Heritrix 3.1.0 源码解析（二）

上文Heritrix 3.1.0 源码解析（一）实际上是讲述Heritrix3.1.0在eclipse中的环境搭建，还属于对Heritrix3.1.0 源码解析的热身阶段，本文接着分析Heritrix 3.1.0的任务配置，Heritrix3.1.0版本与原来的Heritrix1.14.4版本很大的不同是 任务配置文件从order.xml文件转到了crawler-beans.cxml文件，而crawler-beans.cxml实际上是一个spring的容器配置文件，是用spring管理的，我们先来眼熟一下该文件的样子（这里面我配置了一个任务）：

<?xml version="1.0" encoding="UTF-8"?>

<!-- 

  HERITRIX 3 CRAWL JOB CONFIGURATION FILE

  

   This is a relatively minimal configuration suitable for many crawls.

   

   Commented-out beans and properties are provided as an example; values

   shown in comments reflect the actual defaults which are in effect

   if not otherwise specified specification. (To change from the default 

   behavior, uncomment AND alter the shown values.)   

 -->

<beans xmlns="http://www.springframework.org/schema/beans"

         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"

         xmlns:context="http://www.springframework.org/schema/context"

         xmlns:aop="http://www.springframework.org/schema/aop"

         xmlns:tx="http://www.springframework.org/schema/tx"

         xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-3.0.xsd

           http://www.springframework.org/schema/aop http://www.springframework.org/schema/aop/spring-aop-3.0.xsd

           http://www.springframework.org/schema/tx http://www.springframework.org/schema/tx/spring-tx-3.0.xsd

           http://www.springframework.org/schema/context http://www.springframework.org/schema/context/spring-context-3.0.xsd">

 

 <context:annotation-config/>



<!-- 

  OVERRIDES

   Values elsewhere in the configuration may be replaced ('overridden') 

   by a Properties map declared in a PropertiesOverrideConfigurer, 

   using a dotted-bean-path to address individual bean properties. 

   This allows us to collect a few of the most-often changed values

   in an easy-to-edit format here at the beginning of the model

   configuration.    

 -->

 <!-- overrides from a text property list -->

 <bean id="simpleOverrides" class="org.springframework.beans.factory.config.PropertyOverrideConfigurer">

  <property name="properties">

   <value>

# This Properties map is specified in the Java 'property list' text format

# http://java.sun.com/javase/6/docs/api/java/util/Properties.html#load%28java.io.Reader%29



metadata.operatorContactUrl=http://localhost

metadata.jobName=myjob1

metadata.description=myjob1 descrition



##..more?..##

   </value>

  </property>

 </bean>



 <!-- overrides from declared <prop> elements, more easily allowing

      multiline values or even declared beans -->

 <bean id="longerOverrides" class="org.springframework.beans.factory.config.PropertyOverrideConfigurer">

  <property name="properties">

   <props>

    <prop key="seeds.textSource.value">



# URLS HERE

http://www.watiao.net



    </prop>

   </props>

  </property>

 </bean>



 <!-- CRAWL METADATA: including identification of crawler/operator -->

 <bean id="metadata" class="org.archive.modules.CrawlMetadata" autowire="byName">

       <property name="operatorContactUrl" value="http://localhost"/>

       <property name="jobName" value="myjob1"/>

       <property name="description" value="myjob1 descrition"/>

  <!-- <property name="robotsPolicyName" value="obey"/> -->

  <!-- <property name="operator" value=""/> -->

  <!-- <property name="operatorFrom" value=""/> -->

  <!-- <property name="organization" value=""/> -->

  <!-- <property name="audience" value=""/> -->

  <!-- <property name="userAgentTemplate" 

         value="Mozilla/5.0 (compatible; heritrix/3.1.0 [email protected])"/> -->

       

 </bean>

 

 <!-- SEEDS: crawl starting points 

      ConfigString allows simple, inline specification of a moderate

      number of seeds; see below comment for example of using an

      arbitrarily-large external file. -->

 <bean id="seeds" class="org.archive.modules.seeds.TextSeedModule">

     <property name="textSource">

      <bean class="org.archive.spring.ConfigString">

       <property name="value">

        <value>

# [see override above]

        </value>

       </property>

      </bean>

     </property>

<!-- <property name='sourceTagSeeds' value='false'/> -->

<!-- <property name='blockAwaitingSeedLines' value='-1'/> -->

 </bean>

 

 <!-- SEEDS ALTERNATE APPROACH: specifying external seeds.txt file in

      the job directory, similar to the H1 approach. 

