[Htmlparser-cvs] htmlparser/docs/samples links.html,1.2,1.3
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/docs/samples links.html,1.2,1.3
|
From: <der...@us...> - 2003-09-01 20:48:35
|
Update of /cvsroot/htmlparser/htmlparser/docs/samples
In directory sc8-pr-cvs1:/tmp/cvs-serv29574
Modified Files:
links.html
Log Message:
Fix bug #786869 LinkExtractor Sample not working.
Index: links.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/docs/samples/links.html,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** links.html 15 Dec 2002 03:41:25 -0000 1.2
--- links.html 1 Sep 2003 20:48:29 -0000 1.3
***************
*** 4,7 ****
--- 4,10 ----
<title>Link and Mail Extractor </title>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
+ <style type="text/css">
+ <!--code { font-family: Courier New, Courier; font-size: 10pt; margin: 0px; }-->
+ </style>
</head>
***************
*** 11,134 ****
the parserApplications package (in the download bundle, this will be in src.zip).</p>
<p>
! <!-- ======================================================== -->
! <!-- = Java Sourcecode to HTML automatically converted code = -->
! <!-- = J2H V2.0 2002 by Markus Gebhard ma...@ja... = -->
! <!-- = Further information: http://www.java2html.de = -->
! </p>
<center>
! <table align="center" border="2" cellpadding="3" cellspacing="0" bgcolor="#FFFBF0">
<tr>
- <!-- start line numbers -->
- <td align="right" valign="top"> <code> <font color="#808080"> 1<br>
- 2<br>
- 3<br>
- 4<br>
- 5<br>
- 6<br>
- 7<br>
- 8<br>
- 9<br>
- 10<br>
- 11<br>
- 12<br>
- 13<br>
- 14<br>
- 15<br>
- 16<br>
- <a name="17"></a>17<br>
- <a name="18"></a>18<br>
- 19<br>
- 20<br>
- 21<br>
- 22<br>
- 23<br>
- 24<br>
- 25<br>
- 26<br>
- 27<br>
- 28<br>
- 29<br>
- 30<br>
- <a name="31"></a>31<br>
- 32<br>
- 33<br>
- 34<br>
- 35<br>
- 36<br>
- 37<br>
- 38<br>
- 39<br>
- 40<br>
- 41<br>
- 42<br>
- 43<br>
- 44<br>
- 45<br>
- 46<br>
- 47<br>
- 48<br>
- 49<br>
- 50<br>
- </font> </code> </td>
- <!-- end line numbers -->
<!-- start source code -->
! <td valign="top"> <code> <font color="#0000c0">import </font><font color="#000000"></font><font color="#000000">org.htmlparser.HTMLNode;<br>
! </font><font color="#0000c0">import </font><font color="#000000">org.htmlparser.HTMLParser;<br>
! </font><font color="#0000c0">import </font><font color="#000000">org.htmlparser.tags.HTMLLinkTag;<br>
! </font><font color="#0000c0">import </font><font color="#000000">org.htmlparser.util.HTMLEnumeration;<br>
! </font><font color="#0000c0">import </font><font color="#000000">org.htmlparser.util.HTMLParserException;<br>
! <br>
! </font><font color="#008000">/**<br>
! * LinkExtractor extracts all the links from the given webpage<br>
! * and prints them on standard output.<br>
! */<br>
! </font><font color="#0000c0">public class </font><font color="#000000">LinkExtractor </font><font color="#000000">{<br>
! </font><font color="#0000c0">private </font><font color="#000000">String location;<br>
! </font><font color="#0000c0">private </font><font color="#000000">HTMLParser parser;<br>
! </font><font color="#0000c0">public </font><font color="#000000">LinkExtractor</font><font color="#000000">(</font><font color="#000000">String location</font><font color="#000000">) {<br>
! </font><font color="#0000c0">this</font><font color="#000000">.location = location;<br>
! </font><font color="#0000c0">try </font><font color="#000000">{<br>
! </font><font color="#0000c0">this</font><font color="#000000">.parser = </font><font color="#0000c0">new </font><font color="#000000">HTMLParser</font><font color="#000000">(</font><font color="#000000">location</font><font color="#000000">)</font><font color="#000000">; </font><font color="#008000">// Create the parser object<br>
! </font><font color="#000000">parser.registerScanners</font><font color="#000000">()</font><font color="#000000">; </font><font color="#008000">// Register standard scanners (Very Important)<br>
! </font><font color="#000000">}<br>
