import org.w3c.dom.Document;
import org.w3c.tidy.Tidy;
public class HTMLParser {
public static void main(String[] args) {
Tidy tidy = new Tidy();
tidy.setXHTML(true);
Document document = tidy.parseDOM("input.html", null);
org.w3c.dom.Element root = document.getDocumentElement();
traverseDOMTree(root);
}
private static void traverseDOMTree(org.w3c.dom.Element element) {
for (org.w3c.dom.Element child : element.getChildElements()) {
traverseDOMTree(child);
}
}
}