483 lines
13 KiB
HTML
483 lines
13 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN""http://www.w3.org/TR/REC-html40/loose.dtd">
|
|
<!--NewPage-->
|
|
<HTML>
|
|
<HEAD>
|
|
<TITLE>
|
|
jala.HtmlDocument
|
|
</TITLE>
|
|
<LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
|
|
</HEAD>
|
|
<SCRIPT>
|
|
function asd()
|
|
{
|
|
parent.document.title="jala.HtmlDocument";
|
|
}
|
|
</SCRIPT>
|
|
<BODY BGCOLOR="white" onload="asd();">
|
|
|
|
<!-- ========== START OF NAVBAR ========== -->
|
|
<A NAME="navbar_bottom"><!-- --></A>
|
|
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0">
|
|
<TR>
|
|
<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
|
|
<A NAME="navbar_bottom_firstrow"><!-- --></A>
|
|
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3">
|
|
<TR ALIGN="center" VALIGN="top">
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-summary-HtmlDocument.js.html"><FONT CLASS="NavBarFont1"><B>File</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD>
|
|
<!--TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"--> <!--A HREF="deprecated-list.html"--><!--FONT CLASS="NavBarFont1">Deprecated</FONT--><!--/A--><!-- </TD-->
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="index-all.html"--><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD>
|
|
</TR>
|
|
</TABLE>
|
|
</TD>
|
|
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
|
|
<B>Jala 1.3</B>
|
|
</EM>
|
|
</TD
|
|
</TR>
|
|
|
|
<TR>
|
|
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
|
|
<A HREF="jala.History.html"><B>PREV CLASS</B></A><!--
|
|
NEXT CLASS
|
|
-->
|
|
<A HREF="jala.I18n.html"><B>NEXT CLASS</B></A></FONT></TD>
|
|
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
|
|
<A HREF="index.html" TARGET="_top"><B>FRAMES</B></A>
|
|
<A HREF="jala.HtmlDocument.html" TARGET="_top"><B>NO FRAMES</B></A>
|
|
|
|
<SCRIPT>
|
|
<!--
|
|
if(window==top) {
|
|
document.writeln('<A HREF="allclasses-noframe.html" TARGET=""><B>All Classes</B></A>');
|
|
}
|
|
//-->
|
|
</SCRIPT>
|
|
<NOSCRIPT>
|
|
<A HREF="allclasses-noframe.html" TARGET=""><B>All Classes</B></A>
|
|
</NOSCRIPT>
|
|
</FONT></TD>
|
|
</TR>
|
|
<TR>
|
|
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
|
|
SUMMARY: <A HREF="#field_summary">FIELD</A> | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD>
|
|
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
|
|
DETAIL: <A HREF="#field_detail">FIELD</A> | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD>
|
|
</TR>
|
|
</TABLE>
|
|
<!-- =========== END OF NAVBAR =========== -->
|
|
<HR>
|
|
|
|
<!-- ======== START OF CLASS DATA ======== -->
|
|
<H2>Class jala.HtmlDocument</H2>
|
|
<PRE>Object
|
|
|
|
|
+--<b>jala.HtmlDocument</b>
|
|
</PRE>
|
|
|
|
|
|
<HR>
|
|
<DL>
|
|
<!-- Class definition -->
|
|
<DT>class
|
|
<B>jala.HtmlDocument</B>
|
|
|
|
|
|
</DL>
|
|
|
|
<P>
|
|
<BR/>This class provides easy access to the elements of
|
|
an arbitrary HTML document. By using TagSoup, Dom4J and Jaxen
|
|
even invalid HTML can be parsed, turned into an object tree
|
|
and easily be processed with XPath expressions.
