crawlcontroller.html

一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫一个开源的网页爬虫

<DL>
</DL>
</DL>
<HR>

<A NAME="reports"><!-- --></A><H3>
reports</H3>
<PRE>
public transient java.util.logging.Logger <B>reports</B></PRE>
<DL>
<DD>Logger to hold job summary report.

 Large state reports made at infrequent intervals (e.g. job ending) go
 here.
<P>
<DL>
</DL>
</DL>
<HR>

<A NAME="statistics"><!-- --></A><H3>
statistics</H3>
<PRE>
protected <A HREF="../../../../org/archive/crawler/framework/StatisticsTracking.html" title="interface in org.archive.crawler.framework">StatisticsTracking</A> <B>statistics</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="registeredCrawlURIDispositionListeners"><!-- --></A><H3>
registeredCrawlURIDispositionListeners</H3>
<PRE>
protected transient java.util.ArrayList <B>registeredCrawlURIDispositionListeners</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="PROCESSORS_REPORT"><!-- --></A><H3>
PROCESSORS_REPORT</H3>
<PRE>
public static final java.lang.String <B>PROCESSORS_REPORT</B></PRE>
<DL>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.PROCESSORS_REPORT">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="MANIFEST_REPORT"><!-- --></A><H3>
MANIFEST_REPORT</H3>
<PRE>
public static final java.lang.String <B>MANIFEST_REPORT</B></PRE>
<DL>
<DL>
<DT><B>See Also:</B><DD><A HREF="../../../../constant-values.html#org.archive.crawler.framework.CrawlController.MANIFEST_REPORT">Constant Field Values</A></DL>
</DL>
<HR>

<A NAME="REPORTS"><!-- --></A><H3>
REPORTS</H3>
<PRE>
protected static final java.lang.String[] <B>REPORTS</B></PRE>
<DL>
<DL>
</DL>
</DL>

<!-- ========= CONSTRUCTOR DETAIL ======== -->

<A NAME="constructor_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Constructor Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="CrawlController()"><!-- --></A><H3>
CrawlController</H3>
<PRE>
public <B>CrawlController</B>()</PRE>
<DL>
<DD>Default constructor
<P>
</DL>

<!-- ============ METHOD DETAIL ========== -->

<A NAME="method_detail"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">
<B>Method Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="initialize(org.archive.crawler.settings.SettingsHandler)"><!-- --></A><H3>
initialize</H3>
<PRE>
public void <B>initialize</B>(<A HREF="../../../../org/archive/crawler/settings/SettingsHandler.html" title="class in org.archive.crawler.settings">SettingsHandler</A>&nbsp;sH)
                throws <A HREF="../../../../org/archive/crawler/framework/exceptions/InitializationException.html" title="class in org.archive.crawler.framework.exceptions">InitializationException</A></PRE>
<DL>
<DD>Starting from nothing, set up CrawlController and associated
 classes to be ready for a first crawl.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>sH</CODE> - Settings handler.
<DT><B>Throws:</B>
<DD><CODE><A HREF="../../../../org/archive/crawler/framework/exceptions/InitializationException.html" title="class in org.archive.crawler.framework.exceptions">InitializationException</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="setupCheckpointRecover()"><!-- --></A><H3>
setupCheckpointRecover</H3>
<PRE>
protected void <B>setupCheckpointRecover</B>()
                               throws java.io.IOException</PRE>
<DL>
<DD>Does setup of checkpoint recover.
 Copies bdb log files into state dir.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Throws:</B>
<DD><CODE>java.io.IOException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="getCheckpointCopyBdbjeLogs()"><!-- --></A><H3>
getCheckpointCopyBdbjeLogs</H3>
<PRE>
protected boolean <B>getCheckpointCopyBdbjeLogs</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="getBdbEnvironment()"><!-- --></A><H3>
getBdbEnvironment</H3>
<PRE>
public com.sleepycat.je.Environment <B>getBdbEnvironment</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="getClassCatalog()"><!-- --></A><H3>
getClassCatalog</H3>
<PRE>
public com.sleepycat.bind.serial.StoredClassCatalog <B>getClassCatalog</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="addCrawlStatusListener(org.archive.crawler.event.CrawlStatusListener)"><!-- --></A><H3>
addCrawlStatusListener</H3>
<PRE>
public void <B>addCrawlStatusListener</B>(<A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html" title="interface in org.archive.crawler.event">CrawlStatusListener</A>&nbsp;cl)</PRE>
<DL>
<DD>Register for CrawlStatus events.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>cl</CODE> - a class implementing the CrawlStatusListener interface<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/event/CrawlStatusListener.html" title="interface in org.archive.crawler.event"><CODE>CrawlStatusListener</CODE></A></DL>
</DD>
</DL>
<HR>

<A NAME="addCrawlURIDispositionListener(org.archive.crawler.event.CrawlURIDispositionListener)"><!-- --></A><H3>
addCrawlURIDispositionListener</H3>
<PRE>
public void <B>addCrawlURIDispositionListener</B>(<A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event">CrawlURIDispositionListener</A>&nbsp;cl)</PRE>
<DL>
<DD>Register for CrawlURIDisposition events.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>cl</CODE> - a class implementing the CrawlURIDispostionListener interface<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html" title="interface in org.archive.crawler.event"><CODE>CrawlURIDispositionListener</CODE></A></DL>
</DD>
</DL>
<HR>

<A NAME="fireCrawledURISuccessfulEvent(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
fireCrawledURISuccessfulEvent</H3>
<PRE>
public void <B>fireCrawledURISuccessfulEvent</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD>Allows an external class to raise a CrawlURIDispostion
 crawledURISuccessful event that will be broadcast to all listeners that
 have registered with the CrawlController.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - - The CrawlURI that will be sent with the event notification.<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURISuccessful(org.archive.crawler.datamodel.CrawlURI)"><CODE>CrawlURIDispositionListener.crawledURISuccessful(CrawlURI)</CODE></A></DL>
</DD>
</DL>
<HR>

<A NAME="fireCrawledURINeedRetryEvent(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
fireCrawledURINeedRetryEvent</H3>
<PRE>
public void <B>fireCrawledURINeedRetryEvent</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD>Allows an external class to raise a CrawlURIDispostion
 crawledURINeedRetry event that will be broadcast to all listeners that
 have registered with the CrawlController.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - - The CrawlURI that will be sent with the event notification.<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURINeedRetry(org.archive.crawler.datamodel.CrawlURI)"><CODE>CrawlURIDispositionListener.crawledURINeedRetry(CrawlURI)</CODE></A></DL>
</DD>
</DL>
<HR>

<A NAME="fireCrawledURIDisregardEvent(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
fireCrawledURIDisregardEvent</H3>
<PRE>
public void <B>fireCrawledURIDisregardEvent</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD>Allows an external class to raise a CrawlURIDispostion
 crawledURIDisregard event that will be broadcast to all listeners that
 have registered with the CrawlController.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - -
            The CrawlURI that will be sent with the event notification.<DT><B>See Also:</B><DD><A HREF="../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIDisregard(org.archive.crawler.datamodel.CrawlURI)"><CODE>CrawlURIDispositionListener.crawledURIDisregard(CrawlURI)</CODE></A></DL>
</DD>
</DL>
<HR>

<A NAME="fireCrawledURIFailureEvent(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
fireCrawledURIFailureEvent</H3>
<PRE>
public void <B>fireCrawledURIFailureEvent</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD>Allows an external class to raise a CrawlURIDispostion crawledURIFailure event
 that will be broadcast to all listeners that have registered with the CrawlController.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - - Th