Source code: org/htmlparser/parserapplications/LinkExtractor.java
1 // $Header: /home/cvs/jakarta-jmeter/src/htmlparser/org/htmlparser/parserapplications/LinkExtractor.java,v 1.2 2004/02/10 13:41:07 woolfel Exp $
2 /*
3 * ====================================================================
4 * Copyright 2002-2004 The Apache Software Foundation.
5 *
6 * Licensed under the Apache License, Version 2.0 (the "License");
7 * you may not use this file except in compliance with the License.
8 * You may obtain a copy of the License at
9 *
10 * http://www.apache.org/licenses/LICENSE-2.0
11 *
12 * Unless required by applicable law or agreed to in writing, software
13 * distributed under the License is distributed on an "AS IS" BASIS,
14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 * See the License for the specific language governing permissions and
16 * limitations under the License.
17 *
18 */
19
20 // The developers of JMeter and Apache are greatful to the developers
21 // of HTMLParser for giving Apache Software Foundation a non-exclusive
22 // license. The performance benefits of HTMLParser are clear and the
23 // users of JMeter will benefit from the hard work the HTMLParser
24 // team. For detailed information about HTMLParser, the project is
25 // hosted on sourceforge at http://htmlparser.sourceforge.net/.
26 //
27 // HTMLParser was originally created by Somik Raha in 2000. Since then
28 // a healthy community of users has formed and helped refine the
29 // design so that it is able to tackle the difficult task of parsing
30 // dirty HTML. Derrick Oswald is the current lead developer and was kind
31 // enough to assist JMeter.
32
33
34 package org.htmlparser.parserapplications;
35
36
37 import org.htmlparser.Node;
38 import org.htmlparser.Parser;
39 import org.htmlparser.tags.LinkTag;
40 import org.htmlparser.util.ParserException;
41
42 /**
43 * LinkExtractor extracts all the links from the given webpage
44 * and prints them on standard output.
45 */
46 public class LinkExtractor
47 {
48 private String location;
49 private Parser parser;
50 public LinkExtractor(String location)
51 {
52 this.location = location;
53 try
54 {
55 this.parser = new Parser(location); // Create the parser object
56 parser.registerScanners();
57 // Register standard scanners (Very Important)
58 }
59 catch (ParserException e)
60 {
61 e.printStackTrace();
62 }
63
64 }
65 public void extractLinks() throws ParserException
66 {
67 System.out.println("Parsing " + location + " for links...");
68 Node[] links = parser.extractAllNodesThatAre(LinkTag.class);
69 for (int i = 0; i < links.length; i++)
70 {
71 LinkTag linkTag = (LinkTag) links[i];
72 // Print it
73 // System.out.println(linkTag.toString());
74 System.out.println(linkTag.getLink());
75 // To extract only mail addresses, uncomment the following line
76 // if (linkTag.isMailLink()) System.out.println(linkTag.getLink());
77 }
78 }
79
80 public static void main(String[] args)
81 {
82 if (args.length < 0)
83 {
84 System.err.println(
85 "Syntax Error : Please provide the location(URL or file) to parse");
86 System.exit(-1);
87 }
88 LinkExtractor linkExtractor = new LinkExtractor(args[0]);
89 try
90 {
91 linkExtractor.extractLinks();
92 }
93 catch (ParserException e)
94 {
95 e.printStackTrace();
96 }
97 }
98 }