<map>
<entry>
<string>plugin_identifier</string>
<string>edu.rice.library.wrc</string>
</entry>
<entry>
<string>au_def_pause_time</string>
<long>6000</long>
</entry>
<entry>
<string>plugin_version</string>
<string>4</string>
</entry>
<entry>
<string>au_crawl_depth</string>
<int>99</int>
</entry>
<entry>
<string>au_name</string>
<string>"Rice University WRC"</string>
</entry>
<entry>
<string>au_def_new_content_crawl</string>
<long>7776000000</long>
</entry>
<entry>
<string>plugin_name</string>
<string>Rice University WRC</string>
</entry>
<entry>
<string>plugin_notes</string>
<string>The WRC collection is harvested out of a DSPACE instance.
Manifest pages list items by linking to them as '/handle/1911/17017?show=full'. The plugin includes only the manifest pages, bitstreams and links that end in '/handle/1911/NUMBER?show=full'</string>
</entry>
<entry>
<string>au_crawlrules</string>
<list>
<string>1,"^%s/lockss/manifest-wrc.html", base_url</string>
<string>1,"^%s/bitstream/", base_url</string>
<string>1,"^%s/dspace-oai", base_url</string>
<string>1,"/handle/1911/[0-9]+\?show=full$"</string>
</list>
</entry>
<entry>
<string>au_start_url</string>
<string>"%s/lockss/manifest-wrc.html", base_url</string>
</entry>
<entry>
<string>plugin_config_props</string>
<list>
<org.lockss.daemon.ConfigParamDescr>
<key>base_url</key>
<displayName>Base URL</displayName>
<description>Usually of the form http://<journal-name>.com/</description>
<type>3</type>
<size>40</size>
<definitional>true</definitional>
<defaultOnly>false</defaultOnly>
</org.lockss.daemon.ConfigParamDescr>
</list>
</entry>
</map>
Parameter Values |
Status |
Copies |
|
(Loading) |