|
|
<BR/><I>Defined in <a href='overview-summary-HtmlDocument.js.html'>HtmlDocument.js</a></I><BR/><BR/>
|
|
</P>
|
|
|
|
<HR>
|
|
|
|
<!-- ======== NESTED CLASS SUMMARY ======== -->
|
|
|
|
<!-- ======== END NESTED CLASS SUMMARY ======== -->
|
|
|
|
|
|
<!-- =========== FIELD SUMMARY =========== -->
|
|
|
|
|
|
|
|
|
|
<!-- =========== END FIELD SUMMARY =========== -->
|
|
|
|
|
|
<!-- ======== CONSTRUCTOR SUMMARY ======== -->
|
|
|
|
<A NAME="constructor_summary"><!-- --></A>
|
|
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
|
|
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
|
|
<TD COLSPAN=2><FONT SIZE="+2">
|
|
<B>Constructor Summary</B></FONT></TD>
|
|
</TR>
|
|
<TR BGCOLOR="white" CLASS="TableRowColor">
|
|
<TD>
|
|
<CODE>
|
|
<B>
|
|
<A HREF="jala.HtmlDocument.html#jala.HtmlDocument()">jala.HtmlDocument</A>
|
|
</B>
|
|
(<String> source)
|
|
</CODE>
|
|
<BR>
|
|
|
|
Construct a new HTML document.
|
|
</TD>
|
|
</TR>
|
|
</TABLE>
|
|
|
|
<!-- ======== END CONSTRUCTOR SUMMARY ======== -->
|
|
|
|
|
|
|
|
<!-- ========== METHOD SUMMARY =========== -->
|
|
|
|
<A NAME="method_summary"><!-- --></A>
|
|
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
|
|
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
|
|
<TD COLSPAN=2><FONT SIZE="+2">
|
|
<B>Method Summary</B></FONT></TD>
|
|
</TR>
|
|
|
|
|
|
<TR BGCOLOR="white" CLASS="TableRowColor">
|
|
<TD ALIGN="right" VALIGN="top" WIDTH="1%">
|
|
<FONT SIZE="-1">
|
|
<CODE> Array</CODE>
|
|
</FONT>
|
|
</TD>
|
|
<TD>
|
|
<CODE>
|
|
<B>
|
|
<A HREF="#getAll">getAll</A></B>(<String> elementName)
|
|
</CODE>
|
|
<BR>
|
|
|
|
Retrieves all elements by name from the document.
|
|
</TD>
|
|
</TR>
|
|
|
|
<TR BGCOLOR="white" CLASS="TableRowColor">
|
|
<TD ALIGN="right" VALIGN="top" WIDTH="1%">
|
|
<FONT SIZE="-1">
|
|
<CODE> Array</CODE>
|
|
</FONT>
|
|
</TD>
|
|
<TD>
|
|
<CODE>
|
|
<B>
|
|
<A HREF="#getLinks">getLinks</A></B>()
|
|
</CODE>
|
|
<BR>
|
|
|
|
Get all link elements of the HTML document.
|
|
</TD>
|
|
</TR>
|
|
|
|
<TR BGCOLOR="white" CLASS="TableRowColor">
|
|
<TD ALIGN="right" VALIGN="top" WIDTH="1%">
|
|
<FONT SIZE="-1">
|
|
<CODE> org.dom4j.tree.DefaultElement</CODE>
|
|
</FONT>
|
|
</TD>
|
|
<TD>
|
|
<CODE>
|
|
<B>
|
|
<A HREF="#scrape">scrape</A></B>(<String> xpathExpr)
|
|
</CODE>
|
|
<BR>
|
|
|
|
Get all document nodes from an XPath expression.
|
|
</TD>
|
|
</TR>
|
|
|
|
<TR BGCOLOR="white" CLASS="TableRowColor">
|
|
<TD ALIGN="right" VALIGN="top" WIDTH="1%">
|
|
<FONT SIZE="-1">
|
|
<CODE> String</CODE>
|
|
</FONT>
|
|
</TD>
|
|
<TD>
|
|
<CODE>
|
|
<B>
|
|
<A HREF="#toString">toString</A></B>()
|
|
</CODE>
|
|
<BR>
|
|
|
|
Get a string representation of the HTML document.