      Use either the above, or this, but not both. -->

 <!-- 

 <bean id="seeds" class="org.archive.modules.seeds.TextSeedModule">

  <property name="textSource">

   <bean class="org.archive.spring.ConfigFile">

    <property name="path" value="seeds.txt" />

   </bean>

  </property>

  <property name='sourceTagSeeds' value='false'/>

  <property name='blockAwaitingSeedLines' value='-1'/>

 </bean>

  -->

 

 <!-- SCOPE: rules for which discovered URIs to crawl; order is very 

      important because last decision returned other than 'NONE' wins. -->

 <bean id="scope" class="org.archive.modules.deciderules.DecideRuleSequence">

  <!-- <property name="logToFile" value="false" /> -->

  <property name="rules">

   <list>

    <!-- Begin by REJECTing all... -->

    <bean class="org.archive.modules.deciderules.RejectDecideRule">

    </bean>

    <!-- ...then ACCEPT those within configured/seed-implied SURT prefixes... -->

    <bean class="org.archive.modules.deciderules.surt.SurtPrefixedDecideRule">

     <!-- <property name="seedsAsSurtPrefixes" value="true" /> -->

     <!-- <property name="alsoCheckVia" value="false" /> -->

     <!-- <property name="surtsSourceFile" value="" /> -->

     <!-- <property name="surtsDumpFile" value="${launchId}/surts.dump" /> -->

     <!-- <property name="surtsSource">

           <bean class="org.archive.spring.ConfigString">

            <property name="value">

             <value>

              # example.com

              # http://www.example.edu/path1/

              # +http://(org,example,

             </value>

            </property> 

           </bean>

          </property> -->

    </bean>

    <!-- ...but REJECT those more than a configured link-hop-count from start... -->

    <bean class="org.archive.modules.deciderules.TooManyHopsDecideRule">

     <!-- <property name="maxHops" value="20" /> -->

    </bean>

    <!-- ...but ACCEPT those more than a configured link-hop-count from start... -->

    <bean class="org.archive.modules.deciderules.TransclusionDecideRule">

     <!-- <property name="maxTransHops" value="2" /> -->

     <!-- <property name="maxSpeculativeHops" value="1" /> -->

    </bean>

    <!-- ...but REJECT those from a configurable (initially empty) set of REJECT SURTs... -->

    <bean class="org.archive.modules.deciderules.surt.SurtPrefixedDecideRule">

          <property name="decision" value="REJECT"/>

          <property name="seedsAsSurtPrefixes" value="false"/>

          <property name="surtsDumpFile" value="${launchId}/negative-surts.dump" /> 

     <!-- <property name="surtsSource">

           <bean class="org.archive.spring.ConfigFile">

            <property name="path" value="negative-surts.txt" />

           </bean>

          </property> -->

    </bean>

    <!-- ...and REJECT those from a configurable (initially empty) set of URI regexes... -->

    <bean class="org.archive.modules.deciderules.MatchesListRegexDecideRule">

          <property name="decision" value="REJECT"/>

     <!-- <property name="listLogicalOr" value="true" /> -->

     <!-- <property name="regexList">

           <list>

           </list>

          </property> -->

    </bean>

    <!-- ...and REJECT those with suspicious repeating path-segments... -->

    <bean class="org.archive.modules.deciderules.PathologicalPathDecideRule">

     <!-- <property name="maxRepetitions" value="2" /> -->

    </bean>

    <!-- ...and REJECT those with more than threshold number of path-segments... -->

    <bean class="org.archive.modules.deciderules.TooManyPathSegmentsDecideRule">

     <!-- <property name="maxPathDepth" value="20" /> -->

    </bean>

    <!-- ...but always ACCEPT those marked as prerequisitee for another URI... -->

    <bean class="org.archive.modules.deciderules.PrerequisiteAcceptDecideRule">

    </bean>

    <!-- ...but always REJECT those with unsupported URI schemes -->

    <bean class="org.archive.modules.deciderules.SchemeNotInSetDecideRule">

    </bean>

   </list>

  </property>

 </bean>

 

 <!-- 

   PROCESSING CHAINS

    Much of the crawler's work is specified by the sequential 

    application of swappable Processor modules. These Processors

    are collected into three 'chains'. The CandidateChain is applied 

    to URIs being considered for inclusion, before a URI is enqueued

    for collection. The FetchChain is applied to URIs when their 

    turn for collection comes up. The DispositionChain is applied 

    after a URI is fetched and analyzed/link-extracted.