! </font><font color="#0000c0">catch </font><font color="#000000">(</font><font color="#000000">HTMLParserException e</font><font color="#000000">) {<br>
! </font><font color="#000000">e.printStackTrace</font><font color="#000000">()</font><font color="#000000">;<br>
! </font><font color="#000000">}<br>
! <br>
! }<br>
! </font><font color="#0000c0">public </font><font color="#c00000">void </font><font color="#000000">extractLinks</font><font color="#000000">() </font><font color="#0000c0">throws </font><font color="#000000">HTMLParserException </font><font color="#000000">{<br>
! </font><font color="#000000">HTMLNode node;<br>
! HTMLLinkTag linkTag;<br>
! System.out.println</font><font color="#000000">(</font><font color="#990000">"Parsing "</font><font color="#000000">+location+</font><font color="#990000">" for links..."</font><font color="#000000">)</font><font color="#000000">;<br>
! </font><font color="#0000c0">for </font><font color="#000000">(</font><font color="#000000">HTMLEnumeration e = parser.elements</font><font color="#000000">()</font><font color="#000000">;
! e.hasMoreNodes</font><font color="#000000">()</font><font color="#000000">;</font><font color="#000000">) {<br>
! </font><font color="#000000">node = e.nextHTMLNode</font><font color="#000000">()</font><font color="#000000">; </font><font color="#008000">// Get the next HTML Node<br>
! </font><font color="#0000c0">if </font><font color="#000000">(</font><font color="#000000">node </font><font color="#0000c0">instanceof </font><font color="#000000">HTMLLinkTag</font><font color="#000000">) {<br>
! </font><font color="#000000">linkTag = </font><font color="#000000">(</font><font color="#000000">HTMLLinkTag</font><font color="#000000">)</font><font color="#000000">node; </font><font color="#008000">// Downcast to a Link Tag<br>
! </font><font color="#000000">linkTag.print</font><font color="#000000">()</font><font color="#000000">; </font><font color="#008000">// Print it<br>
! </font><font color="#000000">}<br>
! }<br>
! }<br>
! </font><font color="#0000c0">public static </font><font color="#c00000">void </font><font color="#000000">main</font><font color="#000000">(</font><font color="#000000">String</font><font color="#000000">[] </font><font color="#000000">args</font><font color="#000000">) {<br>
! </font><font color="#0000c0">if </font><font color="#000000">(</font><font color="#000000">args.length<</font><font color="#990000">0</font><font color="#000000">) {<br>
! </font><font color="#000000">System.err.println</font><font color="#000000">(</font><font color="#990000">"Syntax Error : Please provide the location(URL or file) to parse"</font><font color="#000000">)</font><font color="#000000">;<br>
! System.exit</font><font color="#000000">(</font><font color="#000000">-</font><font color="#990000">1</font><font color="#000000">)</font><font color="#000000">;<br>
! </font><font color="#000000">}<br>
! </font><font color="#000000">LinkExtractor linkExtractor = </font><font color="#0000c0">new </font><font color="#000000">LinkExtractor</font><font color="#000000">(</font><font color="#000000">args</font><font color="#000000">[</font><font color="#990000">0</font><font color="#000000">])</font><font color="#000000">;<br>
! </font><font color="#0000c0">try </font><font color="#000000">{<br>
! </font><font color="#000000">linkExtractor.extractLinks</font><font color="#000000">()</font><font color="#000000">;<br>
! </font><font color="#000000">}<br>
! </font><font color="#0000c0">catch </font><font color="#000000">(</font><font color="#000000">HTMLParserException e</font><font color="#000000">) {<br>
! </font><font color="#000000">e.printStackTrace</font><font color="#000000">()</font><font color="#000000">;<br>
! </font><font color="#000000">}<br>
! }<br>
! </font><font color="#000000">}</font></code>
</td>
- </tr>
<!-- end source code -->
<!-- start J2H link -->
<tr>
! <td colspan=2 align=right>
<small>
<a href="http://www.java2html.de" target="_blank">Java2html</a>
--- 14,85 ----
the parserApplications package (in the download bundle, this will be in src.zip).</p>
<p>
!
