/*******************************************************************************
Scriba EBook Maker
Copyright (C) 2011 Senato della Repubblica (http://www.senato.it/)

Offices: 
	Ufficio Stampa e internet [1] 
	Servizio dell'Informatica [2]

Contributors:
    Roberto Battistoni (2, roberto.battistoni@senato.it): software engineer and developer
    Carlo Marchetti (2, carlo.marchetti@senato.it): project manager
    Marco Tagliavini (1, marco.tagliavini@senato.it): project visionary

This program 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 3 of the License, or
(at your option) any later version.

This program 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.

You should have received a copy of the GNU General Public License
along with this program.  If not, see <http://www.gnu.org/licenses/>
*******************************************************************************/
package it.senato.areatesti.ebook.ebookmaker.plugin.defaultplugin.boilerpipe;

import it.senato.areatesti.ebook.ebookmaker.plugin.defaultplugin.boilerpipe.base.AbstractBoilerPipePlugin;
import it.senato.areatesti.ebook.ebookmaker.scf.bean.ContentItem;
import it.senato.areatesti.ebook.ebookmaker.scf.bean.base.IItem;

import java.io.IOException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;

import de.l3s.boilerpipe.extractors.CommonExtractors;
import de.l3s.boilerpipe.sax.HTMLHighlighter;

public class ArticleExtractorBPPlugin extends AbstractBoilerPipePlugin
{
	@Override
	public List<ContentItem> elaborateContent(ContentItem content,
			ArrayList<IItem> metadataList) throws IOException
	{
		// Extracts content's text from the URL
		URL url = new URL(content.getContentUrl());
		String text = null;
		extractor = CommonExtractors.ARTICLE_EXTRACTOR;
		hh = HTMLHighlighter.newExtractingInstance();
		
		List<ContentItem> clist = intElaborateContent(content, url, text);
		
		return clist;
	}

}