Here is a picture of sharepoint web architecture: https://pasteboard.co/HkyuMhZ.png
We need to crawl groups at each of the site collections. Each can have unique sharepoint groups.
| <soapenv:Envelope xmlns:soapenv="http://schemas.xmlsoap.org/soap/envelope/" xmlns:soap="http://schemas.microsoft.com/sharepoint/soap/"> | |
| <soapenv:Header/> | |
| <soapenv:Body> | |
| <soap:GetContent> | |
| <soap:objectType>Site</soap:objectType> | |
| <soap:retrieveChildItems>true</soap:retrieveChildItems> | |
| <soap:securityOnly>true</soap:securityOnly> | |
| </soap:GetContent> | |
| </soapenv:Body> | |
| </soapenv:Envelope> |
| 1519885689195 geckodriver INFO geckodriver 0.19.1 | |
| 151988155618998189576 8g9e1c9k5o dgreicvkeord rIiNvFeOr LIiNsFtOe ngiencgk oodnr i12v7e.r0 .00..119:.219 | |
| 1519885865809 | |
| 197 geckodriver INFO Listening on 127.0.0.1:11831 | |
| *** You are running in headless mode. | |
| *** You are running in headless mode. | |
| Mar 01, 2018 6:28:10 AM org.openqa.selenium.remote.ProtocolHandshake createSession | |
| INFO: Detected dialect: W3C | |
| Mar 01, 2018 6:28:10 AM org.openqa.selenium.remote.ProtocolHandshake createSession | |
| INFO: Detected dialect: W3C |
| /home/ndipiazza/Downloads/jdk1.8.0_141/bin/java -agentlib:jdwp=transport=dt_socket,address=127.0.0.1:45155,suspend=y,server=n -javaagent:/home/ndipiazza/Downloads/idea-IC-173.4127.27/plugins/Groovy/lib/agent/gragent.jar -javaagent:/home/ndipiazza/Downloads/idea-IC-173.4127.27/lib/rt/debugger-agent.jar=/tmp/capture.props -Dfile.encoding=UTF-8 -classpath /home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/charsets.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/deploy.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/cldrdata.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/dnsns.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/jaccess.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/jfxrt.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/localedata.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/nashorn.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/sunec.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jre/lib/ext/sunjce_provider.jar:/home/ndipiazza/Downloads/jdk1.8.0_141/jr |
| sudo docker run -t -d -p 8765:8765 -p 8984:8984 -p 8983:8983 -p 8764:8764 --shm-size=2g --name testzombies openjdk:8u151-jdk | |
| sudo docker exec -i -t testzombies /bin/bash | |
| apt-get -y --fix-missing update && \ | |
| apt-get -y --fix-missing upgrade && \ | |
| apt-get -y --no-install-recommends install apt-utils && \ | |
| apt-get install -y wget lbzip2 git openjdk-8-jdk libdbus-glib-1-2 xvfb libgtk-3.0 procps gradle psmisc | |
| wget https://download-installer.cdn.mozilla.net/pub/devedition/releases/59.0b14/linux-x86_64/en-US/firefox-59.0b14.tar.bz2 | |
| tar xvf firefox-59.0b14.tar.bz2 | |
| wget https://github.com/mozilla/geckodriver/releases/download/v0.19.1/geckodriver-v0.19.1-linux64.tar.gz | |
| tar xzvf geckodriver-v0.19.1-linux64.tar.gz |
| import crawler.common.sharepoint.stubs.sitedata.ArrayOfSList; | |
| import crawler.common.sharepoint.stubs.sitedata.GetListCollectionResponse; | |
| import crawler.common.sharepoint.stubs.sitedata.SList; | |
| import crawler.common.sharepoint.stubs.sitedata.SiteData; | |
| import crawler.common.sharepoint.stubs.sitedata.SiteDataSoap; | |
| import org.apache.cxf.configuration.security.AuthorizationPolicy; | |
| import org.apache.cxf.endpoint.Client; | |
| import org.apache.cxf.frontend.ClientProxy; | |
| import org.apache.cxf.transport.http.HTTPConduit; | |
| import org.apache.cxf.transport.http.asyncclient.AsyncHTTPConduit; |
| -Dcom.lucidworks.fusion.plugin.portStart=8871 -Dcom.lucidworks.fusion.plugin.portEnd=8971 -DserviceName=connectors-rpc -Dcom.lucidworks.apollo.solr.zk.connect=localhost:9983/lwfusion/4.2.0-SNAPSHOT/solr -Dcurator.zk.connect=localhost:9983 -Dcurator.namespace=lwfusion/4.2.0-SNAPSHOT/core -Dcom.lucidworks.fusion.plugin.portStart=8871 -Dcom.lucidworks.fusion.plugin.portEnd=8971 -DserviceName=connectors-rpc -Dcom.lucidworks.apollo.solr.zk.connect=localhost:9983/lwfusion/4.2.0-SNAPSHOT/solr -Dcurator.zk.connect=localhost:9983 -Dcurator.namespace=lwfusion/4.2.0-SNAPSHOT/core |
| import com.google.common.collect.Sets; | |
| import org.apache.commons.io.FileUtils; | |
| import org.apache.commons.io.LineIterator; | |
| import java.io.File; | |
| import java.io.IOException; | |
| import java.util.HashSet; | |
| import java.util.Set; | |
| public class DiffTextFilesUtil { |