59,865 [Executor task launch worker for task 332] INFO  Executor - Running task 332.0 in stage 0.0 (TID 332)
 2018-01-30 17:09:59,865 [task-result-getter-0] INFO  TaskSetManager - Finished task 331.0 in stage 0.0 (TID 331) in 4152 ms on localhost (executor driver) (321/3618)
 2018-01-30 17:09:59,867 [Executor task launch worker for task 332] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002114300-00322-crawling209.us.archive.org-6681.warc.gz:0+105067752
 2018-01-30 17:10:10,234 [Executor task launch worker for task 321] INFO  Executor - Finished task 321.0 in stage 0.0 (TID 321). 3118 bytes result sent to driver
 2018-01-30 17:10:10,235 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 333.0 in stage 0.0 (TID 333, localhost, executor driver, partition 333, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:10:10,236 [Executor task launch worker for task 333] INFO  Executor - Running task 333.0 in stage 0.0 (TID 333)
 2018-01-30 17:10:10,236 [task-result-getter-1] INFO  TaskSetManager - Finished task 321.0 in stage 0.0 (TID 321) in 92482 ms on localhost (executor driver) (322/3618)
 2018-01-30 17:10:10,238 [Executor task launch worker for task 333] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002230413-00478-crawling209.us.archive.org-6681.warc.gz:0+111170080
 2018-01-30 17:10:13,372 [Executor task launch worker for task 333] INFO  Executor - Finished task 333.0 in stage 0.0 (TID 333). 1759 bytes result sent to driver
 2018-01-30 17:10:13,373 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 334.0 in stage 0.0 (TID 334, localhost, executor driver, partition 334, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:10:13,373 [Executor task launch worker for task 334] INFO  Executor - Running task 334.0 in stage 0.0 (TID 334)
 2018-01-30 17:10:13,373 [task-result-getter-2] INFO  TaskSetManager - Finished task 333.0 in stage 0.0 (TID 333) in 3138 ms on localhost (executor driver) (323/3618)
 2018-01-30 17:10:13,374 [Executor task launch worker for task 334] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002023208-00154-crawling209.us.archive.org-6681.warc.gz:0+101160205
 2018-01-30 17:10:13,483 [Executor task launch worker for task 330] INFO  Executor - Finished task 330.0 in stage 0.0 (TID 330). 1573 bytes result sent to driver
 2018-01-30 17:10:13,484 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 335.0 in stage 0.0 (TID 335, localhost, executor driver, partition 335, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:10:13,484 [Executor task launch worker for task 335] INFO  Executor - Running task 335.0 in stage 0.0 (TID 335)
 2018-01-30 17:10:13,484 [task-result-getter-3] INFO  TaskSetManager - Finished task 330.0 in stage 0.0 (TID 330) in 41914 ms on localhost (executor driver) (324/3618)
 2018-01-30 17:10:13,485 [Executor task launch worker for task 335] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926052639963-00099.warc.gz:0+1000062678
 2018-01-30 17:10:15,512 [Executor task launch worker for task 332] INFO  Executor - Finished task 332.0 in stage 0.0 (TID 332). 1763 bytes result sent to driver
 2018-01-30 17:10:15,513 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 336.0 in stage 0.0 (TID 336, localhost, executor driver, partition 336, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:10:15,513 [Executor task launch worker for task 336] INFO  Executor - Running task 336.0 in stage 0.0 (TID 336)
 2018-01-30 17:10:15,513 [task-result-getter-0] INFO  TaskSetManager - Finished task 332.0 in stage 0.0 (TID 332) in 15649 ms on localhost (executor driver) (325/3618)
 2018-01-30 17:10:15,514 [Executor task launch worker for task 336] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-POKJKJ-20111206203645-00000-crawling201.us.archive.org-6680.warc.gz:0+100337402
 2018-01-30 17:10:23,332 [Executor task launch worker for task 334] INFO  Executor - Finished task 334.0 in stage 0.0 (TID 334). 1767 bytes result sent to driver
 2018-01-30 17:10:23,337 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 337.0 in stage 0.0 (TID 337, localhost, executor driver, partition 337, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:10:23,337 [Executor task launch worker for task 337] INFO  Executor - Running task 337.0 in stage 0.0 (TID 337)
 2018-01-30 17:10:23,338 [task-result-getter-1] INFO  TaskSetManager - Finished task 334.0 in stage 0.0 (TID 334) in 9965 ms on localhost (executor driver) (326/3618)
 2018-01-30 17:10:23,339 [Executor task launch worker for task 337] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB302697-20170523201417718-00000.warc.gz:0+2528914932
 2018-01-30 17:10:23,591 [Executor task launch worker for task 322] INFO  Executor - Finished task 322.0 in stage 0.0 (TID 322). 2161 bytes result sent to driver
 2018-01-30 17:10:23,592 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 338.0 in stage 0.0 (TID 338, localhost, executor driver, partition 338, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:10:23,593 [Executor task launch worker for task 338] INFO  Executor - Running task 338.0 in stage 0.0 (TID 338)
 2018-01-30 17:10:23,593 [task-result-getter-2] INFO  TaskSetManager - Finished task 322.0 in stage 0.0 (TID 322) in 96311 ms on localhost (executor driver) (327/3618)
 2018-01-30 17:10:23,594 [Executor task launch worker for task 338] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121012210835-00004-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+100062643
 2018-01-30 17:10:26,965 [Executor task launch worker for task 327] INFO  Executor - Finished task 327.0 in stage 0.0 (TID 327). 1759 bytes result sent to driver
 2018-01-30 17:10:26,965 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 339.0 in stage 0.0 (TID 339, localhost, executor driver, partition 339, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:10:26,966 [Executor task launch worker for task 339] INFO  Executor - Running task 339.0 in stage 0.0 (TID 339)
 2018-01-30 17:10:26,966 [task-result-getter-3] INFO  TaskSetManager - Finished task 327.0 in stage 0.0 (TID 327) in 84121 ms on localhost (executor driver) (328/3618)
 2018-01-30 17:10:26,967 [Executor task launch worker for task 339] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-9330-20140224204612273-00007-wbgrp-crawl102.us.archive.org-6442.warc.gz:0+1001051075
 2018-01-30 17:10:32,907 [Executor task launch worker for task 328] INFO  Executor - Finished task 328.0 in stage 0.0 (TID 328). 2068 bytes result sent to driver
 2018-01-30 17:10:32,908 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 340.0 in stage 0.0 (TID 340, localhost, executor driver, partition 340, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:10:32,908 [Executor task launch worker for task 340] INFO  Executor - Running task 340.0 in stage 0.0 (TID 340)
 2018-01-30 17:10:32,909 [task-result-getter-0] INFO  TaskSetManager - Finished task 328.0 in stage 0.0 (TID 328) in 88237 ms on localhost (executor driver) (329/3618)
 2018-01-30 17:10:32,911 [Executor task launch worker for task 340] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB302697-20170524074718441-00005.warc.gz:0+747112604
 2018-01-30 17:10:37,327 [Executor task launch worker for task 336] INFO  Executor - Finished task 336.0 in stage 0.0 (TID 336). 1823 bytes result sent to driver
 2018-01-30 17:10:37,328 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 341.0 in stage 0.0 (TID 341, localhost, executor driver, partition 341, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:10:37,328 [Executor task launch worker for task 341] INFO  Executor - Running task 341.0 in stage 0.0 (TID 341)
 2018-01-30 17:10:37,328 [task-result-getter-1] INFO  TaskSetManager - Finished task 336.0 in stage 0.0 (TID 336) in 21815 ms on localhost (executor driver) (330/3618)
 2018-01-30 17:10:37,329 [Executor task launch worker for task 341] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008185554-00021-crawling208.us.archive.org-6683.warc.gz:0+102885154
 2018-01-30 17:10:50,960 [Executor task launch worker for task 338] INFO  Executor - Finished task 338.0 in stage 0.0 (TID 338). 1724 bytes result sent to driver
 2018-01-30 17:10:50,962 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 342.0 in stage 0.0 (TID 342, localhost, executor driver, partition 342, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:10:50,962 [task-result-getter-2] INFO  TaskSetManager - Finished task 338.0 in stage 0.0 (TID 338) in 27370 ms on localhost (executor driver) (331/3618)
 2018-01-30 17:10:50,962 [Executor task launch worker for task 342] INFO  Executor - Running task 342.0 in stage 0.0 (TID 342)
 2018-01-30 17:10:50,965 [Executor task launch worker for task 342] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727220720593-00034.warc.gz:0+1005059759
 2018-01-30 17:10:56,682 [Executor task launch worker for task 329] INFO  Executor - Finished task 329.0 in stage 0.0 (TID 329). 2420 bytes result sent to driver
 2018-01-30 17:10:56,684 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 343.0 in stage 0.0 (TID 343, localhost, executor driver, partition 343, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:10:56,684 [task-result-getter-3] INFO  TaskSetManager - Finished task 329.0 in stage 0.0 (TID 329) in 87036 ms on localhost (executor driver) (332/3618)
 2018-01-30 17:10:56,684 [Executor task launch worker for task 343] INFO  Executor - Running task 343.0 in stage 0.0 (TID 343)
 2018-01-30 17:10:56,687 [Executor task launch worker for task 343] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003013107-00513-crawling209.us.archive.org-6681.warc.gz:0+104845563
 2018-01-30 17:11:21,280 [Executor task launch worker for task 343] INFO  Executor - Finished task 343.0 in stage 0.0 (TID 343). 1759 bytes result sent to driver
 2018-01-30 17:11:21,283 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 344.0 in stage 0.0 (TID 344, localhost, executor driver, partition 344, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:11:21,283 [Executor task launch worker for task 344] INFO  Executor - Running task 344.0 in stage 0.0 (TID 344)
 2018-01-30 17:11:21,283 [task-result-getter-0] INFO  TaskSetManager - Finished task 343.0 in stage 0.0 (TID 343) in 24600 ms on localhost (executor driver) (333/3618)
 2018-01-30 17:11:21,286 [Executor task launch worker for task 344] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB206270-20160409165654512-00001.warc.gz:0+288556274
 2018-01-30 17:11:22,288 [Executor task launch worker for task 340] INFO  Executor - Finished task 340.0 in stage 0.0 (TID 340). 1759 bytes result sent to driver
 2018-01-30 17:11:22,289 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 345.0 in stage 0.0 (TID 345, localhost, executor driver, partition 345, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:11:22,289 [Executor task launch worker for task 345] INFO  Executor - Running task 345.0 in stage 0.0 (TID 345)
 2018-01-30 17:11:22,289 [task-result-getter-1] INFO  TaskSetManager - Finished task 340.0 in stage 0.0 (TID 340) in 49382 ms on localhost (executor driver) (334/3618)
 2018-01-30 17:11:22,290 [Executor task launch worker for task 345] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120614164635-00019-crawling200.us.archive.org-6681.warc.gz:0+100000416
 2018-01-30 17:11:28,060 [Executor task launch worker for task 341] INFO  Executor - Finished task 341.0 in stage 0.0 (TID 341). 1763 bytes result sent to driver
 2018-01-30 17:11:28,061 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 346.0 in stage 0.0 (TID 346, localhost, executor driver, partition 346, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:28,061 [Executor task launch worker for task 346] INFO  Executor - Running task 346.0 in stage 0.0 (TID 346)
 2018-01-30 17:11:28,061 [task-result-getter-2] INFO  TaskSetManager - Finished task 341.0 in stage 0.0 (TID 341) in 50734 ms on localhost (executor driver) (335/3618)
 2018-01-30 17:11:28,062 [Executor task launch worker for task 346] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929211248-00006-crawling202.us.archive.org-6681.warc.gz:0+100155176
 2018-01-30 17:11:35,651 [Executor task launch worker for task 345] INFO  Executor - Finished task 345.0 in stage 0.0 (TID 345). 1767 bytes result sent to driver
 2018-01-30 17:11:35,652 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 347.0 in stage 0.0 (TID 347, localhost, executor driver, partition 347, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:11:35,652 [Executor task launch worker for task 347] INFO  Executor - Running task 347.0 in stage 0.0 (TID 347)
 2018-01-30 17:11:35,652 [task-result-getter-3] INFO  TaskSetManager - Finished task 345.0 in stage 0.0 (TID 345) in 13363 ms on localhost (executor driver) (336/3618)
 2018-01-30 17:11:35,653 [Executor task launch worker for task 347] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-SZGJAW-20120913052640-00009-crawling203.us.archive.org-6682.warc.gz:0+100000613
 2018-01-30 17:11:42,759 [Executor task launch worker for task 335] INFO  Executor - Finished task 335.0 in stage 0.0 (TID 335). 1958 bytes result sent to driver
 2018-01-30 17:11:42,760 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 348.0 in stage 0.0 (TID 348, localhost, executor driver, partition 348, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:42,760 [Executor task launch worker for task 348] INFO  Executor - Running task 348.0 in stage 0.0 (TID 348)
 2018-01-30 17:11:42,760 [task-result-getter-0] INFO  TaskSetManager - Finished task 335.0 in stage 0.0 (TID 335) in 89276 ms on localhost (executor driver) (337/3618)
 2018-01-30 17:11:42,762 [Executor task launch worker for task 348] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930192707-00254-crawling202.us.archive.org-6681.warc.gz:0+130376375
 2018-01-30 17:11:51,410 [Executor task launch worker for task 348] INFO  Executor - Finished task 348.0 in stage 0.0 (TID 348). 1702 bytes result sent to driver
 2018-01-30 17:11:51,413 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 349.0 in stage 0.0 (TID 349, localhost, executor driver, partition 349, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:51,413 [Executor task launch worker for task 349] INFO  Executor - Running task 349.0 in stage 0.0 (TID 349)
 2018-01-30 17:11:51,413 [task-result-getter-1] INFO  TaskSetManager - Finished task 348.0 in stage 0.0 (TID 348) in 8654 ms on localhost (executor driver) (338/3618)
 2018-01-30 17:11:51,417 [Executor task launch worker for task 349] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930172229-00221-crawling202.us.archive.org-6681.warc.gz:0+101438023
 2018-01-30 17:11:51,508 [Executor task launch worker for task 347] INFO  Executor - Finished task 347.0 in stage 0.0 (TID 347). 1787 bytes result sent to driver
 2018-01-30 17:11:51,509 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 350.0 in stage 0.0 (TID 350, localhost, executor driver, partition 350, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:51,509 [Executor task launch worker for task 350] INFO  Executor - Running task 350.0 in stage 0.0 (TID 350)
 2018-01-30 17:11:51,510 [Executor task launch worker for task 350] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003014418-00516-crawling209.us.archive.org-6681.warc.gz:0+102664893
 2018-01-30 17:11:51,517 [task-result-getter-2] INFO  TaskSetManager - Finished task 347.0 in stage 0.0 (TID 347) in 15866 ms on localhost (executor driver) (339/3618)
 2018-01-30 17:11:52,036 [Executor task launch worker for task 344] INFO  Executor - Finished task 344.0 in stage 0.0 (TID 344). 1759 bytes result sent to driver
 2018-01-30 17:11:52,037 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 351.0 in stage 0.0 (TID 351, localhost, executor driver, partition 351, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:11:52,037 [Executor task launch worker for task 351] INFO  Executor - Running task 351.0 in stage 0.0 (TID 351)
 2018-01-30 17:11:52,037 [task-result-getter-3] INFO  TaskSetManager - Finished task 344.0 in stage 0.0 (TID 344) in 30755 ms on localhost (executor driver) (340/3618)
 2018-01-30 17:11:52,039 [Executor task launch worker for task 351] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-GTHMHP-20121016182307-00000-crawling113.us.archive.org-6680.warc.gz:0+1799554
 2018-01-30 17:11:52,396 [Executor task launch worker for task 351] INFO  Executor - Finished task 351.0 in stage 0.0 (TID 351). 1694 bytes result sent to driver
 2018-01-30 17:11:52,397 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 352.0 in stage 0.0 (TID 352, localhost, executor driver, partition 352, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:52,397 [Executor task launch worker for task 352] INFO  Executor - Running task 352.0 in stage 0.0 (TID 352)
 2018-01-30 17:11:52,397 [task-result-getter-0] INFO  TaskSetManager - Finished task 351.0 in stage 0.0 (TID 351) in 360 ms on localhost (executor driver) (341/3618)
 2018-01-30 17:11:52,398 [Executor task launch worker for task 352] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001165645-00034-crawling209.us.archive.org-6681.warc.gz:0+101216180
 2018-01-30 17:11:59,893 [Executor task launch worker for task 350] INFO  Executor - Finished task 350.0 in stage 0.0 (TID 350). 1686 bytes result sent to driver
 2018-01-30 17:11:59,900 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 353.0 in stage 0.0 (TID 353, localhost, executor driver, partition 353, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:11:59,900 [task-result-getter-1] INFO  TaskSetManager - Finished task 350.0 in stage 0.0 (TID 350) in 8391 ms on localhost (executor driver) (342/3618)
 2018-01-30 17:11:59,901 [Executor task launch worker for task 353] INFO  Executor - Running task 353.0 in stage 0.0 (TID 353)
 2018-01-30 17:11:59,903 [Executor task launch worker for task 353] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930115748-00161-crawling202.us.archive.org-6681.warc.gz:0+100047286
 2018-01-30 17:12:05,710 [Executor task launch worker for task 346] INFO  Executor - Finished task 346.0 in stage 0.0 (TID 346). 1728 bytes result sent to driver
 2018-01-30 17:12:05,712 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 354.0 in stage 0.0 (TID 354, localhost, executor driver, partition 354, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:12:05,712 [Executor task launch worker for task 354] INFO  Executor - Running task 354.0 in stage 0.0 (TID 354)
 2018-01-30 17:12:05,712 [task-result-getter-2] INFO  TaskSetManager - Finished task 346.0 in stage 0.0 (TID 346) in 37652 ms on localhost (executor driver) (343/3618)
 2018-01-30 17:12:05,714 [Executor task launch worker for task 354] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025015732483-00056.warc.gz:0+1000003192
 2018-01-30 17:12:31,062 [Executor task launch worker for task 352] INFO  Executor - Finished task 352.0 in stage 0.0 (TID 352). 1763 bytes result sent to driver
 2018-01-30 17:12:31,064 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 355.0 in stage 0.0 (TID 355, localhost, executor driver, partition 355, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:12:31,064 [task-result-getter-3] INFO  TaskSetManager - Finished task 352.0 in stage 0.0 (TID 352) in 38668 ms on localhost (executor driver) (344/3618)
 2018-01-30 17:12:31,064 [Executor task launch worker for task 355] INFO  Executor - Running task 355.0 in stage 0.0 (TID 355)
 2018-01-30 17:12:31,066 [Executor task launch worker for task 355] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002211221-00452-crawling209.us.archive.org-6681.warc.gz:0+106704934
 2018-01-30 17:12:31,879 [Executor task launch worker for task 349] INFO  Executor - Finished task 349.0 in stage 0.0 (TID 349). 1783 bytes result sent to driver
 2018-01-30 17:12:31,880 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 356.0 in stage 0.0 (TID 356, localhost, executor driver, partition 356, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:12:31,881 [Executor task launch worker for task 356] INFO  Executor - Running task 356.0 in stage 0.0 (TID 356)
 2018-01-30 17:12:31,881 [task-result-getter-0] INFO  TaskSetManager - Finished task 349.0 in stage 0.0 (TID 349) in 40469 ms on localhost (executor driver) (345/3618)
 2018-01-30 17:12:31,882 [Executor task launch worker for task 356] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHWVNX-20120927151004-00000-crawling202.us.archive.org-6682.warc.gz:0+102762872
 2018-01-30 17:12:33,709 [Executor task launch worker for task 355] INFO  Executor - Finished task 355.0 in stage 0.0 (TID 355). 1686 bytes result sent to driver
 2018-01-30 17:12:33,710 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 357.0 in stage 0.0 (TID 357, localhost, executor driver, partition 357, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:12:33,710 [Executor task launch worker for task 357] INFO  Executor - Running task 357.0 in stage 0.0 (TID 357)
 2018-01-30 17:12:33,710 [task-result-getter-1] INFO  TaskSetManager - Finished task 355.0 in stage 0.0 (TID 355) in 2647 ms on localhost (executor driver) (346/3618)
 2018-01-30 17:12:33,712 [Executor task launch worker for task 357] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120930051534-00100-crawling113.us.archive.org-6683.warc.gz:0+111009511
 2018-01-30 17:12:37,962 [Executor task launch worker for task 353] INFO  Executor - Finished task 353.0 in stage 0.0 (TID 353). 1779 bytes result sent to driver
 2018-01-30 17:12:37,964 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 358.0 in stage 0.0 (TID 358, localhost, executor driver, partition 358, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:12:37,964 [Executor task launch worker for task 358] INFO  Executor - Running task 358.0 in stage 0.0 (TID 358)
 2018-01-30 17:12:37,964 [task-result-getter-2] INFO  TaskSetManager - Finished task 353.0 in stage 0.0 (TID 353) in 38065 ms on localhost (executor driver) (347/3618)
 2018-01-30 17:12:37,966 [Executor task launch worker for task 358] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-KSXFGE-20110718220302-00012-crawling200.us.archive.org-6682.warc.gz:0+101560029
 2018-01-30 17:12:53,615 [Executor task launch worker for task 356] INFO  Executor - Finished task 356.0 in stage 0.0 (TID 356). 1775 bytes result sent to driver
 2018-01-30 17:12:53,618 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 359.0 in stage 0.0 (TID 359, localhost, executor driver, partition 359, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:12:53,618 [task-result-getter-3] INFO  TaskSetManager - Finished task 356.0 in stage 0.0 (TID 356) in 21738 ms on localhost (executor driver) (348/3618)
 2018-01-30 17:12:53,618 [Executor task launch worker for task 359] INFO  Executor - Running task 359.0 in stage 0.0 (TID 359)
 2018-01-30 17:12:53,621 [Executor task launch worker for task 359] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111005224533-00007-crawling205.us.archive.org-6681.warc.gz:0+100791961
 2018-01-30 17:13:11,913 [Executor task launch worker for task 358] INFO  Executor - Finished task 358.0 in stage 0.0 (TID 358). 1846 bytes result sent to driver
 2018-01-30 17:13:11,916 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 360.0 in stage 0.0 (TID 360, localhost, executor driver, partition 360, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:13:11,918 [task-result-getter-0] INFO  TaskSetManager - Finished task 358.0 in stage 0.0 (TID 358) in 33955 ms on localhost (executor driver) (349/3618)
 2018-01-30 17:13:11,918 [Executor task launch worker for task 360] INFO  Executor - Running task 360.0 in stage 0.0 (TID 360)
 2018-01-30 17:13:11,924 [Executor task launch worker for task 360] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-XQIAVS-20111129004128-00010-crawling212.us.archive.org-6683.warc.gz:0+104618675
 2018-01-30 17:13:16,083 [Executor task launch worker for task 354] INFO  Executor - Finished task 354.0 in stage 0.0 (TID 354). 2184 bytes result sent to driver
 2018-01-30 17:13:16,084 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 361.0 in stage 0.0 (TID 361, localhost, executor driver, partition 361, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 17:13:16,084 [Executor task launch worker for task 361] INFO  Executor - Running task 361.0 in stage 0.0 (TID 361)
 2018-01-30 17:13:16,085 [task-result-getter-1] INFO  TaskSetManager - Finished task 354.0 in stage 0.0 (TID 354) in 70373 ms on localhost (executor driver) (350/3618)
 2018-01-30 17:13:16,086 [Executor task launch worker for task 361] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121228193809-00020-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+101944512
 2018-01-30 17:13:19,358 [Executor task launch worker for task 357] INFO  Executor - Finished task 357.0 in stage 0.0 (TID 357). 1573 bytes result sent to driver
 2018-01-30 17:13:19,359 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 362.0 in stage 0.0 (TID 362, localhost, executor driver, partition 362, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:13:19,359 [task-result-getter-2] INFO  TaskSetManager - Finished task 357.0 in stage 0.0 (TID 357) in 45649 ms on localhost (executor driver) (351/3618)
 2018-01-30 17:13:19,360 [Executor task launch worker for task 362] INFO  Executor - Running task 362.0 in stage 0.0 (TID 362)
 2018-01-30 17:13:19,361 [Executor task launch worker for task 362] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150728020248071-00040.warc.gz:0+1000000852
 2018-01-30 17:13:36,952 [Executor task launch worker for task 302] INFO  Executor - Finished task 302.0 in stage 0.0 (TID 302). 1835 bytes result sent to driver
 2018-01-30 17:13:36,952 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 363.0 in stage 0.0 (TID 363, localhost, executor driver, partition 363, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:13:36,953 [Executor task launch worker for task 363] INFO  Executor - Running task 363.0 in stage 0.0 (TID 363)
 2018-01-30 17:13:36,953 [task-result-getter-3] INFO  TaskSetManager - Finished task 302.0 in stage 0.0 (TID 302) in 365574 ms on localhost (executor driver) (352/3618)
 2018-01-30 17:13:36,954 [Executor task launch worker for task 363] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-FEEUZB-20120512203933-00001-crawling115.us.archive.org-6683.warc.gz:0+101490143
 2018-01-30 17:13:39,334 [Executor task launch worker for task 359] INFO  Executor - Finished task 359.0 in stage 0.0 (TID 359). 1759 bytes result sent to driver
 2018-01-30 17:13:39,335 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 364.0 in stage 0.0 (TID 364, localhost, executor driver, partition 364, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:13:39,335 [Executor task launch worker for task 364] INFO  Executor - Running task 364.0 in stage 0.0 (TID 364)
 2018-01-30 17:13:39,335 [task-result-getter-0] INFO  TaskSetManager - Finished task 359.0 in stage 0.0 (TID 359) in 45718 ms on localhost (executor driver) (353/3618)
 2018-01-30 17:13:39,336 [Executor task launch worker for task 364] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930034502-00052-crawling202.us.archive.org-6681.warc.gz:0+100601916
 2018-01-30 17:13:58,808 [Executor task launch worker for task 361] INFO  Executor - Finished task 361.0 in stage 0.0 (TID 361). 1573 bytes result sent to driver
 2018-01-30 17:13:58,810 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 365.0 in stage 0.0 (TID 365, localhost, executor driver, partition 365, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:13:58,810 [Executor task launch worker for task 365] INFO  Executor - Running task 365.0 in stage 0.0 (TID 365)
 2018-01-30 17:13:58,810 [task-result-getter-1] INFO  TaskSetManager - Finished task 361.0 in stage 0.0 (TID 361) in 42726 ms on localhost (executor driver) (354/3618)
 2018-01-30 17:13:58,811 [Executor task launch worker for task 365] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301125443-00161-crawling211.us.archive.org-6682.warc.gz:0+109100195
 2018-01-30 17:13:59,500 [Executor task launch worker for task 360] INFO  Executor - Finished task 360.0 in stage 0.0 (TID 360). 1759 bytes result sent to driver
 2018-01-30 17:13:59,501 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 366.0 in stage 0.0 (TID 366, localhost, executor driver, partition 366, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:13:59,501 [Executor task launch worker for task 366] INFO  Executor - Running task 366.0 in stage 0.0 (TID 366)
 2018-01-30 17:13:59,501 [task-result-getter-2] INFO  TaskSetManager - Finished task 360.0 in stage 0.0 (TID 360) in 47586 ms on localhost (executor driver) (355/3618)
 2018-01-30 17:13:59,502 [Executor task launch worker for task 366] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-1608-20140223211321406-00003-wbgrp-crawl102.us.archive.org-6442.warc.gz:0+1000280009
 2018-01-30 17:14:01,385 [Executor task launch worker for task 365] INFO  Executor - Finished task 365.0 in stage 0.0 (TID 365). 1413 bytes result sent to driver
 2018-01-30 17:14:01,386 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 367.0 in stage 0.0 (TID 367, localhost, executor driver, partition 367, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:14:01,386 [Executor task launch worker for task 367] INFO  Executor - Running task 367.0 in stage 0.0 (TID 367)
 2018-01-30 17:14:01,386 [task-result-getter-3] INFO  TaskSetManager - Finished task 365.0 in stage 0.0 (TID 365) in 2577 ms on localhost (executor driver) (356/3618)
 2018-01-30 17:14:01,387 [Executor task launch worker for task 367] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301173623-00239-crawling211.us.archive.org-6682.warc.gz:0+100412094
 2018-01-30 17:14:03,994 [Executor task launch worker for task 367] INFO  Executor - Finished task 367.0 in stage 0.0 (TID 367). 1500 bytes result sent to driver
 2018-01-30 17:14:03,995 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 368.0 in stage 0.0 (TID 368, localhost, executor driver, partition 368, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:14:03,995 [task-result-getter-0] INFO  TaskSetManager - Finished task 367.0 in stage 0.0 (TID 367) in 2609 ms on localhost (executor driver) (357/3618)
 2018-01-30 17:14:03,995 [Executor task launch worker for task 368] INFO  Executor - Running task 368.0 in stage 0.0 (TID 368)
 2018-01-30 17:14:03,997 [Executor task launch worker for task 368] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629073456-00050-crawling212.us.archive.org-6682.warc.gz:0+179354823
 2018-01-30 17:14:04,962 [Executor task launch worker for task 310] INFO  Executor - Finished task 310.0 in stage 0.0 (TID 310). 1783 bytes result sent to driver
 2018-01-30 17:14:04,963 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 369.0 in stage 0.0 (TID 369, localhost, executor driver, partition 369, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:14:04,963 [Executor task launch worker for task 369] INFO  Executor - Running task 369.0 in stage 0.0 (TID 369)
 2018-01-30 17:14:04,963 [task-result-getter-1] INFO  TaskSetManager - Finished task 310.0 in stage 0.0 (TID 310) in 356052 ms on localhost (executor driver) (358/3618)
 2018-01-30 17:14:04,964 [Executor task launch worker for task 369] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-YDUKWP-20111130195030-00005-crawling203.us.archive.org-6680.warc.gz:0+104533289
 2018-01-30 17:14:12,720 [Executor task launch worker for task 363] INFO  Executor - Finished task 363.0 in stage 0.0 (TID 363). 1855 bytes result sent to driver
 2018-01-30 17:14:12,721 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 370.0 in stage 0.0 (TID 370, localhost, executor driver, partition 370, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:14:12,721 [Executor task launch worker for task 370] INFO  Executor - Running task 370.0 in stage 0.0 (TID 370)
 2018-01-30 17:14:12,721 [task-result-getter-2] INFO  TaskSetManager - Finished task 363.0 in stage 0.0 (TID 363) in 35769 ms on localhost (executor driver) (359/3618)
 2018-01-30 17:14:12,722 [Executor task launch worker for task 370] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024171003136-00040.warc.gz:0+1000051596
 2018-01-30 17:14:12,754 [Executor task launch worker for task 316] INFO  Executor - Finished task 316.0 in stage 0.0 (TID 316). 2504 bytes result sent to driver
 2018-01-30 17:14:12,754 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 371.0 in stage 0.0 (TID 371, localhost, executor driver, partition 371, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:14:12,754 [Executor task launch worker for task 371] INFO  Executor - Running task 371.0 in stage 0.0 (TID 371)
 2018-01-30 17:14:12,754 [task-result-getter-3] INFO  TaskSetManager - Finished task 316.0 in stage 0.0 (TID 316) in 351572 ms on localhost (executor driver) (360/3618)
 2018-01-30 17:14:12,755 [Executor task launch worker for task 371] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926041536871-00097.warc.gz:0+1000063946
 2018-01-30 17:14:14,882 [Executor task launch worker for task 324] INFO  Executor - Finished task 324.0 in stage 0.0 (TID 324). 1783 bytes result sent to driver
 2018-01-30 17:14:14,883 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 372.0 in stage 0.0 (TID 372, localhost, executor driver, partition 372, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:14:14,883 [Executor task launch worker for task 372] INFO  Executor - Running task 372.0 in stage 0.0 (TID 372)
 2018-01-30 17:14:14,883 [task-result-getter-0] INFO  TaskSetManager - Finished task 324.0 in stage 0.0 (TID 324) in 325052 ms on localhost (executor driver) (361/3618)
