ant编译apache-nutch-2.2.1结合mysql实现爬虫的安装配置全过程

CREATE TABLE `webpage` (

`id` varchar(767) NOT NULL,

`headers` blob,

`text` longtext DEFAULT NULL,

`status` int(11) DEFAULT NULL,

`markers` blob,

`parseStatus` blob,

`modifiedTime` bigint(20) DEFAULT NULL,

`prevModifiedTime` bigint(20) DEFAULT NULL,

`score` float DEFAULT NULL,

`typ` varchar(32) CHARACTER SET latin1 DEFAULT NULL,

`batchId` varchar(32) CHARACTER SET latin1 DEFAULT NULL,

`baseUrl` varchar(767) DEFAULT NULL,

`content` longblob,

`title` varchar(2048) DEFAULT NULL,

`reprUrl` varchar(767) DEFAULT NULL,

`fetchInterval` int(11) DEFAULT NULL,

`prevFetchTime` bigint(20) DEFAULT NULL,

`inlinks` mediumblob,

`prevSignature` blob,

`outlinks` mediumblob,

`fetchTime` bigint(20) DEFAULT NULL,

`retriesSinceFetch` int(11) DEFAULT NULL,

`protocolStatus` blob,

`signature` blob,

`metadata` blob,

PRIMARY KEY (`id`)

) ENGINE=InnoDB DEFAULT CHARSET=utf8;

<gora-orm>

<class name="org.apache.nutch.storage.WebPage" keyClass="java.lang.String" table="webpage">
  <primarykey column="id" length="512"/>
    <field name="baseUrl" column="baseUrl" length="512"/>    
    <field name="status" column="status"/>
    <field name="prevFetchTime" column="prevFetchTime"/>
    <field name="fetchTime" column="fetchTime"/>
    <field name="fetchInterval" column="fetchInterval"/>
    <field name="retriesSinceFetch" column="retriesSinceFetch"/>
    <field name="reprUrl" column="reprUrl" length="512"/>
    <field name="content" column="content" length="65536"/>
    <field name="contentType" column="typ" length="32"/>    
    <field name="protocolStatus" column="protocolStatus"/>
    <field name="modifiedTime" column="modifiedTime"/>
    <field name="prevModifiedTime" column="prevModifiedTime"/>
    <field name="batchId" column="batchId" length="32"/>

    <!-- parse fields                                       -->
    <field name="title" column="title" length="512"/>
    <field name="text" column="text" length="32000"/>
    <field name="parseStatus" column="parseStatus"/>
    <field name="signature" column="signature"/>
    <field name="prevSignature" column="prevSignature"/>

    <!-- score fields                                       -->
    <field name="score" column="score"/>
    <field name="headers" column="headers"/>
    <field name="inlinks" column="inlinks"/>
    <field name="outlinks" column="outlinks"/>
    <field name="metadata" column="metadata"/>
    <field name="markers" column="markers"/>
</class>

<class name="org.apache.nutch.storage.Host" keyClass="java.lang.String"
table="host">
  <primarykey column="id" length="512"/>
  <field name="metadata" column="metadata"/>
  <field name="inlinks" column="inlinks"/>
  <field name="outlinks" column="outlinks"/>
</class>

</gora-orm>

   添加http.agent.name的值

<property>

<name>http.agent.name</name>

<value>YourNutchSpider</value>

</property>

  在文件末尾添加以下内容

<property>

             <name>http.accept.language</name>

             <value>ja-jp, 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>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>

        

<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>

  特别添加以下内容

<property>

    <name>generate.batch.id</name>

    <value>*</value>

</property>