extractorhtml.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

</DL>
<HR>

<A NAME="processScriptCode(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence)"><!-- --></A><H3>
processScriptCode</H3>
<PRE>
protected void <B>processScriptCode</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)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - <DD><CODE>cs</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="processLink(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, java.lang.CharSequence)"><!-- --></A><H3>
processLink</H3>
<PRE>
protected void <B>processLink</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                           java.lang.CharSequence&nbsp;value,
                           java.lang.CharSequence&nbsp;context)</PRE>
<DL>
<DD>Handle generic HREF cases.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - <DD><CODE>value</CODE> - <DD><CODE>context</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="processEmbed(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, java.lang.CharSequence)"><!-- --></A><H3>
processEmbed</H3>
<PRE>
protected final void <B>processEmbed</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                                  java.lang.CharSequence&nbsp;value,
                                  java.lang.CharSequence&nbsp;context)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="processEmbed(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, java.lang.CharSequence, char)"><!-- --></A><H3>
processEmbed</H3>
<PRE>
protected void <B>processEmbed</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                            java.lang.CharSequence&nbsp;value,
                            java.lang.CharSequence&nbsp;context,
                            char&nbsp;hopType)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="extract(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
extract</H3>
<PRE>
public void <B>extract</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../org/archive/crawler/extractor/Extractor.html#extract(org.archive.crawler.datamodel.CrawlURI)">extract</A></CODE> in class <CODE><A HREF="../../../../org/archive/crawler/extractor/Extractor.html" title="class in org.archive.crawler.extractor">Extractor</A></CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="extract(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence)"><!-- --></A><H3>
extract</H3>
<PRE>
void <B>extract</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)</PRE>
<DL>
<DD>Run extractor.
 This method is package visible to ease testing.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - CrawlURI we're processing.<DD><CODE>cs</CODE> - Sequence from underlying ReplayCharSequence. This
 is TRANSIENT data. Make a copy if you want the data to live outside
 of this extractors' lifetime.</DL>
</DD>
</DL>
<HR>

<A NAME="isHtmlExpectedHere(org.archive.crawler.datamodel.CrawlURI)"><!-- --></A><H3>
isHtmlExpectedHere</H3>
<PRE>
protected boolean <B>isHtmlExpectedHere</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi)
                              throws org.apache.commons.httpclient.URIException</PRE>
<DL>
<DD>Test whether this HTML is so unexpected (eg in place of a GIF URI)
 that it shouldn't be scanned for links.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - CrawlURI to examine.
<DT><B>Returns:</B><DD>True if HTML is acceptable/expected here
<DT><B>Throws:</B>
<DD><CODE>org.apache.commons.httpclient.URIException</CODE></DL>
</DD>
</DL>
<HR>

<A NAME="processScript(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, int)"><!-- --></A><H3>
processScript</H3>
<PRE>
protected void <B>processScript</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                             java.lang.CharSequence&nbsp;sequence,
                             int&nbsp;endOfOpenTag)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="processMeta(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence)"><!-- --></A><H3>
processMeta</H3>
<PRE>
protected boolean <B>processMeta</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)</PRE>
<DL>
<DD>Process metadata tags.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - CrawlURI we're processing.<DD><CODE>cs</CODE> - Sequence from underlying ReplayCharSequence. This
 is TRANSIENT data. Make a copy if you want the data to live outside
 of this extractors' lifetime.
<DT><B>Returns:</B><DD>True robots exclusion metatag.</DL>
</DD>
</DL>
<HR>

<A NAME="processStyle(org.archive.crawler.datamodel.CrawlURI, java.lang.CharSequence, int)"><!-- --></A><H3>
processStyle</H3>
<PRE>
protected void <B>processStyle</B>(<A HREF="../../../../org/archive/crawler/datamodel/CrawlURI.html" title="class in org.archive.crawler.datamodel">CrawlURI</A>&nbsp;curi,
                            java.lang.CharSequence&nbsp;sequence,
                            int&nbsp;endOfOpenTag)</PRE>
<DL>
<DD>Process style text.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>curi</CODE> - CrawlURI we're processing.<DD><CODE>sequence</CODE> - Sequence from underlying ReplayCharSequence. This
 is TRANSIENT data. Make a copy if you want the data to live outside
 of this extractors' lifetime.<DD><CODE>endOfOpenTag</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="report()"><!-- --></A><H3>
report</H3>
<PRE>
public java.lang.String <B>report</B>()</PRE>
<DL>
<DD><B>Description copied from class: <CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html#report()">Processor</A></CODE></B></DD>
<DD>Compiles and returns a report (in human readable form) about the status
 of the processor.  The processor's name (of implementing class) should
 always be included.
 <p>
 Examples of stats declared would include:<br>
 * Number of CrawlURIs handled.<br>
 * Number of links extracted (for link extractors)<br>
 etc.
<P>
<DD><DL>
<DT><B>Overrides:</B><DD><CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html#report()">report</A></CODE> in class <CODE><A HREF="../../../../org/archive/crawler/framework/Processor.html" title="class in org.archive.crawler.framework">Processor</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>A human readable report on the processor's state.</DL>
</DD>
</DL>
<!-- ========= END OF CLASS DATA ========= -->
<HR>


<!-- ======= START OF BOTTOM NAVBAR ====== -->
<A NAME="navbar_bottom"><!-- --></A>
<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
<TR>
<TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
<A NAME="navbar_bottom_firstrow"><!-- --></A>
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
  <TR ALIGN="center" VALIGN="top">
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="class-use/ExtractorHTML.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
  </TR>
</TABLE>
</TD>
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
</EM>
</TD>
</TR>

<TR>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
&nbsp;<A HREF="../../../../org/archive/crawler/extractor/ExtractorDOC.html" title="class in org.archive.crawler.extractor"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../../../org/archive/crawler/extractor/ExtractorHTTP.html" title="class in org.archive.crawler.extractor"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../../index.html?org/archive/crawler/extractor/ExtractorHTML.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="ExtractorHTML.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
&nbsp;<SCRIPT type="text/javascript">
  <!--
  if(window==top) {
    document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>');
  }
  //-->
</SCRIPT>
<NOSCRIPT>
  <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>
</NOSCRIPT>


</FONT></TD>
</TR>
<TR>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
  SUMMARY:&nbsp;<A HREF="#nested_classes_inherited_from_class_org.archive.crawler.settings.ComplexType">NESTED</A>&nbsp;|&nbsp;<A HREF="#field_summary">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
DETAIL:&nbsp;<A HREF="#field_detail">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
</TR>
</TABLE>
<A NAME="skip-navbar_bottom"></A>
<!-- ======== END OF BOTTOM NAVBAR ======= -->

<HR>
Copyright &copy; 2003-2006 Internet Archive. All Rights Reserved.
</BODY>
</HTML>