Heritrix的MirrorWriter

 profiles->default->order.xml

 

<map name="write-processors">
      <newObject name="MirrorWriter" class="org.archive.crawler.writer.MirrorWriterProcessor">
        <boolean name="enabled">true</boolean>
        <newObject name="MirrorWriter#decide-rules" class="org.archive.crawler.deciderules.DecideRuleSequence">
          <map name="rules">
          </map>
        </newObject>
        <boolean name="case-sensitive">true</boolean>
        <stringList name="character-map">
        </stringList>
        <stringList name="content-type-map">
        </stringList>
        <string name="directory-file">index.html</string>
        <string name="dot-begin">%2E</string>
        <string name="dot-end">.</string>
        <stringList name="host-map">
        </stringList>
        <boolean name="host-directory">true</boolean>
        <string name="path">mirror</string>
        <integer name="max-path-length">1023</integer>
        <integer name="max-segment-length">255</integer>
        <boolean name="port-directory">false</boolean>
        <boolean name="suffix-at-end">true</boolean>
        <string name="too-long-directory">LONG</string>
        <stringList name="underscore-set">
        </stringList>
      </newObject>
    </map>