<configuration>
<property>
<name>http.agent.name</name>
<value>My Nutch Spider</value>
</property>

<property>
<name>http.accept.language</name>
<value>zh-cn, en-us,en-gb,en;q=0.7,*;q=0.3</value>
<description>Value of the “Accept-Language” request header field. This allows selecting non-English language as default one to retrieve. It is a useful setting for search engines build for certain national group.
</description>
</property>

<property>
<name>parser.character.encoding.default</name>
<value>utf-8</value>
<description>The character encoding to fall back to when no other information is available</description>
</property>
</configuration>

<regex>
<pattern>\s</pattern>
<substitution>%20</substitution>
</regex>

<property>
<name>plugin.includes</name>
<value>protocol-http|urlfilter-regex|parse-(html|tika|text)|index-(basic|anchor|more)|query-(basic|site|url)|response-(json|xml)|summary-basic|scoring-opic|urlnormalizer-(pass|regex|basic)</value>
</property>

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

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

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

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

<property>
<name>parser.skip.truncated</name>
<value>false</value>
</property>

<mimeType name="application/pdf">
<plugin id="parse-tika"/>
</mimeType>