 2018-01-30 17:14:14,884 [Executor task launch worker for task 372] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929132156-00073-crawling113.us.archive.org-6683.warc.gz:0+114867546
 2018-01-30 17:14:20,999 [Executor task launch worker for task 364] INFO  Executor - Finished task 364.0 in stage 0.0 (TID 364). 1763 bytes result sent to driver
 2018-01-30 17:14:20,999 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 373.0 in stage 0.0 (TID 373, localhost, executor driver, partition 373, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:14:20,999 [task-result-getter-1] INFO  TaskSetManager - Finished task 364.0 in stage 0.0 (TID 364) in 41665 ms on localhost (executor driver) (362/3618)
 2018-01-30 17:14:20,999 [Executor task launch worker for task 373] INFO  Executor - Running task 373.0 in stage 0.0 (TID 373)
 2018-01-30 17:14:21,001 [Executor task launch worker for task 373] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301144715-00192-crawling211.us.archive.org-6682.warc.gz:0+106955131
 2018-01-30 17:14:28,421 [Executor task launch worker for task 373] INFO  Executor - Finished task 373.0 in stage 0.0 (TID 373). 1573 bytes result sent to driver
 2018-01-30 17:14:28,421 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 374.0 in stage 0.0 (TID 374, localhost, executor driver, partition 374, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:14:28,422 [Executor task launch worker for task 374] INFO  Executor - Running task 374.0 in stage 0.0 (TID 374)
 2018-01-30 17:14:28,422 [task-result-getter-2] INFO  TaskSetManager - Finished task 373.0 in stage 0.0 (TID 373) in 7423 ms on localhost (executor driver) (363/3618)
 2018-01-30 17:14:28,423 [Executor task launch worker for task 374] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225062245788-00070.warc.gz:0+1000005346
 2018-01-30 17:14:41,402 [Executor task launch worker for task 369] INFO  Executor - Finished task 369.0 in stage 0.0 (TID 369). 1759 bytes result sent to driver
 2018-01-30 17:14:41,402 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 375.0 in stage 0.0 (TID 375, localhost, executor driver, partition 375, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:14:41,403 [Executor task launch worker for task 375] INFO  Executor - Running task 375.0 in stage 0.0 (TID 375)
 2018-01-30 17:14:41,403 [task-result-getter-3] INFO  TaskSetManager - Finished task 369.0 in stage 0.0 (TID 369) in 36440 ms on localhost (executor driver) (364/3618)
 2018-01-30 17:14:41,404 [Executor task launch worker for task 375] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002184817-00417-crawling209.us.archive.org-6681.warc.gz:0+105410483
 2018-01-30 17:14:48,268 [Executor task launch worker for task 375] INFO  Executor - Finished task 375.0 in stage 0.0 (TID 375). 1686 bytes result sent to driver
 2018-01-30 17:14:48,268 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 376.0 in stage 0.0 (TID 376, localhost, executor driver, partition 376, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:14:48,269 [Executor task launch worker for task 376] INFO  Executor - Running task 376.0 in stage 0.0 (TID 376)
 2018-01-30 17:14:48,269 [task-result-getter-0] INFO  TaskSetManager - Finished task 375.0 in stage 0.0 (TID 375) in 6867 ms on localhost (executor driver) (365/3618)
 2018-01-30 17:14:48,270 [Executor task launch worker for task 376] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002143953-00361-crawling209.us.archive.org-6681.warc.gz:0+105521316
 2018-01-30 17:14:57,219 [Executor task launch worker for task 376] INFO  Executor - Finished task 376.0 in stage 0.0 (TID 376). 1763 bytes result sent to driver
 2018-01-30 17:14:57,219 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 377.0 in stage 0.0 (TID 377, localhost, executor driver, partition 377, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:14:57,219 [Executor task launch worker for task 377] INFO  Executor - Running task 377.0 in stage 0.0 (TID 377)
 2018-01-30 17:14:57,219 [task-result-getter-1] INFO  TaskSetManager - Finished task 376.0 in stage 0.0 (TID 376) in 8951 ms on localhost (executor driver) (366/3618)
 2018-01-30 17:14:57,220 [Executor task launch worker for task 377] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120928130713-00015-crawling113.us.archive.org-6683.warc.gz:0+119483712
 2018-01-30 17:14:59,195 [Executor task launch worker for task 372] INFO  Executor - Finished task 372.0 in stage 0.0 (TID 372). 1573 bytes result sent to driver
 2018-01-30 17:14:59,196 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 378.0 in stage 0.0 (TID 378, localhost, executor driver, partition 378, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:14:59,196 [Executor task launch worker for task 378] INFO  Executor - Running task 378.0 in stage 0.0 (TID 378)
 2018-01-30 17:14:59,196 [task-result-getter-2] INFO  TaskSetManager - Finished task 372.0 in stage 0.0 (TID 372) in 44313 ms on localhost (executor driver) (367/3618)
 2018-01-30 17:14:59,197 [Executor task launch worker for task 378] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171125002650993-00054.warc.gz:0+1000062701
 2018-01-30 17:15:16,604 [Executor task launch worker for task 368] INFO  Executor - Finished task 368.0 in stage 0.0 (TID 368). 1573 bytes result sent to driver
 2018-01-30 17:15:16,605 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 379.0 in stage 0.0 (TID 379, localhost, executor driver, partition 379, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:15:16,605 [Executor task launch worker for task 379] INFO  Executor - Running task 379.0 in stage 0.0 (TID 379)
 2018-01-30 17:15:16,605 [task-result-getter-3] INFO  TaskSetManager - Finished task 368.0 in stage 0.0 (TID 368) in 72610 ms on localhost (executor driver) (368/3618)
 2018-01-30 17:15:16,606 [Executor task launch worker for task 379] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924194756585-00043.warc.gz:0+1000025412
 2018-01-30 17:15:19,273 [Executor task launch worker for task 370] INFO  Executor - Finished task 370.0 in stage 0.0 (TID 370). 2033 bytes result sent to driver
 2018-01-30 17:15:19,273 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 380.0 in stage 0.0 (TID 380, localhost, executor driver, partition 380, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:15:19,274 [Executor task launch worker for task 380] INFO  Executor - Running task 380.0 in stage 0.0 (TID 380)
 2018-01-30 17:15:19,274 [task-result-getter-0] INFO  TaskSetManager - Finished task 370.0 in stage 0.0 (TID 370) in 66554 ms on localhost (executor driver) (369/3618)
 2018-01-30 17:15:19,275 [Executor task launch worker for task 380] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110910034407-00014-crawling211.us.archive.org-6681.warc.gz:0+126667030
 2018-01-30 17:15:24,542 [Executor task launch worker for task 371] INFO  Executor - Finished task 371.0 in stage 0.0 (TID 371). 2249 bytes result sent to driver
 2018-01-30 17:15:24,543 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 381.0 in stage 0.0 (TID 381, localhost, executor driver, partition 381, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:15:24,543 [Executor task launch worker for task 381] INFO  Executor - Running task 381.0 in stage 0.0 (TID 381)
 2018-01-30 17:15:24,543 [task-result-getter-1] INFO  TaskSetManager - Finished task 371.0 in stage 0.0 (TID 371) in 71789 ms on localhost (executor driver) (370/3618)
 2018-01-30 17:15:24,544 [Executor task launch worker for task 381] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121013040627-00011-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+276800603
 2018-01-30 17:15:28,151 [Executor task launch worker for task 286] INFO  Executor - Finished task 286.0 in stage 0.0 (TID 286). 1759 bytes result sent to driver
 2018-01-30 17:15:28,152 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 382.0 in stage 0.0 (TID 382, localhost, executor driver, partition 382, PROCESS_LOCAL, 19523 bytes)
 2018-01-30 17:15:28,152 [Executor task launch worker for task 382] INFO  Executor - Running task 382.0 in stage 0.0 (TID 382)
 2018-01-30 17:15:28,152 [task-result-getter-2] INFO  TaskSetManager - Finished task 286.0 in stage 0.0 (TID 286) in 531885 ms on localhost (executor driver) (371/3618)
 2018-01-30 17:15:28,154 [Executor task launch worker for task 382] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-TEST-JOB225704-20160715202855386-00000.warc.gz:0+1000384736
 2018-01-30 17:15:40,464 [Executor task launch worker for task 377] INFO  Executor - Finished task 377.0 in stage 0.0 (TID 377). 1573 bytes result sent to driver
 2018-01-30 17:15:40,465 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 383.0 in stage 0.0 (TID 383, localhost, executor driver, partition 383, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:15:40,465 [task-result-getter-3] INFO  TaskSetManager - Finished task 377.0 in stage 0.0 (TID 377) in 43246 ms on localhost (executor driver) (372/3618)
 2018-01-30 17:15:40,465 [Executor task launch worker for task 383] INFO  Executor - Running task 383.0 in stage 0.0 (TID 383)
 2018-01-30 17:15:40,467 [Executor task launch worker for task 383] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925224517891-00088.warc.gz:0+1000043308
 2018-01-30 17:15:44,637 [Executor task launch worker for task 374] INFO  Executor - Finished task 374.0 in stage 0.0 (TID 374). 2101 bytes result sent to driver
 2018-01-30 17:15:44,639 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 384.0 in stage 0.0 (TID 384, localhost, executor driver, partition 384, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:15:44,639 [Executor task launch worker for task 384] INFO  Executor - Running task 384.0 in stage 0.0 (TID 384)
 2018-01-30 17:15:44,639 [task-result-getter-0] INFO  TaskSetManager - Finished task 374.0 in stage 0.0 (TID 374) in 76218 ms on localhost (executor driver) (373/3618)
 2018-01-30 17:15:44,641 [Executor task launch worker for task 384] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171125092628179-00070.warc.gz:0+1000003663
 2018-01-30 17:16:06,706 [Executor task launch worker for task 378] INFO  Executor - Finished task 378.0 in stage 0.0 (TID 378). 2033 bytes result sent to driver
 2018-01-30 17:16:06,708 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 385.0 in stage 0.0 (TID 385, localhost, executor driver, partition 385, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:16:06,708 [Executor task launch worker for task 385] INFO  Executor - Running task 385.0 in stage 0.0 (TID 385)
 2018-01-30 17:16:06,709 [task-result-getter-1] INFO  TaskSetManager - Finished task 378.0 in stage 0.0 (TID 378) in 67514 ms on localhost (executor driver) (374/3618)
 2018-01-30 17:16:06,711 [Executor task launch worker for task 385] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001193430-00056-crawling209.us.archive.org-6681.warc.gz:0+107128610
 2018-01-30 17:16:12,770 [Executor task launch worker for task 385] INFO  Executor - Finished task 385.0 in stage 0.0 (TID 385). 1767 bytes result sent to driver
 2018-01-30 17:16:12,770 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 386.0 in stage 0.0 (TID 386, localhost, executor driver, partition 386, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:16:12,771 [Executor task launch worker for task 386] INFO  Executor - Running task 386.0 in stage 0.0 (TID 386)
 2018-01-30 17:16:12,771 [task-result-getter-2] INFO  TaskSetManager - Finished task 385.0 in stage 0.0 (TID 385) in 6064 ms on localhost (executor driver) (375/3618)
 2018-01-30 17:16:12,772 [Executor task launch worker for task 386] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-20244-20130517214504284-00000-wbgrp-crawl100.us.archive.org-6444.warc.gz:0+110783782
 2018-01-30 17:16:14,876 [Executor task launch worker for task 380] INFO  Executor - Finished task 380.0 in stage 0.0 (TID 380). 1573 bytes result sent to driver
 2018-01-30 17:16:14,877 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 387.0 in stage 0.0 (TID 387, localhost, executor driver, partition 387, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:16:14,877 [Executor task launch worker for task 387] INFO  Executor - Running task 387.0 in stage 0.0 (TID 387)
 2018-01-30 17:16:14,877 [task-result-getter-3] INFO  TaskSetManager - Finished task 380.0 in stage 0.0 (TID 380) in 55604 ms on localhost (executor driver) (376/3618)
 2018-01-30 17:16:14,878 [Executor task launch worker for task 387] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110910162520-00020-crawling211.us.archive.org-6681.warc.gz:0+101863556
 2018-01-30 17:16:21,710 [Executor task launch worker for task 386] INFO  Executor - Finished task 386.0 in stage 0.0 (TID 386). 1871 bytes result sent to driver
 2018-01-30 17:16:21,711 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 388.0 in stage 0.0 (TID 388, localhost, executor driver, partition 388, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:16:21,711 [Executor task launch worker for task 388] INFO  Executor - Running task 388.0 in stage 0.0 (TID 388)
 2018-01-30 17:16:21,711 [task-result-getter-0] INFO  TaskSetManager - Finished task 386.0 in stage 0.0 (TID 386) in 8941 ms on localhost (executor driver) (377/3618)
 2018-01-30 17:16:21,713 [Executor task launch worker for task 388] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-EEMLKQ-20120522183406-00000-crawling200.us.archive.org-6681.warc.gz:0+1794544
 2018-01-30 17:16:22,059 [Executor task launch worker for task 388] INFO  Executor - Finished task 388.0 in stage 0.0 (TID 388). 1690 bytes result sent to driver
 2018-01-30 17:16:22,060 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 389.0 in stage 0.0 (TID 389, localhost, executor driver, partition 389, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:16:22,060 [task-result-getter-1] INFO  TaskSetManager - Finished task 388.0 in stage 0.0 (TID 388) in 349 ms on localhost (executor driver) (378/3618)
 2018-01-30 17:16:22,073 [Executor task launch worker for task 389] INFO  Executor - Running task 389.0 in stage 0.0 (TID 389)
 2018-01-30 17:16:22,074 [Executor task launch worker for task 389] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930133711-00176-crawling202.us.archive.org-6681.warc.gz:0+114406547
 2018-01-30 17:16:26,090 [Executor task launch worker for task 339] INFO  Executor - Finished task 339.0 in stage 0.0 (TID 339). 1763 bytes result sent to driver
 2018-01-30 17:16:26,091 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 390.0 in stage 0.0 (TID 390, localhost, executor driver, partition 390, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:16:26,091 [Executor task launch worker for task 390] INFO  Executor - Running task 390.0 in stage 0.0 (TID 390)
 2018-01-30 17:16:26,091 [task-result-getter-2] INFO  TaskSetManager - Finished task 339.0 in stage 0.0 (TID 339) in 359126 ms on localhost (executor driver) (379/3618)
 2018-01-30 17:16:26,092 [Executor task launch worker for task 390] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024191911697-00044.warc.gz:0+1000055659
 2018-01-30 17:16:27,608 [Executor task launch worker for task 389] INFO  Executor - Finished task 389.0 in stage 0.0 (TID 389). 1710 bytes result sent to driver
 2018-01-30 17:16:27,608 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 391.0 in stage 0.0 (TID 391, localhost, executor driver, partition 391, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:16:27,608 [Executor task launch worker for task 391] INFO  Executor - Running task 391.0 in stage 0.0 (TID 391)
 2018-01-30 17:16:27,608 [task-result-getter-3] INFO  TaskSetManager - Finished task 389.0 in stage 0.0 (TID 389) in 5548 ms on localhost (executor driver) (380/3618)
 2018-01-30 17:16:27,609 [Executor task launch worker for task 391] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003004447-00500-crawling209.us.archive.org-6681.warc.gz:0+101277742
 2018-01-30 17:16:34,375 [Executor task launch worker for task 379] INFO  Executor - Finished task 379.0 in stage 0.0 (TID 379). 1997 bytes result sent to driver
 2018-01-30 17:16:34,376 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 392.0 in stage 0.0 (TID 392, localhost, executor driver, partition 392, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:16:34,376 [Executor task launch worker for task 392] INFO  Executor - Running task 392.0 in stage 0.0 (TID 392)
 2018-01-30 17:16:34,376 [task-result-getter-0] INFO  TaskSetManager - Finished task 379.0 in stage 0.0 (TID 379) in 77772 ms on localhost (executor driver) (381/3618)
 2018-01-30 17:16:34,377 [Executor task launch worker for task 392] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024152917484-00037.warc.gz:0+1000073114
 2018-01-30 17:16:36,118 [Executor task launch worker for task 391] INFO  Executor - Finished task 391.0 in stage 0.0 (TID 391). 1759 bytes result sent to driver
 2018-01-30 17:16:36,119 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 393.0 in stage 0.0 (TID 393, localhost, executor driver, partition 393, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:16:36,119 [Executor task launch worker for task 393] INFO  Executor - Running task 393.0 in stage 0.0 (TID 393)
 2018-01-30 17:16:36,119 [task-result-getter-1] INFO  TaskSetManager - Finished task 391.0 in stage 0.0 (TID 391) in 8511 ms on localhost (executor driver) (382/3618)
 2018-01-30 17:16:36,121 [Executor task launch worker for task 393] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-12967-20140605230904340-00001-wbgrp-crawl053.us.archive.org-6444.warc.gz:0+995279789
 2018-01-30 17:16:46,369 [Executor task launch worker for task 387] INFO  Executor - Finished task 387.0 in stage 0.0 (TID 387). 1759 bytes result sent to driver
 2018-01-30 17:16:46,373 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 394.0 in stage 0.0 (TID 394, localhost, executor driver, partition 394, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:16:46,373 [Executor task launch worker for task 394] INFO  Executor - Running task 394.0 in stage 0.0 (TID 394)
 2018-01-30 17:16:46,377 [Executor task launch worker for task 394] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024181514092-00042.warc.gz:0+1000060967
 2018-01-30 17:16:46,380 [task-result-getter-2] INFO  TaskSetManager - Finished task 387.0 in stage 0.0 (TID 387) in 31503 ms on localhost (executor driver) (383/3618)
 2018-01-30 17:16:53,920 [Executor task launch worker for task 381] INFO  Executor - Finished task 381.0 in stage 0.0 (TID 381). 1759 bytes result sent to driver
 2018-01-30 17:16:53,922 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 395.0 in stage 0.0 (TID 395, localhost, executor driver, partition 395, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:16:53,922 [Executor task launch worker for task 395] INFO  Executor - Running task 395.0 in stage 0.0 (TID 395)
 2018-01-30 17:16:53,923 [task-result-getter-3] INFO  TaskSetManager - Finished task 381.0 in stage 0.0 (TID 381) in 89380 ms on localhost (executor driver) (384/3618)
 2018-01-30 17:16:53,926 [Executor task launch worker for task 395] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930095634-00146-crawling202.us.archive.org-6681.warc.gz:0+102643046
 2018-01-30 17:17:00,114 [Executor task launch worker for task 383] INFO  Executor - Finished task 383.0 in stage 0.0 (TID 383). 1962 bytes result sent to driver
 2018-01-30 17:17:00,115 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 396.0 in stage 0.0 (TID 396, localhost, executor driver, partition 396, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:00,116 [Executor task launch worker for task 396] INFO  Executor - Running task 396.0 in stage 0.0 (TID 396)
 2018-01-30 17:17:00,118 [Executor task launch worker for task 396] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-OUWWLJ-20111024181337-00015-crawling202.us.archive.org-6683.warc.gz:0+100021847
 2018-01-30 17:17:00,136 [task-result-getter-0] INFO  TaskSetManager - Finished task 383.0 in stage 0.0 (TID 383) in 79672 ms on localhost (executor driver) (385/3618)
 2018-01-30 17:17:06,505 [Executor task launch worker for task 384] INFO  Executor - Finished task 384.0 in stage 0.0 (TID 384). 2001 bytes result sent to driver
 2018-01-30 17:17:06,508 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 397.0 in stage 0.0 (TID 397, localhost, executor driver, partition 397, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:17:06,509 [Executor task launch worker for task 397] INFO  Executor - Running task 397.0 in stage 0.0 (TID 397)
 2018-01-30 17:17:06,509 [task-result-getter-1] INFO  TaskSetManager - Finished task 384.0 in stage 0.0 (TID 384) in 81870 ms on localhost (executor driver) (386/3618)
 2018-01-30 17:17:06,513 [Executor task launch worker for task 397] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB310054-20170624092412759-00005.warc.gz:0+697282026
 2018-01-30 17:17:16,395 [Executor task launch worker for task 395] INFO  Executor - Finished task 395.0 in stage 0.0 (TID 395). 1779 bytes result sent to driver
 2018-01-30 17:17:16,396 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 398.0 in stage 0.0 (TID 398, localhost, executor driver, partition 398, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:16,396 [Executor task launch worker for task 398] INFO  Executor - Running task 398.0 in stage 0.0 (TID 398)
 2018-01-30 17:17:16,396 [task-result-getter-2] INFO  TaskSetManager - Finished task 395.0 in stage 0.0 (TID 395) in 22475 ms on localhost (executor driver) (387/3618)
 2018-01-30 17:17:16,397 [Executor task launch worker for task 398] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008212155-00048-crawling208.us.archive.org-6683.warc.gz:0+115100621
 2018-01-30 17:17:32,023 [Executor task launch worker for task 396] INFO  Executor - Finished task 396.0 in stage 0.0 (TID 396). 1759 bytes result sent to driver
 2018-01-30 17:17:32,025 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 399.0 in stage 0.0 (TID 399, localhost, executor driver, partition 399, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:32,027 [task-result-getter-3] INFO  TaskSetManager - Finished task 396.0 in stage 0.0 (TID 396) in 31911 ms on localhost (executor driver) (388/3618)
 2018-01-30 17:17:32,035 [Executor task launch worker for task 399] INFO  Executor - Running task 399.0 in stage 0.0 (TID 399)
 2018-01-30 17:17:32,038 [Executor task launch worker for task 399] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301032506-00028-crawling211.us.archive.org-6682.warc.gz:0+102072257
 2018-01-30 17:17:32,326 [Executor task launch worker for task 397] INFO  Executor - Finished task 397.0 in stage 0.0 (TID 397). 1759 bytes result sent to driver
 2018-01-30 17:17:32,327 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 400.0 in stage 0.0 (TID 400, localhost, executor driver, partition 400, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:32,327 [Executor task launch worker for task 400] INFO  Executor - Running task 400.0 in stage 0.0 (TID 400)
 2018-01-30 17:17:32,327 [task-result-getter-0] INFO  TaskSetManager - Finished task 397.0 in stage 0.0 (TID 397) in 25820 ms on localhost (executor driver) (389/3618)
 2018-01-30 17:17:32,330 [Executor task launch worker for task 400] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930085243-00126-crawling202.us.archive.org-6681.warc.gz:0+100024919
 2018-01-30 17:17:36,033 [Executor task launch worker for task 390] INFO  Executor - Finished task 390.0 in stage 0.0 (TID 390). 2060 bytes result sent to driver
 2018-01-30 17:17:36,037 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 401.0 in stage 0.0 (TID 401, localhost, executor driver, partition 401, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:17:36,038 [Executor task launch worker for task 401] INFO  Executor - Running task 401.0 in stage 0.0 (TID 401)
 2018-01-30 17:17:36,038 [task-result-getter-1] INFO  TaskSetManager - Finished task 390.0 in stage 0.0 (TID 390) in 69948 ms on localhost (executor driver) (390/3618)
 2018-01-30 17:17:36,040 [Executor task launch worker for task 401] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QDPLNZ-20120713151527-00015-crawling105.us.archive.org-6681.warc.gz:0+100049220
 2018-01-30 17:17:41,296 [Executor task launch worker for task 392] INFO  Executor - Finished task 392.0 in stage 0.0 (TID 392). 2353 bytes result sent to driver
 2018-01-30 17:17:41,297 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 402.0 in stage 0.0 (TID 402, localhost, executor driver, partition 402, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:17:41,297 [Executor task launch worker for task 402] INFO  Executor - Running task 402.0 in stage 0.0 (TID 402)
 2018-01-30 17:17:41,298 [task-result-getter-2] INFO  TaskSetManager - Finished task 392.0 in stage 0.0 (TID 392) in 66923 ms on localhost (executor driver) (391/3618)
 2018-01-30 17:17:41,301 [Executor task launch worker for task 402] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-23778-20130926192328676-00000-wbgrp-crawl100.us.archive.org-6442.warc.gz:0+132132
 2018-01-30 17:17:41,319 [Executor task launch worker for task 402] INFO  Executor - Finished task 402.0 in stage 0.0 (TID 402). 1500 bytes result sent to driver
 2018-01-30 17:17:41,321 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 403.0 in stage 0.0 (TID 403, localhost, executor driver, partition 403, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:41,321 [Executor task launch worker for task 403] INFO  Executor - Running task 403.0 in stage 0.0 (TID 403)
 2018-01-30 17:17:41,321 [task-result-getter-3] INFO  TaskSetManager - Finished task 402.0 in stage 0.0 (TID 402) in 24 ms on localhost (executor driver) (392/3618)
 2018-01-30 17:17:41,322 [Executor task launch worker for task 403] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-KSXFGE-20110718211105-00008-crawling200.us.archive.org-6682.warc.gz:0+118530223
 2018-01-30 17:17:42,861 [Executor task launch worker for task 342] INFO  Executor - Finished task 342.0 in stage 0.0 (TID 342). 1759 bytes result sent to driver
 2018-01-30 17:17:42,864 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 404.0 in stage 0.0 (TID 404, localhost, executor driver, partition 404, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:42,864 [task-result-getter-0] INFO  TaskSetManager - Finished task 342.0 in stage 0.0 (TID 342) in 411903 ms on localhost (executor driver) (393/3618)
 2018-01-30 17:17:42,864 [Executor task launch worker for task 404] INFO  Executor - Running task 404.0 in stage 0.0 (TID 404)
 2018-01-30 17:17:42,866 [Executor task launch worker for task 404] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110911101107-00029-crawling211.us.archive.org-6681.warc.gz:0+111532968
 2018-01-30 17:17:51,879 [Executor task launch worker for task 394] INFO  Executor - Finished task 394.0 in stage 0.0 (TID 394). 1973 bytes result sent to driver
 2018-01-30 17:17:51,883 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 405.0 in stage 0.0 (TID 405, localhost, executor driver, partition 405, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:17:51,883 [Executor task launch worker for task 405] INFO  Executor - Running task 405.0 in stage 0.0 (TID 405)
 2018-01-30 17:17:51,883 [task-result-getter-1] INFO  TaskSetManager - Finished task 394.0 in stage 0.0 (TID 394) in 65512 ms on localhost (executor driver) (394/3618)
 2018-01-30 17:17:51,888 [Executor task launch worker for task 405] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-31786-20140117214148220-00000-wbgrp-crawl051.us.archive.org-6444.warc.gz:0+165531833
 2018-01-30 17:17:52,600 [Executor task launch worker for task 401] INFO  Executor - Finished task 401.0 in stage 0.0 (TID 401). 1771 bytes result sent to driver
 2018-01-30 17:17:52,600 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 406.0 in stage 0.0 (TID 406, localhost, executor driver, partition 406, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:52,601 [Executor task launch worker for task 406] INFO  Executor - Running task 406.0 in stage 0.0 (TID 406)
 2018-01-30 17:17:52,601 [task-result-getter-2] INFO  TaskSetManager - Finished task 401.0 in stage 0.0 (TID 401) in 16566 ms on localhost (executor driver) (395/3618)
 2018-01-30 17:17:52,602 [Executor task launch worker for task 406] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301154706-00208-crawling211.us.archive.org-6682.warc.gz:0+104855503
 2018-01-30 17:17:53,347 [Executor task launch worker for task 398] INFO  Executor - Finished task 398.0 in stage 0.0 (TID 398). 1573 bytes result sent to driver
 2018-01-30 17:17:53,348 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 407.0 in stage 0.0 (TID 407, localhost, executor driver, partition 407, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:53,348 [task-result-getter-3] INFO  TaskSetManager - Finished task 398.0 in stage 0.0 (TID 398) in 36952 ms on localhost (executor driver) (396/3618)
 2018-01-30 17:17:53,348 [Executor task launch worker for task 407] INFO  Executor - Running task 407.0 in stage 0.0 (TID 407)
 2018-01-30 17:17:53,349 [Executor task launch worker for task 407] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008204002-00030-crawling208.us.archive.org-6683.warc.gz:0+111827408
 2018-01-30 17:17:59,375 [Executor task launch worker for task 406] INFO  Executor - Finished task 406.0 in stage 0.0 (TID 406). 1573 bytes result sent to driver
 2018-01-30 17:17:59,382 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 408.0 in stage 0.0 (TID 408, localhost, executor driver, partition 408, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:17:59,382 [Executor task launch worker for task 408] INFO  Executor - Running task 408.0 in stage 0.0 (TID 408)
 2018-01-30 17:17:59,382 [task-result-getter-0] INFO  TaskSetManager - Finished task 406.0 in stage 0.0 (TID 406) in 6782 ms on localhost (executor driver) (397/3618)
 2018-01-30 17:17:59,388 [Executor task launch worker for task 408] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929175122-00091-crawling113.us.archive.org-6683.warc.gz:0+102127650
 2018-01-30 17:17:59,922 [Executor task launch worker for task 399] INFO  Executor - Finished task 399.0 in stage 0.0 (TID 399). 1573 bytes result sent to driver
 2018-01-30 17:17:59,924 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 409.0 in stage 0.0 (TID 409, localhost, executor driver, partition 409, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:17:59,924 [Executor task launch worker for task 409] INFO  Executor - Running task 409.0 in stage 0.0 (TID 409)
 2018-01-30 17:17:59,925 [task-result-getter-1] INFO  TaskSetManager - Finished task 399.0 in stage 0.0 (TID 399) in 27900 ms on localhost (executor driver) (398/3618)
 2018-01-30 17:17:59,926 [Executor task launch worker for task 409] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-YDUKWP-20111130194720-00003-crawling203.us.archive.org-6680.warc.gz:0+110573274
 2018-01-30 17:18:04,378 [Executor task launch worker for task 405] INFO  Executor - Finished task 405.0 in stage 0.0 (TID 405). 1863 bytes result sent to driver
 2018-01-30 17:18:04,379 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 410.0 in stage 0.0 (TID 410, localhost, executor driver, partition 410, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:18:04,379 [Executor task launch worker for task 410] INFO  Executor - Running task 410.0 in stage 0.0 (TID 410)
 2018-01-30 17:18:04,380 [task-result-getter-2] INFO  TaskSetManager - Finished task 405.0 in stage 0.0 (TID 405) in 12498 ms on localhost (executor driver) (399/3618)
 2018-01-30 17:18:04,381 [Executor task launch worker for task 410] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002041442-00192-crawling209.us.archive.org-6681.warc.gz:0+101135049
 2018-01-30 17:18:10,856 [Executor task launch worker for task 400] INFO  Executor - Finished task 400.0 in stage 0.0 (TID 400). 1787 bytes result sent to driver
 2018-01-30 17:18:10,856 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 411.0 in stage 0.0 (TID 411, localhost, executor driver, partition 411, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:18:10,856 [Executor task launch worker for task 411] INFO  Executor - Running task 411.0 in stage 0.0 (TID 411)
 2018-01-30 17:18:10,856 [task-result-getter-3] INFO  TaskSetManager - Finished task 400.0 in stage 0.0 (TID 400) in 38529 ms on localhost (executor driver) (400/3618)
 2018-01-30 17:18:10,857 [Executor task launch worker for task 411] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002071947-00247-crawling209.us.archive.org-6681.warc.gz:0+106662508
 2018-01-30 17:18:25,262 [Executor task launch worker for task 404] INFO  Executor - Finished task 404.0 in stage 0.0 (TID 404). 1771 bytes result sent to driver
 2018-01-30 17:18:25,263 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 412.0 in stage 0.0 (TID 412, localhost, executor driver, partition 412, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:18:25,263 [Executor task launch worker for task 412] INFO  Executor - Running task 412.0 in stage 0.0 (TID 412)
 2018-01-30 17:18:25,263 [task-result-getter-0] INFO  TaskSetManager - Finished task 404.0 in stage 0.0 (TID 404) in 42400 ms on localhost (executor driver) (401/3618)
 2018-01-30 17:18:25,264 [Executor task launch worker for task 412] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225013559226-00059.warc.gz:0+1000079508
 2018-01-30 17:18:33,259 [Executor task launch worker for task 403] INFO  Executor - Finished task 403.0 in stage 0.0 (TID 403). 1759 bytes result sent to driver
