Create intelligent Web spiders

 public class SpiderParserCallback extends HTMLEditorKit.ParserCallback {
 /**
  * Inner class used to html handle parser callbacks
  */
  public class SpiderParserCallback extends HTMLEditorKit.ParserCallback {
      /** URL node being parsed */
      private UrlTreeNode node;
      /** Tree node */
      private DefaultMutableTreeNode treenode;
      /** Contents of last text element */
      private String lastText = "";
      /**
       * Creates a new instance of SpiderParserCallback
       * @param atreenode search tree node that is being parsed
       */
     public SpiderParserCallback(DefaultMutableTreeNode atreenode) {
            treenode = atreenode;
            node = (UrlTreeNode)treenode.getUserObject();
     }
     /**
      *  Handle HTML tags that don't have a start and end tag
      * @param t HTML tag
      * @param a HTML attributes
      * @param pos Position within file
      */ 
     public void handleSimpleTag(HTML.Tag t,
                             MutableAttributeSet a,
                             int pos)
     {
       if(t.equals(HTML.Tag.IMG))
       {
         node.addImages(1);
         return;
       }
        if(t.equals(HTML.Tag.BASE))
       {
         Object value = a.getAttribute(HTML.Attribute.HREF);
         if(value != null)
          node.setBase(fixHref(value.toString())); 
       }    
         
     }
     /**
      *  Take care of start tags
      * @param t HTML tag
      * @param a HTML attributes
      * @param pos Position within file
      */
      public void handleStartTag(HTML.Tag t,
                             MutableAttributeSet a,
                             int pos)
     {
        if(t.equals(HTML.Tag.TITLE))
       {
         lastText="";
         return;
       }
       if(t.equals(HTML.Tag.A))
       {
         Object value = a.getAttribute(HTML.Attribute.HREF);
         if(value != null)
         {
          node.addLinks(1); 
          String href = value.toString();
          href = fixHref(href);
          try{
            URL referencedURL = new URL(node.getBase(),href);
            searchWeb(treenode, referencedURL.getProtocol()+"://"+referencedURL.getHost()+referencedURL.getPath());
          }
          catch (MalformedURLException e)
          {
            messageArea.append("    Bad URL encountered : "+href+"\n\n");   
            return;  
          }
         }
       }
          
     }
      
      /**
      *  Take care of start tags
      * @param t HTML tag
      * @param pos Position within file
      */
      public void handleEndTag(HTML.Tag t,
                                int pos)
     {
       if(t.equals(HTML.Tag.TITLE) && lastText != null)
       {
         node.setTitle(lastText.trim());
         DefaultTreeModel tm = (DefaultTreeModel)searchTree.getModel();
         tm.nodeChanged(treenode);
        }
          
     }
      /**
       * Take care of text between tags, check against keyword list for matches, if
       * match found, set the node match status to true
       * @param data Text between tags
       * @param pos position of text within Webpage
       */
      public void handleText(char[] data, int pos)
      {
        lastText = new String(data);
        node.addChars(lastText.length());
        String text = lastText.toUpperCase();
        for(int i = 0; i < keywordList.length; i++)
        {
          if(text.indexOf(keywordList[i]) >= 0)
          {
            if(!node.isMatch())
            {
             sitesFound++;
             updateStats();
            }
            node.setMatch(keywordList[i]); 
            return;
          }
        }
      }
      
   
  }