  -->

  

 <!-- CANDIDATE CHAIN --> 

 <!-- first, processors are declared as top-level named beans -->

 <bean id="candidateScoper" class="org.archive.crawler.prefetch.CandidateScoper">

 </bean>

 <bean id="preparer" class="org.archive.crawler.prefetch.FrontierPreparer">

  <!-- <property name="preferenceDepthHops" value="-1" /> -->

  <!-- <property name="preferenceEmbedHops" value="1" /> -->

  <!-- <property name="canonicalizationPolicy"> 

        <ref bean="canonicalizationPolicy" />

       </property> -->

  <!-- <property name="queueAssignmentPolicy"> 

        <ref bean="queueAssignmentPolicy" />

       </property> -->

  <!-- <property name="uriPrecedencePolicy"> 

        <ref bean="uriPrecedencePolicy" />

       </property> -->

  <!-- <property name="costAssignmentPolicy"> 

        <ref bean="costAssignmentPolicy" />

       </property> -->

 </bean>

 <!-- now, processors are assembled into ordered CandidateChain bean -->

 <bean id="candidateProcessors" class="org.archive.modules.CandidateChain">

  <property name="processors">

   <list>

    <!-- apply scoping rules to each individual candidate URI... -->

    <ref bean="candidateScoper"/>

    <!-- ...then prepare those ACCEPTed to be enqueued to frontier. -->

    <ref bean="preparer"/>

   </list>

  </property>

 </bean>

  

 <!-- FETCH CHAIN --> 

 <!-- first, processors are declared as top-level named beans -->

 <bean id="preselector" class="org.archive.crawler.prefetch.MyPreselector">

      <!-- <property name="recheckScope" value="false" />-->

     <!--  <property name="blockAll" value="false" />-->

     <!--  <property name="blockByRegex" value="" />-->

     <!--  <property name="allowByRegex" value="" />-->

 </bean>

 <bean id="preconditions" class="org.archive.crawler.prefetch.PreconditionEnforcer">