 2018-01-30 17:18:33,260 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 413.0 in stage 0.0 (TID 413, localhost, executor driver, partition 413, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:18:33,260 [Executor task launch worker for task 413] INFO  Executor - Running task 413.0 in stage 0.0 (TID 413)
 2018-01-30 17:18:33,260 [task-result-getter-1] INFO  TaskSetManager - Finished task 403.0 in stage 0.0 (TID 403) in 51940 ms on localhost (executor driver) (402/3618)
 2018-01-30 17:18:33,261 [Executor task launch worker for task 413] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025163150459-00082.warc.gz:0+1000027868
 2018-01-30 17:18:34,522 [Executor task launch worker for task 407] INFO  Executor - Finished task 407.0 in stage 0.0 (TID 407). 1573 bytes result sent to driver
 2018-01-30 17:18:34,523 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 414.0 in stage 0.0 (TID 414, localhost, executor driver, partition 414, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:18:34,523 [Executor task launch worker for task 414] INFO  Executor - Running task 414.0 in stage 0.0 (TID 414)
 2018-01-30 17:18:34,523 [task-result-getter-2] INFO  TaskSetManager - Finished task 407.0 in stage 0.0 (TID 407) in 41175 ms on localhost (executor driver) (403/3618)
 2018-01-30 17:18:34,524 [Executor task launch worker for task 414] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002134127-00349-crawling209.us.archive.org-6681.warc.gz:0+102137848
 2018-01-30 17:18:36,502 [Executor task launch worker for task 411] INFO  Executor - Finished task 411.0 in stage 0.0 (TID 411). 1763 bytes result sent to driver
 2018-01-30 17:18:36,503 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 415.0 in stage 0.0 (TID 415, localhost, executor driver, partition 415, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:18:36,503 [Executor task launch worker for task 415] INFO  Executor - Running task 415.0 in stage 0.0 (TID 415)
 2018-01-30 17:18:36,503 [task-result-getter-3] INFO  TaskSetManager - Finished task 411.0 in stage 0.0 (TID 411) in 25647 ms on localhost (executor driver) (404/3618)
 2018-01-30 17:18:36,504 [Executor task launch worker for task 415] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-KOINAK-20121112213529-00008-wbgrp-crawl057.us.archive.org-6681.warc.gz:0+146806902
 2018-01-30 17:18:40,748 [Executor task launch worker for task 409] INFO  Executor - Finished task 409.0 in stage 0.0 (TID 409). 1759 bytes result sent to driver
 2018-01-30 17:18:40,751 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 416.0 in stage 0.0 (TID 416, localhost, executor driver, partition 416, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:18:40,751 [task-result-getter-0] INFO  TaskSetManager - Finished task 409.0 in stage 0.0 (TID 409) in 40827 ms on localhost (executor driver) (405/3618)
 2018-01-30 17:18:40,752 [Executor task launch worker for task 416] INFO  Executor - Running task 416.0 in stage 0.0 (TID 416)
 2018-01-30 17:18:40,754 [Executor task launch worker for task 416] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301064632-00072-crawling211.us.archive.org-6682.warc.gz:0+105728006
 2018-01-30 17:18:42,013 [Executor task launch worker for task 408] INFO  Executor - Finished task 408.0 in stage 0.0 (TID 408). 1573 bytes result sent to driver
 2018-01-30 17:18:42,014 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 417.0 in stage 0.0 (TID 417, localhost, executor driver, partition 417, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:18:42,014 [task-result-getter-1] INFO  TaskSetManager - Finished task 408.0 in stage 0.0 (TID 408) in 42633 ms on localhost (executor driver) (406/3618)
 2018-01-30 17:18:42,014 [Executor task launch worker for task 417] INFO  Executor - Running task 417.0 in stage 0.0 (TID 417)
 2018-01-30 17:18:42,016 [Executor task launch worker for task 417] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628223641-00034-crawling212.us.archive.org-6682.warc.gz:0+106904934
 2018-01-30 17:18:42,141 [Executor task launch worker for task 410] INFO  Executor - Finished task 410.0 in stage 0.0 (TID 410). 1767 bytes result sent to driver
 2018-01-30 17:18:42,142 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 418.0 in stage 0.0 (TID 418, localhost, executor driver, partition 418, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:18:42,142 [task-result-getter-2] INFO  TaskSetManager - Finished task 410.0 in stage 0.0 (TID 410) in 37763 ms on localhost (executor driver) (407/3618)
 2018-01-30 17:18:42,142 [Executor task launch worker for task 418] INFO  Executor - Running task 418.0 in stage 0.0 (TID 418)
 2018-01-30 17:18:42,143 [Executor task launch worker for task 418] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225132158115-00087.warc.gz:0+1000045676
 2018-01-30 17:19:07,548 [Executor task launch worker for task 414] INFO  Executor - Finished task 414.0 in stage 0.0 (TID 414). 1763 bytes result sent to driver
 2018-01-30 17:19:07,548 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 419.0 in stage 0.0 (TID 419, localhost, executor driver, partition 419, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:19:07,549 [Executor task launch worker for task 419] INFO  Executor - Running task 419.0 in stage 0.0 (TID 419)
 2018-01-30 17:19:07,549 [task-result-getter-3] INFO  TaskSetManager - Finished task 414.0 in stage 0.0 (TID 414) in 33027 ms on localhost (executor driver) (408/3618)
 2018-01-30 17:19:07,550 [Executor task launch worker for task 419] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912043234-00059-crawling211.us.archive.org-6681.warc.gz:0+100157033
 2018-01-30 17:19:10,205 [Executor task launch worker for task 366] INFO  Executor - Finished task 366.0 in stage 0.0 (TID 366). 1759 bytes result sent to driver
 2018-01-30 17:19:10,206 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 420.0 in stage 0.0 (TID 420, localhost, executor driver, partition 420, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:19:10,206 [Executor task launch worker for task 420] INFO  Executor - Running task 420.0 in stage 0.0 (TID 420)
 2018-01-30 17:19:10,206 [task-result-getter-0] INFO  TaskSetManager - Finished task 366.0 in stage 0.0 (TID 366) in 310706 ms on localhost (executor driver) (409/3618)
 2018-01-30 17:19:10,207 [Executor task launch worker for task 420] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB236656-20160917070845632-00001.warc.gz:0+1000000320
 2018-01-30 17:19:11,331 [Executor task launch worker for task 362] INFO  Executor - Finished task 362.0 in stage 0.0 (TID 362). 1783 bytes result sent to driver
 2018-01-30 17:19:11,331 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 421.0 in stage 0.0 (TID 421, localhost, executor driver, partition 421, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:19:11,331 [Executor task launch worker for task 421] INFO  Executor - Running task 421.0 in stage 0.0 (TID 421)
 2018-01-30 17:19:11,331 [task-result-getter-1] INFO  TaskSetManager - Finished task 362.0 in stage 0.0 (TID 362) in 351972 ms on localhost (executor driver) (410/3618)
 2018-01-30 17:19:11,332 [Executor task launch worker for task 421] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301155001-00209-crawling211.us.archive.org-6682.warc.gz:0+105506391
 2018-01-30 17:19:14,525 [Executor task launch worker for task 416] INFO  Executor - Finished task 416.0 in stage 0.0 (TID 416). 1573 bytes result sent to driver
 2018-01-30 17:19:14,526 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 422.0 in stage 0.0 (TID 422, localhost, executor driver, partition 422, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:19:14,526 [Executor task launch worker for task 422] INFO  Executor - Running task 422.0 in stage 0.0 (TID 422)
 2018-01-30 17:19:14,526 [task-result-getter-2] INFO  TaskSetManager - Finished task 416.0 in stage 0.0 (TID 416) in 33776 ms on localhost (executor driver) (411/3618)
 2018-01-30 17:19:14,527 [Executor task launch worker for task 422] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629114428-00057-crawling212.us.archive.org-6682.warc.gz:0+100041961
 2018-01-30 17:19:18,585 [Executor task launch worker for task 417] INFO  Executor - Finished task 417.0 in stage 0.0 (TID 417). 1573 bytes result sent to driver
 2018-01-30 17:19:18,586 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 423.0 in stage 0.0 (TID 423, localhost, executor driver, partition 423, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:19:18,586 [Executor task launch worker for task 423] INFO  Executor - Running task 423.0 in stage 0.0 (TID 423)
 2018-01-30 17:19:18,586 [task-result-getter-3] INFO  TaskSetManager - Finished task 417.0 in stage 0.0 (TID 417) in 36573 ms on localhost (executor driver) (412/3618)
 2018-01-30 17:19:18,587 [Executor task launch worker for task 423] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-VGINVR-20121004193459-00011-wbgrp-crawl058.us.archive.org-6680.warc.gz:0+307102234
 2018-01-30 17:19:23,027 [Executor task launch worker for task 421] INFO  Executor - Finished task 421.0 in stage 0.0 (TID 421). 1573 bytes result sent to driver
 2018-01-30 17:19:23,027 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 424.0 in stage 0.0 (TID 424, localhost, executor driver, partition 424, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:19:23,027 [task-result-getter-0] INFO  TaskSetManager - Finished task 421.0 in stage 0.0 (TID 421) in 11696 ms on localhost (executor driver) (413/3618)
 2018-01-30 17:19:23,027 [Executor task launch worker for task 424] INFO  Executor - Running task 424.0 in stage 0.0 (TID 424)
 2018-01-30 17:19:23,028 [Executor task launch worker for task 424] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727222936207-00035.warc.gz:0+1001455532
 2018-01-30 17:19:26,200 [Executor task launch worker for task 415] INFO  Executor - Finished task 415.0 in stage 0.0 (TID 415). 1819 bytes result sent to driver
 2018-01-30 17:19:26,201 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 425.0 in stage 0.0 (TID 425, localhost, executor driver, partition 425, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:19:26,201 [Executor task launch worker for task 425] INFO  Executor - Running task 425.0 in stage 0.0 (TID 425)
 2018-01-30 17:19:26,201 [task-result-getter-1] INFO  TaskSetManager - Finished task 415.0 in stage 0.0 (TID 415) in 49699 ms on localhost (executor driver) (414/3618)
 2018-01-30 17:19:26,202 [Executor task launch worker for task 425] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002235221-00490-crawling209.us.archive.org-6681.warc.gz:0+114852731
 2018-01-30 17:19:35,950 [Executor task launch worker for task 419] INFO  Executor - Finished task 419.0 in stage 0.0 (TID 419). 1759 bytes result sent to driver
 2018-01-30 17:19:35,951 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 426.0 in stage 0.0 (TID 426, localhost, executor driver, partition 426, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:19:35,951 [Executor task launch worker for task 426] INFO  Executor - Running task 426.0 in stage 0.0 (TID 426)
 2018-01-30 17:19:35,951 [task-result-getter-2] INFO  TaskSetManager - Finished task 419.0 in stage 0.0 (TID 419) in 28403 ms on localhost (executor driver) (415/3618)
 2018-01-30 17:19:35,952 [Executor task launch worker for task 426] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150728053520339-00041.warc.gz:0+1000150907
 2018-01-30 17:19:36,696 [Executor task launch worker for task 412] INFO  Executor - Finished task 412.0 in stage 0.0 (TID 412). 1823 bytes result sent to driver
 2018-01-30 17:19:36,696 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 427.0 in stage 0.0 (TID 427, localhost, executor driver, partition 427, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:19:36,697 [Executor task launch worker for task 427] INFO  Executor - Running task 427.0 in stage 0.0 (TID 427)
 2018-01-30 17:19:36,697 [task-result-getter-3] INFO  TaskSetManager - Finished task 412.0 in stage 0.0 (TID 412) in 71435 ms on localhost (executor driver) (416/3618)
 2018-01-30 17:19:36,698 [Executor task launch worker for task 427] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB266557-20170211001407792-00000.warc.gz:0+89396790
 2018-01-30 17:19:43,815 [Executor task launch worker for task 422] INFO  Executor - Finished task 422.0 in stage 0.0 (TID 422). 1573 bytes result sent to driver
 2018-01-30 17:19:43,816 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 428.0 in stage 0.0 (TID 428, localhost, executor driver, partition 428, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:19:43,816 [task-result-getter-0] INFO  TaskSetManager - Finished task 422.0 in stage 0.0 (TID 422) in 29290 ms on localhost (executor driver) (417/3618)
 2018-01-30 17:19:43,817 [Executor task launch worker for task 428] INFO  Executor - Running task 428.0 in stage 0.0 (TID 428)
 2018-01-30 17:19:43,818 [Executor task launch worker for task 428] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-WHIZKW-20121218183055-00000-crawling113.us.archive.org-6683.warc.gz:0+2396943
 2018-01-30 17:19:44,313 [Executor task launch worker for task 428] INFO  Executor - Finished task 428.0 in stage 0.0 (TID 428). 1607 bytes result sent to driver
 2018-01-30 17:19:44,314 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 429.0 in stage 0.0 (TID 429, localhost, executor driver, partition 429, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:19:44,314 [Executor task launch worker for task 429] INFO  Executor - Running task 429.0 in stage 0.0 (TID 429)
 2018-01-30 17:19:44,315 [task-result-getter-1] INFO  TaskSetManager - Finished task 428.0 in stage 0.0 (TID 428) in 500 ms on localhost (executor driver) (418/3618)
 2018-01-30 17:19:44,316 [Executor task launch worker for task 429] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008203600-00028-crawling208.us.archive.org-6683.warc.gz:0+104397929
 2018-01-30 17:19:46,794 [Executor task launch worker for task 425] INFO  Executor - Finished task 425.0 in stage 0.0 (TID 425). 1759 bytes result sent to driver
 2018-01-30 17:19:46,794 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 430.0 in stage 0.0 (TID 430, localhost, executor driver, partition 430, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:19:46,795 [Executor task launch worker for task 430] INFO  Executor - Running task 430.0 in stage 0.0 (TID 430)
 2018-01-30 17:19:46,795 [task-result-getter-2] INFO  TaskSetManager - Finished task 425.0 in stage 0.0 (TID 425) in 20595 ms on localhost (executor driver) (419/3618)
 2018-01-30 17:19:46,796 [Executor task launch worker for task 430] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-15522-20140603214649599-00001-wbgrp-crawl054.us.archive.org-6441.warc.gz:0+181270283
 2018-01-30 17:19:47,858 [Executor task launch worker for task 413] INFO  Executor - Finished task 413.0 in stage 0.0 (TID 413). 1973 bytes result sent to driver
 2018-01-30 17:19:47,858 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 431.0 in stage 0.0 (TID 431, localhost, executor driver, partition 431, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:19:47,858 [Executor task launch worker for task 431] INFO  Executor - Running task 431.0 in stage 0.0 (TID 431)
 2018-01-30 17:19:47,858 [task-result-getter-3] INFO  TaskSetManager - Finished task 413.0 in stage 0.0 (TID 413) in 74598 ms on localhost (executor driver) (420/3618)
 2018-01-30 17:19:47,860 [Executor task launch worker for task 431] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171025030733475-00058.warc.gz:0+1000018779
 2018-01-30 17:19:50,831 [Executor task launch worker for task 418] INFO  Executor - Finished task 418.0 in stage 0.0 (TID 418). 1871 bytes result sent to driver
 2018-01-30 17:19:50,832 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 432.0 in stage 0.0 (TID 432, localhost, executor driver, partition 432, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:19:50,832 [Executor task launch worker for task 432] INFO  Executor - Running task 432.0 in stage 0.0 (TID 432)
 2018-01-30 17:19:50,832 [task-result-getter-0] INFO  TaskSetManager - Finished task 418.0 in stage 0.0 (TID 418) in 68690 ms on localhost (executor driver) (421/3618)
 2018-01-30 17:19:50,833 [Executor task launch worker for task 432] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126182515861-00131.warc.gz:0+1000048701
 2018-01-30 17:19:57,471 [Executor task launch worker for task 427] INFO  Executor - Finished task 427.0 in stage 0.0 (TID 427). 1819 bytes result sent to driver
 2018-01-30 17:19:57,472 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 433.0 in stage 0.0 (TID 433, localhost, executor driver, partition 433, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:19:57,472 [task-result-getter-1] INFO  TaskSetManager - Finished task 427.0 in stage 0.0 (TID 427) in 20776 ms on localhost (executor driver) (422/3618)
 2018-01-30 17:19:57,472 [Executor task launch worker for task 433] INFO  Executor - Running task 433.0 in stage 0.0 (TID 433)
 2018-01-30 17:19:57,473 [Executor task launch worker for task 433] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001205735-00073-crawling209.us.archive.org-6681.warc.gz:0+112675481
 2018-01-30 17:20:04,034 [Executor task launch worker for task 433] INFO  Executor - Finished task 433.0 in stage 0.0 (TID 433). 1694 bytes result sent to driver
 2018-01-30 17:20:04,036 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 434.0 in stage 0.0 (TID 434, localhost, executor driver, partition 434, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:20:04,036 [Executor task launch worker for task 434] INFO  Executor - Running task 434.0 in stage 0.0 (TID 434)
 2018-01-30 17:20:04,036 [task-result-getter-2] INFO  TaskSetManager - Finished task 433.0 in stage 0.0 (TID 433) in 6565 ms on localhost (executor driver) (423/3618)
 2018-01-30 17:20:04,037 [Executor task launch worker for task 434] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406044222-00019-crawling200.us.archive.org-6682.warc.gz:0+102963405
 2018-01-30 17:20:04,858 [Executor task launch worker for task 382] INFO  Executor - Finished task 382.0 in stage 0.0 (TID 382). 2193 bytes result sent to driver
 2018-01-30 17:20:04,859 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 435.0 in stage 0.0 (TID 435, localhost, executor driver, partition 435, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:20:04,859 [task-result-getter-3] INFO  TaskSetManager - Finished task 382.0 in stage 0.0 (TID 382) in 276708 ms on localhost (executor driver) (424/3618)
 2018-01-30 17:20:04,859 [Executor task launch worker for task 435] INFO  Executor - Running task 435.0 in stage 0.0 (TID 435)
 2018-01-30 17:20:04,860 [Executor task launch worker for task 435] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB193801-20160129213045437-00000.warc.gz:0+1000003096
 2018-01-30 17:20:15,872 [Executor task launch worker for task 429] INFO  Executor - Finished task 429.0 in stage 0.0 (TID 429). 1573 bytes result sent to driver
 2018-01-30 17:20:15,873 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 436.0 in stage 0.0 (TID 436, localhost, executor driver, partition 436, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:20:15,874 [task-result-getter-0] INFO  TaskSetManager - Finished task 429.0 in stage 0.0 (TID 429) in 31560 ms on localhost (executor driver) (425/3618)
 2018-01-30 17:20:15,874 [Executor task launch worker for task 436] INFO  Executor - Running task 436.0 in stage 0.0 (TID 436)
 2018-01-30 17:20:15,876 [Executor task launch worker for task 436] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB208915-20160423191426471-00000.warc.gz:0+105546820
 2018-01-30 17:21:12,747 [Executor task launch worker for task 420] INFO  Executor - Finished task 420.0 in stage 0.0 (TID 420). 1759 bytes result sent to driver
 2018-01-30 17:21:12,751 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 437.0 in stage 0.0 (TID 437, localhost, executor driver, partition 437, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:21:12,751 [Executor task launch worker for task 437] INFO  Executor - Running task 437.0 in stage 0.0 (TID 437)
 2018-01-30 17:21:12,752 [task-result-getter-1] INFO  TaskSetManager - Finished task 420.0 in stage 0.0 (TID 420) in 122545 ms on localhost (executor driver) (426/3618)
 2018-01-30 17:21:12,755 [Executor task launch worker for task 437] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003091512-00564-crawling209.us.archive.org-6681.warc.gz:0+100759810
 2018-01-30 17:21:14,494 [Executor task launch worker for task 434] INFO  Executor - Finished task 434.0 in stage 0.0 (TID 434). 1672 bytes result sent to driver
 2018-01-30 17:21:14,495 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 438.0 in stage 0.0 (TID 438, localhost, executor driver, partition 438, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:21:14,495 [Executor task launch worker for task 438] INFO  Executor - Running task 438.0 in stage 0.0 (TID 438)
 2018-01-30 17:21:14,495 [task-result-getter-2] INFO  TaskSetManager - Finished task 434.0 in stage 0.0 (TID 434) in 70460 ms on localhost (executor driver) (427/3618)
 2018-01-30 17:21:14,496 [Executor task launch worker for task 438] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926150038127-00115.warc.gz:0+1000076519
 2018-01-30 17:21:22,063 [Executor task launch worker for task 430] INFO  Executor - Finished task 430.0 in stage 0.0 (TID 430). 1783 bytes result sent to driver
 2018-01-30 17:21:22,064 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 439.0 in stage 0.0 (TID 439, localhost, executor driver, partition 439, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:21:22,065 [Executor task launch worker for task 439] INFO  Executor - Running task 439.0 in stage 0.0 (TID 439)
 2018-01-30 17:21:22,065 [task-result-getter-3] INFO  TaskSetManager - Finished task 430.0 in stage 0.0 (TID 430) in 95271 ms on localhost (executor driver) (428/3618)
 2018-01-30 17:21:22,066 [Executor task launch worker for task 439] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-YDUKWP-20111130180651-00001-crawling203.us.archive.org-6680.warc.gz:0+109921590
 2018-01-30 17:21:24,267 [Executor task launch worker for task 437] INFO  Executor - Finished task 437.0 in stage 0.0 (TID 437). 1759 bytes result sent to driver
 2018-01-30 17:21:24,268 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 440.0 in stage 0.0 (TID 440, localhost, executor driver, partition 440, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:21:24,268 [Executor task launch worker for task 440] INFO  Executor - Running task 440.0 in stage 0.0 (TID 440)
 2018-01-30 17:21:24,269 [task-result-getter-0] INFO  TaskSetManager - Finished task 437.0 in stage 0.0 (TID 437) in 11519 ms on localhost (executor driver) (429/3618)
 2018-01-30 17:21:24,270 [Executor task launch worker for task 440] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930180352-00230-crawling202.us.archive.org-6681.warc.gz:0+106604912
 2018-01-30 17:21:25,422 [Executor task launch worker for task 436] INFO  Executor - Finished task 436.0 in stage 0.0 (TID 436). 1985 bytes result sent to driver
 2018-01-30 17:21:25,423 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 441.0 in stage 0.0 (TID 441, localhost, executor driver, partition 441, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:21:25,423 [Executor task launch worker for task 441] INFO  Executor - Running task 441.0 in stage 0.0 (TID 441)
 2018-01-30 17:21:25,423 [task-result-getter-1] INFO  TaskSetManager - Finished task 436.0 in stage 0.0 (TID 436) in 69550 ms on localhost (executor driver) (430/3618)
 2018-01-30 17:21:25,424 [Executor task launch worker for task 441] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-CSRYZP-20120813134651-00009-crawling208.us.archive.org-6681.warc.gz:0+100000005
 2018-01-30 17:21:34,234 [Executor task launch worker for task 431] INFO  Executor - Finished task 431.0 in stage 0.0 (TID 431). 2185 bytes result sent to driver
 2018-01-30 17:21:34,238 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 442.0 in stage 0.0 (TID 442, localhost, executor driver, partition 442, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:21:34,238 [Executor task launch worker for task 442] INFO  Executor - Running task 442.0 in stage 0.0 (TID 442)
 2018-01-30 17:21:34,238 [task-result-getter-2] INFO  TaskSetManager - Finished task 431.0 in stage 0.0 (TID 431) in 106380 ms on localhost (executor driver) (431/3618)
 2018-01-30 17:22:02,345 [Executor task launch worker for task 442] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JZRKSY-20120214060804-00003-crawling211.us.archive.org-6682.warc.gz:0+100000025
 2018-01-30 17:22:05,682 [Executor task launch worker for task 432] INFO  Executor - Finished task 432.0 in stage 0.0 (TID 432). 1969 bytes result sent to driver
 2018-01-30 17:22:05,683 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 443.0 in stage 0.0 (TID 443, localhost, executor driver, partition 443, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:22:05,683 [Executor task launch worker for task 443] INFO  Executor - Running task 443.0 in stage 0.0 (TID 443)
 2018-01-30 17:22:05,683 [task-result-getter-3] INFO  TaskSetManager - Finished task 432.0 in stage 0.0 (TID 432) in 134852 ms on localhost (executor driver) (432/3618)
 2018-01-30 17:22:05,684 [Executor task launch worker for task 443] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120228065845-00006-crawling211.us.archive.org-6682.warc.gz:0+137552289
 2018-01-30 17:22:07,442 [Executor task launch worker for task 441] INFO  Executor - Finished task 441.0 in stage 0.0 (TID 441). 1771 bytes result sent to driver
 2018-01-30 17:22:07,443 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 444.0 in stage 0.0 (TID 444, localhost, executor driver, partition 444, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:22:07,443 [Executor task launch worker for task 444] INFO  Executor - Running task 444.0 in stage 0.0 (TID 444)
 2018-01-30 17:22:07,443 [task-result-getter-0] INFO  TaskSetManager - Finished task 441.0 in stage 0.0 (TID 441) in 42021 ms on localhost (executor driver) (433/3618)
 2018-01-30 17:22:07,444 [Executor task launch worker for task 444] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003140507-00631-crawling209.us.archive.org-6681.warc.gz:0+102307023
 2018-01-30 17:22:08,926 [Executor task launch worker for task 440] INFO  Executor - Finished task 440.0 in stage 0.0 (TID 440). 1771 bytes result sent to driver
 2018-01-30 17:22:08,928 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 445.0 in stage 0.0 (TID 445, localhost, executor driver, partition 445, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:22:08,928 [Executor task launch worker for task 445] INFO  Executor - Running task 445.0 in stage 0.0 (TID 445)
 2018-01-30 17:22:08,928 [task-result-getter-1] INFO  TaskSetManager - Finished task 440.0 in stage 0.0 (TID 440) in 44660 ms on localhost (executor driver) (434/3618)
 2018-01-30 17:22:08,929 [Executor task launch worker for task 445] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002075805-00262-crawling209.us.archive.org-6681.warc.gz:0+129311397
 2018-01-30 17:22:18,557 [Executor task launch worker for task 423] INFO  Executor - Finished task 423.0 in stage 0.0 (TID 423). 1759 bytes result sent to driver
 2018-01-30 17:22:18,558 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 446.0 in stage 0.0 (TID 446, localhost, executor driver, partition 446, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:22:18,558 [Executor task launch worker for task 446] INFO  Executor - Running task 446.0 in stage 0.0 (TID 446)
 2018-01-30 17:22:18,559 [task-result-getter-2] INFO  TaskSetManager - Finished task 423.0 in stage 0.0 (TID 423) in 179974 ms on localhost (executor driver) (435/3618)
 2018-01-30 17:22:18,561 [Executor task launch worker for task 446] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225194218655-00103.warc.gz:0+1000065822
 2018-01-30 17:22:19,268 [Executor task launch worker for task 439] INFO  Executor - Finished task 439.0 in stage 0.0 (TID 439). 1763 bytes result sent to driver
 2018-01-30 17:22:19,268 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 447.0 in stage 0.0 (TID 447, localhost, executor driver, partition 447, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:22:19,269 [task-result-getter-3] INFO  TaskSetManager - Finished task 439.0 in stage 0.0 (TID 439) in 57205 ms on localhost (executor driver) (436/3618)
 2018-01-30 17:22:19,270 [Executor task launch worker for task 447] INFO  Executor - Running task 447.0 in stage 0.0 (TID 447)
 2018-01-30 17:22:19,271 [Executor task launch worker for task 447] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727214114737-00033.warc.gz:0+1007215380
 2018-01-30 17:22:25,192 [Executor task launch worker for task 442] INFO  Executor - Finished task 442.0 in stage 0.0 (TID 442). 1815 bytes result sent to driver
 2018-01-30 17:22:25,192 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 448.0 in stage 0.0 (TID 448, localhost, executor driver, partition 448, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:22:25,193 [task-result-getter-0] INFO  TaskSetManager - Finished task 442.0 in stage 0.0 (TID 442) in 50956 ms on localhost (executor driver) (437/3618)
 2018-01-30 17:22:25,193 [Executor task launch worker for task 448] INFO  Executor - Running task 448.0 in stage 0.0 (TID 448)
 2018-01-30 17:22:25,195 [Executor task launch worker for task 448] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924172841107-00039.warc.gz:0+1000032343
 2018-01-30 17:23:12,945 [Executor task launch worker for task 445] INFO  Executor - Finished task 445.0 in stage 0.0 (TID 445). 1850 bytes result sent to driver
 2018-01-30 17:23:12,948 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 449.0 in stage 0.0 (TID 449, localhost, executor driver, partition 449, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:23:12,949 [task-result-getter-1] INFO  TaskSetManager - Finished task 445.0 in stage 0.0 (TID 445) in 64023 ms on localhost (executor driver) (438/3618)
 2018-01-30 17:23:12,949 [Executor task launch worker for task 449] INFO  Executor - Running task 449.0 in stage 0.0 (TID 449)
 2018-01-30 17:23:12,954 [Executor task launch worker for task 449] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925081423220-00064.warc.gz:0+1000041355
 2018-01-30 17:23:14,765 [Executor task launch worker for task 444] INFO  Executor - Finished task 444.0 in stage 0.0 (TID 444). 1759 bytes result sent to driver
 2018-01-30 17:23:14,767 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 450.0 in stage 0.0 (TID 450, localhost, executor driver, partition 450, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:23:14,767 [Executor task launch worker for task 450] INFO  Executor - Running task 450.0 in stage 0.0 (TID 450)
 2018-01-30 17:23:14,767 [task-result-getter-2] INFO  TaskSetManager - Finished task 444.0 in stage 0.0 (TID 444) in 67324 ms on localhost (executor driver) (439/3618)
 2018-01-30 17:23:14,769 [Executor task launch worker for task 450] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628055756-00022-crawling212.us.archive.org-6682.warc.gz:0+442185630
 2018-01-30 17:23:20,355 [Executor task launch worker for task 443] INFO  Executor - Finished task 443.0 in stage 0.0 (TID 443). 1573 bytes result sent to driver
 2018-01-30 17:23:20,356 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 451.0 in stage 0.0 (TID 451, localhost, executor driver, partition 451, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:23:20,357 [Executor task launch worker for task 451] INFO  Executor - Running task 451.0 in stage 0.0 (TID 451)
 2018-01-30 17:23:20,357 [task-result-getter-3] INFO  TaskSetManager - Finished task 443.0 in stage 0.0 (TID 443) in 74675 ms on localhost (executor driver) (440/3618)
 2018-01-30 17:23:20,360 [Executor task launch worker for task 451] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002041629-00193-crawling209.us.archive.org-6681.warc.gz:0+103884195
 2018-01-30 17:23:38,084 [Executor task launch worker for task 435] INFO  Executor - Finished task 435.0 in stage 0.0 (TID 435). 1894 bytes result sent to driver
 2018-01-30 17:23:38,085 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 452.0 in stage 0.0 (TID 452, localhost, executor driver, partition 452, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:23:38,086 [Executor task launch worker for task 452] INFO  Executor - Running task 452.0 in stage 0.0 (TID 452)
 2018-01-30 17:23:38,086 [task-result-getter-0] INFO  TaskSetManager - Finished task 435.0 in stage 0.0 (TID 435) in 213228 ms on localhost (executor driver) (441/3618)
 2018-01-30 17:23:38,091 [Executor task launch worker for task 452] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629072351-00048-crawling212.us.archive.org-6682.warc.gz:0+133902144
 2018-01-30 17:24:40,376 [Executor task launch worker for task 438] INFO  Executor - Finished task 438.0 in stage 0.0 (TID 438). 1958 bytes result sent to driver
 2018-01-30 17:24:40,378 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 453.0 in stage 0.0 (TID 453, localhost, executor driver, partition 453, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:24:40,379 [Executor task launch worker for task 453] INFO  Executor - Running task 453.0 in stage 0.0 (TID 453)
