1
/* Copyright 2002, 2003 Elliotte Rusty Harold
3
This library is free software; you can redistribute it and/or modify
4
it under the terms of version 2.1 of the GNU Lesser General Public
5
License as published by the Free Software Foundation.
7
This library is distributed in the hope that it will be useful,
8
but WITHOUT ANY WARRANTY; without even the implied warranty of
9
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
10
GNU Lesser General Public License for more details.
12
You should have received a copy of the GNU Lesser General Public
13
License along with this library; if not, write to the
14
Free Software Foundation, Inc., 59 Temple Place, Suite 330,
15
Boston, MA 02111-1307 USA
17
You can contact Elliotte Rusty Harold by sending e-mail to
18
elharo@metalab.unc.edu. Please include the word "XOM" in the
19
subject line. The XOM home page is located at http://www.xom.nu/
22
package nu.xom.samples;
24
import java.io.IOException;
26
import nu.xom.Builder;
27
import nu.xom.Document;
28
import nu.xom.ParsingException;
33
* Demonstrates the <code>getValue()</code> method of the
34
* <code>Document</code> class.
37
* @author Elliotte Rusty Harold
41
public class TextExtractor {
43
public static void main(String[] args) {
45
if (args.length <= 0) {
47
"Usage: java nu.xom.samples.TextExtractor URL");
52
Builder parser = new Builder();
53
Document doc = parser.build(args[0]);
54
System.out.println(doc.getValue());
57
catch (ParsingException ex) {
58
System.out.println(args[0] + " is not well-formed.");
59
System.out.println(" at line " + ex.getLineNumber()
60
+ ", column " + ex.getColumnNumber());
61
System.out.println(ex.getMessage());
63
catch (IOException ex) {
65
"Due to an IOException, the parser could not check "
b'\\ No newline at end of file'