! <!-- ======================================================== -->
! <!-- = Java Sourcecode to HTML automatically converted code = -->
! <!-- = Java to HTML Converter V3.2 2003 by Markus Gebhard ma...@ja... = -->
! <!-- = Further information: http://www.java2html.de = -->
<center>
! <table align="center" border="2" cellpadding="3" cellspacing="0" bgcolor="#ffffff">
<tr>
<!-- start source code -->
! <td nowrap valign="top" align="left">
! <code>
! <font color="#808080">01 </font><font color="#0000c0"><b>import </b></font><font color="#000000">org.htmlparser.Node;</font><br>
! <font color="#808080">02 </font><font color="#0000c0"><b>import </b></font><font color="#000000">org.htmlparser.Parser;</font><br>
! <font color="#808080">03 </font><font color="#0000c0"><b>import </b></font><font color="#000000">org.htmlparser.tags.LinkTag;</font><br>
! <font color="#808080">04 </font><font color="#0000c0"><b>import </b></font><font color="#000000">org.htmlparser.util.ParserException;</font><br>
! <font color="#808080">05 </font><font color="#ffffff"></font><br>
! <font color="#808080">06 </font><font color="#008000">/**</font><br>
! <font color="#808080">07 </font><font color="#ffffff"> </font><font color="#008000">* LinkExtractor extracts all the links from the given webpage</font><br>
! <font color="#808080">08 </font><font color="#ffffff"> </font><font color="#008000">* and prints them on standard output.</font><br>
! <font color="#808080">09 </font><font color="#ffffff"> </font><font color="#008000">*/</font><br>
! <font color="#808080">10 </font><font color="#0000c0"><b>public class </b></font><font color="#000000">LinkExtractor </font><font color="#000000">{</font><br>
! <font color="#808080">11 </font><font color="#ffffff"> </font><font color="#0000c0"><b>private </b></font><font color="#000000">String location;</font><br>
! <font color="#808080">12 </font><font color="#ffffff"> </font><font color="#0000c0"><b>private </b></font><font color="#000000">Parser parser;</font><br>
! <font color="#808080">13 </font><font color="#ffffff"> </font><font color="#0000c0"><b>public </b></font><font color="#000000">LinkExtractor</font><font color="#000000">(</font><font color="#000000">String location</font><font color="#000000">) {</font><br>
! <font color="#808080">14 </font><font color="#ffffff"> </font><font color="#0000c0"><b>this</b></font><font color="#000000">.location = location;</font><br>
! <font color="#808080">15 </font><font color="#ffffff"> </font><font color="#0000c0"><b>try </b></font><font color="#000000">{</font><br>
! <font color="#808080"><a name="16">16</a> </font><font color="#ffffff"> </font><font color="#0000c0"><b>this</b></font><font color="#000000">.parser = </font><font color="#0000c0"><b>new </b></font><font color="#000000">Parser</font><font color="#000000">(</font><font color="#000000">location</font><font color="#000000">)</font><font color="#000000">; </font><font color="#008000">// Create the parser object</font><br>
! <font color="#808080"><a name="17">17</a> </font><font color="#ffffff"> </font><font color="#000000">parser.registerScanners</font><font color="#000000">()</font><font color="#000000">; </font><font color="#008000">// Register standard scanners (Very Important)</font><br>
! <font color="#808080">18 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">19 </font><font color="#ffffff"> </font><font color="#0000c0"><b>catch </b></font><font color="#000000">(</font><font color="#000000">ParserException e</font><font color="#000000">) {</font><br>
! <font color="#808080">20 </font><font color="#ffffff"> </font><font color="#000000">e.printStackTrace</font><font color="#000000">()</font><font color="#000000">;</font><br>
! <font color="#808080">21 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">22 </font><font color="#ffffff"> </font><br>
! <font color="#808080">23 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">24 </font><font color="#ffffff"> </font><font color="#0000c0"><b>public </b></font><font color="#c00000"><b>void </b></font><font color="#000000">extractLinks</font><font color="#000000">() </font><font color="#0000c0"><b>throws </b></font><font color="#000000">ParserException </font><font color="#000000">{</font><br>
! <font color="#808080">25 </font><font color="#ffffff"> </font><font color="#000000">System.out.println</font><font color="#000000">(</font><font color="#990000">"Parsing "</font><font color="#000000">+location+</font><font color="#990000">" for links..."</font><font color="#000000">)</font><font color="#000000">;</font><br>
! <font color="#808080"><a name="26">26</a> </font><font color="#ffffff"> </font><font color="#000000">Node </font><font color="#000000">[] </font><font color="#000000">links = parser.extractAllNodesThatAre</font><font color="#000000">(</font><font color="#000000">LinkTag.</font><font color="#0000c0"><b>class</b></font><font color="#000000">)</font><font color="#000000">;</font><br>
! <font color="#808080">27 </font><font color="#ffffff"> </font><font color="#0000c0"><b>for </b></font><font color="#000000">(</font><font color="#c00000"><b>int </b></font><font color="#000000">i = </font><font color="#990000">0</font><font color="#000000">;i < links.length;i++</font><font color="#000000">) {</font><br>