 2018-01-30 17:24:40,379 [task-result-getter-1] INFO  TaskSetManager - Finished task 438.0 in stage 0.0 (TID 438) in 205885 ms on localhost (executor driver) (442/3618)
 2018-01-30 17:24:40,382 [Executor task launch worker for task 453] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EQSHTS-20120316183958-00001-crawling200.us.archive.org-6681.warc.gz:0+101452621
 2018-01-30 17:26:23,306 [Executor task launch worker for task 393] INFO  Executor - Finished task 393.0 in stage 0.0 (TID 393). 1767 bytes result sent to driver
 2018-01-30 17:26:23,307 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 454.0 in stage 0.0 (TID 454, localhost, executor driver, partition 454, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:26:23,307 [Executor task launch worker for task 454] INFO  Executor - Running task 454.0 in stage 0.0 (TID 454)
 2018-01-30 17:26:23,307 [task-result-getter-2] INFO  TaskSetManager - Finished task 393.0 in stage 0.0 (TID 393) in 587188 ms on localhost (executor driver) (443/3618)
 2018-01-30 17:26:23,309 [Executor task launch worker for task 454] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-19744-20131220213014943-00000-wbgrp-crawl066.us.archive.org-6442.warc.gz:0+165966690
 2018-01-30 17:26:23,918 [Executor task launch worker for task 451] INFO  Executor - Finished task 451.0 in stage 0.0 (TID 451). 1767 bytes result sent to driver
 2018-01-30 17:26:23,919 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 455.0 in stage 0.0 (TID 455, localhost, executor driver, partition 455, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:26:23,919 [task-result-getter-3] INFO  TaskSetManager - Finished task 451.0 in stage 0.0 (TID 451) in 183563 ms on localhost (executor driver) (444/3618)
 2018-01-30 17:26:23,921 [Executor task launch worker for task 455] INFO  Executor - Running task 455.0 in stage 0.0 (TID 455)
 2018-01-30 17:26:23,922 [Executor task launch worker for task 455] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008181616-00006-crawling208.us.archive.org-6683.warc.gz:0+123183471
 2018-01-30 17:26:38,806 [Executor task launch worker for task 454] INFO  Executor - Finished task 454.0 in stage 0.0 (TID 454). 1946 bytes result sent to driver
 2018-01-30 17:26:38,810 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 456.0 in stage 0.0 (TID 456, localhost, executor driver, partition 456, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:26:38,810 [Executor task launch worker for task 456] INFO  Executor - Running task 456.0 in stage 0.0 (TID 456)
 2018-01-30 17:26:38,810 [task-result-getter-0] INFO  TaskSetManager - Finished task 454.0 in stage 0.0 (TID 454) in 15503 ms on localhost (executor driver) (445/3618)
 2018-01-30 17:26:38,815 [Executor task launch worker for task 456] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124035428441-00017.warc.gz:0+1000073751
 2018-01-30 17:26:39,276 [Executor task launch worker for task 453] INFO  Executor - Finished task 453.0 in stage 0.0 (TID 453). 1867 bytes result sent to driver
 2018-01-30 17:26:39,277 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 457.0 in stage 0.0 (TID 457, localhost, executor driver, partition 457, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:26:39,277 [task-result-getter-1] INFO  TaskSetManager - Finished task 453.0 in stage 0.0 (TID 453) in 118900 ms on localhost (executor driver) (446/3618)
 2018-01-30 17:26:39,279 [Executor task launch worker for task 457] INFO  Executor - Running task 457.0 in stage 0.0 (TID 457)
 2018-01-30 17:26:39,280 [Executor task launch worker for task 457] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171126130908780-00121.warc.gz:0+1000016696
 2018-01-30 17:26:45,934 [Executor task launch worker for task 448] INFO  Executor - Finished task 448.0 in stage 0.0 (TID 448). 1954 bytes result sent to driver
 2018-01-30 17:26:45,935 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 458.0 in stage 0.0 (TID 458, localhost, executor driver, partition 458, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:26:45,935 [task-result-getter-2] INFO  TaskSetManager - Finished task 448.0 in stage 0.0 (TID 448) in 260743 ms on localhost (executor driver) (447/3618)
 2018-01-30 17:26:45,935 [Executor task launch worker for task 458] INFO  Executor - Running task 458.0 in stage 0.0 (TID 458)
 2018-01-30 17:26:45,938 [Executor task launch worker for task 458] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-CSRYZP-20120813101841-00008-crawling208.us.archive.org-6681.warc.gz:0+103812722
 2018-01-30 17:26:46,042 [Executor task launch worker for task 452] INFO  Executor - Finished task 452.0 in stage 0.0 (TID 452). 1573 bytes result sent to driver
 2018-01-30 17:26:46,042 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 459.0 in stage 0.0 (TID 459, localhost, executor driver, partition 459, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:26:46,042 [Executor task launch worker for task 459] INFO  Executor - Running task 459.0 in stage 0.0 (TID 459)
 2018-01-30 17:26:46,042 [task-result-getter-3] INFO  TaskSetManager - Finished task 452.0 in stage 0.0 (TID 452) in 187957 ms on localhost (executor driver) (448/3618)
 2018-01-30 17:26:46,043 [Executor task launch worker for task 459] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003020340-00520-crawling209.us.archive.org-6681.warc.gz:0+102390546
 2018-01-30 17:26:48,040 [Executor task launch worker for task 446] INFO  Executor - Finished task 446.0 in stage 0.0 (TID 446). 1902 bytes result sent to driver
 2018-01-30 17:26:48,040 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 460.0 in stage 0.0 (TID 460, localhost, executor driver, partition 460, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:26:48,040 [Executor task launch worker for task 460] INFO  Executor - Running task 460.0 in stage 0.0 (TID 460)
 2018-01-30 17:26:48,040 [task-result-getter-0] INFO  TaskSetManager - Finished task 446.0 in stage 0.0 (TID 446) in 269482 ms on localhost (executor driver) (449/3618)
 2018-01-30 17:26:48,042 [Executor task launch worker for task 460] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB255299-20161217001423689-00000.warc.gz:0+1000016025
 2018-01-30 17:26:58,666 [Executor task launch worker for task 458] INFO  Executor - Finished task 458.0 in stage 0.0 (TID 458). 1799 bytes result sent to driver
 2018-01-30 17:26:58,666 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 461.0 in stage 0.0 (TID 461, localhost, executor driver, partition 461, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:26:58,667 [task-result-getter-1] INFO  TaskSetManager - Finished task 458.0 in stage 0.0 (TID 458) in 12732 ms on localhost (executor driver) (450/3618)
 2018-01-30 17:26:58,667 [Executor task launch worker for task 461] INFO  Executor - Running task 461.0 in stage 0.0 (TID 461)
 2018-01-30 17:26:58,668 [Executor task launch worker for task 461] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926101455650-00107.warc.gz:0+1000001578
 2018-01-30 17:26:58,810 [Executor task launch worker for task 455] INFO  Executor - Finished task 455.0 in stage 0.0 (TID 455). 1672 bytes result sent to driver
 2018-01-30 17:26:58,811 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 462.0 in stage 0.0 (TID 462, localhost, executor driver, partition 462, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:26:58,811 [Executor task launch worker for task 462] INFO  Executor - Running task 462.0 in stage 0.0 (TID 462)
 2018-01-30 17:26:58,811 [task-result-getter-2] INFO  TaskSetManager - Finished task 455.0 in stage 0.0 (TID 455) in 34892 ms on localhost (executor driver) (451/3618)
 2018-01-30 17:26:58,812 [Executor task launch worker for task 462] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-10754-20140418213602882-00000-wbgrp-crawl050.us.archive.org-6443.warc.gz:0+345019119
 2018-01-30 17:27:00,068 [Executor task launch worker for task 459] INFO  Executor - Finished task 459.0 in stage 0.0 (TID 459). 1759 bytes result sent to driver
 2018-01-30 17:27:00,069 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 463.0 in stage 0.0 (TID 463, localhost, executor driver, partition 463, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:27:00,069 [Executor task launch worker for task 463] INFO  Executor - Running task 463.0 in stage 0.0 (TID 463)
 2018-01-30 17:27:00,069 [task-result-getter-3] INFO  TaskSetManager - Finished task 459.0 in stage 0.0 (TID 459) in 14027 ms on localhost (executor driver) (452/3618)
 2018-01-30 17:27:00,070 [Executor task launch worker for task 463] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929154041-00088-crawling113.us.archive.org-6683.warc.gz:0+124972223
 2018-01-30 17:27:02,560 [Executor task launch worker for task 337] INFO  Executor - Finished task 337.0 in stage 0.0 (TID 337). 2101 bytes result sent to driver
 2018-01-30 17:27:02,562 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 464.0 in stage 0.0 (TID 464, localhost, executor driver, partition 464, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:27:02,562 [task-result-getter-0] INFO  TaskSetManager - Finished task 337.0 in stage 0.0 (TID 337) in 999225 ms on localhost (executor driver) (453/3618)
 2018-01-30 17:27:02,562 [Executor task launch worker for task 464] INFO  Executor - Running task 464.0 in stage 0.0 (TID 464)
 2018-01-30 17:27:02,564 [Executor task launch worker for task 464] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QRDYRH-20120312212032-00011-crawling113.us.archive.org-6681.warc.gz:0+106130579
 2018-01-30 17:27:04,288 [Executor task launch worker for task 449] INFO  Executor - Finished task 449.0 in stage 0.0 (TID 449). 1962 bytes result sent to driver
 2018-01-30 17:27:04,288 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 465.0 in stage 0.0 (TID 465, localhost, executor driver, partition 465, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:27:04,288 [Executor task launch worker for task 465] INFO  Executor - Running task 465.0 in stage 0.0 (TID 465)
 2018-01-30 17:27:04,289 [task-result-getter-1] INFO  TaskSetManager - Finished task 449.0 in stage 0.0 (TID 449) in 231341 ms on localhost (executor driver) (454/3618)
 2018-01-30 17:27:04,290 [Executor task launch worker for task 465] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001223907-00099-crawling209.us.archive.org-6681.warc.gz:0+105082522
 2018-01-30 17:27:27,387 [Executor task launch worker for task 465] INFO  Executor - Finished task 465.0 in stage 0.0 (TID 465). 1767 bytes result sent to driver
 2018-01-30 17:27:27,387 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 466.0 in stage 0.0 (TID 466, localhost, executor driver, partition 466, PROCESS_LOCAL, 19533 bytes)
 2018-01-30 17:27:27,387 [Executor task launch worker for task 466] INFO  Executor - Running task 466.0 in stage 0.0 (TID 466)
 2018-01-30 17:27:27,387 [task-result-getter-2] INFO  TaskSetManager - Finished task 465.0 in stage 0.0 (TID 465) in 23099 ms on localhost (executor driver) (455/3618)
 2018-01-30 17:27:27,388 [Executor task launch worker for task 466] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QA_PATCH_CRAWL-JOB178246-20151013172053947-00000.warc.gz:0+1132720
 2018-01-30 17:27:27,585 [Executor task launch worker for task 466] INFO  Executor - Finished task 466.0 in stage 0.0 (TID 466). 1694 bytes result sent to driver
 2018-01-30 17:27:27,585 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 467.0 in stage 0.0 (TID 467, localhost, executor driver, partition 467, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:27:27,585 [Executor task launch worker for task 467] INFO  Executor - Running task 467.0 in stage 0.0 (TID 467)
 2018-01-30 17:27:27,585 [task-result-getter-3] INFO  TaskSetManager - Finished task 466.0 in stage 0.0 (TID 466) in 198 ms on localhost (executor driver) (456/3618)
 2018-01-30 17:27:27,586 [Executor task launch worker for task 467] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001075530-00008-crawling209.us.archive.org-6681.warc.gz:0+100135174
 2018-01-30 17:27:48,329 [Executor task launch worker for task 464] INFO  Executor - Finished task 464.0 in stage 0.0 (TID 464). 1779 bytes result sent to driver
 2018-01-30 17:27:48,329 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 468.0 in stage 0.0 (TID 468, localhost, executor driver, partition 468, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:27:48,329 [task-result-getter-0] INFO  TaskSetManager - Finished task 464.0 in stage 0.0 (TID 464) in 45767 ms on localhost (executor driver) (457/3618)
 2018-01-30 17:27:48,329 [Executor task launch worker for task 468] INFO  Executor - Running task 468.0 in stage 0.0 (TID 468)
 2018-01-30 17:27:48,330 [Executor task launch worker for task 468] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111005222208-00006-crawling205.us.archive.org-6681.warc.gz:0+100880825
 2018-01-30 17:27:56,752 [Executor task launch worker for task 467] INFO  Executor - Finished task 467.0 in stage 0.0 (TID 467). 1791 bytes result sent to driver
 2018-01-30 17:27:56,753 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 469.0 in stage 0.0 (TID 469, localhost, executor driver, partition 469, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:27:56,753 [Executor task launch worker for task 469] INFO  Executor - Running task 469.0 in stage 0.0 (TID 469)
 2018-01-30 17:27:56,753 [task-result-getter-1] INFO  TaskSetManager - Finished task 467.0 in stage 0.0 (TID 467) in 29168 ms on localhost (executor driver) (458/3618)
 2018-01-30 17:27:56,754 [Executor task launch worker for task 469] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226013814566-00118.warc.gz:0+1000065456
 2018-01-30 17:28:09,718 [Executor task launch worker for task 456] INFO  Executor - Finished task 456.0 in stage 0.0 (TID 456). 2033 bytes result sent to driver
 2018-01-30 17:28:09,719 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 470.0 in stage 0.0 (TID 470, localhost, executor driver, partition 470, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:09,719 [Executor task launch worker for task 470] INFO  Executor - Running task 470.0 in stage 0.0 (TID 470)
 2018-01-30 17:28:09,719 [task-result-getter-2] INFO  TaskSetManager - Finished task 456.0 in stage 0.0 (TID 456) in 90911 ms on localhost (executor driver) (459/3618)
 2018-01-30 17:28:09,720 [Executor task launch worker for task 470] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-JWRICE-20111205185709-00013-crawling210.us.archive.org-6682.warc.gz:0+100052830
 2018-01-30 17:28:09,730 [Executor task launch worker for task 450] INFO  Executor - Finished task 450.0 in stage 0.0 (TID 450). 1573 bytes result sent to driver
 2018-01-30 17:28:09,731 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 471.0 in stage 0.0 (TID 471, localhost, executor driver, partition 471, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:09,731 [Executor task launch worker for task 471] INFO  Executor - Running task 471.0 in stage 0.0 (TID 471)
 2018-01-30 17:28:09,731 [task-result-getter-3] INFO  TaskSetManager - Finished task 450.0 in stage 0.0 (TID 450) in 294965 ms on localhost (executor driver) (460/3618)
 2018-01-30 17:28:09,732 [Executor task launch worker for task 471] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301090129-00102-crawling211.us.archive.org-6682.warc.gz:0+100743893
 2018-01-30 17:28:13,700 [Executor task launch worker for task 471] INFO  Executor - Finished task 471.0 in stage 0.0 (TID 471). 1500 bytes result sent to driver
 2018-01-30 17:28:13,701 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 472.0 in stage 0.0 (TID 472, localhost, executor driver, partition 472, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:13,702 [Executor task launch worker for task 472] INFO  Executor - Running task 472.0 in stage 0.0 (TID 472)
 2018-01-30 17:28:13,702 [task-result-getter-0] INFO  TaskSetManager - Finished task 471.0 in stage 0.0 (TID 471) in 3972 ms on localhost (executor driver) (461/3618)
 2018-01-30 17:28:13,703 [Executor task launch worker for task 472] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930180812-00232-crawling202.us.archive.org-6681.warc.gz:0+108401072
 2018-01-30 17:28:13,937 [Executor task launch worker for task 462] INFO  Executor - Finished task 462.0 in stage 0.0 (TID 462). 1886 bytes result sent to driver
 2018-01-30 17:28:13,938 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 473.0 in stage 0.0 (TID 473, localhost, executor driver, partition 473, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:28:13,938 [Executor task launch worker for task 473] INFO  Executor - Running task 473.0 in stage 0.0 (TID 473)
 2018-01-30 17:28:13,938 [task-result-getter-1] INFO  TaskSetManager - Finished task 462.0 in stage 0.0 (TID 462) in 75128 ms on localhost (executor driver) (462/3618)
 2018-01-30 17:28:13,939 [Executor task launch worker for task 473] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-JYDOMM-20110715213911-00000-crawling209.us.archive.org-6681.warc.gz:0+2356107
 2018-01-30 17:28:14,531 [Executor task launch worker for task 473] INFO  Executor - Finished task 473.0 in stage 0.0 (TID 473). 1686 bytes result sent to driver
 2018-01-30 17:28:14,532 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 474.0 in stage 0.0 (TID 474, localhost, executor driver, partition 474, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:28:14,532 [Executor task launch worker for task 474] INFO  Executor - Running task 474.0 in stage 0.0 (TID 474)
 2018-01-30 17:28:14,532 [task-result-getter-2] INFO  TaskSetManager - Finished task 473.0 in stage 0.0 (TID 473) in 595 ms on localhost (executor driver) (463/3618)
 2018-01-30 17:28:14,534 [Executor task launch worker for task 474] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-10694-20140608211945405-00001-wbgrp-crawl062.us.archive.org-6441.warc.gz:0+2264739053
 2018-01-30 17:28:16,034 [Executor task launch worker for task 457] INFO  Executor - Finished task 457.0 in stage 0.0 (TID 457). 1942 bytes result sent to driver
 2018-01-30 17:28:16,034 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 475.0 in stage 0.0 (TID 475, localhost, executor driver, partition 475, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:28:16,034 [Executor task launch worker for task 475] INFO  Executor - Running task 475.0 in stage 0.0 (TID 475)
 2018-01-30 17:28:16,034 [task-result-getter-3] INFO  TaskSetManager - Finished task 457.0 in stage 0.0 (TID 457) in 96758 ms on localhost (executor driver) (464/3618)
 2018-01-30 17:28:16,035 [Executor task launch worker for task 475] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-31627-20140903204020781-00000-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+73808031
 2018-01-30 17:28:17,912 [Executor task launch worker for task 468] INFO  Executor - Finished task 468.0 in stage 0.0 (TID 468). 1767 bytes result sent to driver
 2018-01-30 17:28:17,912 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 476.0 in stage 0.0 (TID 476, localhost, executor driver, partition 476, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:28:17,912 [Executor task launch worker for task 476] INFO  Executor - Running task 476.0 in stage 0.0 (TID 476)
 2018-01-30 17:28:17,912 [task-result-getter-0] INFO  TaskSetManager - Finished task 468.0 in stage 0.0 (TID 468) in 29583 ms on localhost (executor driver) (465/3618)
 2018-01-30 17:28:17,913 [Executor task launch worker for task 476] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120612205311-00002-crawling200.us.archive.org-6681.warc.gz:0+100001090
 2018-01-30 17:28:25,270 [Executor task launch worker for task 475] INFO  Executor - Finished task 475.0 in stage 0.0 (TID 475). 1791 bytes result sent to driver
 2018-01-30 17:28:25,270 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 477.0 in stage 0.0 (TID 477, localhost, executor driver, partition 477, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:28:25,270 [Executor task launch worker for task 477] INFO  Executor - Running task 477.0 in stage 0.0 (TID 477)
 2018-01-30 17:28:25,270 [task-result-getter-1] INFO  TaskSetManager - Finished task 475.0 in stage 0.0 (TID 475) in 9236 ms on localhost (executor driver) (466/3618)
 2018-01-30 17:28:25,272 [Executor task launch worker for task 477] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024040958736-00016.warc.gz:0+1000028348
 2018-01-30 17:28:27,305 [Executor task launch worker for task 472] INFO  Executor - Finished task 472.0 in stage 0.0 (TID 472). 1775 bytes result sent to driver
 2018-01-30 17:28:27,306 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 478.0 in stage 0.0 (TID 478, localhost, executor driver, partition 478, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:28:27,306 [Executor task launch worker for task 478] INFO  Executor - Running task 478.0 in stage 0.0 (TID 478)
 2018-01-30 17:28:27,306 [task-result-getter-2] INFO  TaskSetManager - Finished task 472.0 in stage 0.0 (TID 472) in 13605 ms on localhost (executor driver) (467/3618)
 2018-01-30 17:28:27,307 [Executor task launch worker for task 478] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB164119-20150710215629467-00000.warc.gz:0+257059107
 2018-01-30 17:28:34,806 [Executor task launch worker for task 424] INFO  Executor - Finished task 424.0 in stage 0.0 (TID 424). 1763 bytes result sent to driver
 2018-01-30 17:28:34,807 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 479.0 in stage 0.0 (TID 479, localhost, executor driver, partition 479, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:34,807 [task-result-getter-3] INFO  TaskSetManager - Finished task 424.0 in stage 0.0 (TID 424) in 551780 ms on localhost (executor driver) (468/3618)
 2018-01-30 17:28:34,807 [Executor task launch worker for task 479] INFO  Executor - Running task 479.0 in stage 0.0 (TID 479)
 2018-01-30 17:28:34,809 [Executor task launch worker for task 479] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930181600-00234-crawling202.us.archive.org-6681.warc.gz:0+100875650
 2018-01-30 17:28:35,730 [Executor task launch worker for task 470] INFO  Executor - Finished task 470.0 in stage 0.0 (TID 470). 1759 bytes result sent to driver
 2018-01-30 17:28:35,731 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 480.0 in stage 0.0 (TID 480, localhost, executor driver, partition 480, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:35,731 [Executor task launch worker for task 480] INFO  Executor - Running task 480.0 in stage 0.0 (TID 480)
 2018-01-30 17:28:35,731 [task-result-getter-0] INFO  TaskSetManager - Finished task 470.0 in stage 0.0 (TID 470) in 26013 ms on localhost (executor driver) (469/3618)
 2018-01-30 17:28:35,732 [Executor task launch worker for task 480] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-MGJAWT-20110719211606-00000-crawling210.us.archive.org-6682.warc.gz:0+101440668
 2018-01-30 17:28:40,823 [Executor task launch worker for task 461] INFO  Executor - Finished task 461.0 in stage 0.0 (TID 461). 2238 bytes result sent to driver
 2018-01-30 17:28:40,823 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 481.0 in stage 0.0 (TID 481, localhost, executor driver, partition 481, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:28:40,824 [Executor task launch worker for task 481] INFO  Executor - Running task 481.0 in stage 0.0 (TID 481)
 2018-01-30 17:28:40,824 [task-result-getter-1] INFO  TaskSetManager - Finished task 461.0 in stage 0.0 (TID 461) in 102158 ms on localhost (executor driver) (470/3618)
 2018-01-30 17:28:40,825 [Executor task launch worker for task 481] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170923193358949-00001.warc.gz:0+1000019918
 2018-01-30 17:28:41,001 [Executor task launch worker for task 476] INFO  Executor - Finished task 476.0 in stage 0.0 (TID 476). 1815 bytes result sent to driver
 2018-01-30 17:28:41,002 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 482.0 in stage 0.0 (TID 482, localhost, executor driver, partition 482, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:41,002 [task-result-getter-2] INFO  TaskSetManager - Finished task 476.0 in stage 0.0 (TID 476) in 23090 ms on localhost (executor driver) (471/3618)
 2018-01-30 17:28:41,002 [Executor task launch worker for task 482] INFO  Executor - Running task 482.0 in stage 0.0 (TID 482)
 2018-01-30 17:28:41,003 [Executor task launch worker for task 482] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-NHHENM-20120529205310-00007-crawling212.us.archive.org-6680.warc.gz:0+523920001
 2018-01-30 17:28:44,291 [Executor task launch worker for task 479] INFO  Executor - Finished task 479.0 in stage 0.0 (TID 479). 1775 bytes result sent to driver
 2018-01-30 17:28:44,292 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 483.0 in stage 0.0 (TID 483, localhost, executor driver, partition 483, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:28:44,292 [Executor task launch worker for task 483] INFO  Executor - Running task 483.0 in stage 0.0 (TID 483)
 2018-01-30 17:28:44,292 [task-result-getter-3] INFO  TaskSetManager - Finished task 479.0 in stage 0.0 (TID 479) in 9486 ms on localhost (executor driver) (472/3618)
 2018-01-30 17:28:44,294 [Executor task launch worker for task 483] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-30431-20140711222859341-00000-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+178902957
 2018-01-30 17:28:47,546 [Executor task launch worker for task 460] INFO  Executor - Finished task 460.0 in stage 0.0 (TID 460). 1922 bytes result sent to driver
 2018-01-30 17:28:47,547 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 484.0 in stage 0.0 (TID 484, localhost, executor driver, partition 484, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:28:47,547 [task-result-getter-0] INFO  TaskSetManager - Finished task 460.0 in stage 0.0 (TID 460) in 119507 ms on localhost (executor driver) (473/3618)
 2018-01-30 17:28:47,547 [Executor task launch worker for task 484] INFO  Executor - Running task 484.0 in stage 0.0 (TID 484)
 2018-01-30 17:28:47,549 [Executor task launch worker for task 484] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-DXOVPL-20120327192448-00001-crawling207.us.archive.org-6680.warc.gz:0+1506156
 2018-01-30 17:28:47,972 [Executor task launch worker for task 484] INFO  Executor - Finished task 484.0 in stage 0.0 (TID 484). 1686 bytes result sent to driver
 2018-01-30 17:28:47,973 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 485.0 in stage 0.0 (TID 485, localhost, executor driver, partition 485, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:28:47,973 [Executor task launch worker for task 485] INFO  Executor - Running task 485.0 in stage 0.0 (TID 485)
 2018-01-30 17:28:47,973 [task-result-getter-1] INFO  TaskSetManager - Finished task 484.0 in stage 0.0 (TID 484) in 427 ms on localhost (executor driver) (474/3618)
 2018-01-30 17:28:47,974 [Executor task launch worker for task 485] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-CSRYZP-20120812222616-00004-crawling208.us.archive.org-6681.warc.gz:0+100000201
 2018-01-30 17:28:56,273 [Executor task launch worker for task 478] INFO  Executor - Finished task 478.0 in stage 0.0 (TID 478). 2005 bytes result sent to driver
 2018-01-30 17:28:56,273 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 486.0 in stage 0.0 (TID 486, localhost, executor driver, partition 486, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:28:56,274 [Executor task launch worker for task 486] INFO  Executor - Running task 486.0 in stage 0.0 (TID 486)
 2018-01-30 17:28:56,274 [task-result-getter-2] INFO  TaskSetManager - Finished task 478.0 in stage 0.0 (TID 478) in 28969 ms on localhost (executor driver) (475/3618)
 2018-01-30 17:28:56,275 [Executor task launch worker for task 486] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JZRKSY-20120212203326-00001-crawling204.us.archive.org-6680.warc.gz:0+101182846
 2018-01-30 17:28:58,942 [Executor task launch worker for task 426] INFO  Executor - Finished task 426.0 in stage 0.0 (TID 426). 1803 bytes result sent to driver
 2018-01-30 17:28:58,943 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 487.0 in stage 0.0 (TID 487, localhost, executor driver, partition 487, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:28:58,943 [task-result-getter-3] INFO  TaskSetManager - Finished task 426.0 in stage 0.0 (TID 426) in 562993 ms on localhost (executor driver) (476/3618)
 2018-01-30 17:28:58,945 [Executor task launch worker for task 487] INFO  Executor - Running task 487.0 in stage 0.0 (TID 487)
 2018-01-30 17:28:58,946 [Executor task launch worker for task 487] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB185170-20151127213100817-00000.warc.gz:0+1000021633
 2018-01-30 17:29:01,652 [Executor task launch worker for task 483] INFO  Executor - Finished task 483.0 in stage 0.0 (TID 483). 1859 bytes result sent to driver
 2018-01-30 17:29:01,653 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 488.0 in stage 0.0 (TID 488, localhost, executor driver, partition 488, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:01,653 [task-result-getter-0] INFO  TaskSetManager - Finished task 483.0 in stage 0.0 (TID 483) in 17361 ms on localhost (executor driver) (477/3618)
 2018-01-30 17:29:01,654 [Executor task launch worker for task 488] INFO  Executor - Running task 488.0 in stage 0.0 (TID 488)
 2018-01-30 17:29:01,655 [Executor task launch worker for task 488] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002142654-00359-crawling209.us.archive.org-6681.warc.gz:0+106044267
 2018-01-30 17:29:07,771 [Executor task launch worker for task 485] INFO  Executor - Finished task 485.0 in stage 0.0 (TID 485). 1807 bytes result sent to driver
 2018-01-30 17:29:07,773 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 489.0 in stage 0.0 (TID 489, localhost, executor driver, partition 489, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:29:07,773 [task-result-getter-1] INFO  TaskSetManager - Finished task 485.0 in stage 0.0 (TID 485) in 19800 ms on localhost (executor driver) (478/3618)
 2018-01-30 17:29:07,773 [Executor task launch worker for task 489] INFO  Executor - Running task 489.0 in stage 0.0 (TID 489)
 2018-01-30 17:29:07,776 [Executor task launch worker for task 489] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171026065222478-00102.warc.gz:0+1000027487
 2018-01-30 17:29:11,437 [Executor task launch worker for task 480] INFO  Executor - Finished task 480.0 in stage 0.0 (TID 480). 1763 bytes result sent to driver
 2018-01-30 17:29:11,438 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 490.0 in stage 0.0 (TID 490, localhost, executor driver, partition 490, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:29:11,438 [Executor task launch worker for task 490] INFO  Executor - Running task 490.0 in stage 0.0 (TID 490)
 2018-01-30 17:29:11,438 [task-result-getter-2] INFO  TaskSetManager - Finished task 480.0 in stage 0.0 (TID 480) in 35707 ms on localhost (executor driver) (479/3618)
 2018-01-30 17:29:11,440 [Executor task launch worker for task 490] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QDPLNZ-20120712211746-00003-crawling105.us.archive.org-6681.warc.gz:0+117883429
 2018-01-30 17:29:19,882 [Executor task launch worker for task 488] INFO  Executor - Finished task 488.0 in stage 0.0 (TID 488). 1763 bytes result sent to driver
 2018-01-30 17:29:19,884 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 491.0 in stage 0.0 (TID 491, localhost, executor driver, partition 491, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:29:19,884 [task-result-getter-3] INFO  TaskSetManager - Finished task 488.0 in stage 0.0 (TID 488) in 18231 ms on localhost (executor driver) (480/3618)
 2018-01-30 17:29:19,884 [Executor task launch worker for task 491] INFO  Executor - Running task 491.0 in stage 0.0 (TID 491)
 2018-01-30 17:29:19,886 [Executor task launch worker for task 491] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024054400671-00019.warc.gz:0+1000002851
 2018-01-30 17:29:24,098 [Executor task launch worker for task 486] INFO  Executor - Finished task 486.0 in stage 0.0 (TID 486). 1871 bytes result sent to driver
 2018-01-30 17:29:24,098 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 492.0 in stage 0.0 (TID 492, localhost, executor driver, partition 492, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:29:24,098 [task-result-getter-0] INFO  TaskSetManager - Finished task 486.0 in stage 0.0 (TID 486) in 27825 ms on localhost (executor driver) (481/3618)
 2018-01-30 17:29:24,098 [Executor task launch worker for task 492] INFO  Executor - Running task 492.0 in stage 0.0 (TID 492)
 2018-01-30 17:29:24,100 [Executor task launch worker for task 492] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-DSYXLF-20121212204026-00001-wbgrp-crawl056.us.archive.org-6680.warc.gz:0+100001687
 2018-01-30 17:29:27,969 [Executor task launch worker for task 469] INFO  Executor - Finished task 469.0 in stage 0.0 (TID 469). 1831 bytes result sent to driver
 2018-01-30 17:29:27,970 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 493.0 in stage 0.0 (TID 493, localhost, executor driver, partition 493, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:27,970 [Executor task launch worker for task 493] INFO  Executor - Running task 493.0 in stage 0.0 (TID 493)
 2018-01-30 17:29:27,970 [task-result-getter-1] INFO  TaskSetManager - Finished task 469.0 in stage 0.0 (TID 469) in 91218 ms on localhost (executor driver) (482/3618)
