charsequencelinkextractor.html

来自「网络爬虫开源代码」· HTML 代码 · 共 731 行 · 第 1/3 页

<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;java.lang.Object</CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#next()">next</A></B>()</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;<A HREF="../../../org/archive/crawler/extractor/Link.html" title="class in org.archive.crawler.extractor">Link</A></CODE></FONT></TD>
<TD><CODE><B><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#nextLink()">nextLink</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Alternative to Iterator.next() which returns type Link.</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#remove()">remove</A></B>()</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#reset()">reset</A></B>()</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Discard all state.</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#setup(org.archive.net.UURI, java.lang.CharSequence, org.archive.extractor.ExtractErrorListener)">setup</A></B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;sourceandbase,
      java.lang.CharSequence&nbsp;content,
      <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Convenience method for when source and base are same.</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#setup(org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)">setup</A></B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;sourceandbase,
      java.io.InputStream&nbsp;content,
      java.nio.charset.Charset&nbsp;charset,
      <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Convenience version of above for common case where source and base are 
 same.</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#setup(org.archive.net.UURI, org.archive.net.UURI, java.lang.CharSequence, org.archive.extractor.ExtractErrorListener)">setup</A></B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;source,
      <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;base,
      java.lang.CharSequence&nbsp;content,
      <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</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><A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html#setup(org.archive.net.UURI, org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)">setup</A></B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;source,
      <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;base,
      java.io.InputStream&nbsp;content,
      java.nio.charset.Charset&nbsp;charset,
      <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</CODE>

<BR>
&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Setup the LinkExtractor to operate on the given stream and charset,
 considering the given contextURI as the initial 'base' URI for
 resolving relative URIs.</TD>
</TR>
</TABLE>
&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
</TR>
</TABLE>
&nbsp;
<P>

<!-- ============ FIELD DETAIL =========== -->

<A NAME="field_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>Field Detail</B></FONT></TH>
</TR>
</TABLE>

<A NAME="source"><!-- --></A><H3>
source</H3>
<PRE>
protected <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A> <B>source</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="base"><!-- --></A><H3>
base</H3>
<PRE>
protected <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A> <B>base</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="extractErrorListener"><!-- --></A><H3>
extractErrorListener</H3>
<PRE>
protected <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A> <B>extractErrorListener</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="sourceContent"><!-- --></A><H3>
sourceContent</H3>
<PRE>
protected java.lang.CharSequence <B>sourceContent</B></PRE>
<DL>
<DL>
</DL>
</DL>
<HR>

<A NAME="next"><!-- --></A><H3>
next</H3>
<PRE>
protected java.util.LinkedList&lt;<A HREF="../../../org/archive/crawler/extractor/Link.html" title="class in org.archive.crawler.extractor">Link</A>&gt; <B>next</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="CharSequenceLinkExtractor()"><!-- --></A><H3>
CharSequenceLinkExtractor</H3>
<PRE>
public <B>CharSequenceLinkExtractor</B>()</PRE>
<DL>
</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="setup(org.archive.net.UURI, org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)"><!-- --></A><H3>
setup</H3>
<PRE>
public void <B>setup</B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;source,
                  <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;base,
                  java.io.InputStream&nbsp;content,
                  java.nio.charset.Charset&nbsp;charset,
                  <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</PRE>
<DL>
<DD><B>Description copied from interface: <CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#setup(org.archive.net.UURI, org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)">LinkExtractor</A></CODE></B></DD>
<DD>Setup the LinkExtractor to operate on the given stream and charset,
 considering the given contextURI as the initial 'base' URI for
 resolving relative URIs.

 May be called to 'reset' a LinkExtractor to start with new input.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#setup(org.archive.net.UURI, org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)">setup</A></CODE> in interface <CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html" title="interface in org.archive.extractor">LinkExtractor</A></CODE></DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>source</CODE> - source URI<DD><CODE>base</CODE> - base URI (usually the source URI) for URI derelativizing<DD><CODE>content</CODE> - input stream of content to scan for links<DD><CODE>charset</CODE> - Charset to consult to decode stream to characters<DD><CODE>listener</CODE> - ExtractErrorListener to notify, rather than raising
   exception through extraction loop</DL>
</DD>
</DL>
<HR>

<A NAME="setup(org.archive.net.UURI, org.archive.net.UURI, java.lang.CharSequence, org.archive.extractor.ExtractErrorListener)"><!-- --></A><H3>
setup</H3>
<PRE>
public void <B>setup</B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;source,
                  <A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;base,
                  java.lang.CharSequence&nbsp;content,
                  <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>source</CODE> - <DD><CODE>base</CODE> - <DD><CODE>content</CODE> - <DD><CODE>listener</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="setup(org.archive.net.UURI, java.lang.CharSequence, org.archive.extractor.ExtractErrorListener)"><!-- --></A><H3>
setup</H3>
<PRE>
public void <B>setup</B>(<A HREF="../../../org/archive/net/UURI.html" title="class in org.archive.net">UURI</A>&nbsp;sourceandbase,
                  java.lang.CharSequence&nbsp;content,
                  <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;listener)</PRE>
<DL>
<DD>Convenience method for when source and base are same.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>sourceandbase</CODE> - <DD><CODE>content</CODE> - <DD><CODE>listener</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="setup(org.archive.net.UURI, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)"><!-- --></A><H3>