|
|
</TD>
|
|
</TR>
|
|
|
|
|
|
</TABLE>
|
|
|
|
|
|
|
|
<P>
|
|
<!-- ========== END METHOD SUMMARY =========== -->
|
|
|
|
|
|
<!-- ============ FIELD DETAIL START =========== -->
|
|
|
|
|
|
<!-- ============ FIELD DETAIL END =========== -->
|
|
|
|
<!-- ========= CONSTRUCTOR DETAIL START ======== -->
|
|
|
|
<A NAME="constructor_detail"><!-- --></A>
|
|
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
|
|
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
|
|
<TD COLSPAN=1>
|
|
<FONT SIZE="+2"><B>Constructor Detail</B></FONT>
|
|
</TD>
|
|
</TR>
|
|
</TABLE>
|
|
|
|
<A NAME="jala.HtmlDocument()"><!-- --></A><H3>
|
|
jala.HtmlDocument</H3>
|
|
<PRE><B>jala.HtmlDocument</B>(<String> source)</PRE>
|
|
|
|
|
|
<UL>
|
|
Construct a new HTML document.
|
|
</UL>
|
|
|
|
|
|
|
|
<UL>
|
|
<B>Parameters:</B>
|
|
|
|
<UL><CODE>source</CODE> - The HTML source code.
|
|
</UL>
|
|
|
|
|
|
</UL>
|
|
|
|
|
|
<!-- Constructor return value(s) -->
|
|
|
|
<UL>
|
|
<B>Returns:</B>
|
|
<UL>
|
|
A new HTML document.
|
|
</UL>
|
|
</UL>
|
|
|
|
<!-- End constructor return value(s) -->
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES -->
|
|
|
|
<HR/>
|
|
<!-- END ADDITIONAL ATTRIBUTES -->
|
|
|
|
<!-- ========= CONSTRUCTOR DETAIL END ======== -->
|
|
|
|
|
|
<!-- ============ METHOD DETAIL START ========== -->
|
|
|
|
<A NAME="method_detail"><!-- --></A>
|
|
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
|
|
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
|
|
<TD COLSPAN=1><FONT SIZE="+2">
|
|
<B>Method Detail</B></FONT>
|
|
</TD>
|
|
</TR>
|
|
</TABLE>
|
|
|
|
<!-- One single method detail entry -->
|
|
|
|
<A NAME="getAll"><!-- --></A>
|
|
<H3>getAll</H3>
|
|
<PRE>Array <B>getAll</B>(<String> elementName)</PRE>
|
|
|
|
<UL>Retrieves all elements by name from the document.
|
|
The returned object structure is compatible for usage
|
|
in <a href="jala.XmlWriter.html#">jala.XmlWriter</a>.</UL>
|
|
|
|
|
|
<!-- METHOD PARAMETERS START -->
|
|
|
|
<UL>
|
|
<B>Parameters:</B>
|
|
|
|
<UL><CODE>elementName</CODE> - The name of the desired element
|
|
</UL>
|
|
|
|
</UL>
|
|
|
|
<!-- METHOD PARAMETERS END -->
|
|
|
|
|
|
<UL>
|
|
<B>Returns:</B>
|
|
<UL>
|
|
The list of available elements in the document
|
|
</UL>
|
|
</UL>
|
|
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES START -->
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES END -->
|
|
<HR>
|
|
|
|
<A NAME="getLinks"><!-- --></A>
|
|
<H3>getLinks</H3>
|
|
<PRE>Array <B>getLinks</B>()</PRE>
|
|
|
|
<UL>Get all link elements of the HTML document.</UL>
|
|
|
|
|
|
<!-- METHOD PARAMETERS START -->
|
|
|
|
<!-- METHOD PARAMETERS END -->
|
|
|
|
|
|
<UL>
|
|
<B>Returns:</B>
|
|
<UL>
|
|
A list of link elements.
|
|
</UL>
|
|
</UL>
|
|
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES START -->
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES END -->
|
|
<HR>
|
|
|
|
<A NAME="scrape"><!-- --></A>
|
|
<H3>scrape</H3>
|
|
<PRE>org.dom4j.tree.DefaultElement <B>scrape</B>(<String> xpathExpr)</PRE>
|
|
|
|
<UL>Get all document nodes from an XPath expression.</UL>
|
|
|
|
|
|
<!-- METHOD PARAMETERS START -->
|
|
|
|
<UL>
|
|
<B>Parameters:</B>
|
|
|
|
<UL><CODE>xpathExpr</CODE> - An XPath expression.