 2018-01-30 17:29:27,971 [Executor task launch worker for task 493] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008210935-00042-crawling208.us.archive.org-6683.warc.gz:0+105051508
 2018-01-30 17:29:30,370 [Executor task launch worker for task 463] INFO  Executor - Finished task 463.0 in stage 0.0 (TID 463). 1660 bytes result sent to driver
 2018-01-30 17:29:30,371 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 494.0 in stage 0.0 (TID 494, localhost, executor driver, partition 494, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:30,371 [Executor task launch worker for task 494] INFO  Executor - Running task 494.0 in stage 0.0 (TID 494)
 2018-01-30 17:29:30,371 [task-result-getter-2] INFO  TaskSetManager - Finished task 463.0 in stage 0.0 (TID 463) in 150302 ms on localhost (executor driver) (483/3618)
 2018-01-30 17:29:30,372 [Executor task launch worker for task 494] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-DURLKV-20111101133413-00000-crawling115.us.archive.org-6682.warc.gz:0+44295198
 2018-01-30 17:29:43,255 [Executor task launch worker for task 494] INFO  Executor - Finished task 494.0 in stage 0.0 (TID 494). 1763 bytes result sent to driver
 2018-01-30 17:29:43,256 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 495.0 in stage 0.0 (TID 495, localhost, executor driver, partition 495, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:29:43,256 [Executor task launch worker for task 495] INFO  Executor - Running task 495.0 in stage 0.0 (TID 495)
 2018-01-30 17:29:43,256 [task-result-getter-3] INFO  TaskSetManager - Finished task 494.0 in stage 0.0 (TID 494) in 12886 ms on localhost (executor driver) (484/3618)
 2018-01-30 17:29:43,258 [Executor task launch worker for task 495] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB256529-20161224001423749-00000.warc.gz:0+37788271
 2018-01-30 17:29:45,485 [Executor task launch worker for task 490] INFO  Executor - Finished task 490.0 in stage 0.0 (TID 490). 1815 bytes result sent to driver
 2018-01-30 17:29:45,486 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 496.0 in stage 0.0 (TID 496, localhost, executor driver, partition 496, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:45,487 [Executor task launch worker for task 496] INFO  Executor - Running task 496.0 in stage 0.0 (TID 496)
 2018-01-30 17:29:45,487 [task-result-getter-0] INFO  TaskSetManager - Finished task 490.0 in stage 0.0 (TID 490) in 34050 ms on localhost (executor driver) (485/3618)
 2018-01-30 17:29:45,488 [Executor task launch worker for task 496] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001221737-00094-crawling209.us.archive.org-6681.warc.gz:0+100003848
 2018-01-30 17:29:45,762 [Executor task launch worker for task 477] INFO  Executor - Finished task 477.0 in stage 0.0 (TID 477). 1950 bytes result sent to driver
 2018-01-30 17:29:45,764 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 497.0 in stage 0.0 (TID 497, localhost, executor driver, partition 497, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:45,764 [Executor task launch worker for task 497] INFO  Executor - Running task 497.0 in stage 0.0 (TID 497)
 2018-01-30 17:29:45,764 [task-result-getter-1] INFO  TaskSetManager - Finished task 477.0 in stage 0.0 (TID 477) in 80494 ms on localhost (executor driver) (486/3618)
 2018-01-30 17:29:45,765 [Executor task launch worker for task 497] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002031004-00163-crawling209.us.archive.org-6681.warc.gz:0+101060741
 2018-01-30 17:29:45,868 [Executor task launch worker for task 492] INFO  Executor - Finished task 492.0 in stage 0.0 (TID 492). 1882 bytes result sent to driver
 2018-01-30 17:29:45,869 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 498.0 in stage 0.0 (TID 498, localhost, executor driver, partition 498, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:29:45,869 [Executor task launch worker for task 498] INFO  Executor - Running task 498.0 in stage 0.0 (TID 498)
 2018-01-30 17:29:45,869 [task-result-getter-2] INFO  TaskSetManager - Finished task 492.0 in stage 0.0 (TID 492) in 21771 ms on localhost (executor driver) (487/3618)
 2018-01-30 17:29:45,870 [Executor task launch worker for task 498] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-FEEUZB-20120513013818-00009-crawling115.us.archive.org-6683.warc.gz:0+116564545
 2018-01-30 17:29:47,951 [Executor task launch worker for task 495] INFO  Executor - Finished task 495.0 in stage 0.0 (TID 495). 1734 bytes result sent to driver
 2018-01-30 17:29:47,952 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 499.0 in stage 0.0 (TID 499, localhost, executor driver, partition 499, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:29:47,952 [task-result-getter-3] INFO  TaskSetManager - Finished task 495.0 in stage 0.0 (TID 495) in 4697 ms on localhost (executor driver) (488/3618)
 2018-01-30 17:29:47,952 [Executor task launch worker for task 499] INFO  Executor - Running task 499.0 in stage 0.0 (TID 499)
 2018-01-30 17:29:47,954 [Executor task launch worker for task 499] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226020105462-00119.warc.gz:0+1000024067
 2018-01-30 17:29:51,186 [Executor task launch worker for task 496] INFO  Executor - Finished task 496.0 in stage 0.0 (TID 496). 1694 bytes result sent to driver
 2018-01-30 17:29:51,187 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 500.0 in stage 0.0 (TID 500, localhost, executor driver, partition 500, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:29:51,187 [Executor task launch worker for task 500] INFO  Executor - Running task 500.0 in stage 0.0 (TID 500)
 2018-01-30 17:29:51,187 [task-result-getter-0] INFO  TaskSetManager - Finished task 496.0 in stage 0.0 (TID 496) in 5702 ms on localhost (executor driver) (489/3618)
 2018-01-30 17:29:51,188 [Executor task launch worker for task 500] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170924095910839-00026.warc.gz:0+1000028779
 2018-01-30 17:29:56,759 [Executor task launch worker for task 497] INFO  Executor - Finished task 497.0 in stage 0.0 (TID 497). 1767 bytes result sent to driver
 2018-01-30 17:29:56,761 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 501.0 in stage 0.0 (TID 501, localhost, executor driver, partition 501, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:56,761 [Executor task launch worker for task 501] INFO  Executor - Running task 501.0 in stage 0.0 (TID 501)
 2018-01-30 17:29:56,762 [task-result-getter-1] INFO  TaskSetManager - Finished task 497.0 in stage 0.0 (TID 497) in 10998 ms on localhost (executor driver) (490/3618)
 2018-01-30 17:29:56,764 [Executor task launch worker for task 501] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912040243-00057-crawling211.us.archive.org-6681.warc.gz:0+100918645
 2018-01-30 17:29:57,436 [Executor task launch worker for task 493] INFO  Executor - Finished task 493.0 in stage 0.0 (TID 493). 1486 bytes result sent to driver
 2018-01-30 17:29:57,437 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 502.0 in stage 0.0 (TID 502, localhost, executor driver, partition 502, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:29:57,437 [Executor task launch worker for task 502] INFO  Executor - Running task 502.0 in stage 0.0 (TID 502)
 2018-01-30 17:29:57,437 [task-result-getter-2] INFO  TaskSetManager - Finished task 493.0 in stage 0.0 (TID 493) in 29468 ms on localhost (executor driver) (491/3618)
 2018-01-30 17:29:57,438 [Executor task launch worker for task 502] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-23712-20130927225016109-00016-wbgrp-crawl100.us.archive.org-6441.warc.gz:0+5044163
 2018-01-30 17:29:57,880 [Executor task launch worker for task 502] INFO  Executor - Finished task 502.0 in stage 0.0 (TID 502). 1694 bytes result sent to driver
 2018-01-30 17:29:57,881 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 503.0 in stage 0.0 (TID 503, localhost, executor driver, partition 503, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:29:57,881 [Executor task launch worker for task 503] INFO  Executor - Running task 503.0 in stage 0.0 (TID 503)
 2018-01-30 17:29:57,881 [task-result-getter-3] INFO  TaskSetManager - Finished task 502.0 in stage 0.0 (TID 502) in 444 ms on localhost (executor driver) (492/3618)
 2018-01-30 17:29:57,882 [Executor task launch worker for task 503] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110910000840-00006-crawling211.us.archive.org-6681.warc.gz:0+101366438
 2018-01-30 17:30:08,478 [Executor task launch worker for task 498] INFO  Executor - Finished task 498.0 in stage 0.0 (TID 498). 1843 bytes result sent to driver
 2018-01-30 17:30:08,480 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 504.0 in stage 0.0 (TID 504, localhost, executor driver, partition 504, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:30:08,480 [task-result-getter-0] INFO  TaskSetManager - Finished task 498.0 in stage 0.0 (TID 498) in 22611 ms on localhost (executor driver) (493/3618)
 2018-01-30 17:30:08,480 [Executor task launch worker for task 504] INFO  Executor - Running task 504.0 in stage 0.0 (TID 504)
 2018-01-30 17:30:08,484 [Executor task launch worker for task 504] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB506460-20171124224724851-00051.warc.gz:0+1000036948
 2018-01-30 17:30:25,636 [Executor task launch worker for task 503] INFO  Executor - Finished task 503.0 in stage 0.0 (TID 503). 1775 bytes result sent to driver
 2018-01-30 17:30:25,638 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 505.0 in stage 0.0 (TID 505, localhost, executor driver, partition 505, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:25,638 [Executor task launch worker for task 505] INFO  Executor - Running task 505.0 in stage 0.0 (TID 505)
 2018-01-30 17:30:25,638 [task-result-getter-1] INFO  TaskSetManager - Finished task 503.0 in stage 0.0 (TID 503) in 27757 ms on localhost (executor driver) (494/3618)
 2018-01-30 17:30:25,641 [Executor task launch worker for task 505] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002104823-00308-crawling209.us.archive.org-6681.warc.gz:0+124819034
 2018-01-30 17:30:28,046 [Executor task launch worker for task 501] INFO  Executor - Finished task 501.0 in stage 0.0 (TID 501). 1660 bytes result sent to driver
 2018-01-30 17:30:28,047 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 506.0 in stage 0.0 (TID 506, localhost, executor driver, partition 506, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:28,047 [Executor task launch worker for task 506] INFO  Executor - Running task 506.0 in stage 0.0 (TID 506)
 2018-01-30 17:30:28,047 [task-result-getter-2] INFO  TaskSetManager - Finished task 501.0 in stage 0.0 (TID 501) in 31287 ms on localhost (executor driver) (495/3618)
 2018-01-30 17:30:28,049 [Executor task launch worker for task 506] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002041827-00194-crawling209.us.archive.org-6681.warc.gz:0+101461919
 2018-01-30 17:30:34,692 [Executor task launch worker for task 505] INFO  Executor - Finished task 505.0 in stage 0.0 (TID 505). 1763 bytes result sent to driver
 2018-01-30 17:30:34,695 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 507.0 in stage 0.0 (TID 507, localhost, executor driver, partition 507, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:30:34,695 [Executor task launch worker for task 507] INFO  Executor - Running task 507.0 in stage 0.0 (TID 507)
 2018-01-30 17:30:34,695 [task-result-getter-3] INFO  TaskSetManager - Finished task 505.0 in stage 0.0 (TID 505) in 9058 ms on localhost (executor driver) (496/3618)
 2018-01-30 17:30:34,698 [Executor task launch worker for task 507] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929231212-00097-crawling113.us.archive.org-6683.warc.gz:0+100661580
 2018-01-30 17:30:35,361 [Executor task launch worker for task 487] INFO  Executor - Finished task 487.0 in stage 0.0 (TID 487). 1902 bytes result sent to driver
 2018-01-30 17:30:35,362 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 508.0 in stage 0.0 (TID 508, localhost, executor driver, partition 508, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:30:35,362 [task-result-getter-0] INFO  TaskSetManager - Finished task 487.0 in stage 0.0 (TID 487) in 96419 ms on localhost (executor driver) (497/3618)
 2018-01-30 17:30:35,362 [Executor task launch worker for task 508] INFO  Executor - Running task 508.0 in stage 0.0 (TID 508)
 2018-01-30 17:30:35,363 [Executor task launch worker for task 508] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004225521292-00017-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+783066
 2018-01-30 17:30:35,468 [Executor task launch worker for task 508] INFO  Executor - Finished task 508.0 in stage 0.0 (TID 508). 1690 bytes result sent to driver
 2018-01-30 17:30:35,468 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 509.0 in stage 0.0 (TID 509, localhost, executor driver, partition 509, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:35,468 [task-result-getter-1] INFO  TaskSetManager - Finished task 508.0 in stage 0.0 (TID 508) in 107 ms on localhost (executor driver) (498/3618)
 2018-01-30 17:30:35,468 [Executor task launch worker for task 509] INFO  Executor - Running task 509.0 in stage 0.0 (TID 509)
 2018-01-30 17:30:35,469 [Executor task launch worker for task 509] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001210523-00075-crawling209.us.archive.org-6681.warc.gz:0+105869842
 2018-01-30 17:30:36,431 [Executor task launch worker for task 489] INFO  Executor - Finished task 489.0 in stage 0.0 (TID 489). 1958 bytes result sent to driver
 2018-01-30 17:30:36,432 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 510.0 in stage 0.0 (TID 510, localhost, executor driver, partition 510, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:30:36,432 [task-result-getter-2] INFO  TaskSetManager - Finished task 489.0 in stage 0.0 (TID 489) in 88660 ms on localhost (executor driver) (499/3618)
 2018-01-30 17:30:36,432 [Executor task launch worker for task 510] INFO  Executor - Running task 510.0 in stage 0.0 (TID 510)
 2018-01-30 17:30:36,434 [Executor task launch worker for task 510] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QAOHFF-20120412231648-00019-crawling201.us.archive.org-6682.warc.gz:0+100835237
 2018-01-30 17:30:39,912 [Executor task launch worker for task 491] INFO  Executor - Finished task 491.0 in stage 0.0 (TID 491). 1958 bytes result sent to driver
 2018-01-30 17:30:39,913 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 511.0 in stage 0.0 (TID 511, localhost, executor driver, partition 511, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:30:39,913 [task-result-getter-3] INFO  TaskSetManager - Finished task 491.0 in stage 0.0 (TID 491) in 80030 ms on localhost (executor driver) (500/3618)
 2018-01-30 17:30:39,914 [Executor task launch worker for task 511] INFO  Executor - Running task 511.0 in stage 0.0 (TID 511)
 2018-01-30 17:30:39,915 [Executor task launch worker for task 511] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224045347388-00012.warc.gz:0+1000054093
 2018-01-30 17:30:40,726 [Executor task launch worker for task 447] INFO  Executor - Finished task 447.0 in stage 0.0 (TID 447). 1767 bytes result sent to driver
 2018-01-30 17:30:40,728 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 512.0 in stage 0.0 (TID 512, localhost, executor driver, partition 512, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:30:40,728 [Executor task launch worker for task 512] INFO  Executor - Running task 512.0 in stage 0.0 (TID 512)
 2018-01-30 17:30:40,728 [task-result-getter-0] INFO  TaskSetManager - Finished task 447.0 in stage 0.0 (TID 447) in 501460 ms on localhost (executor driver) (501/3618)
 2018-01-30 17:30:40,729 [Executor task launch worker for task 512] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB191814-20160115213016200-00000.warc.gz:0+1000005999
 2018-01-30 17:30:44,255 [Executor task launch worker for task 482] INFO  Executor - Finished task 482.0 in stage 0.0 (TID 482). 1759 bytes result sent to driver
 2018-01-30 17:30:44,257 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 513.0 in stage 0.0 (TID 513, localhost, executor driver, partition 513, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:44,257 [Executor task launch worker for task 513] INFO  Executor - Running task 513.0 in stage 0.0 (TID 513)
 2018-01-30 17:30:44,257 [task-result-getter-1] INFO  TaskSetManager - Finished task 482.0 in stage 0.0 (TID 482) in 123256 ms on localhost (executor driver) (502/3618)
 2018-01-30 17:30:44,259 [Executor task launch worker for task 513] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301071503-00077-crawling211.us.archive.org-6682.warc.gz:0+103348044
 2018-01-30 17:30:48,220 [Executor task launch worker for task 509] INFO  Executor - Finished task 509.0 in stage 0.0 (TID 509). 1767 bytes result sent to driver
 2018-01-30 17:30:48,221 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 514.0 in stage 0.0 (TID 514, localhost, executor driver, partition 514, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:48,221 [Executor task launch worker for task 514] INFO  Executor - Running task 514.0 in stage 0.0 (TID 514)
 2018-01-30 17:30:48,221 [task-result-getter-2] INFO  TaskSetManager - Finished task 509.0 in stage 0.0 (TID 509) in 12753 ms on localhost (executor driver) (503/3618)
 2018-01-30 17:30:48,222 [Executor task launch worker for task 514] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929220844-00029-crawling202.us.archive.org-6681.warc.gz:0+100426082
 2018-01-30 17:30:49,919 [Executor task launch worker for task 506] INFO  Executor - Finished task 506.0 in stage 0.0 (TID 506). 1763 bytes result sent to driver
 2018-01-30 17:30:49,920 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 515.0 in stage 0.0 (TID 515, localhost, executor driver, partition 515, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:30:49,920 [Executor task launch worker for task 515] INFO  Executor - Running task 515.0 in stage 0.0 (TID 515)
 2018-01-30 17:30:49,920 [task-result-getter-3] INFO  TaskSetManager - Finished task 506.0 in stage 0.0 (TID 506) in 21874 ms on localhost (executor driver) (504/3618)
 2018-01-30 17:30:49,921 [Executor task launch worker for task 515] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929062558-00056-crawling113.us.archive.org-6683.warc.gz:0+108720208
 2018-01-30 17:30:50,374 [Executor task launch worker for task 513] INFO  Executor - Finished task 513.0 in stage 0.0 (TID 513). 1573 bytes result sent to driver
 2018-01-30 17:30:50,375 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 516.0 in stage 0.0 (TID 516, localhost, executor driver, partition 516, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:30:50,375 [Executor task launch worker for task 516] INFO  Executor - Running task 516.0 in stage 0.0 (TID 516)
 2018-01-30 17:30:50,375 [task-result-getter-0] INFO  TaskSetManager - Finished task 513.0 in stage 0.0 (TID 513) in 6119 ms on localhost (executor driver) (505/3618)
 2018-01-30 17:30:50,376 [Executor task launch worker for task 516] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004231519940-00021-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+4609100
 2018-01-30 17:30:50,765 [Executor task launch worker for task 516] INFO  Executor - Finished task 516.0 in stage 0.0 (TID 516). 1690 bytes result sent to driver
 2018-01-30 17:30:50,766 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 517.0 in stage 0.0 (TID 517, localhost, executor driver, partition 517, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:30:50,766 [Executor task launch worker for task 517] INFO  Executor - Running task 517.0 in stage 0.0 (TID 517)
 2018-01-30 17:30:50,766 [task-result-getter-1] INFO  TaskSetManager - Finished task 516.0 in stage 0.0 (TID 516) in 392 ms on localhost (executor driver) (506/3618)
 2018-01-30 17:30:50,767 [Executor task launch worker for task 517] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171225152028475-00092.warc.gz:0+1000018006
 2018-01-30 17:30:54,903 [Executor task launch worker for task 507] INFO  Executor - Finished task 507.0 in stage 0.0 (TID 507). 1573 bytes result sent to driver
 2018-01-30 17:30:54,904 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 518.0 in stage 0.0 (TID 518, localhost, executor driver, partition 518, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:30:54,904 [Executor task launch worker for task 518] INFO  Executor - Running task 518.0 in stage 0.0 (TID 518)
 2018-01-30 17:30:54,904 [task-result-getter-2] INFO  TaskSetManager - Finished task 507.0 in stage 0.0 (TID 507) in 20210 ms on localhost (executor driver) (507/3618)
 2018-01-30 17:30:54,906 [Executor task launch worker for task 518] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226214714512-00166.warc.gz:0+1000055661
 2018-01-30 17:30:59,745 [Executor task launch worker for task 510] INFO  Executor - Finished task 510.0 in stage 0.0 (TID 510). 1763 bytes result sent to driver
 2018-01-30 17:30:59,746 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 519.0 in stage 0.0 (TID 519, localhost, executor driver, partition 519, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:30:59,747 [Executor task launch worker for task 519] INFO  Executor - Running task 519.0 in stage 0.0 (TID 519)
 2018-01-30 17:30:59,747 [task-result-getter-3] INFO  TaskSetManager - Finished task 510.0 in stage 0.0 (TID 510) in 23316 ms on localhost (executor driver) (508/3618)
 2018-01-30 17:30:59,749 [Executor task launch worker for task 519] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZJUDHD-20110912031443-00047-crawling211.us.archive.org-6681.warc.gz:0+194482954
 2018-01-30 17:31:06,219 [Executor task launch worker for task 514] INFO  Executor - Finished task 514.0 in stage 0.0 (TID 514). 1791 bytes result sent to driver
 2018-01-30 17:31:06,220 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 520.0 in stage 0.0 (TID 520, localhost, executor driver, partition 520, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:31:06,220 [Executor task launch worker for task 520] INFO  Executor - Running task 520.0 in stage 0.0 (TID 520)
 2018-01-30 17:31:06,220 [task-result-getter-0] INFO  TaskSetManager - Finished task 514.0 in stage 0.0 (TID 514) in 17999 ms on localhost (executor driver) (509/3618)
 2018-01-30 17:31:06,222 [Executor task launch worker for task 520] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120628221038-00031-crawling212.us.archive.org-6682.warc.gz:0+364879742
 2018-01-30 17:31:06,899 [Executor task launch worker for task 515] INFO  Executor - Finished task 515.0 in stage 0.0 (TID 515). 1573 bytes result sent to driver
 2018-01-30 17:31:06,900 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 521.0 in stage 0.0 (TID 521, localhost, executor driver, partition 521, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:31:06,900 [Executor task launch worker for task 521] INFO  Executor - Running task 521.0 in stage 0.0 (TID 521)
 2018-01-30 17:31:06,900 [task-result-getter-1] INFO  TaskSetManager - Finished task 515.0 in stage 0.0 (TID 515) in 16981 ms on localhost (executor driver) (510/3618)
 2018-01-30 17:31:06,901 [Executor task launch worker for task 521] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-SZGJAW-20120914160818-00016-crawling203.us.archive.org-6682.warc.gz:0+100001160
 2018-01-30 17:31:14,475 [Executor task launch worker for task 481] INFO  Executor - Finished task 481.0 in stage 0.0 (TID 481). 3063 bytes result sent to driver
 2018-01-30 17:31:14,476 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 522.0 in stage 0.0 (TID 522, localhost, executor driver, partition 522, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:31:14,476 [Executor task launch worker for task 522] INFO  Executor - Running task 522.0 in stage 0.0 (TID 522)
 2018-01-30 17:31:14,476 [task-result-getter-2] INFO  TaskSetManager - Finished task 481.0 in stage 0.0 (TID 481) in 153653 ms on localhost (executor driver) (511/3618)
 2018-01-30 17:31:14,477 [Executor task launch worker for task 522] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301090721-00104-crawling211.us.archive.org-6682.warc.gz:0+100016276
 2018-01-30 17:31:15,176 [Executor task launch worker for task 500] INFO  Executor - Finished task 500.0 in stage 0.0 (TID 500). 2060 bytes result sent to driver
 2018-01-30 17:31:15,176 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 523.0 in stage 0.0 (TID 523, localhost, executor driver, partition 523, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:31:15,176 [Executor task launch worker for task 523] INFO  Executor - Running task 523.0 in stage 0.0 (TID 523)
 2018-01-30 17:31:15,177 [task-result-getter-3] INFO  TaskSetManager - Finished task 500.0 in stage 0.0 (TID 500) in 83991 ms on localhost (executor driver) (512/3618)
 2018-01-30 17:31:15,177 [Executor task launch worker for task 523] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FRYBJH-20111008210737-00041-crawling208.us.archive.org-6683.warc.gz:0+102926698
 2018-01-30 17:31:19,053 [Executor task launch worker for task 521] INFO  Executor - Finished task 521.0 in stage 0.0 (TID 521). 1759 bytes result sent to driver
 2018-01-30 17:31:19,053 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 524.0 in stage 0.0 (TID 524, localhost, executor driver, partition 524, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:31:19,053 [Executor task launch worker for task 524] INFO  Executor - Running task 524.0 in stage 0.0 (TID 524)
 2018-01-30 17:31:19,054 [task-result-getter-0] INFO  TaskSetManager - Finished task 521.0 in stage 0.0 (TID 521) in 12154 ms on localhost (executor driver) (513/3618)
 2018-01-30 17:31:19,054 [Executor task launch worker for task 524] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-SZGJAW-20120912222441-00001-crawling203.us.archive.org-6682.warc.gz:0+105117766
 2018-01-30 17:31:23,084 [Executor task launch worker for task 522] INFO  Executor - Finished task 522.0 in stage 0.0 (TID 522). 1573 bytes result sent to driver
 2018-01-30 17:31:23,087 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 525.0 in stage 0.0 (TID 525, localhost, executor driver, partition 525, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:31:23,088 [Executor task launch worker for task 525] INFO  Executor - Running task 525.0 in stage 0.0 (TID 525)
 2018-01-30 17:31:23,088 [task-result-getter-1] INFO  TaskSetManager - Finished task 522.0 in stage 0.0 (TID 522) in 8613 ms on localhost (executor driver) (514/3618)
 2018-01-30 17:31:23,090 [Executor task launch worker for task 525] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003084550-00557-crawling209.us.archive.org-6681.warc.gz:0+101816248
 2018-01-30 17:31:25,026 [Executor task launch worker for task 499] INFO  Executor - Finished task 499.0 in stage 0.0 (TID 499). 2129 bytes result sent to driver
 2018-01-30 17:31:25,027 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 526.0 in stage 0.0 (TID 526, localhost, executor driver, partition 526, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:31:25,027 [Executor task launch worker for task 526] INFO  Executor - Running task 526.0 in stage 0.0 (TID 526)
 2018-01-30 17:31:25,027 [task-result-getter-2] INFO  TaskSetManager - Finished task 499.0 in stage 0.0 (TID 499) in 97075 ms on localhost (executor driver) (515/3618)
 2018-01-30 17:31:25,028 [Executor task launch worker for task 526] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB166244-20150727153036910-00022.warc.gz:0+1008131246
 2018-01-30 17:31:32,557 [Executor task launch worker for task 523] INFO  Executor - Finished task 523.0 in stage 0.0 (TID 523). 1573 bytes result sent to driver
 2018-01-30 17:31:32,557 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 527.0 in stage 0.0 (TID 527, localhost, executor driver, partition 527, PROCESS_LOCAL, 19553 bytes)
 2018-01-30 17:31:32,558 [task-result-getter-3] INFO  TaskSetManager - Finished task 523.0 in stage 0.0 (TID 523) in 17382 ms on localhost (executor driver) (516/3618)
 2018-01-30 17:31:32,558 [Executor task launch worker for task 527] INFO  Executor - Running task 527.0 in stage 0.0 (TID 527)
 2018-01-30 17:31:32,560 [Executor task launch worker for task 527] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-3872-20131030193203791-00002-wbgrp-crawl050.us.archive.org-6444.warc.gz:0+71513760
 2018-01-30 17:31:33,083 [Executor task launch worker for task 525] INFO  Executor - Finished task 525.0 in stage 0.0 (TID 525). 1759 bytes result sent to driver
 2018-01-30 17:31:33,083 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 528.0 in stage 0.0 (TID 528, localhost, executor driver, partition 528, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:31:33,083 [Executor task launch worker for task 528] INFO  Executor - Running task 528.0 in stage 0.0 (TID 528)
 2018-01-30 17:31:33,084 [task-result-getter-0] INFO  TaskSetManager - Finished task 525.0 in stage 0.0 (TID 525) in 9997 ms on localhost (executor driver) (517/3618)
 2018-01-30 17:31:33,085 [Executor task launch worker for task 528] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226183336704-00158.warc.gz:0+1000038743
 2018-01-30 17:31:35,501 [Executor task launch worker for task 524] INFO  Executor - Finished task 524.0 in stage 0.0 (TID 524). 1855 bytes result sent to driver
 2018-01-30 17:31:35,502 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 529.0 in stage 0.0 (TID 529, localhost, executor driver, partition 529, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:31:35,502 [Executor task launch worker for task 529] INFO  Executor - Running task 529.0 in stage 0.0 (TID 529)
 2018-01-30 17:31:35,502 [task-result-getter-1] INFO  TaskSetManager - Finished task 524.0 in stage 0.0 (TID 524) in 16449 ms on localhost (executor driver) (518/3618)
 2018-01-30 17:31:35,503 [Executor task launch worker for task 529] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-KNGFRC-20120619182856-00000-crawling208.us.archive.org-6683.warc.gz:0+1849732
 2018-01-30 17:31:35,799 [Executor task launch worker for task 529] INFO  Executor - Finished task 529.0 in stage 0.0 (TID 529). 1690 bytes result sent to driver
 2018-01-30 17:31:35,800 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 530.0 in stage 0.0 (TID 530, localhost, executor driver, partition 530, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:31:35,800 [Executor task launch worker for task 530] INFO  Executor - Running task 530.0 in stage 0.0 (TID 530)
 2018-01-30 17:31:35,800 [task-result-getter-2] INFO  TaskSetManager - Finished task 529.0 in stage 0.0 (TID 529) in 299 ms on localhost (executor driver) (519/3618)
 2018-01-30 17:31:35,801 [Executor task launch worker for task 530] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111001130301-00014-crawling209.us.archive.org-6681.warc.gz:0+100004625
 2018-01-30 17:31:38,220 [Executor task launch worker for task 504] INFO  Executor - Finished task 504.0 in stage 0.0 (TID 504). 2089 bytes result sent to driver
 2018-01-30 17:31:38,220 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 531.0 in stage 0.0 (TID 531, localhost, executor driver, partition 531, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:31:38,220 [Executor task launch worker for task 531] INFO  Executor - Running task 531.0 in stage 0.0 (TID 531)
 2018-01-30 17:31:38,220 [task-result-getter-3] INFO  TaskSetManager - Finished task 504.0 in stage 0.0 (TID 504) in 89740 ms on localhost (executor driver) (520/3618)
 2018-01-30 17:31:38,221 [Executor task launch worker for task 531] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629152812-00072-crawling212.us.archive.org-6682.warc.gz:0+111888179
 2018-01-30 17:31:40,424 [Executor task launch worker for task 519] INFO  Executor - Finished task 519.0 in stage 0.0 (TID 519). 1573 bytes result sent to driver
 2018-01-30 17:31:40,425 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 532.0 in stage 0.0 (TID 532, localhost, executor driver, partition 532, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:31:40,425 [Executor task launch worker for task 532] INFO  Executor - Running task 532.0 in stage 0.0 (TID 532)
 2018-01-30 17:31:40,426 [Executor task launch worker for task 532] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB317509-20170727030125419-00000.warc.gz:0+1040763135
 2018-01-30 17:31:40,430 [task-result-getter-0] INFO  TaskSetManager - Finished task 519.0 in stage 0.0 (TID 519) in 40684 ms on localhost (executor driver) (521/3618)
 2018-01-30 17:31:50,668 [Executor task launch worker for task 527] INFO  Executor - Finished task 527.0 in stage 0.0 (TID 527). 1759 bytes result sent to driver
 2018-01-30 17:31:50,668 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 533.0 in stage 0.0 (TID 533, localhost, executor driver, partition 533, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:31:50,668 [Executor task launch worker for task 533] INFO  Executor - Running task 533.0 in stage 0.0 (TID 533)
 2018-01-30 17:31:50,668 [task-result-getter-1] INFO  TaskSetManager - Finished task 527.0 in stage 0.0 (TID 527) in 18111 ms on localhost (executor driver) (522/3618)
 2018-01-30 17:31:50,669 [Executor task launch worker for task 533] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-12892-20140905213019934-00000-wbgrp-tmphdp06.us.archive.org-6441.warc.gz:0+182897799
 2018-01-30 17:31:55,991 [Executor task launch worker for task 530] INFO  Executor - Finished task 530.0 in stage 0.0 (TID 530). 1779 bytes result sent to driver