  <!-- <property name="ipValidityDurationSeconds" value="21600" /> -->

  <!-- <property name="robotsValidityDurationSeconds" value="86400" /> -->

  <!-- <property name="calculateRobotsOnly" value="false" /> -->

 </bean>

 <bean id="fetchDns" class="org.archive.modules.fetcher.FetchDNS">

  <!-- <property name="acceptNonDnsResolves" value="false" /> -->

  <!-- <property name="digestContent" value="true" /> -->

  <!-- <property name="digestAlgorithm" value="sha1" /> -->

 </bean>

 <!-- <bean id="fetchWhois" class="org.archive.modules.fetcher.FetchWhois">

       <property name="specialQueryTemplates">

        <map>

         <entry key="whois.verisign-grs.com" value="domain %s" />

         <entry key="whois.arin.net" value="z + %s" />

         <entry key="whois.denic.de" value="-T dn %s" />

        </map>

       </property> 

      </bean> -->

 <bean id="fetchHttp" class="org.archive.modules.fetcher.FetchHTTP">

  <!-- <property name="useHTTP11" value="false" /> -->

  <!-- <property name="maxLengthBytes" value="0" /> -->

  <!-- <property name="timeoutSeconds" value="1200" /> -->

  <!-- <property name="maxFetchKBSec" value="0" /> -->

  <!-- <property name="defaultEncoding" value="ISO-8859-1" /> -->

  <!-- <property name="shouldFetchBodyRule"> 

        <bean class="org.archive.modules.deciderules.AcceptDecideRule"/>

       </property> -->

  <!-- <property name="soTimeoutMs" value="20000" /> -->

  <!-- <property name="sendIfModifiedSince" value="true" /> -->

  <!-- <property name="sendIfNoneMatch" value="true" /> -->

  <!-- <property name="sendConnectionClose" value="true" /> -->

  <!-- <property name="sendReferer" value="true" /> -->

  <!-- <property name="sendRange" value="false" /> -->

  <!-- <property name="ignoreCookies" value="false" /> -->

  <!-- <property name="sslTrustLevel" value="OPEN" /> -->

  <!-- <property name="acceptHeaders"> 

        <list>

         <value>Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8</value>

        </list>

       </property>

  -->

  <!-- <property name="httpBindAddress" value="" /> -->

  <!-- <property name="httpProxyHost" value="" /> -->

  <!-- <property name="httpProxyPort" value="0" /> -->

  <!-- <property name="httpProxyUser" value="" /> -->

  <!-- <property name="httpProxyPassword" value="" /> -->

  <!-- <property name="digestContent" value="true" /> -->

  <!-- <property name="digestAlgorithm" value="sha1" /> -->

 </bean>

 <bean id="extractorHttp" class="org.archive.modules.extractor.ExtractorHTTP">

 </bean>

 <bean id="extractorHtml" class="org.archive.modules.extractor.ExtractorHTML">

  <!-- <property name="extractJavascript" value="true" /> -->

  <!-- <property name="extractValueAttributes" value="true" /> -->

  <!-- <property name="ignoreFormActionUrls" value="false" /> -->

  <!-- <property name="extractOnlyFormGets" value="true" /> -->

  <!-- <property name="treatFramesAsEmbedLinks" value="true" /> -->

  <!-- <property name="ignoreUnexpectedHtml" value="true" /> -->

  <!-- <property name="maxElementLength" value="1024" /> -->

  <!-- <property name="maxAttributeNameLength" value="1024" /> -->

  <!-- <property name="maxAttributeValueLength" value="16384" /> -->

 </bean>

 <bean id="extractorCss" class="org.archive.modules.extractor.ExtractorCSS">

 </bean> 

 <bean id="extractorJs" class="org.archive.modules.extractor.ExtractorJS">

 </bean>

 <bean id="extractorSwf" class="org.archive.modules.extractor.ExtractorSWF">

 </bean>    

 <!-- now, processors are assembled into ordered FetchChain bean -->

 <bean id="fetchProcessors" class="org.archive.modules.FetchChain">

  <property name="processors">

   <list>

    <!-- re-check scope, if so enabled... -->

    <ref bean="preselector"/>

    <!-- ...then verify or trigger prerequisite URIs fetched, allow crawling... -->

    <ref bean="preconditions"/>

    <!-- ...fetch if DNS URI... -->

    <ref bean="fetchDns"/>

    <!-- <ref bean="fetchWhois"/> -->

    <!-- ...fetch if HTTP URI... -->

    <ref bean="fetchHttp"/>

    <!-- ...extract outlinks from HTTP headers... -->

    <ref bean="extractorHttp"/>

    <!-- ...extract outlinks from HTML content... -->

    <ref bean="extractorHtml"/>

    <!-- ...extract outlinks from CSS content... -->

    <ref bean="extractorCss"/>

    <!-- ...extract outlinks from Javascript content... -->

    <ref bean="extractorJs"/>

    <!-- ...extract outlinks from Flash content... -->

    <ref bean="extractorSwf"/>

   </list>

  </property>

 </bean>

  

 <!-- DISPOSITION CHAIN -->

 <!-- first, processors are declared as top-level named beans  -->

 <bean id="warcWriter" class="org.archive.modules.writer.MirrorWriterProcessor">

  <!-- <property name="compress" value="true" /> -->

  <!-- <property name="prefix" value="IAH" /> -->

  <!-- <property name="suffix" value="${HOSTNAME}" /> -->

  <!-- <property name="maxFileSizeBytes" value="1000000000" /> -->

  <!-- <property name="poolMaxActive" value="1" /> -->

  <!-- <property name="MaxWaitForIdleMs" value="500" /> -->

  <!-- <property name="skipIdenticalDigests" value="false" /> -->

  <!-- <property name="maxTotalBytesToWrite" value="0" /> -->

  <!-- <property name="directory" value="${launchId}" /> -->

  <!-- <property name="storePaths">

        <list>

         <value>warcs</value>

        </list>

       </property> -->

  <!-- <property name="writeRequests" value="true" /> -->

  <!-- <property name="writeMetadata" value="true" /> -->

  <!-- <property name="writeRevisitForIdenticalDigests" value="true" /> -->

  <!-- <property name="writeRevisitForNotModified" value="true" /> -->

 </bean>

 <bean id="candidates" class="org.archive.crawler.postprocessor.CandidatesProcessor">

  <!-- <property name="seedsRedirectNewSeeds" value="true" /> -->

 </bean>

 <bean id="disposition" class="org.archive.crawler.postprocessor.DispositionProcessor">

  <!-- <property name="delayFactor" value="5.0" /> -->

  <!-- <property name="minDelayMs" value="3000" /> -->

  <!-- <property name="respectCrawlDelayUpToSeconds" value="300" /> -->

  <!-- <property name="maxDelayMs" value="30000" /> -->

  <!-- <property name="maxPerHostBandwidthUsageKbSec" value="0" /> -->

 </bean>

 <!-- <bean id="rescheduler" class="org.archive.crawler.postprocessor.ReschedulingProcessor">

