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>My Test</value>
  </property>
  <property>
    <name>storage.data.store.class</name>
    <value>org.apache.gora.cassandra.store.CassandraStore</value>
    <description>Default class for storing data</description>
  </property>
  <property>
    <name>plugin.includes</name>
    <value>protocol-http|urlfilter-regex|parse-(html|tika|metatags)|index-(basic|anchor|metadata)|indexer-solr|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
    <description></description>
  </property>
  <property>
    <name>metatags.names</name>
    <value>*</value>
    <description>Names of the metatages to extract, separated by ','.
      Use '*' to extract all metatags. Prefixes the names with 'metatag.'
      in the parse-metadata. For instance to index description and keywords,
      you need to activate the plugin index-metadata and set the value of the
      parameter 'index.parse.md' to 'metatag.description,metatag.keywords'.
    </description>
  </property>
  <property>
    <name>index.parse.md</name>
    <value>*</value>
    <description></description>
  </property>
  <property>
    <name></name>
    <value></value>
    <description></description>
  </property>
</configuration>