 2018-01-30 17:31:55,991 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 534.0 in stage 0.0 (TID 534, localhost, executor driver, partition 534, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:31:55,992 [Executor task launch worker for task 534] INFO  Executor - Running task 534.0 in stage 0.0 (TID 534)
 2018-01-30 17:31:55,992 [task-result-getter-2] INFO  TaskSetManager - Finished task 530.0 in stage 0.0 (TID 530) in 20193 ms on localhost (executor driver) (523/3618)
 2018-01-30 17:31:55,993 [Executor task launch worker for task 534] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226232502420-00170.warc.gz:0+299310343
 2018-01-30 17:32:00,987 [Executor task launch worker for task 531] INFO  Executor - Finished task 531.0 in stage 0.0 (TID 531). 1573 bytes result sent to driver
 2018-01-30 17:32:00,988 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 535.0 in stage 0.0 (TID 535, localhost, executor driver, partition 535, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:32:00,988 [Executor task launch worker for task 535] INFO  Executor - Running task 535.0 in stage 0.0 (TID 535)
 2018-01-30 17:32:00,988 [task-result-getter-3] INFO  TaskSetManager - Finished task 531.0 in stage 0.0 (TID 531) in 22768 ms on localhost (executor driver) (524/3618)
 2018-01-30 17:32:00,989 [Executor task launch worker for task 535] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170926190759836-00122.warc.gz:0+164948771
 2018-01-30 17:32:05,081 [Executor task launch worker for task 520] INFO  Executor - Finished task 520.0 in stage 0.0 (TID 520). 1573 bytes result sent to driver
 2018-01-30 17:32:05,081 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 536.0 in stage 0.0 (TID 536, localhost, executor driver, partition 536, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:32:05,082 [Executor task launch worker for task 536] INFO  Executor - Running task 536.0 in stage 0.0 (TID 536)
 2018-01-30 17:32:05,082 [task-result-getter-0] INFO  TaskSetManager - Finished task 520.0 in stage 0.0 (TID 520) in 58863 ms on localhost (executor driver) (525/3618)
 2018-01-30 17:32:05,083 [Executor task launch worker for task 536] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB193236-20160128214321161-00010.warc.gz:0+1001978887
 2018-01-30 17:32:07,491 [Executor task launch worker for task 533] INFO  Executor - Finished task 533.0 in stage 0.0 (TID 533). 1843 bytes result sent to driver
 2018-01-30 17:32:07,491 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 537.0 in stage 0.0 (TID 537, localhost, executor driver, partition 537, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:32:07,491 [Executor task launch worker for task 537] INFO  Executor - Running task 537.0 in stage 0.0 (TID 537)
 2018-01-30 17:32:07,491 [task-result-getter-1] INFO  TaskSetManager - Finished task 533.0 in stage 0.0 (TID 533) in 16823 ms on localhost (executor driver) (526/3618)
 2018-01-30 17:32:07,493 [Executor task launch worker for task 537] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224163225494-00039.warc.gz:0+1000056838
 2018-01-30 17:32:14,667 [Executor task launch worker for task 511] INFO  Executor - Finished task 511.0 in stage 0.0 (TID 511). 1835 bytes result sent to driver
 2018-01-30 17:32:14,668 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 538.0 in stage 0.0 (TID 538, localhost, executor driver, partition 538, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:32:14,668 [Executor task launch worker for task 538] INFO  Executor - Running task 538.0 in stage 0.0 (TID 538)
 2018-01-30 17:32:14,668 [task-result-getter-2] INFO  TaskSetManager - Finished task 511.0 in stage 0.0 (TID 511) in 94756 ms on localhost (executor driver) (527/3618)
 2018-01-30 17:32:14,669 [Executor task launch worker for task 538] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-QDPLNZ-20120713150818-00012-crawling105.us.archive.org-6681.warc.gz:0+226183796
 2018-01-30 17:32:15,923 [Executor task launch worker for task 535] INFO  Executor - Finished task 535.0 in stage 0.0 (TID 535). 1962 bytes result sent to driver
 2018-01-30 17:32:15,924 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 539.0 in stage 0.0 (TID 539, localhost, executor driver, partition 539, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:32:15,924 [Executor task launch worker for task 539] INFO  Executor - Running task 539.0 in stage 0.0 (TID 539)
 2018-01-30 17:32:15,924 [task-result-getter-3] INFO  TaskSetManager - Finished task 535.0 in stage 0.0 (TID 535) in 14937 ms on localhost (executor driver) (528/3618)
 2018-01-30 17:32:15,925 [Executor task launch worker for task 539] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-DXOVPL-20120327185815-00000-crawling207.us.archive.org-6680.warc.gz:0+100153656
 2018-01-30 17:32:24,166 [Executor task launch worker for task 534] INFO  Executor - Finished task 534.0 in stage 0.0 (TID 534). 1835 bytes result sent to driver
 2018-01-30 17:32:24,167 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 540.0 in stage 0.0 (TID 540, localhost, executor driver, partition 540, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:32:24,167 [Executor task launch worker for task 540] INFO  Executor - Running task 540.0 in stage 0.0 (TID 540)
 2018-01-30 17:32:24,167 [task-result-getter-0] INFO  TaskSetManager - Finished task 534.0 in stage 0.0 (TID 534) in 28176 ms on localhost (executor driver) (529/3618)
 2018-01-30 17:32:24,168 [Executor task launch worker for task 540] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925051402982-00059.warc.gz:0+1000075622
 2018-01-30 17:32:25,665 [Executor task launch worker for task 539] INFO  Executor - Finished task 539.0 in stage 0.0 (TID 539). 1767 bytes result sent to driver
 2018-01-30 17:32:25,666 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 541.0 in stage 0.0 (TID 541, localhost, executor driver, partition 541, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:32:25,666 [Executor task launch worker for task 541] INFO  Executor - Running task 541.0 in stage 0.0 (TID 541)
 2018-01-30 17:32:25,666 [task-result-getter-1] INFO  TaskSetManager - Finished task 539.0 in stage 0.0 (TID 539) in 9743 ms on localhost (executor driver) (530/3618)
 2018-01-30 17:32:25,667 [Executor task launch worker for task 541] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120929150510-00080-crawling113.us.archive.org-6683.warc.gz:0+105285232
 2018-01-30 17:32:27,620 [Executor task launch worker for task 517] INFO  Executor - Finished task 517.0 in stage 0.0 (TID 517). 1986 bytes result sent to driver
 2018-01-30 17:32:27,621 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 542.0 in stage 0.0 (TID 542, localhost, executor driver, partition 542, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:32:27,621 [Executor task launch worker for task 542] INFO  Executor - Running task 542.0 in stage 0.0 (TID 542)
 2018-01-30 17:32:27,621 [task-result-getter-2] INFO  TaskSetManager - Finished task 517.0 in stage 0.0 (TID 517) in 96856 ms on localhost (executor driver) (531/3618)
 2018-01-30 17:32:27,622 [Executor task launch worker for task 542] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB178983-20151016213251768-00000.warc.gz:0+1000001572
 2018-01-30 17:32:32,258 [Executor task launch worker for task 518] INFO  Executor - Finished task 518.0 in stage 0.0 (TID 518). 1835 bytes result sent to driver
 2018-01-30 17:32:32,259 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 543.0 in stage 0.0 (TID 543, localhost, executor driver, partition 543, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:32:32,259 [Executor task launch worker for task 543] INFO  Executor - Running task 543.0 in stage 0.0 (TID 543)
 2018-01-30 17:32:32,260 [task-result-getter-3] INFO  TaskSetManager - Finished task 518.0 in stage 0.0 (TID 518) in 97356 ms on localhost (executor driver) (532/3618)
 2018-01-30 17:32:32,261 [Executor task launch worker for task 543] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929211632-00008-crawling202.us.archive.org-6681.warc.gz:0+120561964
 2018-01-30 17:32:35,409 [Executor task launch worker for task 512] INFO  Executor - Finished task 512.0 in stage 0.0 (TID 512). 1922 bytes result sent to driver
 2018-01-30 17:32:35,410 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 544.0 in stage 0.0 (TID 544, localhost, executor driver, partition 544, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:32:35,410 [Executor task launch worker for task 544] INFO  Executor - Running task 544.0 in stage 0.0 (TID 544)
 2018-01-30 17:32:35,410 [task-result-getter-0] INFO  TaskSetManager - Finished task 512.0 in stage 0.0 (TID 512) in 114683 ms on localhost (executor driver) (533/3618)
 2018-01-30 17:32:35,411 [Executor task launch worker for task 544] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002003130-00125-crawling209.us.archive.org-6681.warc.gz:0+103069512
 2018-01-30 17:32:43,670 [Executor task launch worker for task 544] INFO  Executor - Finished task 544.0 in stage 0.0 (TID 544). 1767 bytes result sent to driver
 2018-01-30 17:32:43,671 [dispatcher-event-loop-6] INFO  TaskSetManager - Starting task 545.0 in stage 0.0 (TID 545, localhost, executor driver, partition 545, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:32:43,671 [Executor task launch worker for task 545] INFO  Executor - Running task 545.0 in stage 0.0 (TID 545)
 2018-01-30 17:32:43,672 [task-result-getter-1] INFO  TaskSetManager - Finished task 544.0 in stage 0.0 (TID 544) in 8262 ms on localhost (executor driver) (534/3618)
 2018-01-30 17:32:43,673 [Executor task launch worker for task 545] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930090631-00134-crawling202.us.archive.org-6681.warc.gz:0+116121801
 2018-01-30 17:32:49,659 [Executor task launch worker for task 541] INFO  Executor - Finished task 541.0 in stage 0.0 (TID 541). 1573 bytes result sent to driver
 2018-01-30 17:32:49,660 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 546.0 in stage 0.0 (TID 546, localhost, executor driver, partition 546, PROCESS_LOCAL, 19523 bytes)
 2018-01-30 17:32:49,660 [task-result-getter-2] INFO  TaskSetManager - Finished task 541.0 in stage 0.0 (TID 541) in 23995 ms on localhost (executor driver) (535/3618)
 2018-01-30 17:32:49,660 [Executor task launch worker for task 546] INFO  Executor - Running task 546.0 in stage 0.0 (TID 546)
 2018-01-30 17:32:49,661 [Executor task launch worker for task 546] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-TEST-JOB225704-20160716073132463-00001.warc.gz:0+781796611
 2018-01-30 17:33:04,560 [Executor task launch worker for task 528] INFO  Executor - Finished task 528.0 in stage 0.0 (TID 528). 1835 bytes result sent to driver
 2018-01-30 17:33:04,561 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 547.0 in stage 0.0 (TID 547, localhost, executor driver, partition 547, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:33:04,561 [Executor task launch worker for task 547] INFO  Executor - Running task 547.0 in stage 0.0 (TID 547)
 2018-01-30 17:33:04,562 [task-result-getter-3] INFO  TaskSetManager - Finished task 528.0 in stage 0.0 (TID 528) in 91479 ms on localhost (executor driver) (536/3618)
 2018-01-30 17:33:04,564 [Executor task launch worker for task 547] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121013040423-00010-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+168130191
 2018-01-30 17:33:05,162 [Executor task launch worker for task 543] INFO  Executor - Finished task 543.0 in stage 0.0 (TID 543). 1799 bytes result sent to driver
 2018-01-30 17:33:05,163 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 548.0 in stage 0.0 (TID 548, localhost, executor driver, partition 548, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:33:05,163 [Executor task launch worker for task 548] INFO  Executor - Running task 548.0 in stage 0.0 (TID 548)
 2018-01-30 17:33:05,163 [task-result-getter-0] INFO  TaskSetManager - Finished task 543.0 in stage 0.0 (TID 543) in 32904 ms on localhost (executor driver) (537/3618)
 2018-01-30 17:33:05,164 [Executor task launch worker for task 548] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002134928-00351-crawling209.us.archive.org-6681.warc.gz:0+100522102
 2018-01-30 17:33:13,007 [Executor task launch worker for task 538] INFO  Executor - Finished task 538.0 in stage 0.0 (TID 538). 1763 bytes result sent to driver
 2018-01-30 17:33:13,007 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 549.0 in stage 0.0 (TID 549, localhost, executor driver, partition 549, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:33:13,008 [Executor task launch worker for task 549] INFO  Executor - Running task 549.0 in stage 0.0 (TID 549)
 2018-01-30 17:33:13,008 [task-result-getter-1] INFO  TaskSetManager - Finished task 538.0 in stage 0.0 (TID 538) in 58340 ms on localhost (executor driver) (538/3618)
 2018-01-30 17:33:13,009 [Executor task launch worker for task 549] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB163106-20150703213014976-00000.warc.gz:0+292441047
 2018-01-30 17:33:18,212 [Executor task launch worker for task 545] INFO  Executor - Finished task 545.0 in stage 0.0 (TID 545). 1795 bytes result sent to driver
 2018-01-30 17:33:18,213 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 550.0 in stage 0.0 (TID 550, localhost, executor driver, partition 550, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:33:18,213 [Executor task launch worker for task 550] INFO  Executor - Running task 550.0 in stage 0.0 (TID 550)
 2018-01-30 17:33:18,214 [task-result-getter-2] INFO  TaskSetManager - Finished task 545.0 in stage 0.0 (TID 545) in 34544 ms on localhost (executor driver) (539/3618)
 2018-01-30 17:33:18,215 [Executor task launch worker for task 550] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-BLTYFO-20120202225934-00000-crawling208.us.archive.org-6681.warc.gz:0+6119460
 2018-01-30 17:33:19,234 [Executor task launch worker for task 550] INFO  Executor - Finished task 550.0 in stage 0.0 (TID 550). 1690 bytes result sent to driver
 2018-01-30 17:33:19,235 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 551.0 in stage 0.0 (TID 551, localhost, executor driver, partition 551, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:33:19,235 [Executor task launch worker for task 551] INFO  Executor - Running task 551.0 in stage 0.0 (TID 551)
 2018-01-30 17:33:19,235 [task-result-getter-3] INFO  TaskSetManager - Finished task 550.0 in stage 0.0 (TID 550) in 1022 ms on localhost (executor driver) (540/3618)
 2018-01-30 17:33:19,236 [Executor task launch worker for task 551] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171026011001472-00092.warc.gz:0+1000055651
 2018-01-30 17:33:29,933 [Executor task launch worker for task 548] INFO  Executor - Finished task 548.0 in stage 0.0 (TID 548). 1850 bytes result sent to driver
 2018-01-30 17:33:29,934 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 552.0 in stage 0.0 (TID 552, localhost, executor driver, partition 552, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:33:29,935 [task-result-getter-0] INFO  TaskSetManager - Finished task 548.0 in stage 0.0 (TID 548) in 24771 ms on localhost (executor driver) (541/3618)
 2018-01-30 17:33:29,936 [Executor task launch worker for task 552] INFO  Executor - Running task 552.0 in stage 0.0 (TID 552)
 2018-01-30 17:33:30,074 [Executor task launch worker for task 552] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629215913-00097-crawling212.us.archive.org-6682.warc.gz:0+135697595
 2018-01-30 17:33:35,229 [Executor task launch worker for task 537] INFO  Executor - Finished task 537.0 in stage 0.0 (TID 537). 2409 bytes result sent to driver
 2018-01-30 17:33:35,230 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 553.0 in stage 0.0 (TID 553, localhost, executor driver, partition 553, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:33:35,230 [Executor task launch worker for task 553] INFO  Executor - Running task 553.0 in stage 0.0 (TID 553)
 2018-01-30 17:33:35,231 [task-result-getter-1] INFO  TaskSetManager - Finished task 537.0 in stage 0.0 (TID 537) in 87740 ms on localhost (executor driver) (542/3618)
 2018-01-30 17:33:35,232 [Executor task launch worker for task 553] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB258797-20170107002117484-00000.warc.gz:0+38293692
 2018-01-30 17:33:40,074 [Executor task launch worker for task 553] INFO  Executor - Finished task 553.0 in stage 0.0 (TID 553). 1807 bytes result sent to driver
 2018-01-30 17:33:40,075 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 554.0 in stage 0.0 (TID 554, localhost, executor driver, partition 554, PROCESS_LOCAL, 19555 bytes)
 2018-01-30 17:33:40,075 [Executor task launch worker for task 554] INFO  Executor - Running task 554.0 in stage 0.0 (TID 554)
 2018-01-30 17:33:40,075 [task-result-getter-2] INFO  TaskSetManager - Finished task 553.0 in stage 0.0 (TID 553) in 4846 ms on localhost (executor driver) (543/3618)
 2018-01-30 17:33:40,078 [Executor task launch worker for task 554] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-PBLTCT-20121012213143-00005-wbgrp-crawl063.us.archive.org-6683.warc.gz:0+117233125
 2018-01-30 17:33:48,094 [Executor task launch worker for task 549] INFO  Executor - Finished task 549.0 in stage 0.0 (TID 549). 1871 bytes result sent to driver
 2018-01-30 17:33:48,096 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 555.0 in stage 0.0 (TID 555, localhost, executor driver, partition 555, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:33:48,096 [Executor task launch worker for task 555] INFO  Executor - Running task 555.0 in stage 0.0 (TID 555)
 2018-01-30 17:33:48,096 [task-result-getter-3] INFO  TaskSetManager - Finished task 549.0 in stage 0.0 (TID 549) in 35089 ms on localhost (executor driver) (544/3618)
 2018-01-30 17:33:48,098 [Executor task launch worker for task 555] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-XUQFKQ-20120930110537-00110-crawling113.us.archive.org-6683.warc.gz:0+103540476
 2018-01-30 17:33:49,077 [Executor task launch worker for task 540] INFO  Executor - Finished task 540.0 in stage 0.0 (TID 540). 1985 bytes result sent to driver
 2018-01-30 17:33:49,078 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 556.0 in stage 0.0 (TID 556, localhost, executor driver, partition 556, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:33:49,078 [Executor task launch worker for task 556] INFO  Executor - Running task 556.0 in stage 0.0 (TID 556)
 2018-01-30 17:33:49,078 [task-result-getter-0] INFO  TaskSetManager - Finished task 540.0 in stage 0.0 (TID 540) in 84912 ms on localhost (executor driver) (545/3618)
 2018-01-30 17:33:49,079 [Executor task launch worker for task 556] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024051230738-00018.warc.gz:0+1000061390
 2018-01-30 17:33:50,033 [Executor task launch worker for task 547] INFO  Executor - Finished task 547.0 in stage 0.0 (TID 547). 1759 bytes result sent to driver
 2018-01-30 17:33:50,034 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 557.0 in stage 0.0 (TID 557, localhost, executor driver, partition 557, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:33:50,034 [task-result-getter-1] INFO  TaskSetManager - Finished task 547.0 in stage 0.0 (TID 547) in 45474 ms on localhost (executor driver) (546/3618)
 2018-01-30 17:33:50,035 [Executor task launch worker for task 557] INFO  Executor - Running task 557.0 in stage 0.0 (TID 557)
 2018-01-30 17:33:50,036 [Executor task launch worker for task 557] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003084139-00556-crawling209.us.archive.org-6681.warc.gz:0+103124574
 2018-01-30 17:33:56,887 [Executor task launch worker for task 555] INFO  Executor - Finished task 555.0 in stage 0.0 (TID 555). 1573 bytes result sent to driver
 2018-01-30 17:33:56,889 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 558.0 in stage 0.0 (TID 558, localhost, executor driver, partition 558, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:33:56,889 [Executor task launch worker for task 558] INFO  Executor - Running task 558.0 in stage 0.0 (TID 558)
 2018-01-30 17:33:56,889 [task-result-getter-2] INFO  TaskSetManager - Finished task 555.0 in stage 0.0 (TID 555) in 8794 ms on localhost (executor driver) (547/3618)
 2018-01-30 17:33:56,892 [Executor task launch worker for task 558] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003125438-00615-crawling209.us.archive.org-6681.warc.gz:0+106871254
 2018-01-30 17:34:05,254 [Executor task launch worker for task 558] INFO  Executor - Finished task 558.0 in stage 0.0 (TID 558). 1759 bytes result sent to driver
 2018-01-30 17:34:05,255 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 559.0 in stage 0.0 (TID 559, localhost, executor driver, partition 559, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:05,255 [Executor task launch worker for task 559] INFO  Executor - Running task 559.0 in stage 0.0 (TID 559)
 2018-01-30 17:34:05,255 [task-result-getter-3] INFO  TaskSetManager - Finished task 558.0 in stage 0.0 (TID 558) in 8367 ms on localhost (executor driver) (548/3618)
 2018-01-30 17:34:05,257 [Executor task launch worker for task 559] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006080224-00041-crawling205.us.archive.org-6681.warc.gz:0+110234136
 2018-01-30 17:34:06,210 [Executor task launch worker for task 552] INFO  Executor - Finished task 552.0 in stage 0.0 (TID 552). 1573 bytes result sent to driver
 2018-01-30 17:34:06,211 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 560.0 in stage 0.0 (TID 560, localhost, executor driver, partition 560, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:06,211 [Executor task launch worker for task 560] INFO  Executor - Running task 560.0 in stage 0.0 (TID 560)
 2018-01-30 17:34:06,211 [task-result-getter-0] INFO  TaskSetManager - Finished task 552.0 in stage 0.0 (TID 552) in 36278 ms on localhost (executor driver) (549/3618)
 2018-01-30 17:34:06,212 [Executor task launch worker for task 560] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301145347-00194-crawling211.us.archive.org-6682.warc.gz:0+105721504
 2018-01-30 17:34:08,165 [Executor task launch worker for task 554] INFO  Executor - Finished task 554.0 in stage 0.0 (TID 554). 1807 bytes result sent to driver
 2018-01-30 17:34:08,167 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 561.0 in stage 0.0 (TID 561, localhost, executor driver, partition 561, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:34:08,167 [Executor task launch worker for task 561] INFO  Executor - Running task 561.0 in stage 0.0 (TID 561)
 2018-01-30 17:34:08,167 [task-result-getter-1] INFO  TaskSetManager - Finished task 554.0 in stage 0.0 (TID 554) in 28092 ms on localhost (executor driver) (550/3618)
 2018-01-30 17:34:08,169 [Executor task launch worker for task 561] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171024184741236-00043.warc.gz:0+1000053304
 2018-01-30 17:34:11,116 [Executor task launch worker for task 560] INFO  Executor - Finished task 560.0 in stage 0.0 (TID 560). 1587 bytes result sent to driver
 2018-01-30 17:34:11,118 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 562.0 in stage 0.0 (TID 562, localhost, executor driver, partition 562, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:34:11,118 [Executor task launch worker for task 562] INFO  Executor - Running task 562.0 in stage 0.0 (TID 562)
 2018-01-30 17:34:11,118 [task-result-getter-2] INFO  TaskSetManager - Finished task 560.0 in stage 0.0 (TID 560) in 4908 ms on localhost (executor driver) (551/3618)
 2018-01-30 17:34:11,121 [Executor task launch worker for task 562] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB454374-20170925172000647-00079.warc.gz:0+1000081732
 2018-01-30 17:34:15,447 [Executor task launch worker for task 557] INFO  Executor - Finished task 557.0 in stage 0.0 (TID 557). 1759 bytes result sent to driver
 2018-01-30 17:34:15,447 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 563.0 in stage 0.0 (TID 563, localhost, executor driver, partition 563, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:15,447 [Executor task launch worker for task 563] INFO  Executor - Running task 563.0 in stage 0.0 (TID 563)
 2018-01-30 17:34:15,447 [task-result-getter-3] INFO  TaskSetManager - Finished task 557.0 in stage 0.0 (TID 557) in 25414 ms on localhost (executor driver) (552/3618)
 2018-01-30 17:34:15,449 [Executor task launch worker for task 563] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930155500-00204-crawling202.us.archive.org-6681.warc.gz:0+100028434
 2018-01-30 17:34:22,679 [Executor task launch worker for task 542] INFO  Executor - Finished task 542.0 in stage 0.0 (TID 542). 1969 bytes result sent to driver
 2018-01-30 17:34:22,681 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 564.0 in stage 0.0 (TID 564, localhost, executor driver, partition 564, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:22,681 [task-result-getter-0] INFO  TaskSetManager - Finished task 542.0 in stage 0.0 (TID 542) in 115060 ms on localhost (executor driver) (553/3618)
 2018-01-30 17:34:22,681 [Executor task launch worker for task 564] INFO  Executor - Running task 564.0 in stage 0.0 (TID 564)
 2018-01-30 17:34:22,685 [Executor task launch worker for task 564] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-ZTNWHO-20120406012804-00007-crawling200.us.archive.org-6682.warc.gz:0+105882890
 2018-01-30 17:34:37,745 [Executor task launch worker for task 559] INFO  Executor - Finished task 559.0 in stage 0.0 (TID 559). 1660 bytes result sent to driver
 2018-01-30 17:34:37,746 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 565.0 in stage 0.0 (TID 565, localhost, executor driver, partition 565, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:34:37,746 [Executor task launch worker for task 565] INFO  Executor - Running task 565.0 in stage 0.0 (TID 565)
 2018-01-30 17:34:37,747 [task-result-getter-1] INFO  TaskSetManager - Finished task 559.0 in stage 0.0 (TID 559) in 32493 ms on localhost (executor driver) (554/3618)
 2018-01-30 17:34:37,749 [Executor task launch worker for task 565] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB263594-20170127064514486-00003.warc.gz:0+1000005207
 2018-01-30 17:34:38,286 [Executor task launch worker for task 563] INFO  Executor - Finished task 563.0 in stage 0.0 (TID 563). 1803 bytes result sent to driver
 2018-01-30 17:34:38,287 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 566.0 in stage 0.0 (TID 566, localhost, executor driver, partition 566, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:38,287 [Executor task launch worker for task 566] INFO  Executor - Running task 566.0 in stage 0.0 (TID 566)
 2018-01-30 17:34:38,287 [task-result-getter-2] INFO  TaskSetManager - Finished task 563.0 in stage 0.0 (TID 563) in 22840 ms on localhost (executor driver) (555/3618)
 2018-01-30 17:34:38,288 [Executor task launch worker for task 566] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002152940-00373-crawling209.us.archive.org-6681.warc.gz:0+103191320
 2018-01-30 17:34:40,367 [Executor task launch worker for task 551] INFO  Executor - Finished task 551.0 in stage 0.0 (TID 551). 1969 bytes result sent to driver
 2018-01-30 17:34:40,368 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 567.0 in stage 0.0 (TID 567, localhost, executor driver, partition 567, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:34:40,368 [Executor task launch worker for task 567] INFO  Executor - Running task 567.0 in stage 0.0 (TID 567)
 2018-01-30 17:34:40,369 [task-result-getter-3] INFO  TaskSetManager - Finished task 551.0 in stage 0.0 (TID 551) in 81134 ms on localhost (executor driver) (556/3618)
 2018-01-30 17:34:40,370 [Executor task launch worker for task 567] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629093825-00052-crawling212.us.archive.org-6682.warc.gz:0+103014179
 2018-01-30 17:34:49,262 [Executor task launch worker for task 566] INFO  Executor - Finished task 566.0 in stage 0.0 (TID 566). 1850 bytes result sent to driver
 2018-01-30 17:34:49,264 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 568.0 in stage 0.0 (TID 568, localhost, executor driver, partition 568, PROCESS_LOCAL, 19551 bytes)
 2018-01-30 17:34:49,264 [Executor task launch worker for task 568] INFO  Executor - Running task 568.0 in stage 0.0 (TID 568)
 2018-01-30 17:34:49,264 [task-result-getter-0] INFO  TaskSetManager - Finished task 566.0 in stage 0.0 (TID 566) in 10978 ms on localhost (executor driver) (557/3618)
 2018-01-30 17:34:49,267 [Executor task launch worker for task 568] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JZPWIF-20120731183011-00000-crawling109.us.archive.org-6683.warc.gz:0+2204376
 2018-01-30 17:34:49,792 [Executor task launch worker for task 568] INFO  Executor - Finished task 568.0 in stage 0.0 (TID 568). 1690 bytes result sent to driver
 2018-01-30 17:34:49,792 [dispatcher-event-loop-2] INFO  TaskSetManager - Starting task 569.0 in stage 0.0 (TID 569, localhost, executor driver, partition 569, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:34:49,793 [Executor task launch worker for task 569] INFO  Executor - Running task 569.0 in stage 0.0 (TID 569)
 2018-01-30 17:34:49,793 [task-result-getter-1] INFO  TaskSetManager - Finished task 568.0 in stage 0.0 (TID 568) in 530 ms on localhost (executor driver) (558/3618)
 2018-01-30 17:34:49,794 [Executor task launch worker for task 569] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301143405-00188-crawling211.us.archive.org-6682.warc.gz:0+102859591
 2018-01-30 17:34:53,392 [Executor task launch worker for task 564] INFO  Executor - Finished task 564.0 in stage 0.0 (TID 564). 1846 bytes result sent to driver
 2018-01-30 17:34:53,394 [dispatcher-event-loop-4] INFO  TaskSetManager - Starting task 570.0 in stage 0.0 (TID 570, localhost, executor driver, partition 570, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:34:53,395 [Executor task launch worker for task 570] INFO  Executor - Running task 570.0 in stage 0.0 (TID 570)
 2018-01-30 17:34:53,395 [task-result-getter-2] INFO  TaskSetManager - Finished task 564.0 in stage 0.0 (TID 564) in 30715 ms on localhost (executor driver) (559/3618)
 2018-01-30 17:34:53,399 [Executor task launch worker for task 570] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171224063251065-00016.warc.gz:0+1000074542
 2018-01-30 17:34:57,351 [Executor task launch worker for task 569] INFO  Executor - Finished task 569.0 in stage 0.0 (TID 569). 1573 bytes result sent to driver
 2018-01-30 17:34:57,351 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 571.0 in stage 0.0 (TID 571, localhost, executor driver, partition 571, PROCESS_LOCAL, 19557 bytes)
 2018-01-30 17:34:57,351 [Executor task launch worker for task 571] INFO  Executor - Running task 571.0 in stage 0.0 (TID 571)
 2018-01-30 17:34:57,351 [task-result-getter-3] INFO  TaskSetManager - Finished task 569.0 in stage 0.0 (TID 569) in 7559 ms on localhost (executor driver) (560/3618)
 2018-01-30 17:34:57,352 [Executor task launch worker for task 571] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-VAEDVZ-20121231110346-00039-wbgrp-crawl065.us.archive.org-6681.warc.gz:0+101060953
 2018-01-30 17:35:01,617 [Executor task launch worker for task 571] INFO  Executor - Finished task 571.0 in stage 0.0 (TID 571). 1500 bytes result sent to driver
 2018-01-30 17:35:01,620 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 572.0 in stage 0.0 (TID 572, localhost, executor driver, partition 572, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:35:01,620 [Executor task launch worker for task 572] INFO  Executor - Running task 572.0 in stage 0.0 (TID 572)
 2018-01-30 17:35:01,620 [task-result-getter-0] INFO  TaskSetManager - Finished task 571.0 in stage 0.0 (TID 571) in 4269 ms on localhost (executor driver) (561/3618)
 2018-01-30 17:35:01,624 [Executor task launch worker for task 572] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-MWZFCS-20120629193226-00087-crawling212.us.archive.org-6682.warc.gz:0+117365364
 2018-01-30 17:35:01,833 [Executor task launch worker for task 526] INFO  Executor - Finished task 526.0 in stage 0.0 (TID 526). 1922 bytes result sent to driver
 2018-01-30 17:35:01,834 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 573.0 in stage 0.0 (TID 573, localhost, executor driver, partition 573, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:35:01,834 [task-result-getter-1] INFO  TaskSetManager - Finished task 526.0 in stage 0.0 (TID 526) in 216808 ms on localhost (executor driver) (562/3618)
 2018-01-30 17:35:01,834 [Executor task launch worker for task 573] INFO  Executor - Running task 573.0 in stage 0.0 (TID 573)
 2018-01-30 17:35:01,835 [Executor task launch worker for task 573] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB218574-20160611143412372-00001.warc.gz:0+144793713
 2018-01-30 17:35:08,871 [Executor task launch worker for task 532] INFO  Executor - Finished task 532.0 in stage 0.0 (TID 532). 2353 bytes result sent to driver
 2018-01-30 17:35:08,872 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 574.0 in stage 0.0 (TID 574, localhost, executor driver, partition 574, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:08,872 [Executor task launch worker for task 574] INFO  Executor - Running task 574.0 in stage 0.0 (TID 574)
 2018-01-30 17:35:08,872 [task-result-getter-2] INFO  TaskSetManager - Finished task 532.0 in stage 0.0 (TID 532) in 208448 ms on localhost (executor driver) (563/3618)