       <property name="rescheduleDelaySeconds" value="-1" />

      </bean> -->

 <!-- now, processors are assembled into ordered DispositionChain bean -->

 <bean id="dispositionProcessors" class="org.archive.modules.DispositionChain">

  <property name="processors">

   <list>

    <!-- write to aggregate archival files... -->

    <ref bean="warcWriter"/>

    <!-- ...send each outlink candidate URI to CandidateChain, 

         and enqueue those ACCEPTed to the frontier... -->

    <ref bean="candidates"/>

    <!-- ...then update stats, shared-structures, frontier decisions -->

    <ref bean="disposition"/>

    <!-- <ref bean="rescheduler" /> -->

   </list>

  </property>

 </bean>

 

 <!-- CRAWLCONTROLLER: Control interface, unifying context -->

 <bean id="crawlController" 

   class="org.archive.crawler.framework.CrawlController">

  <!-- <property name="maxToeThreads" value="25" /> -->

  <!-- <property name="pauseAtStart" value="true" /> -->

  <!-- <property name="runWhileEmpty" value="false" /> -->

  <!-- <property name="recorderInBufferBytes" value="524288" /> -->

  <!-- <property name="recorderOutBufferBytes" value="16384" /> -->

  <!-- <property name="scratchDir" value="scratch" /> -->

 </bean>

 

 <!-- FRONTIER: Record of all URIs discovered and queued-for-collection -->

 <bean id="frontier" 

   class="org.archive.crawler.frontier.BdbFrontier">

  <!-- <property name="queueTotalBudget" value="-1" /> -->

  <!-- <property name="balanceReplenishAmount" value="3000" /> -->

  <!-- <property name="errorPenaltyAmount" value="100" /> -->

  <!-- <property name="precedenceFloor" value="255" /> -->

  <!-- <property name="queuePrecedencePolicy">

        <bean class="org.archive.crawler.frontier.precedence.BaseQueuePrecedencePolicy" />

       </property> -->

  <!-- <property name="snoozeLongMs" value="300000" /> -->

  <!-- <property name="retryDelaySeconds" value="900" /> -->

  <!-- <property name="maxRetries" value="30" /> -->

  <!-- <property name="recoveryLogEnabled" value="true" /> -->

  <!-- <property name="maxOutlinks" value="6000" /> -->

  <!-- <property name="extractIndependently" value="false" /> -->

  <!-- <property name="outbound">

        <bean class="java.util.concurrent.ArrayBlockingQueue">

         <constructor-arg value="200"/>

         <constructor-arg value="true"/>

        </bean>

       </property> -->

  <!-- <property name="inbound">

        <bean class="java.util.concurrent.ArrayBlockingQueue">

         <constructor-arg value="40000"/>

         <constructor-arg value="true"/>

        </bean>

       </property> -->

  <!-- <property name="dumpPendingAtClose" value="false" /> -->

 </bean>

 

 <!-- URI UNIQ FILTER: Used by frontier to remember already-included URIs --> 

 <bean id="uriUniqFilter" 

   class="org.archive.crawler.util.BdbUriUniqFilter">

 </bean>

 

 <!--

   EXAMPLE SETTINGS OVERLAY SHEETS

   Sheets allow some settings to vary by context - usually by URI context,

   so that different sites or sections of sites can be treated differently. 

   Here are some example Sheets for common purposes. The SheetOverlaysManager

   (below) automatically collects all Sheet instances declared among the 

   original beans, but others can be added during the crawl via the scripting 

   interface.

  -->



<!-- forceRetire: any URI to which this sheet's settings are applied 

     will force its containing queue to 'retired' status. -->

<bean id='forceRetire' class='org.archive.spring.Sheet'>

 <property name='map'>

  <map>

   <entry key='disposition.forceRetire' value='true'/>

  </map>

 </property>

</bean>



<!-- smallBudget: any URI to which this sheet's settings are applied 

     will give its containing queue small values for balanceReplenishAmount 

     (causing it to have shorter 'active' periods while other queues are 

     waiting) and queueTotalBudget (causing the queue to enter 'retired' 

