crawluri.html

用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧

</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>abstract &nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B>Credential.</B><B><A HREF="../../../../../org/archive/crawler/datamodel/credential/Credential.html#populate(org.archive.crawler.datamodel.CrawlURI, org.apache.commons.httpclient.HttpClient, org.apache.commons.httpclient.HttpMethod, java.lang.String)">populate</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
         org.apache.commons.httpclient.HttpClient&nbsp;http,
         org.apache.commons.httpclient.HttpMethod&nbsp;method,
         java.lang.String&nbsp;payload)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;boolean</CODE></FONT></TD>
<TD><CODE><B>Credential.</B><B><A HREF="../../../../../org/archive/crawler/datamodel/credential/Credential.html#rootUriMatch(org.archive.crawler.framework.CrawlController, org.archive.crawler.datamodel.CrawlURI)">rootUriMatch</A></B>(<A HREF="../../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A>&nbsp;controller,
             <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Test passed curi matches this credentials rootUri.</TD>
</TR>
</TABLE>
&nbsp;
<P>
<A NAME="org.archive.crawler.event"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
Uses of <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> in <A HREF="../../../../../org/archive/crawler/event/package-summary.html">org.archive.crawler.event</A></FONT></TH>
</TR>
</TABLE>
&nbsp;
<P>

<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2">Methods in <A HREF="../../../../../org/archive/crawler/event/package-summary.html">org.archive.crawler.event</A> with parameters of type <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></FONT></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>CrawlURIDispositionListener.</B><B><A HREF="../../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIDisregard(org.archive.crawler.datamodel.CrawlURI)">crawledURIDisregard</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Notification of a crawled URI that is to be disregarded.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>CrawlURIDispositionListener.</B><B><A HREF="../../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURIFailure(org.archive.crawler.datamodel.CrawlURI)">crawledURIFailure</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Notification of a failed crawling of a URI.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>CrawlURIDispositionListener.</B><B><A HREF="../../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURINeedRetry(org.archive.crawler.datamodel.CrawlURI)">crawledURINeedRetry</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Notification of a failed crawl of a URI that
 will be retried (failure due to possible transient
 problems).</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>CrawlURIDispositionListener.</B><B><A HREF="../../../../../org/archive/crawler/event/CrawlURIDispositionListener.html#crawledURISuccessful(org.archive.crawler.datamodel.CrawlURI)">crawledURISuccessful</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Notification of a successfully crawled URI</TD>
</TR>
</TABLE>
&nbsp;
<P>
<A NAME="org.archive.crawler.extractor"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">
Uses of <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A> in <A HREF="../../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</A></FONT></TH>
</TR>
</TABLE>
&nbsp;
<P>

<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2">Fields in <A HREF="../../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</A> declared as <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></FONT></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>(package private) &nbsp;<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></CODE></FONT></TD>
<TD><CODE><B>CrawlUriSWFAction.</B><B><A HREF="../../../../../org/archive/crawler/extractor/CrawlUriSWFAction.html#curi">curi</A></B></CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
</TABLE>
&nbsp;
<P>

<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2">Methods in <A HREF="../../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</A> that return <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></FONT></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></CODE></FONT></TD>
<TD><CODE><B>ExtractorTool.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorTool.html#getCrawlURI(org.archive.io.arc.ARCRecord, org.archive.util.HttpRecorder)">getCrawlURI</A></B>(<A HREF="../../../../../org/archive/io/arc/ARCRecord.html" title="class in org.archive.io.arc">ARCRecord</A>&nbsp;record,
            <A HREF="../../../../../org/archive/util/HttpRecorder.html" title="class in org.archive.util">HttpRecorder</A>&nbsp;hr)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
</TABLE>
&nbsp;
<P>

<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#CCCCFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left" COLSPAN="2">Methods in <A HREF="../../../../../org/archive/crawler/extractor/package-summary.html">org.archive.crawler.extractor</A> with parameters of type <A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A></FONT></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorHTTP.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorHTTP.html#addHeaderLink(org.archive.crawler.datamodel.CrawlURI, org.apache.commons.httpclient.Header)">addHeaderLink</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
              org.apache.commons.httpclient.Header&nbsp;loc)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>static&nbsp;long</CODE></FONT></TD>
<TD><CODE><B>ExtractorJS.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorJS.html#considerStrings(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, org.archive.crawler.framework.CrawlController, boolean)">considerStrings</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                java.lang.CharSequence&nbsp;cs,
                <A HREF="../../../../../org/archive/crawler/framework/CrawlController.html" title="class in org.archive.crawler.framework">CrawlController</A>&nbsp;controller,
                boolean&nbsp;handlingJSFile)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorXML.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorXML.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorUniversal.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorUniversal.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorURI.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorURI.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Perform usual extraction on a CrawlURI</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorSWF.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorSWF.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>protected &nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorPDF.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorPDF.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorJS.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorJS.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE>&nbsp;void</CODE></FONT></TD>
<TD><CODE><B>ExtractorImpliedURI.</B><B><A HREF="../../../../../org/archive/crawler/extractor/ExtractorImpliedURI.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></B>(<A HREF="../../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</CODE>

<BR>