! <font color="#808080">28 </font><font color="#ffffff"> </font><font color="#000000">LinkTag linkTag = </font><font color="#000000">(</font><font color="#000000">LinkTag</font><font color="#000000">)</font><font color="#000000">links</font><font color="#000000">[</font><font color="#000000">i</font><font color="#000000">]</font><font color="#000000">;</font><br>
! <font color="#808080">29 </font><font color="#ffffff"> </font><font color="#008000">// To extract only mail addresses, uncomment the following line</font><br>
! <font color="#808080">30 </font><font color="#ffffff"> </font><font color="#008000">// if (linkTag.isMailLink())</font><br>
! <font color="#808080">31 </font><font color="#ffffff"> </font><font color="#000000">System.out.println</font><font color="#000000">(</font><font color="#000000">linkTag.getLink</font><font color="#000000">())</font><font color="#000000">;</font><br>
! <font color="#808080">32 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">33 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">34 </font><font color="#ffffff"></font><br>
! <font color="#808080">35 </font><font color="#ffffff"> </font><font color="#0000c0"><b>public static </b></font><font color="#c00000"><b>void </b></font><font color="#000000">main</font><font color="#000000">(</font><font color="#000000">String</font><font color="#000000">[] </font><font color="#000000">args</font><font color="#000000">) {</font><br>
! <font color="#808080">36 </font><font color="#ffffff"> </font><font color="#0000c0"><b>if </b></font><font color="#000000">(</font><font color="#000000">args.length != </font><font color="#990000">1</font><font color="#000000">) {</font><br>
! <font color="#808080">37 </font><font color="#ffffff"> </font><font color="#000000">System.err.println</font><font color="#000000">(</font><font color="#990000">"Syntax Error : Please provide the location(URL or file) to parse"</font><font color="#000000">)</font><font color="#000000">;</font><br>
! <font color="#808080">38 </font><font color="#ffffff"> </font><font color="#000000">System.exit</font><font color="#000000">(</font><font color="#000000">-</font><font color="#990000">1</font><font color="#000000">)</font><font color="#000000">;</font><br>
! <font color="#808080">39 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">40 </font><font color="#ffffff"> </font><font color="#000000">LinkExtractor linkExtractor = </font><font color="#0000c0"><b>new </b></font><font color="#000000">LinkExtractor</font><font color="#000000">(</font><font color="#000000">args</font><font color="#000000">[</font><font color="#990000">0</font><font color="#000000">])</font><font color="#000000">;</font><br>
! <font color="#808080">41 </font><font color="#ffffff"> </font><font color="#0000c0"><b>try </b></font><font color="#000000">{</font><br>
! <font color="#808080">42 </font><font color="#ffffff"> </font><font color="#000000">linkExtractor.extractLinks</font><font color="#000000">()</font><font color="#000000">;</font><br>
! <font color="#808080">43 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">44 </font><font color="#ffffff"> </font><font color="#0000c0"><b>catch </b></font><font color="#000000">(</font><font color="#000000">ParserException e</font><font color="#000000">) {</font><br>
! <font color="#808080">45 </font><font color="#ffffff"> </font><font color="#000000">e.printStackTrace</font><font color="#000000">()</font><font color="#000000">;</font><br>
! <font color="#808080">46 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">47 </font><font color="#ffffff"> </font><font color="#000000">}</font><br>
! <font color="#808080">48 </font><font color="#000000">}</font><br>
! <font color="#ffffff"></font><font color="#ffffff">
! </font></code>
</td>
<!-- end source code -->
+ </tr>
<!-- start J2H link -->
<tr>
! <td align="right">
<small>
<a href="http://www.java2html.de" target="_blank">Java2html</a>
***************
*** 143,170 ****
!
! <p>Let us look at whats really happening here. In <a href="#17">line 17</a>, we
are creating a parser object that will work on a given location. The location
! can be a URL or a file. In <a href="#18">line 18</a>, we ask the parser to register
itself with certain standard scanners, that give it the capability to handle
! special tags (like links, images, etc..). If line 18 is not provided, the program
will not output any link tags.</p>
! <p>The extractLinks() method is the heart of the program. All it really has a
! loop that utilizes an iterator - called HTMLEnumeration. HTMLEnumeration has
! a really simple interface - hasMoreNodes() and nextHTMLNode(). This is very
! similar to java's own Enumeration (hasMoreElements() and nextElement()). The
! reason of not using Enumeration and instead having our own version of it - is
! that we'd like to save previous CPU time on the downcasts. Since we know that
! we're only dealing with HTMLNode objects, we'd like to directly return them.