     status once that expenditure is reached by URI attempts and errors) -->

<bean id='smallBudget' class='org.archive.spring.Sheet'>

 <property name='map'>

  <map>

   <entry key='frontier.balanceReplenishAmount' value='20'/>

   <entry key='frontier.queueTotalBudget' value='100'/>

  </map>

 </property>

</bean>



<!-- veryPolite: any URI to which this sheet's settings are applied 

     will cause its queue to take extra-long politeness snoozes -->

<bean id='veryPolite' class='org.archive.spring.Sheet'>

 <property name='map'>

  <map>

   <entry key='disposition.delayFactor' value='10'/>

   <entry key='disposition.minDelayMs' value='10000'/>

   <entry key='disposition.maxDelayMs' value='1000000'/>

   <entry key='disposition.respectCrawlDelayUpToSeconds' value='3600'/>

  </map>

 </property>

</bean>



<!-- highPrecedence: any URI to which this sheet's settings are applied 

     will give its containing queue a slightly-higher than default 

     queue precedence value. That queue will then be preferred over 

     other queues for active crawling, never waiting behind lower-

     precedence queues. -->

<bean id='highPrecedence' class='org.archive.spring.Sheet'>

 <property name='map'>

  <map>

   <entry key='frontier.balanceReplenishAmount' value='20'/>

   <entry key='frontier.queueTotalBudget' value='100'/>

  </map>

 </property>

</bean>



<!--

   EXAMPLE SETTINGS OVERLAY SHEET-ASSOCIATION

   A SheetAssociation says certain URIs should have certain overlay Sheets

   applied. This example applies two sheets to URIs matching two SURT-prefixes.

   New associations may also be added mid-crawl using the scripting facility.

  -->



<!--

<bean class='org.archive.crawler.spring.SurtPrefixesSheetAssociation'>

 <property name='surtPrefixes'>

  <list>

   <value>http://(org,example,</value>

   <value>http://(com,example,www,)/</value>

  </list>

 </property>

 <property name='targetSheetNames'>

  <list>

   <value>veryPolite</value>

   <value>smallBudget</value>

  </list>

 </property>

</bean>

-->



 <!-- 

   OPTIONAL BUT RECOMMENDED BEANS

  -->

  

 <!-- ACTIONDIRECTORY: disk directory for mid-crawl operations

      Running job will watch directory for new files with URIs, 

      scripts, and other data to be processed during a crawl. -->

 <bean id="actionDirectory" class="org.archive.crawler.framework.ActionDirectory">

  <!-- <property name="actionDir" value="action" /> -->

  <!-- <property name="doneDir" value="${launchId}/actions-done" /> -->

  <!-- <property name="initialDelaySeconds" value="10" /> -->

  <!-- <property name="delaySeconds" value="30" /> -->

 </bean> 

 

 <!--  CRAWLLIMITENFORCER: stops crawl when it reaches configured limits -->

 <bean id="crawlLimiter" class="org.archive.crawler.framework.CrawlLimitEnforcer">

  <!-- <property name="maxBytesDownload" value="0" /> -->

  <!-- <property name="maxDocumentsDownload" value="0" /> -->

  <!-- <property name="maxTimeSeconds" value="0" /> -->

 </bean>

 

 <!-- CHECKPOINTSERVICE: checkpointing assistance -->

 <bean id="checkpointService" 

   class="org.archive.crawler.framework.CheckpointService">

  <!-- <property name="checkpointIntervalMinutes" value="-1"/> -->

  <!-- <property name="checkpointsDir" value="checkpoints"/> -->

 </bean>

 

 <!-- 

   OPTIONAL BEANS

    Uncomment and expand as needed, or if non-default alternate 

    implementations are preferred.

  -->

  

 <!-- CANONICALIZATION POLICY -->

 <!--

 <bean id="canonicalizationPolicy" 

   class="org.archive.modules.canonicalize.RulesCanonicalizationPolicy">

   <property name="rules">

    <list>

     <bean class="org.archive.modules.canonicalize.LowercaseRule" />

     <bean class="org.archive.modules.canonicalize.StripUserinfoRule" />

     <bean class="org.archive.modules.canonicalize.StripWWWNRule" />

     <bean class="org.archive.modules.canonicalize.StripSessionIDs" />

     <bean class="org.archive.modules.canonicalize.StripSessionCFIDs" />

     <bean class="org.archive.modules.canonicalize.FixupQueryString" />

    </list>

  </property>

 </bean>

 -->

 



 <!-- QUEUE ASSIGNMENT POLICY -->

 <!--

 <bean id="queueAssignmentPolicy" 

   class="org.archive.crawler.frontier.SurtAuthorityQueueAssignmentPolicy">

  <property name="forceQueueAssignment" value="" />

  <property name="deferToPrevious" value="true" />

  <property name="parallelQueues" value="1" />

 </bean>

 -->

 

 <!-- URI PRECEDENCE POLICY -->

 <!--

 <bean id="uriPrecedencePolicy" 

   class="org.archive.crawler.frontier.precedence.CostUriPrecedencePolicy">

 </bean>

 -->

 

 <!-- COST ASSIGNMENT POLICY -->

 <!--

 <bean id="costAssignmentPolicy" 

   class="org.archive.crawler.frontier.UnitCostAssignmentPolicy">

 </bean>

 -->

 

