The web page extractor is a very simple set of methods to extract text and metadata from wab pages.

public static void main(String[] args) {
		try {
			WebPageExtractor extractor = new WebPageExtractor(new URL("http://www.inria.fr/recherche/equipes/edelweiss.en.html"));
			extractor.extract();
			// show internal structure
			System.out.println(extractor.toString());
			// show extracted text
			System.out.println("========================\n"+ extractor.fullText());

		} catch (MalformedURLException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}