Take a look at HTMLEditorKit and it's read method. Here's a very simple
example that just dumps an HTML document.
You could also look at the HTMLDocument.getIterator(..) method for parsing
specific tags.

import javax.swing.text.html.*;
import java.io.*;
import java.net.*;
import javax.swing.text.*;
import java.util.*;

public class Sampler
{
public static void parseElement( Element elem, int offset )
{
 for( int y = 0; y < offset; y++ )
 {
  System.out.print("  ");
 }

 System.out.println(elem.getName());
 AttributeSet as = elem.getAttributes();
 Enumeration en = as.getAttributeNames();
 while( en.hasMoreElements())
 {
  for( int y = 0; y < offset; y++ )
  {
   System.out.print("  ");
  }
  System.out.println("<" + as.getAttribute(en.nextElement()) + ">");
 }

 for( int x = 0; x< elem.getElementCount(); x++ )
 {
  parseElement( elem.getElement(x), offset+1);
 }
}

 public static void main(String[] args)
 {
 try
 {
  HTMLEditorKit kit = new HTMLEditorKit();
  HTMLDocument doc = new HTMLDocument();
  URL pageontheweb = new URL("http://java.sun.com");
  InputStream is = new BufferedInputStream(pageontheweb.openStream());
  kit.read(is, doc, 0);
  Element[] elems = doc.getRootElements();
  for( int x = 0; x < elems.length; x++ )
  {
   System.out.println(elems[x].getClass().getName());
   parseElement( elems[x], 0 );
  }
 }
 catch(BadLocationException ex)
 {
 }
 catch(MalformedURLException ex)
 {
 }
 catch(IOException ex)
 {
 }
 }
}