 <!-- CREDENTIAL STORE: HTTP authentication or FORM POST credentials -->

 <!-- 

 <bean id="credentialStore" 

   class="org.archive.modules.credential.CredentialStore">

 </bean>

 -->

 

 <!-- DISK SPACE MONITOR: 

      Pauses the crawl if disk space at monitored paths falls below minimum threshold -->

 <!-- 

 <bean id="diskSpaceMonitor" class="org.archive.crawler.monitor.DiskSpaceMonitor">

   <property name="pauseThresholdMiB" value="500" />

   <property name="monitorConfigPaths" value="true" />

   <property name="monitorPaths">

     <list>

       <value>PATH</value>

     </list>

   </property>

 </bean>

 -->

 

 <!-- 

   REQUIRED STANDARD BEANS

    It will be very rare to replace or reconfigure the following beans.

  -->



 <!-- STATISTICSTRACKER: standard stats/reporting collector -->

 <bean id="statisticsTracker" 

   class="org.archive.crawler.reporting.StatisticsTracker" autowire="byName">

  <!-- <property name="reports">

        <list>

         <bean id="crawlSummaryReport" class="org.archive.crawler.reporting.CrawlSummaryReport" />

         <bean id="seedsReport" class="org.archive.crawler.reporting.SeedsReport" />

         <bean id="hostsReport" class="org.archive.crawler.reporting.HostsReport" />

         <bean id="sourceTagsReport" class="org.archive.crawler.reporting.SourceTagsReport" />

         <bean id="mimetypesReport" class="org.archive.crawler.reporting.MimetypesReport" />

         <bean id="responseCodeReport" class="org.archive.crawler.reporting.ResponseCodeReport" />

         <bean id="processorsReport" class="org.archive.crawler.reporting.ProcessorsReport" />

         <bean id="frontierSummaryReport" class="org.archive.crawler.reporting.FrontierSummaryReport" />

         <bean id="frontierNonemptyReport" class="org.archive.crawler.reporting.FrontierNonemptyReport" />

         <bean id="toeThreadsReport" class="org.archive.crawler.reporting.ToeThreadsReport" />

        </list>

       </property> -->

  <!-- <property name="reportsDir" value="${launchId}/reports" /> -->

  <!-- <property name="liveHostReportSize" value="20" /> -->

  <!-- <property name="intervalSeconds" value="20" /> -->

  <!-- <property name="keepSnapshotsCount" value="5" /> -->

  <!-- <property name="liveHostReportSize" value="20" /> -->

 </bean>

 

 <!-- CRAWLERLOGGERMODULE: shared logging facility -->

 <bean id="loggerModule" 

   class="org.archive.crawler.reporting.CrawlerLoggerModule">

  <!-- <property name="path" value="${launchId}/logs" /> -->

  <!-- <property name="crawlLogPath" value="crawl.log" /> -->

  <!-- <property name="alertsLogPath" value="alerts.log" /> -->

  <!-- <property name="progressLogPath" value="progress-statistics.log" /> -->

  <!-- <property name="uriErrorsLogPath" value="uri-errors.log" /> -->

  <!-- <property name="runtimeErrorsLogPath" value="runtime-errors.log" /> -->

  <!-- <property name="nonfatalErrorsLogPath" value="nonfatal-errors.log" /> -->

  <!-- <property name="logExtraInfo" value="false" /> -->

 </bean>

 

 <!-- SHEETOVERLAYMANAGER: manager of sheets of contextual overlays

      Autowired to include any SheetForSurtPrefix or 

      SheetForDecideRuled beans -->

 <bean id="sheetOverlaysManager" autowire="byType"

   class="org.archive.crawler.spring.SheetOverlaysManager">

 </bean>



 <!-- BDBMODULE: shared BDB-JE disk persistence manager -->

 <bean id="bdb" 

  class="org.archive.bdb.BdbModule">

  <!-- <property name="dir" value="state" /> -->

  <!-- <property name="cachePercent" value="60" /> -->

  <!-- <property name="useSharedCache" value="true" /> -->

  <!-- <property name="expectedConcurrency" value="25" /> -->

 </bean>

 

 <!-- BDBCOOKIESTORAGE: disk-based cookie storage for FetchHTTP -->

 <bean id="cookieStorage" 

   class="org.archive.modules.fetcher.BdbCookieStorage">

  <!-- <property name="cookiesLoadFile"><null/></property> -->

  <!-- <property name="cookiesSaveFile"><null/></property> -->

  <!-- <property name="bdb">

        <ref bean="bdb"/>

       </property> -->

 </bean>

 

