NekoHTML:

final DOMParser parser = new DOMParser();

try {

parser.parse(new InputSource(urlIS));

document = parser.getDocument();

} catch (SAXException e) {

e.printStackTrace();

} catch (IOException e) {

e.printStackTrace();

}

TagSoup:

final Parser parser = new Parser();

SAX2DOM sax2dom = null;

try {

sax2dom = new SAX2DOM();

parser.setContentHandler(sax2dom);

parser.setFeature(Parser.namespacesFeature, false);

parser.parse(new InputSource(urlIS));

} catch (Exception e) {

e.printStackTrace();

}

document = sax2dom.getDOM();

jTidy:

final Tidy tidy = new Tidy();

tidy.setQuiet(true);

tidy.setShowWarnings(false);

tidy.setForceOutput(true);

document = tidy.parseDOM(urlIS, null);

HtmlCleaner:

final HtmlCleaner cleaner = new HtmlCleaner(urlIS);

try {

cleaner.clean();

document = cleaner.createDOM();

} catch (Exception e) {

e.printStackTrace();

}