 2018-01-30 17:35:08,874 [Executor task launch worker for task 574] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-EWVEGS-20120301115115-00144-crawling211.us.archive.org-6682.warc.gz:0+100080523
 2018-01-30 17:35:10,351 [Executor task launch worker for task 567] INFO  Executor - Finished task 567.0 in stage 0.0 (TID 567). 1573 bytes result sent to driver
 2018-01-30 17:35:10,351 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 575.0 in stage 0.0 (TID 575, localhost, executor driver, partition 575, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:35:10,351 [Executor task launch worker for task 575] INFO  Executor - Running task 575.0 in stage 0.0 (TID 575)
 2018-01-30 17:35:10,352 [task-result-getter-3] INFO  TaskSetManager - Finished task 567.0 in stage 0.0 (TID 567) in 29985 ms on localhost (executor driver) (564/3618)
 2018-01-30 17:35:10,352 [Executor task launch worker for task 575] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB535858-20171226031227531-00122.warc.gz:0+1000003435
 2018-01-30 17:35:12,691 [Executor task launch worker for task 556] INFO  Executor - Finished task 556.0 in stage 0.0 (TID 556). 1989 bytes result sent to driver
 2018-01-30 17:35:12,691 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 576.0 in stage 0.0 (TID 576, localhost, executor driver, partition 576, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:12,691 [Executor task launch worker for task 576] INFO  Executor - Running task 576.0 in stage 0.0 (TID 576)
 2018-01-30 17:35:12,691 [task-result-getter-0] INFO  TaskSetManager - Finished task 556.0 in stage 0.0 (TID 556) in 83613 ms on localhost (executor driver) (565/3618)
 2018-01-30 17:35:12,692 [Executor task launch worker for task 576] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-GREGYM-20111208180103-00000-crawling204.us.archive.org-6680.warc.gz:0+13631745
 2018-01-30 17:35:14,596 [Executor task launch worker for task 576] INFO  Executor - Finished task 576.0 in stage 0.0 (TID 576). 1714 bytes result sent to driver
 2018-01-30 17:35:14,596 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 577.0 in stage 0.0 (TID 577, localhost, executor driver, partition 577, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:14,596 [Executor task launch worker for task 577] INFO  Executor - Running task 577.0 in stage 0.0 (TID 577)
 2018-01-30 17:35:14,596 [task-result-getter-1] INFO  TaskSetManager - Finished task 576.0 in stage 0.0 (TID 576) in 1905 ms on localhost (executor driver) (566/3618)
 2018-01-30 17:35:14,598 [Executor task launch worker for task 577] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002112731-00318-crawling209.us.archive.org-6681.warc.gz:0+103325182
 2018-01-30 17:35:16,564 [Executor task launch worker for task 574] INFO  Executor - Finished task 574.0 in stage 0.0 (TID 574). 1500 bytes result sent to driver
 2018-01-30 17:35:16,565 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 578.0 in stage 0.0 (TID 578, localhost, executor driver, partition 578, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:16,565 [Executor task launch worker for task 578] INFO  Executor - Running task 578.0 in stage 0.0 (TID 578)
 2018-01-30 17:35:16,565 [task-result-getter-2] INFO  TaskSetManager - Finished task 574.0 in stage 0.0 (TID 574) in 7693 ms on localhost (executor driver) (567/3618)
 2018-01-30 17:35:16,566 [Executor task launch worker for task 578] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930045342-00069-crawling202.us.archive.org-6681.warc.gz:0+147133469
 2018-01-30 17:35:18,359 [Executor task launch worker for task 573] INFO  Executor - Finished task 573.0 in stage 0.0 (TID 573). 1759 bytes result sent to driver
 2018-01-30 17:35:18,360 [dispatcher-event-loop-13] INFO  TaskSetManager - Starting task 579.0 in stage 0.0 (TID 579, localhost, executor driver, partition 579, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:18,360 [Executor task launch worker for task 579] INFO  Executor - Running task 579.0 in stage 0.0 (TID 579)
 2018-01-30 17:35:18,360 [task-result-getter-3] INFO  TaskSetManager - Finished task 573.0 in stage 0.0 (TID 573) in 16527 ms on localhost (executor driver) (568/3618)
 2018-01-30 17:35:18,361 [Executor task launch worker for task 579] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-JWRICE-20111205191115-00014-crawling210.us.archive.org-6682.warc.gz:0+100003255
 2018-01-30 17:35:25,331 [Executor task launch worker for task 577] INFO  Executor - Finished task 577.0 in stage 0.0 (TID 577). 1763 bytes result sent to driver
 2018-01-30 17:35:25,332 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 580.0 in stage 0.0 (TID 580, localhost, executor driver, partition 580, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:35:25,332 [Executor task launch worker for task 580] INFO  Executor - Running task 580.0 in stage 0.0 (TID 580)
 2018-01-30 17:35:25,332 [task-result-getter-0] INFO  TaskSetManager - Finished task 577.0 in stage 0.0 (TID 577) in 10736 ms on localhost (executor driver) (569/3618)
 2018-01-30 17:35:25,334 [Executor task launch worker for task 580] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-19745-20131203165810378-00000-wbgrp-crawl050.us.archive.org-6442.warc.gz:0+20651058
 2018-01-30 17:35:28,664 [Executor task launch worker for task 572] INFO  Executor - Finished task 572.0 in stage 0.0 (TID 572). 1573 bytes result sent to driver
 2018-01-30 17:35:28,665 [dispatcher-event-loop-3] INFO  TaskSetManager - Starting task 581.0 in stage 0.0 (TID 581, localhost, executor driver, partition 581, PROCESS_LOCAL, 19528 bytes)
 2018-01-30 17:35:28,665 [Executor task launch worker for task 581] INFO  Executor - Running task 581.0 in stage 0.0 (TID 581)
 2018-01-30 17:35:28,665 [task-result-getter-1] INFO  TaskSetManager - Finished task 572.0 in stage 0.0 (TID 572) in 27046 ms on localhost (executor driver) (570/3618)
 2018-01-30 17:35:28,666 [Executor task launch worker for task 581] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-QUARTERLY-JOB316808-20170723191738166-00000.warc.gz:0+1000016347
 2018-01-30 17:35:29,506 [Executor task launch worker for task 580] INFO  Executor - Finished task 580.0 in stage 0.0 (TID 580). 1706 bytes result sent to driver
 2018-01-30 17:35:29,506 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 582.0 in stage 0.0 (TID 582, localhost, executor driver, partition 582, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:35:29,506 [task-result-getter-2] INFO  TaskSetManager - Finished task 580.0 in stage 0.0 (TID 580) in 4174 ms on localhost (executor driver) (571/3618)
 2018-01-30 17:35:29,506 [Executor task launch worker for task 582] INFO  Executor - Running task 582.0 in stage 0.0 (TID 582)
 2018-01-30 17:35:29,507 [Executor task launch worker for task 582] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-29401-20131004214020228-00002-wbgrp-crawl060.us.archive.org-6442.warc.gz:0+3370041
 2018-01-30 17:35:29,881 [Executor task launch worker for task 582] INFO  Executor - Finished task 582.0 in stage 0.0 (TID 582). 1694 bytes result sent to driver
 2018-01-30 17:35:29,881 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 583.0 in stage 0.0 (TID 583, localhost, executor driver, partition 583, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:35:29,881 [Executor task launch worker for task 583] INFO  Executor - Running task 583.0 in stage 0.0 (TID 583)
 2018-01-30 17:35:29,881 [task-result-getter-3] INFO  TaskSetManager - Finished task 582.0 in stage 0.0 (TID 582) in 375 ms on localhost (executor driver) (572/3618)
 2018-01-30 17:35:29,882 [Executor task launch worker for task 583] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171023221451559-00005.warc.gz:0+1000036481
 2018-01-30 17:35:30,450 [Executor task launch worker for task 546] INFO  Executor - Finished task 546.0 in stage 0.0 (TID 546). 1958 bytes result sent to driver
 2018-01-30 17:35:30,451 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 584.0 in stage 0.0 (TID 584, localhost, executor driver, partition 584, PROCESS_LOCAL, 19523 bytes)
 2018-01-30 17:35:30,451 [Executor task launch worker for task 584] INFO  Executor - Running task 584.0 in stage 0.0 (TID 584)
 2018-01-30 17:35:30,451 [task-result-getter-0] INFO  TaskSetManager - Finished task 546.0 in stage 0.0 (TID 546) in 160792 ms on localhost (executor driver) (573/3618)
 2018-01-30 17:35:30,452 [Executor task launch worker for task 584] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-TEST-JOB506600-20171124160504321-00002.warc.gz:0+357735305
 2018-01-30 17:35:36,795 [Executor task launch worker for task 561] INFO  Executor - Finished task 561.0 in stage 0.0 (TID 561). 1973 bytes result sent to driver
 2018-01-30 17:35:36,795 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 585.0 in stage 0.0 (TID 585, localhost, executor driver, partition 585, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:36,795 [Executor task launch worker for task 585] INFO  Executor - Running task 585.0 in stage 0.0 (TID 585)
 2018-01-30 17:35:36,795 [task-result-getter-1] INFO  TaskSetManager - Finished task 561.0 in stage 0.0 (TID 561) in 88629 ms on localhost (executor driver) (574/3618)
 2018-01-30 17:35:36,797 [Executor task launch worker for task 585] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-JRKGCB-20110715172131-00000-crawling206.us.archive.org-6682.warc.gz:0+31144103
 2018-01-30 17:35:41,375 [Executor task launch worker for task 585] INFO  Executor - Finished task 585.0 in stage 0.0 (TID 585). 1706 bytes result sent to driver
 2018-01-30 17:35:41,376 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 586.0 in stage 0.0 (TID 586, localhost, executor driver, partition 586, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:41,376 [Executor task launch worker for task 586] INFO  Executor - Running task 586.0 in stage 0.0 (TID 586)
 2018-01-30 17:35:41,376 [task-result-getter-2] INFO  TaskSetManager - Finished task 585.0 in stage 0.0 (TID 585) in 4581 ms on localhost (executor driver) (575/3618)
 2018-01-30 17:35:41,377 [Executor task launch worker for task 586] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-CHONHQ-20111006105212-00049-crawling205.us.archive.org-6681.warc.gz:0+100106309
 2018-01-30 17:35:46,744 [Executor task launch worker for task 579] INFO  Executor - Finished task 579.0 in stage 0.0 (TID 579). 1771 bytes result sent to driver
 2018-01-30 17:35:46,745 [dispatcher-event-loop-0] INFO  TaskSetManager - Starting task 587.0 in stage 0.0 (TID 587, localhost, executor driver, partition 587, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:46,745 [Executor task launch worker for task 587] INFO  Executor - Running task 587.0 in stage 0.0 (TID 587)
 2018-01-30 17:35:46,745 [task-result-getter-3] INFO  TaskSetManager - Finished task 579.0 in stage 0.0 (TID 579) in 28385 ms on localhost (executor driver) (576/3618)
 2018-01-30 17:35:46,746 [Executor task launch worker for task 587] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110929232459-00038-crawling202.us.archive.org-6681.warc.gz:0+100154343
 2018-01-30 17:35:49,857 [Executor task launch worker for task 562] INFO  Executor - Finished task 562.0 in stage 0.0 (TID 562). 1969 bytes result sent to driver
 2018-01-30 17:35:49,858 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 588.0 in stage 0.0 (TID 588, localhost, executor driver, partition 588, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:35:49,858 [Executor task launch worker for task 588] INFO  Executor - Running task 588.0 in stage 0.0 (TID 588)
 2018-01-30 17:35:49,858 [task-result-getter-0] INFO  TaskSetManager - Finished task 562.0 in stage 0.0 (TID 562) in 98741 ms on localhost (executor driver) (577/3618)
 2018-01-30 17:35:49,859 [Executor task launch worker for task 588] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-XQIAVS-20111129002448-00007-crawling212.us.archive.org-6683.warc.gz:0+101267752
 2018-01-30 17:36:04,014 [Executor task launch worker for task 536] INFO  Executor - Finished task 536.0 in stage 0.0 (TID 536). 1823 bytes result sent to driver
 2018-01-30 17:36:04,015 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 589.0 in stage 0.0 (TID 589, localhost, executor driver, partition 589, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:36:04,015 [Executor task launch worker for task 589] INFO  Executor - Running task 589.0 in stage 0.0 (TID 589)
 2018-01-30 17:36:04,015 [task-result-getter-1] INFO  TaskSetManager - Finished task 536.0 in stage 0.0 (TID 536) in 238934 ms on localhost (executor driver) (578/3618)
 2018-01-30 17:36:04,016 [Executor task launch worker for task 589] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-CSRYZP-20120813072908-00007-crawling208.us.archive.org-6681.warc.gz:0+137610754
 2018-01-30 17:36:59,178 [Executor task launch worker for task 586] INFO  Executor - Finished task 586.0 in stage 0.0 (TID 586). 1759 bytes result sent to driver
 2018-01-30 17:36:59,179 [dispatcher-event-loop-7] INFO  TaskSetManager - Starting task 590.0 in stage 0.0 (TID 590, localhost, executor driver, partition 590, PROCESS_LOCAL, 19554 bytes)
 2018-01-30 17:36:59,179 [Executor task launch worker for task 590] INFO  Executor - Running task 590.0 in stage 0.0 (TID 590)
 2018-01-30 17:36:59,180 [task-result-getter-2] INFO  TaskSetManager - Finished task 586.0 in stage 0.0 (TID 586) in 77804 ms on localhost (executor driver) (579/3618)
 2018-01-30 17:36:59,181 [Executor task launch worker for task 590] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-12967-20140611163747900-00000-wbgrp-crawl053.us.archive.org-6444.warc.gz:0+31058900
 2018-01-30 17:37:03,010 [Executor task launch worker for task 578] INFO  Executor - Finished task 578.0 in stage 0.0 (TID 578). 1791 bytes result sent to driver
 2018-01-30 17:37:03,011 [dispatcher-event-loop-9] INFO  TaskSetManager - Starting task 591.0 in stage 0.0 (TID 591, localhost, executor driver, partition 591, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:37:03,011 [Executor task launch worker for task 591] INFO  Executor - Running task 591.0 in stage 0.0 (TID 591)
 2018-01-30 17:37:03,011 [task-result-getter-3] INFO  TaskSetManager - Finished task 578.0 in stage 0.0 (TID 578) in 106446 ms on localhost (executor driver) (580/3618)
 2018-01-30 17:37:03,012 [Executor task launch worker for task 591] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111003142813-00637-crawling209.us.archive.org-6681.warc.gz:0+51817578
 2018-01-30 17:37:04,086 [Executor task launch worker for task 587] INFO  Executor - Finished task 587.0 in stage 0.0 (TID 587). 1767 bytes result sent to driver
 2018-01-30 17:37:04,087 [dispatcher-event-loop-12] INFO  TaskSetManager - Starting task 592.0 in stage 0.0 (TID 592, localhost, executor driver, partition 592, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:37:04,087 [Executor task launch worker for task 592] INFO  Executor - Running task 592.0 in stage 0.0 (TID 592)
 2018-01-30 17:37:04,087 [task-result-getter-0] INFO  TaskSetManager - Finished task 587.0 in stage 0.0 (TID 587) in 77342 ms on localhost (executor driver) (581/3618)
 2018-01-30 17:37:04,088 [Executor task launch worker for task 592] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-UHNVDX-20110930042759-00060-crawling202.us.archive.org-6681.warc.gz:0+112355552
 2018-01-30 17:37:05,311 [Executor task launch worker for task 590] INFO  Executor - Finished task 590.0 in stage 0.0 (TID 590). 1706 bytes result sent to driver
 2018-01-30 17:37:05,313 [dispatcher-event-loop-1] INFO  TaskSetManager - Starting task 593.0 in stage 0.0 (TID 593, localhost, executor driver, partition 593, PROCESS_LOCAL, 19526 bytes)
 2018-01-30 17:37:05,313 [Executor task launch worker for task 593] INFO  Executor - Running task 593.0 in stage 0.0 (TID 593)
 2018-01-30 17:37:05,313 [task-result-getter-1] INFO  TaskSetManager - Finished task 590.0 in stage 0.0 (TID 590) in 6134 ms on localhost (executor driver) (582/3618)
 2018-01-30 17:37:05,314 [Executor task launch worker for task 593] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-JOB470197-20171026035824335-00097.warc.gz:0+1000050233
 2018-01-30 17:37:06,232 [Executor task launch worker for task 591] INFO  Executor - Finished task 591.0 in stage 0.0 (TID 591). 1686 bytes result sent to driver
 2018-01-30 17:37:06,232 [dispatcher-event-loop-15] INFO  TaskSetManager - Starting task 594.0 in stage 0.0 (TID 594, localhost, executor driver, partition 594, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:37:06,232 [Executor task launch worker for task 594] INFO  Executor - Running task 594.0 in stage 0.0 (TID 594)
 2018-01-30 17:37:06,233 [task-result-getter-2] INFO  TaskSetManager - Finished task 591.0 in stage 0.0 (TID 591) in 3222 ms on localhost (executor driver) (583/3618)
 2018-01-30 17:37:06,233 [Executor task launch worker for task 594] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB319454-20170805001359700-00000.warc.gz:0+57009410
 2018-01-30 17:37:09,585 [Executor task launch worker for task 588] INFO  Executor - Finished task 588.0 in stage 0.0 (TID 588). 1573 bytes result sent to driver
 2018-01-30 17:37:09,586 [dispatcher-event-loop-5] INFO  TaskSetManager - Starting task 595.0 in stage 0.0 (TID 595, localhost, executor driver, partition 595, PROCESS_LOCAL, 19525 bytes)
 2018-01-30 17:37:09,586 [Executor task launch worker for task 595] INFO  Executor - Running task 595.0 in stage 0.0 (TID 595)
 2018-01-30 17:37:09,586 [task-result-getter-3] INFO  TaskSetManager - Finished task 588.0 in stage 0.0 (TID 588) in 79728 ms on localhost (executor driver) (584/3618)
 2018-01-30 17:37:09,587 [Executor task launch worker for task 595] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-JOB250029-20161119211707492-00002.warc.gz:0+380137873
 2018-01-30 17:37:13,406 [Executor task launch worker for task 474] INFO  Executor - Finished task 474.0 in stage 0.0 (TID 474). 1573 bytes result sent to driver
 2018-01-30 17:37:13,406 [dispatcher-event-loop-8] INFO  TaskSetManager - Starting task 596.0 in stage 0.0 (TID 596, localhost, executor driver, partition 596, PROCESS_LOCAL, 19556 bytes)
 2018-01-30 17:37:13,406 [Executor task launch worker for task 596] INFO  Executor - Running task 596.0 in stage 0.0 (TID 596)
 2018-01-30 17:37:13,406 [task-result-getter-0] INFO  TaskSetManager - Finished task 474.0 in stage 0.0 (TID 474) in 538875 ms on localhost (executor driver) (585/3618)
 2018-01-30 17:37:13,407 [Executor task launch worker for task 596] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-WEEKLY-18639-20140103213112918-00000-wbgrp-crawl060.us.archive.org-6440.warc.gz:0+229873595
 2018-01-30 17:37:14,915 [Executor task launch worker for task 594] INFO  Executor - Finished task 594.0 in stage 0.0 (TID 594). 1811 bytes result sent to driver
 2018-01-30 17:37:14,915 [dispatcher-event-loop-10] INFO  TaskSetManager - Starting task 597.0 in stage 0.0 (TID 597, localhost, executor driver, partition 597, PROCESS_LOCAL, 19549 bytes)
 2018-01-30 17:37:14,915 [Executor task launch worker for task 597] INFO  Executor - Running task 597.0 in stage 0.0 (TID 597)
 2018-01-30 17:37:14,916 [task-result-getter-1] INFO  TaskSetManager - Finished task 594.0 in stage 0.0 (TID 594) in 8683 ms on localhost (executor driver) (586/3618)
 2018-01-30 17:37:14,917 [Executor task launch worker for task 597] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-NONE-FWPGCP-20111002200932-00437-crawling209.us.archive.org-6681.warc.gz:0+101042202
 2018-01-30 17:37:17,036 [Executor task launch worker for task 589] INFO  Executor - Finished task 589.0 in stage 0.0 (TID 589). 1874 bytes result sent to driver
 2018-01-30 17:37:17,036 [dispatcher-event-loop-11] INFO  TaskSetManager - Starting task 598.0 in stage 0.0 (TID 598, localhost, executor driver, partition 598, PROCESS_LOCAL, 19552 bytes)
 2018-01-30 17:37:17,036 [Executor task launch worker for task 598] INFO  Executor - Running task 598.0 in stage 0.0 (TID 598)
 2018-01-30 17:37:17,037 [task-result-getter-2] INFO  TaskSetManager - Finished task 589.0 in stage 0.0 (TID 589) in 73023 ms on localhost (executor driver) (587/3618)
 2018-01-30 17:37:17,037 [Executor task launch worker for task 598] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-MONTHLY-OZBJIK-20120613051835-00010-crawling200.us.archive.org-6681.warc.gz:0+102063484
 2018-01-30 17:37:20,923 [Executor task launch worker for task 570] INFO  Executor - Finished task 570.0 in stage 0.0 (TID 570). 2253 bytes result sent to driver
 2018-01-30 17:37:20,923 [dispatcher-event-loop-14] INFO  TaskSetManager - Starting task 599.0 in stage 0.0 (TID 599, localhost, executor driver, partition 599, PROCESS_LOCAL, 19529 bytes)
 2018-01-30 17:37:20,924 [task-result-getter-3] INFO  TaskSetManager - Finished task 570.0 in stage 0.0 (TID 570) in 147531 ms on localhost (executor driver) (588/3618)
 2018-01-30 17:37:20,924 [Executor task launch worker for task 599] INFO  Executor - Running task 599.0 in stage 0.0 (TID 599)
 2018-01-30 17:37:20,925 [Executor task launch worker for task 599] INFO  NewHadoopRDD - Input split: file:/data/401/1830/warcs/ARCHIVEIT-1830-SEMIANNUAL-JOB193236-20160129141918491-00011.warc.gz:0+1000021852
 2018-01-30 17:39:22,225 [dispatcher-event-loop-0] WARN  HeartbeatReceiver - Removing executor driver with no recent heartbeats: 124874 ms exceeds timeout 120000 ms
 2018-01-30 17:39:22,226 [dispatcher-event-loop-0] ERROR TaskSchedulerImpl - Lost executor driver on localhost: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 137), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 550), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 146), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 559), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 218), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 568), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 227), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 433), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 92), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 442), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 101), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 200), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 514), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 173), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 523), so marking it as still running
 2018-01-30 17:39:22,232 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 209), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 182), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 191), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 254), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 424), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 83), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 496), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 469), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 155), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 505), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 478), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 164), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 577), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 245), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 451), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 110), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 460), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 119), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 532), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 128), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 541), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 406), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 415), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 487), so marking it as still running
 2018-01-30 17:39:22,233 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 236), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 23), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 436), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 95), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 445), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 104), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 517), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 391), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 472), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 131), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 427), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 463), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 122), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 194), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 508), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 176), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 409), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 418), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 77), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 490), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 86), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 185), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 499), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 158), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 167), so marking it as still running
 2018-01-30 17:39:22,234 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 50), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 364), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 400), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 59), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 373), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 32), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 41), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 68), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 382), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 481), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 454), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 140), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 113), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 149), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 346), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 355), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 394), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 53), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 367), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 403), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 62), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 134), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 35), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 376), so marking it as still running
 2018-01-30 17:39:22,235 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 8), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 349), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 44), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 17), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 358), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 430), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 26), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 125), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 304), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 331), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 340), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 421), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 80), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 89), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 286), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 295), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 448), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 457), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 116), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 439), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 412), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 98), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 71), so marking it as still running
 2018-01-30 17:39:22,236 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 107), so marking it as still running
 2018-01-30 17:39:22,238 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 597.0 in stage 0.0 (TID 597, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,242 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 313), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 385), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 322), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 11), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 567), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 307), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 388), so marking it as still running
 2018-01-30 17:39:22,243 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 74), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 397), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 56), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 262), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 298), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 370), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 29), so marking it as still running
 2018-01-30 17:39:22,244 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 343), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 38), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 379), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 352), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 47), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 576), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 585), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 558), so marking it as still running
 2018-01-30 17:39:22,245 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 244), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 594), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 226), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 253), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 325), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 361), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 20), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 334), so marking it as still running
 2018-01-30 17:39:22,246 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 2), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 540), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 549), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 235), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 289), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 316), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 65), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 271), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 280), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 5), so marking it as still running
 2018-01-30 17:39:22,247 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 319), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 516), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 552), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 525), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 184), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 534), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 193), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 265), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 301), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 480), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 175), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 256), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 337), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 211), so marking it as still running
 2018-01-30 17:39:22,254 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 283), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 292), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 498), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 507), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 166), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 579), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 588), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 247), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 274), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 14), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 328), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 489), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 561), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 220), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 570), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 543), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 229), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 202), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 238), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 310), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 277), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 474), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 483), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 142), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 492), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 151), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 564), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 223), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 250), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 573), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 232), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 259), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 438), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 124), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 537), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 447), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 133), so marking it as still running
