1. 程式人生 > >Nutch2.2.1 開發環境搭建

Nutch2.2.1 開發環境搭建

<property>
  <name>http.agent.name</name>
  <value>YourNutchSpider</value>
 </property>
 
 <property>
  <name>http.accept.language</name>
  <value>ja-jp, en-us,en-gb,en,zh-cn,zh-tw;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>
 
 <property>
  <name>plugin.folders</name>
  <value>src/plugin</value>
  <description>Directories where nutch plugins are located. Each
  element may be a relative or absolute path. If absolute, it is used
  as is. If relative, it is searched for on the classpath.</description>
 </property>
</pre><pre name="code" class="html"><!-- 為解決utf-8類中的空指標問題 -->
<property>
<span> </span><name>generate.batch.id</name>
<span> </span><value>*</value>
</property>
 
 <property>
  <name>storage.data.store.class</name>
  <value>org.apache.gora.sql.store.SqlStore</value>
  <description>The Gora DataStore class for storing and retrieving data.
  Currently the following stores are available: ….</description>
 </property>