nutch-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
 <name>http.agent.name</name>
 <value>InsyWinsy</value>
</property>

<property>
 <name>plugin.includes</name>
 <value>protocol-http|urlfilter-regex|parse-(tika)|index-(basic|anchor)|indexer-solr|scoring-opic|urlnormalizer-(pass|regex|basic)
 </value>
</property>

<property>
  <name>http.robot.rules.whitelist</name>
  <value>http://jachermocilla.org</value>
 </property>

 <property>
   <name>http.timeout</name>
   <value>60000</value>
 </property>

<property>
  <name>http.content.limit</name>
  <value>-1</value>
</property>

<property>
  <name>http.content.size</name>
  <value>-1</value>
</property>

</configuration>