charsequencelinkextractor.html

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

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.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, java.io.InputStream, java.nio.charset.Charset, org.archive.extractor.ExtractErrorListener)">LinkExtractor</A></CODE></B></DD>
<DD>Convenience version of above for common case where source and base are 
 same.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#setup(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>sourceandbase</CODE> - URI to use as source and base for 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="nextLink()"><!-- --></A><H3>
nextLink</H3>
<PRE>
public <A HREF="../../../org/archive/crawler/extractor/Link.html" title="class in org.archive.crawler.extractor">Link</A> <B>nextLink</B>()</PRE>
<DL>
<DD><B>Description copied from interface: <CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#nextLink()">LinkExtractor</A></CODE></B></DD>
<DD>Alternative to Iterator.next() which returns type Link.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#nextLink()">nextLink</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>Returns:</B><DD>a discovered Link</DL>
</DD>
</DL>
<HR>

<A NAME="reset()"><!-- --></A><H3>
reset</H3>
<PRE>
public void <B>reset</B>()</PRE>
<DL>
<DD>Discard all state. Another setup() is required to use again.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../org/archive/extractor/LinkExtractor.html#reset()">reset</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>
</DL>
</DD>
</DL>
<HR>

<A NAME="hasNext()"><!-- --></A><H3>
hasNext</H3>
<PRE>
public boolean <B>hasNext</B>()</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE>hasNext</CODE> in interface <CODE>java.util.Iterator</CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="findNextLink()"><!-- --></A><H3>
findNextLink</H3>
<PRE>
protected abstract boolean <B>findNextLink</B>()</PRE>
<DL>
<DD>Scan to the next link(s), if any, loading it into the next buffer.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>true if any links are found/available, false otherwise</DL>
</DD>
</DL>
<HR>

<A NAME="next()"><!-- --></A><H3>
next</H3>
<PRE>
public java.lang.Object <B>next</B>()</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE>next</CODE> in interface <CODE>java.util.Iterator</CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="remove()"><!-- --></A><H3>
remove</H3>
<PRE>
public void <B>remove</B>()</PRE>
<DL>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE>remove</CODE> in interface <CODE>java.util.Iterator</CODE></DL>
</DD>
<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="charSequenceFrom(java.io.InputStream, java.nio.charset.Charset)"><!-- --></A><H3>
charSequenceFrom</H3>
<PRE>
protected java.lang.CharSequence <B>charSequenceFrom</B>(java.io.InputStream&nbsp;content,
                                                  java.nio.charset.Charset&nbsp;charset)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>content</CODE> - <DD><CODE>charset</CODE> - 
<DT><B>Returns:</B><DD>CharSequence obtained from stream in given charset</DL>
</DD>
</DL>
<HR>

<A NAME="createCharSequenceFrom(java.io.InputStream, java.nio.charset.Charset)"><!-- --></A><H3>
createCharSequenceFrom</H3>
<PRE>
protected java.lang.CharSequence <B>createCharSequenceFrom</B>(java.io.InputStream&nbsp;content,
                                                        java.nio.charset.Charset&nbsp;charset)</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>content</CODE> - <DD><CODE>charset</CODE> - 
<DT><B>Returns:</B><DD>CharSequence built over given stream in given charset</DL>
</DD>
</DL>
<HR>

<A NAME="extract(java.lang.CharSequence, org.archive.net.UURI, org.archive.net.UURI, java.util.List, org.archive.extractor.ExtractErrorListener)"><!-- --></A><H3>
extract</H3>
<PRE>
public static void <B>extract</B>(java.lang.CharSequence&nbsp;content,
                           <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.util.List&lt;<A HREF="../../../org/archive/crawler/extractor/Link.html" title="class in org.archive.crawler.extractor">Link</A>&gt;&nbsp;collector,
                           <A HREF="../../../org/archive/extractor/ExtractErrorListener.html" title="interface in org.archive.extractor">ExtractErrorListener</A>&nbsp;extractErrorListener)</PRE>
<DL>
<DD>Convenience method to do default extraction.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>content</CODE> - <DD><CODE>source</CODE> - <DD><CODE>base</CODE> - <DD><CODE>collector</CODE> - <DD><CODE>extractErrorListener</CODE> - </DL>
</DD>
</DL>
<HR>

<A NAME="newDefaultInstance()"><!-- --></A><H3>
newDefaultInstance</H3>
<PRE>
protected static <A HREF="../../../org/archive/extractor/CharSequenceLinkExtractor.html" title="class in org.archive.extractor">CharSequenceLinkExtractor</A> <B>newDefaultInstance</B>()</PRE>
<DL>
<DD><DL>
</DL>
</DD>
<DD><DL>
</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/CharSequenceLinkExtractor.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;PREV CLASS&nbsp;
&nbsp;<A HREF="../../../org/archive/extractor/CharSequenceProvider.html" title="interface in org.archive.extractor"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../index.html?org/archive/extractor/CharSequenceLinkExtractor.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="CharSequenceLinkExtractor.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;NESTED&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; 2003-2007 Internet Archive. All Rights Reserved.
</BODY>
</HTML>