/***************************************************************
* This file is part of the [fleXive](R) project.
*
* Copyright (c) 1999-2008
* UCS - unique computing solutions gmbh (http://www.ucs.at)
* All rights reserved
*
* The [fleXive](R) project is free software; you can redistribute
* it and/or modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation;
* either version 2 of the License, or (at your option) any
* later version.
*
* The GNU General Public License can be found at
* http://www.gnu.org/copyleft/gpl.html.
* A copy is found in the textfile GPL.txt and important notices to the
* license from the author are found in LICENSE.txt distributed with
* these libraries.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* For further information about UCS - unique computing solutions gmbh,
* please see the company website: http://www.ucs.at
*
* For further information about [fleXive](R), please see the
* project website: http://www.flexive.org
*
*
* This copyright notice MUST APPEAR in all copies of the file!
***************************************************************/
package com.flexive.extractor.htmlExtractor;
import java.io.FileInputStream;
public class consoleTest {
public static void main(String [ ] args) {
FileInputStream input = null;
try {
input = new FileInputStream(args[0]);
HtmlExtractor result = new HtmlExtractor(input,true);
System.out.println(result.getText());
System.out.println("title:"+result.getTitle());
System.out.println("word#:"+result.getWordCount());
System.out.println("char#:"+result.getCharacterCount());
} catch (Exception exc) {
System.err.println("ERROR>>> "+exc.getMessage());
exc.printStackTrace();
} finally {
try {
if (input!=null) input.close();
} catch (Exception exc) {/*nothing*/}
}
}
}
|