Using an ObjectFindingVisitor to Extract Links

A visitor visits all links, and an ObjectFindingVisitor is designed to find one specific class of nodes, in this case LinkTag tags:

import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.ObjectFindingVisitor;

public class LinkDemo
{
    public static void main (String[] args) throws ParserException
    {
        Parser parser = new Parser ("http://urlIWantToParse.com");
        ObjectFindingVisitor visitor = new ObjectFindingVisitor (LinkTag.class);
        parser.visitAllNodesWith (visitor);
        Node[] links = visitor.getTags ();
        for (int i = 0; i < links.length; i++)
        {
            LinkTag linkTag = (LinkTag)links[i];
            System.out.print ("\"" + linkTag.getLinkText () + "\" => ");
            System.out.println (linkTag.getLink ());
        }
    }
}




Last edited on Wednesday, January 7, 2004 4:09:50 pm.