|
|
</UL>
|
|
|
|
</UL>
|
|
|
|
<!-- METHOD PARAMETERS END -->
|
|
|
|
|
|
<UL>
|
|
<B>Returns:</B>
|
|
<UL>
|
|
A list of HTML elements.
|
|
</UL>
|
|
</UL>
|
|
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES START -->
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES END -->
|
|
<HR>
|
|
|
|
<A NAME="toString"><!-- --></A>
|
|
<H3>toString</H3>
|
|
<PRE>String <B>toString</B>()</PRE>
|
|
|
|
<UL>Get a string representation of the HTML document.</UL>
|
|
|
|
|
|
<!-- METHOD PARAMETERS START -->
|
|
|
|
<!-- METHOD PARAMETERS END -->
|
|
|
|
|
|
<UL>
|
|
<B>Returns:</B>
|
|
<UL>
|
|
A string representation of the HTML document.
|
|
</UL>
|
|
</UL>
|
|
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES START -->
|
|
|
|
<!-- ADDITIONAL ATTRIBUTES END -->
|
|
<HR>
|
|
|
|
|
|
|
|
<!-- ============ METHOD DETAIL END ========== -->
|
|
|
|
<!-- ========= END OF CLASS DATA ========= -->
|
|
|
|
<!-- ========== START OF NAVBAR ========== -->
|
|
<A NAME="navbar_bottom"><!-- --></A>
|
|
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0">
|
|
<TR>
|
|
<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
|
|
<A NAME="navbar_bottom_firstrow"><!-- --></A>
|
|
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3">
|
|
<TR ALIGN="center" VALIGN="top">
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-summary-HtmlDocument.js.html"><FONT CLASS="NavBarFont1"><B>File</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="overview-tree.html"><FONT CLASS="NavBarFont1"><b>Tree</b></FONT></A> </TD>
|
|
<!--TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"--> <!--A HREF="deprecated-list.html"--><!--FONT CLASS="NavBarFont1">Deprecated</FONT--><!--/A--><!-- </TD-->
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD>
|
|
<TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD>
|
|
</TR>
|
|
</TABLE>
|
|
</TD>
|
|
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
|
|
<B>Jala 1.3</B>
|
|
</EM>
|
|
</TD
|
|
</TR>
|
|
|
|
<TR>
|
|
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
|
|
<A HREF="jala.History.html"><B>PREV CLASS</B></A><!--
|
|
NEXT CLASS
|
|
-->
|
|
<A HREF="jala.I18n.html"><B>NEXT CLASS</B></A></FONT></TD>
|
|
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
|
|
<A HREF="index.html" TARGET="_top"><B>FRAMES</B></A>
|
|
<A HREF="jala.HtmlDocument.html" TARGET="_top"><B>NO FRAMES</B></A>
|
|
|
|
<SCRIPT>
|
|
<!--
|
|
if(window==top) {
|
|
document.writeln('<A HREF="allclasses-noframe.html" TARGET=""><B>All Classes</B></A>');
|
|
}
|
|
//-->
|
|
</SCRIPT>
|
|
<NOSCRIPT>
|
|
<A HREF="allclasses-noframe.html" TARGET=""><B>All Classes</B></A>
|
|
</NOSCRIPT>
|
|
</FONT></TD>
|
|
</TR>
|
|
<TR>
|
|
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
|
|
SUMMARY: <A HREF="#field_summary">FIELD</A> | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD>
|
|
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
|
|
DETAIL: <A HREF="#field_detail">FIELD</A> | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD>
|
|
</TR>
|
|
</TABLE>
|
|
|
|
<!-- =========== END OF NAVBAR =========== -->
|
|
|
|
<HR>
|
|
<FONT SIZE="-1">
|
|
|
|
</FONT>
|
|
<div class="jsdoc_ctime">Documentation generated by <a href="http://jsdoc.sourceforge.net/" target="_parent">JSDoc</a> on Tue Jan 8 15:45:31 2008</div>
|
|
</BODY>
|
|
</HTML>
|