 <!-- SERVERCACHE: shared cache of server/host info -->

 <bean id="serverCache" 

   class="org.archive.modules.net.BdbServerCache">

  <!-- <property name="bdb">

        <ref bean="bdb"/>

       </property> -->

 </bean>



 <!-- CONFIG PATH CONFIGURER: required helper making crawl paths relative

      to crawler-beans.cxml file, and tracking crawl files for web UI -->

 <bean id="configPathConfigurer" 

   class="org.archive.spring.ConfigPathConfigurer">

 </bean>

 

</beans>

粗看上去，我们大概能够明白新版本的采集任务配置在bean属性里面，bean之间还存在一些依赖关系

前面部分显然是加载任务种子

<bean id="longerOverrides" class="org.springframework.beans.factory.config.PropertyOverrideConfigurer"></bean>

<bean id="metadata" class="org.archive.modules.CrawlMetadata" autowire="byName"></bean>

<bean id="seeds" class="org.archive.modules.seeds.TextSeedModule"></bean>

scope控制CrawlURI是ACCEPT NONE, 还是REJECT的决策，在org.archive.modules.Processor 的process(CrawlURI uri) 方法被调用

<bean id="scope" class="org.archive.modules.deciderules.DecideRuleSequence"></bean>

再下面部分是处理器链及相关处理器的依赖关系

我通过打印输出了Heritrix3.1.0的处理器链的结构，下面可以看到FetchChain、DispositionChain、CandidateChain三类处理器链各自所依赖的处理器（CandidateChain处理器链实际是DispositionChain处理器链中的CandidatesProcessor处理器所引用的）修正

FetchChain:org.archive.modules.FetchChain


org.archive.crawler.prefetch.Preselector

org.archive.crawler.prefetch.PreconditionEnforcer

org.archive.modules.fetcher.FetchDNS

org.archive.modules.fetcher.FetchHTTP

org.archive.modules.extractor.ExtractorHTTP

org.archive.modules.extractor.ExtractorHTML

org.archive.modules.extractor.ExtractorCSS

org.archive.modules.extractor.ExtractorJS

org.archive.modules.extractor.ExtractorSWF



Frontier:org.archive.crawler.frontier.BdbFrontier



DispositionChain:org.archive.modules.DispositionChain


org.archive.modules.writer.MirrorWriterProcessor

org.archive.crawler.postprocessor.CandidatesProcessor

org.archive.crawler.postprocessor.DispositionProcessor



CandidateChain:org.archive.modules.CandidateChain


org.archive.crawler.prefetch.CandidateScoper

org.archive.crawler.prefetch.FrontierPreparer

正好与上面的crawler-beans.cxml文件相互印证

crawler-beans.cxml文件后面部分的主要是为前面的处理器设置值（用于自定义设置相关采集地址与处理器对象的属性值的映射）

<bean id='forceRetire' class='org.archive.spring.Sheet'></bean>

<bean id='smallBudget' class='org.archive.spring.Sheet'></bean>

<bean id='veryPolite' class='org.archive.spring.Sheet'></bean>

<bean id='highPrecedence' class='org.archive.spring.Sheet'></bean>

后面这个名称为sheetOverlaysManager的bean是管理上面的Sheet部分与处理器的属性值的加载的

<bean id="sheetOverlaysManager" autowire="byType" class="org.archive.crawler.spring.SheetOverlaysManager"></bean>

后面的比较容易理解，其实crawler-beans.cxml文件里面的英文注释已经比较清楚了

<bean id="actionDirectory" class="org.archive.crawler.framework.ActionDirectory"></bean>

<bean id="crawlLimiter" class="org.archive.crawler.framework.CrawlLimitEnforcer"></bean>

<bean id="checkpointService" class="org.archive.crawler.framework.CheckpointService"></bean>

<bean id="statisticsTracker" class="org.archive.crawler.reporting.StatisticsTracker" autowire="byName"></bean>

<bean id="loggerModule" class="org.archive.crawler.reporting.CrawlerLoggerModule"></bean>

<bean id="bdb" class="org.archive.bdb.BdbModule"></bean>

<bean id="cookieStorage" class="org.archive.modules.fetcher.BdbCookieStorage">

<bean id="serverCache"    class="org.archive.modules.net.BdbServerCache"></bean>

<bean id="configPathConfigurer" class="org.archive.spring.ConfigPathConfigurer"></bean>

---------------------------------------------------------------------------

本系列Heritrix 3.1.0 源码解析系本人原创

转载请注明出处 博客园 刺猬的温驯

本文链接 http://www.cnblogs.com/chenying99/archive/2013/04/10/3013284.html

DispositionChain