01: /***************************************************************
02: * This file is part of the [fleXive](R) project.
03: *
04: * Copyright (c) 1999-2008
05: * UCS - unique computing solutions gmbh (http://www.ucs.at)
06: * All rights reserved
07: *
08: * The [fleXive](R) project is free software; you can redistribute
09: * it and/or modify it under the terms of the GNU General Public
10: * License as published by the Free Software Foundation;
11: * either version 2 of the License, or (at your option) any
12: * later version.
13: *
14: * The GNU General Public License can be found at
15: * http://www.gnu.org/copyleft/gpl.html.
16: * A copy is found in the textfile GPL.txt and important notices to the
17: * license from the author are found in LICENSE.txt distributed with
18: * these libraries.
19: *
20: * This library is distributed in the hope that it will be useful,
21: * but WITHOUT ANY WARRANTY; without even the implied warranty of
22: * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
23: * GNU General Public License for more details.
24: *
25: * For further information about UCS - unique computing solutions gmbh,
26: * please see the company website: http://www.ucs.at
27: *
28: * For further information about [fleXive](R), please see the
29: * project website: http://www.flexive.org
30: *
31: *
32: * This copyright notice MUST APPEAR in all copies of the file!
33: ***************************************************************/package com.flexive.tests.extractor;
34:
35: import com.flexive.extractor.ExtractedData;
36: import com.flexive.extractor.Extractor;
37:
38: public class HtmlTest {
39:
40: public static void main(String[] args) {
41: ExtractedData data = Extractor.extractData(args[0],
42: Extractor.DocumentType.HTML);
43: System.out.println("Title:"
44: + data.getSummaryInformation().getTitle());
45: System.out.println("Text: " + data.getText());
46: System.out.println("--------------------------");
47: System.out
48: .println("CompressedText:" + data.getCompressedText());
49: }
50: }
|