import java.io.*;
import java.net.*;
import java.util.*;
 
public class CustomWebCrawler implements Runnable
{
    ArrayList alCurrentSearches = new ArrayList();
    ArrayList alAlreadySearched = new ArrayList();
    ArrayList alMatchingSearches = new ArrayList();
    Thread running;
    URL enteredURL;
    int count = 0;
 
    public CustomWebCrawler()
    {
 
    }
 
    public void start()
    {
 
        if (running == null)
        {
            running = new Thread();
        }
    }
 
    public void stop()
    {
 
        if (running != null)
        {
            running = null;
 
        }
    }
 
    public void run()
    {
        if (enteredURL == null || enteredURL.getProtocol().compareTo("http") != 0)
        {
            running = null;
        }
	alCurrentSearches.add(enteredURL);
 
          BufferedReader br = null;
        try
        {
           br = new BufferedReader(new InputStreamReader(enteredURL.openStream()));
           String inputText = "";
           while ((inputText = br.readLine()) != null)
          {
                int first = inputText.lastIndexOf("<a href=");
                int end = inputText.indexOf("\">",first);
                if (first != -1 && end != -1)
                {
                    findURL(inputText,first,end);
                }
                else
                {
                }
 
            }
          }
 
        catch(Exception e)
        {
            e.printStackTrace();
        }
    }
 
    public void findURL(String text, int numFirst, int numEnd)
    {
        String link = text.substring(numFirst+9, numEnd);
	try
	{
		URL newURL = new URL(link);
		if (newURL.getProtocol().compareTo("http") == 0)
		{
			if (!(alMatchingSearches.contains(newURL)))
			{
				alAlreadySearched.add(newURL);
				alMatchingSearches.add(newURL);
				System.out.println(newURL + "");
			}
		}
	}
	catch(MalformedURLException mue)
	{
	}
    }
 
 
}

/*
 Import all the needed packages.  IO is needed to open streams.
 net is needed for the URL object.  The util class is needed for
 ArrayList.
 */
import java.io.*;
import java.net.*;
import java.util.*;
 
/**
 *  Create a class called CustomWebCrawler that implements Runnable.
 *  Runnable is needed for threadiing
 **/
public class CustomWebCrawler implements Runnable
{
    /*
     Create an arraylist to hold the actuall searches.
     */
    ArrayList alMatchingSearches = new ArrayList();
    Thread running;
    URL enteredURL;
    int count = 0;
    int count2 = 0;
    /*
     Constructor
     */
    public CustomWebCrawler()
    {
 
    }
 
    public void start()
    {
        if (running == null)
        {
            running = new Thread();
        }
    }
 
    public void stop()
    {
        if (running != null)
        {
            running = null;
        }
    }
 
    public void run()
    {
        if (enteredURL == null)
        {
            running = null;
        }
	/*
	 If we make it this far, then then the thread is running.
	 So lets call the load method.
	 */
            load();  
    }
 
    /**
     *  This method takes three parameters.  The text, which is whats being 
     *  currently read from the URL.  The second parameter is the index of
     *  the first occurence of an anchor tag.  The third parameter is the ending
     *  index of the anchor tag.
     **/
    public void findURL(String text, int numFirst, int numEnd)
    {
	/*
	 Create a STRING link out of the given parameters.
	 */
        String link = text.substring(numFirst+9, numEnd);
 
    /*
     try to create an actuall URL out of the String link
     if we are able to, then check to make sure it has the right protocol
     */
    try
    {
        URL newURL = new URL(link);
        if (newURL.getProtocol().compareTo("http") == 0)
        {
	    /*
	     Make sure we haven't already searched it.
	     */
            if (!(alMatchingSearches.contains(newURL)))
            {
                    alMatchingSearches.add(newURL);
                    System.out.println(count2 + "   " + newURL + "");
                    count2++;
            }
        }
    }
    catch(MalformedURLException mue)
    {
    }   
    }   
 
    /**
     This method called load, will make sure we have less than 101 searches,
     and then try looping through the searched URLs
     **/
    public void load()
    {
            while(alMatchingSearches.size() < 100)
            {
                BufferedReader br = null;
                int count = 0;
		/*
		 Try reading from the URL
		 */
                try
                {
                      br = new BufferedReader(new InputStreamReader(enteredURL.openStream()));
                      String inputText = "";
		      /*
		       While the inputText is not null, then loop
		       */
                      while ((inputText = br.readLine()) != null)
                      {
                          int first = inputText.lastIndexOf("<a href=");
                          int end = inputText.indexOf("\">",first);
			  /*
			   If the read text contains an anchor tag, then
			   send the findURL method the parameters.
			   */
                          if (first != -1 && end != -1)
                          {
                             findURL(inputText,first,end);
                            }
                            else
                            {
                            } 
                        }
                    }
                    catch(MalformedURLException mue)
                    {
                        System.out.println("Malformed Exception");
                        break;
 
                    }
                        catch(IOException ioe)
                        {
                            System.out.println("IO Exception");
                            break;
                        }
		/*
		 Change the enteredURl to the next URl in the ArrayList
		 */
                enteredURL = (URL)alMatchingSearches.get(count);
		/*
		 Make it run again
		 */
                run();
                count++;
 
            }
 
            running = null;
       }
}

import java.util.*;
import java.net.*;
 
public class TestWebCrawler
{
    public static void main(String[] args)
    {
          CustomWebCrawler wc = new CustomWebCrawler();
          try
          {
            wc.enteredURL = new URL("http://java.sun.com");
            wc.start();
            wc.run();
        }
        catch(MalformedURLException ue)
        {
        }
    }
}