import org.ccil.cowan.tagsoup.Parser;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
public class TagSoupExample {
public static void main(String[] args) {
try {
XMLReader reader = new Parser();
DefaultHandler handler = new MyHandler();
reader.setContentHandler(handler);
reader.parse("example.html");
} catch (Exception e) {
e.printStackTrace();
}
}
}
class MyHandler extends DefaultHandler {
public void characters(char[] ch, int start, int length) {
String content = new String(ch, start, length);
System.out.println(content);
}
}
Parser parser = new Parser();
parser.setFeature(Parser.ignoreBogonsFeature, true);
parser.setFeature(Parser.ignoreNamespaceFeature, true);