urltreenode.java

不错的网络蜘蛛

/*
 * UrlTreeNode.java
 *
 * Created on September 20, 2004, 11:20 AM
 */
import javax.swing.*;
import javax.swing.tree.*;
import java.util.*;
import java.net.*;

/**
 * Class used to hold information about a web site that has
 * been searched by the spider class
 *
 * @author  Mark Pendergast
 */
public class UrlTreeNode {
    /** URL  */
    private URL url;
    /** base web address for this page */
    private URL base;
    /** is match, set to true if node matched search criteria */
    private boolean isMatch;
    /** set if the node is a plain text and not url */
    private boolean isText = false;
   /** list of keywords matched by this node */
    private Vector keywords = new Vector(3,2);
    /** title of web page */
    private String title = "";
    /** number of text characters on page */
    private int nChars = 0;
    /** number of images on page */
    private int nImages = 0;
    /** number of links on page */
    private int nLinks = 0;

    /** Creates a new instance of UrlTreeNode 
     * @param aurl url of the web page
     */
    public UrlTreeNode(URL aurl) {
        url = aurl;
        isMatch = false;
        base = url; // initialize default value of base
        isText = false;
    }
    
    /** Creates a new instance of UrlTreeNode 
     * @param atext text for the node
     */
    public UrlTreeNode(String atext)
    {
      isMatch = false;
      base = null;
      isText = true;
      title = atext;
    }
    /**
     * return url string for display on screen
     * @return String representation of the object
     */
    public String toString()
    {
      if(isText)
        return title;
      else
      {
  //       return url.getProtocol()+"://"+url.getHost()+url.getPath(); 
       return title+" - "+url.getProtocol()+"://"+url.getHost()+url.getPath();
      }
    }
    /**
     * get the keywords found in this node
     * @return all keywords in this node as a single comma separated string
     */
    public String getKeywords()
    {
       String s ="";
       if(keywords.size() > 0)
       {
         s += (String)keywords.get(0);
         
         for(int i = 1; i < keywords.size(); i++)
            s +=  ", "+(String)keywords.get(i);
        
       }
        return s;      
        
    }
    /**
     * return state of node
     * @return true if node matched search criteria
     */
    public boolean isMatch()
    {
      return isMatch;
    }
 
    /**
     * returns the url object for this node or null if it is a text node
     * @return url of the node or null
     */
    public URL getUrl()
    {
      if(isText)
          return null;
      else
        return url;
    }
    /**
     *
     * returns whether or not this node contains a match for the spiders search criteria
      * @param keyword keyword found in web site.
     */
    public void setMatch(String keyword)
    {
        isMatch = true;
        if(!keywords.contains(keyword))
            keywords.addElement(keyword);
    
    }
    /**
     * sets the base location for the node, called in response to finding a base tag in the web page
     *
     * @param abase  base url to use for relative addressing
     */
    public void setBase(String abase)
    {
     try{
         base = new URL(abase);
     }
     catch(MalformedURLException e)
     {
         
     }
    }
    /**
     * returns base url
     * @return base url 
     */
    public URL getBase()
    {
      return base;
    }
  
    /**
     * sets the title attribute of the node
     * @param atitle title of web page from <TITLE> tag
     */
    public void setTitle(String atitle)
    {
      title = atitle;
    }
    /**
     * test for equality
     * @param urlstr string containing url to compare
     * @return true if it is the same page
     */
    public boolean equals(String urlstr)
    {
     if(isText)
      return title.equals(urlstr);
     else
      return urlstr.equals(url.getProtocol()+"://"+url.getHost()+url.getPath());
    }
    
    /**
     * Increments character count
     * @param n number of characters to add
     */
    public void addChars(int n)
    {
      nChars += n;
    }
    /**
     * Increments link count
     * @param n number of linkss to add
     */
    public void addLinks(int n)
    {
      nLinks += n;
    }
   /**
     * Increments image count
     * @param n number of images to add
     */
    public void addImages(int n)
    {
      nImages += n;
    }
 /**
  *  retrieves character, link, and image count as a displayable string
  * @return pages statistics
  */
   public String getNodeStats()
   {
     return "Page has "+nChars+" total text characters, "+nImages+" images, and "+nLinks+ " links.";
   }
/**
  *  retrieves the url as a string
  * @return url
  */
   public String getUrlString()
   {
     return url.getProtocol()+"://"+url.getHost()+url.getPath();
   }
        
}