</p>
! <p>Every call to nextHTMLNode() advances the parser to the next object. Please
! remember that this is a streaming parser, and the elements are coming in real
! time. </p>
! <p>Now, we'd like to filter out all objects except links. <a href="#31">Line 31</a>
! accomplishes this. We check if the node is an instance of HTMLLinkTag. If it
! is, then this is the link object that has just been parsed from the webpage.
! We can make a call to its print() method, or we can print it the way we like,
using its interface methods such as getLink() and getLinkText(). Try making
! the following modifications to Line 33.</p>
<p>
<!-- ======================================================== -->
--- 94,112 ----
! <p>Let us look at whats really happening here. In <a href="#16">line 16</a>, we
are creating a parser object that will work on a given location. The location
! can be a URL or a file. In <a href="#17">line 17</a>, we ask the parser to register
itself with certain standard scanners, that give it the capability to handle
! special tags (like links, images, etc..). If line 17 is not provided, the program
will not output any link tags.</p>
! <p>The extractAllNodesThatAre() method call on <a href="#26">line 26</a> in
! extractLinks() is the heart of the program. As it's name suggests, it traverses
! all the nodes in the page and picks out the ones that match the class object
! provided, in this case a LinkTag class.
</p>
! <p>We can now cycle through the array of nodes and print out each link URL.
! We can make a call to the LinkTag print() method, or we can print it the way we like,
using its interface methods such as getLink() and getLinkText(). Try making
! the following modifications to Line 31.</p>
<p>
<!-- ======================================================== -->
***************
*** 177,181 ****
<tr>
<!-- start line numbers -->
! <td align="right" valign="top"> <code> <font color="#808080"> 33<br>
</font>
</code>
--- 119,123 ----
<tr>
<!-- start line numbers -->
! <td align="right" valign="top"> <code> <font color="#808080"> 31<br>
</font>
</code>
***************
*** 215,219 ****
<tr>
<!-- start line numbers -->
! <td align="right" valign="top"> <code> <font color="#808080"> 33<br>
</font>
</code>
--- 157,161 ----
<tr>
<!-- start line numbers -->
! <td align="right" valign="top"> <code> <font color="#808080"> 31<br>
</font>
</code>
***************
*** 241,287 ****
<!-- = END of automatically generated HTML code = -->
<!-- ======================================================== -->
! <p>We can also check if the link is a mailto link, using the method HTMLLinkTag.isMailLink().
! Suppose we wish to modify the above program to print all the email addresses
! from a webpage, we'd only have to modify line 33 to : </p>
! <p>
! <!-- ======================================================== -->
! <!-- = Java Sourcecode to HTML automatically converted code = -->
! <!-- = J2H V2.0 2002 by Markus Gebhard ma...@ja... = -->
! <!-- = Further information: http://www.java2html.de = -->
! </p>
! <center>
! <table align="center" border="2" cellpadding="3" cellspacing="0" bgcolor="#FFFBF0">
! <tr>
! <!-- start line numbers -->
! <td align="right" valign="top"> <code> <font color="#808080"> 33<br>
! </font>
! </code>
! </td>
! <!-- end line numbers -->
! <!-- start source code -->
! <td valign="top">
! <code>
! <font color="#0000c0">if </font><font color="#000000">(</font><font color="#000000">linkTag.isMailLink</font><font color="#000000">()) </font><font color="#000000">System.out.println</font><font color="#000000">(</font><font color="#000000">linkTag.getLink</font><font color="#000000">())</font><font color="#000000">;</font></code>
!
! </td>
! </tr>
! <!-- end source code -->
! <!-- start J2H link -->
! <tr>
! <td colspan=2 align=right>
! <small>
! <a href="http://www.java2html.de" target="_blank">Java2html</a>
! </small>
! </td>
! </tr>
! <!-- end J2H link -->
! </table>
! </center>
! <!-- = END of automatically generated HTML code = -->
! <!-- ======================================================== -->
! <p><strong>Limitations of this program</strong></p>
! <p>It cannot provide embedded links - links that are within other recognized tags
! (like the form tag). To uniformly extract embedded links across all tags, check
! <a href="linksEmbedded.html">Extracting Embedded Links/Images</a>.</p>
<p><a href="index.html">Back to Samples</a><br>
<a href="../index.html">Back to HTMLParser Home Page</a></p>
--- 183,188 ----
<!-- = END of automatically generated HTML code = -->
<!-- ======================================================== -->
! <p>We can also check if the link is a mailto link, using the method LinkTag.isMailLink()
! by just uncommenting line 30.</p>
<p><a href="index.html">Back to Samples</a><br>
<a href="../index.html">Back to HTMLParser Home Page</a></p>
|
