//THIS IS JUST A TEST!!!!!!!!


import java.net.*;
import java.io.*;

public class WebProject
{

	public static void main(String [] args)
	{	
		List links = new ArrayList();	//will be used to store any links


		try
		{
			URL address = new URL(args[0]);  //take in the url to be searched from args
			
			BufferedReader in = new BufferedReader(new InputStreamReader(address.openStream()));    //open up a "link" to the url
			PrintWriter myFile = new PrintWriter("output.HTML");   //create a printwroter to write the contents to a file, output.html
			
			String input = "";

			while((input = in.readLine()) != null) //continue while the is still data to read
			{
				myFile.println(input);  //print out what has just been read
			}

			in.close();  //close the link
			myFile.close();  //close and save output

		}
	
		catch(MalformedURLException e)
		{
			System.out.println("Error!!, the supplied URL doesn't exist. ");  //an error message
			System.out.println(args[0]);
		}
	
		catch(IOException e)
		{
			System.out.println("Error!!, data handeling problem");  //another warning message
		}
	}

}

public bool isValidUrl(String urlStr)
{
	try
	{
		java.net.URL url = new java.net.URL(urlStr);
		java.net.HttpURLConnection httpConn = (java.net.HttpURLConnection)url.openConnection();
		httpConn.connect();
		if(httpConn.getResponseCode() != 200)
			return false;
		else
			return true; //it does return 200 and is a valid link
	}
	catch(Exception e)
	{
		e.printStackTrace();
	}

}

import java.net.URL;
import java.net.URLConnection;
import java.net.HttpURLConnection;
import java.util.Vector;
import java.util.regex.Pattern;
import java.util.regex.Matcher;
 
class URLCrawler {
	public static void main(String[] argv) {
		if(argv.length != 1)
			System.out.println("Arguments: <address (String)>");
		else
			checkAddresses(parseAddressese(downloadSource(address))));
	}
 
	private String downloadSource(String url) {
		byte[] read;
		try {
			URL url = new URL(address);
			URLConnection urlc = url.openConnection();
			InputStream is = urlc.getInputStream();
			read = new byte[urlc.getContentLength()];
			is.read(read);
			is.close();
		} catch(IOException ioex) {
			ioex.printStackTrace();
			System.exit(1);
		}
		return new String(read);
	}
 
	private String[] parseAddresses(String html) {
		String regex = "a\\s+[^>]*?class=l\\s+[^>]*?href\\s?=[\\s'\"]+(.*?)['\"]+.*?>[^<]*</a>";
		Pattern p = Pattern.compile(regex);
		Matcher m = p.matcher(html);
		Vector addresses = new Vector<String>();
		while(m.find())
			addresses.addElement(m.group());
		addresses.trimToSize();
		return addresses.toArray(new String[0]);
	}
 
	private void checkAddresses(String[] urls) {
		int i = 0;
		for(String url : urls)
			i = (isBroken(url) ?  i + 1 : i);
		System.console().format("%s urls extracted were broken and %s were in tact, out of %s urls", i, urls.length - i, urls.length);
	}
 
	private boolean isBroken(String url) {
		try {
			URL u = new URL(url);
			HttpURLConnection huc = (HttpURLConnection) u;
			return (!huc.getResponseCode() == 200) ? true : false;
		} catch(IOException ioex) {
			ioex.printStackTrace();
		}
		return true;
	}
}