KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > opencms > util > CmsHtmlExtractor


1 /*
2  * File : $Source: /usr/local/cvs/opencms/src/org/opencms/util/CmsHtmlExtractor.java,v $
3  * Date : $Date: 2006/03/27 14:52:41 $
4  * Version: $Revision: 1.10 $
5  *
6  * This library is part of OpenCms -
7  * the Open Source Content Mananagement System
8  *
9  * Copyright (c) 2005 Alkacon Software GmbH (http://www.alkacon.com)
10  *
11  * This library is free software; you can redistribute it and/or
12  * modify it under the terms of the GNU Lesser General Public
13  * License as published by the Free Software Foundation; either
14  * version 2.1 of the License, or (at your option) any later version.
15  *
16  * This library is distributed in the hope that it will be useful,
17  * but WITHOUT ANY WARRANTY; without even the implied warranty of
18  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19  * Lesser General Public License for more details.
20  *
21  * For further information about Alkacon Software GmbH, please see the
22  * company website: http://www.alkacon.com
23  *
24  * For further information about OpenCms, please see the
25  * project website: http://www.opencms.org
26  *
27  * You should have received a copy of the GNU Lesser General Public
28  * License along with this library; if not, write to the Free Software
29  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
30  */
31
32 package org.opencms.util;
33
34 import org.opencms.staticexport.CmsLinkProcessor;
35
36 import java.io.ByteArrayInputStream JavaDoc;
37 import java.io.InputStream JavaDoc;
38 import java.io.UnsupportedEncodingException JavaDoc;
39
40 import org.htmlparser.Parser;
41 import org.htmlparser.beans.StringBean;
42 import org.htmlparser.lexer.Lexer;
43 import org.htmlparser.lexer.Page;
44 import org.htmlparser.util.ParserException;
45
46 /**
47  * Extracts plain text from HTML.<p>
48  *
49  * @author Alexander Kandzior
50  *
51  * @version $Revision: 1.10 $
52  *
53  * @since 6.0.0
54  */
55 public final class CmsHtmlExtractor {
56
57     /**
58      * Hides the public constructor.<p>
59      */
60     private CmsHtmlExtractor() {
61
62         // hides the public constructor
63 }
64
65     /**
66      * Extract the text from a HTML page.<p>
67      *
68      * @param in the html content input stream
69      * @param encoding the encoding of the content
70      *
71      * @return the extracted text from the page
72      * @throws ParserException if the parsing of the HTML failed
73      * @throws UnsupportedEncodingException if the given encoding is not supported
74      */
75     public static String JavaDoc extractText(InputStream JavaDoc in, String JavaDoc encoding)
76     throws ParserException, UnsupportedEncodingException JavaDoc {
77
78         Parser parser = new Parser();
79         Lexer lexer = new Lexer();
80         Page page = new Page(in, encoding);
81         lexer.setPage(page);
82         parser.setLexer(lexer);
83
84         StringBean stringBean = new StringBean();
85         parser.visitAllNodesWith(stringBean);
86
87         return stringBean.getStrings();
88     }
89
90     /**
91      * Extract the text from a HTML page.<p>
92      *
93      * @param content the html content
94      * @param encoding the encoding of the content
95      *
96      * @return the extracted text from the page
97      * @throws ParserException if the parsing of the HTML failed
98      * @throws UnsupportedEncodingException if the given encoding is not supported
99      */
100     public static String JavaDoc extractText(String JavaDoc content, String JavaDoc encoding)
101     throws ParserException, UnsupportedEncodingException JavaDoc {
102
103         // we must make sure that the content passed to the parser always is
104 // a "valid" HTML page, i.e. is surrounded by <html><body>...</body></html>
105 // otherwise you will get strange results for some specific HTML constructs
106 StringBuffer JavaDoc newContent = new StringBuffer JavaDoc(content.length() + 32);
107
108         newContent.append(CmsLinkProcessor.HTML_START);
109         newContent.append(content);
110         newContent.append(CmsLinkProcessor.HTML_END);
111
112         // make sure the Lexer uses the right encoding
113 InputStream JavaDoc in = new ByteArrayInputStream JavaDoc(newContent.toString().getBytes(encoding));
114
115         // use the stream based version to process the results
116 return extractText(in, encoding);
117     }
118 }
Popular Tags