 2018-01-30 17:39:22,255 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 106), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 546), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 519), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 205), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 555), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 214), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 528), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 420), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 429), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 501), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 160), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 510), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 169), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 582), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 178), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 591), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 456), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 465), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 115), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 187), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 196), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 241), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 268), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 369), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 441), so marking it as still running
 2018-01-30 17:39:22,256 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 181), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 163), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 477), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 513), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 172), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 387), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 46), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 459), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 432), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 118), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 468), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 127), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 136), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 199), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 208), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 217), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 414), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 100), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 450), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 423), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 109), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 82), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 522), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 495), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 91), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 531), so marking it as still running
 2018-01-30 17:39:22,257 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 504), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 190), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 396), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 55), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 405), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 64), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 378), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 73), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 486), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 145), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 154), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 360), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 426), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 399), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 85), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 58), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 408), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 67), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 94), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 139), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 300), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 381), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 40), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 354), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 390), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 49), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 471), so marking it as still running
 2018-01-30 17:39:22,258 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 130), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 336), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 4), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 345), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 13), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 372), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 453), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 148), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 462), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 121), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 157), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 22), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 363), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 435), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 31), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 444), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 417), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 103), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 76), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 112), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 309), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 318), so marking it as still running
 2018-01-30 17:39:22,259 [dispatcher-event-loop-0] ERROR TaskSetManager - Task 597 in stage 0.0 failed 1 times; aborting job
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 327), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 16), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 357), so marking it as still running
 2018-01-30 17:39:22,259 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 97), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 563), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 312), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 7), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 348), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 393), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 79), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 402), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 88), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 294), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 303), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 375), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 411), so marking it as still running
 2018-01-30 17:39:22,260 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 70), so marking it as still running
 2018-01-30 17:39:22,262 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 384), so marking it as still running
 2018-01-30 17:39:22,262 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 43), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 52), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 590), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 249), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 276), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 258), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 285), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 267), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 330), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 25), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 339), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 366), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 34), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 572), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 240), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 321), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 61), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 10), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 521), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 557), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 530), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 189), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 225), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 306), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 512), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 37), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 180), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 333), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 1), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 342), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 548), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 207), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 216), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 288), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 324), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 297), so marking it as still running
 2018-01-30 17:39:22,269 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 503), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 539), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 198), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 270), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 252), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 279), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 351), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 19), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 28), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 566), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 234), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 261), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 243), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 315), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 282), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 174), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 488), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 147), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 587), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 497), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 183), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 156), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 569), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 255), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 228), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 578), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 264), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 461), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 470), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 443), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 129), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 542), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 479), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 452), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 138), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 551), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 210), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 560), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 219), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 291), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 120), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 506), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 165), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 515), so marking it as still running
 2018-01-30 17:39:22,270 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 237), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 246), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 524), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 533), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 192), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 201), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 273), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 60), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 186), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 213), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 222), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 87), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 437), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 96), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 509), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 482), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 168), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 518), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 177), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 383), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 392), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 464), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 150), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 500), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 473), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 159), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 132), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 545), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 141), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 554), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 446), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 419), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 105), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 455), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 428), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 114), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 527), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 123), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 536), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 195), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 204), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 401), so marking it as still running
 2018-01-30 17:39:22,271 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 410), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 69), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 78), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 491), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 231), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 332), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 431), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 404), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 90), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 63), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 99), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 386), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 45), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 395), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 54), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 341), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 422), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 171), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 377), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 413), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 72), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 485), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 144), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 81), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 494), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 467), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 153), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 126), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 162), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 359), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 27), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 368), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 440), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 36), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 476), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 449), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 135), so marking it as still running
 2018-01-30 17:39:22,272 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 108), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 458), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 117), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 350), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 9), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 323), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 18), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 389), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 48), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 362), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 21), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 57), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 263), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 272), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 344), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 3), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 317), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 353), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 12), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 425), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 84), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 434), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 93), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 102), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 299), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 326), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 335), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 308), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 380), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 416), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 75), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 281), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 290), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 30), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 371), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 39), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 586), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 111), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 398), so marking it as still running
 2018-01-30 17:39:22,273 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 407), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 66), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 15), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 356), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 562), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 230), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 42), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 51), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 257), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 24), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 338), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 33), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 347), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 374), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 6), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 553), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 589), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 221), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 248), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 320), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 302), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 329), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 535), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 544), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 203), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 212), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 275), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 284), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 311), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 293), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 365), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 526), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 571), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 580), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 266), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 239), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 314), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 511), so marking it as still running
 2018-01-30 17:39:22,274 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 520), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 493), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 179), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 152), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 188), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 502), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 260), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 269), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 475), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 484), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 170), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 143), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 556), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 215), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 466), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 547), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 287), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 161), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 574), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 242), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 251), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 529), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 538), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 197), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 224), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 206), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 233), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 296), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 278), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 305), so marking it as still running
 2018-01-30 17:39:22,275 [dag-scheduler-event-loop] INFO  DAGScheduler - Resubmitted ShuffleMapTask(0, 0), so marking it as still running
 2018-01-30 17:39:22,282 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 599.0 in stage 0.0 (TID 599, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,282 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 581.0 in stage 0.0 (TID 581, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,282 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 584.0 in stage 0.0 (TID 584, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,282 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 593.0 in stage 0.0 (TID 593, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,283 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 575.0 in stage 0.0 (TID 575, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,283 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 596.0 in stage 0.0 (TID 596, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,283 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 595.0 in stage 0.0 (TID 595, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,284 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 598.0 in stage 0.0 (TID 598, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,284 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 592.0 in stage 0.0 (TID 592, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,284 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 565.0 in stage 0.0 (TID 565, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,284 [dispatcher-event-loop-0] WARN  TaskSetManager - Lost task 583.0 in stage 0.0 (TID 583, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 2018-01-30 17:39:22,286 [dispatcher-event-loop-0] INFO  TaskSchedulerImpl - Removed TaskSet 0.0, whose tasks have all completed, from pool 
 2018-01-30 17:39:22,287 [dag-scheduler-event-loop] INFO  TaskSchedulerImpl - Cancelling stage 0
 2018-01-30 17:39:22,290 [dag-scheduler-event-loop] INFO  DAGScheduler - ShuffleMapStage 0 (map at RecordRDD.scala:38) failed in 3006.201 s due to Job aborted due to stage failure: Task 597 in stage 0.0 failed 1 times, most recent failure: Lost task 597.0 in stage 0.0 (TID 597, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 Driver stacktrace:
 2018-01-30 17:39:22,293 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,294 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,294 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,294 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,294 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,317 [kill-executor-thread] WARN  SparkContext - Killing executors is only supported in coarse-grained mode
 2018-01-30 17:39:22,318 [dag-scheduler-event-loop] INFO  DAGScheduler - Executor lost: driver (epoch 0)
 2018-01-30 17:39:22,319 [dispatcher-event-loop-6] INFO  BlockManagerMasterEndpoint - Trying to remove executor driver from BlockManagerMaster.
 2018-01-30 17:39:22,320 [dispatcher-event-loop-6] INFO  BlockManagerMasterEndpoint - Removing block manager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,321 [dag-scheduler-event-loop] INFO  BlockManagerMaster - Removed driver successfully in removeExecutor
 2018-01-30 17:39:22,324 [main] INFO  DAGScheduler - Job 0 failed: sortBy at RecordRDD.scala:40, took 3006.603356 s
 2018-01-30 17:39:22,324 [dag-scheduler-event-loop] INFO  DAGScheduler - Shuffle files lost for executor: driver (epoch 0)
 2018-01-30 17:39:22,325 [driver-heartbeater] ERROR BlockManager - Failed to report broadcast_0_piece0 to master; giving up.
 2018-01-30 17:39:22,325 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,325 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,325 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,326 [dispatcher-event-loop-10] INFO  BlockManagerMasterEndpoint - Registering block manager 192.168.32.19:34009 with 47.8 GB RAM, BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,326 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,326 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,326 [dispatcher-event-loop-9] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,327 [dispatcher-event-loop-11] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,327 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,327 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,327 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,327 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,327 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,328 [dispatcher-event-loop-1] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,328 [dispatcher-event-loop-14] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,328 [dispatcher-event-loop-3] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,328 [dispatcher-event-loop-4] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,328 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,329 [dispatcher-event-loop-6] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,329 [dispatcher-event-loop-8] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,329 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,329 [dispatcher-event-loop-9] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,329 [dispatcher-event-loop-11] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,330 [dispatcher-event-loop-1] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,330 [dispatcher-event-loop-14] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,330 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,330 [dispatcher-event-loop-3] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,331 [dispatcher-event-loop-4] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,331 [dispatcher-event-loop-6] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,331 [dispatcher-event-loop-8] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,331 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,331 [dispatcher-event-loop-9] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,332 [dispatcher-event-loop-11] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,332 [dispatcher-event-loop-1] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,332 [dispatcher-event-loop-14] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  Executor - Told to re-register on heartbeat
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManager - BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None) re-registering with master
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManagerMaster - Registering BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManagerMaster - Registered BlockManager BlockManagerId(driver, 192.168.32.19, 34009, None)
 2018-01-30 17:39:22,332 [driver-heartbeater] INFO  BlockManager - Reporting 4 blocks to the master.
 2018-01-30 17:39:22,333 [dispatcher-event-loop-3] INFO  BlockManagerInfo - Added broadcast_0_piece0 in memory on 192.168.32.19:34009 (size: 20.2 KB, free: 47.8 GB)
 2018-01-30 17:39:22,333 [dispatcher-event-loop-4] INFO  BlockManagerInfo - Added broadcast_1_piece0 in memory on 192.168.32.19:34009 (size: 2.9 KB, free: 47.8 GB)
 2018-01-30 17:39:22,334 [dag-scheduler-event-loop] INFO  DAGScheduler - Host added was in lost list earlier: localhost
 org.apache.spark.SparkException: Job aborted due to stage failure: Task 597 in stage 0.0 failed 1 times, most recent failure: Lost task 597.0 in stage 0.0 (TID 597, localhost, executor driver): ExecutorLostFailure (executor driver exited caused by one of the running tasks) Reason: Executor heartbeat timed out after 124874 ms
 Driver stacktrace:
  at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
  at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
  at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
  at scala.Option.foreach(Option.scala:257)
  at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
  at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:1965)
  at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:936)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
  at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
  at org.apache.spark.rdd.RDD.collect(RDD.scala:935)
  at org.apache.spark.RangePartitioner$.sketch(Partitioner.scala:266)
  at org.apache.spark.RangePartitioner.<init>(Partitioner.scala:128)
  at org.apache.spark.rdd.OrderedRDDFunctions$$anonfun$sortByKey$1.apply(OrderedRDDFunctions.scala:62)
  at org.apache.spark.rdd.OrderedRDDFunctions$$anonfun$sortByKey$1.apply(OrderedRDDFunctions.scala:61)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
  at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
  at org.apache.spark.rdd.OrderedRDDFunctions.sortByKey(OrderedRDDFunctions.scala:61)
  at org.apache.spark.rdd.RDD$$anonfun$sortBy$1.apply(RDD.scala:619)
  at org.apache.spark.rdd.RDD$$anonfun$sortBy$1.apply(RDD.scala:620)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
  at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
  at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
  at org.apache.spark.rdd.RDD.sortBy(RDD.scala:617)
  at io.archivesunleashed.spark.rdd.RecordRDD$CountableRDD.countItems(RecordRDD.scala:40)
  ... 73 elided
No results found