Hi,

I am a newbie to java and html parsing although I have done lex/yacc
compilers before. I am trying to leech any http link from a given file
be it a proper 'http://www.....' or just a reference like
'/somedierctory/..../stuff' .... For now I plan on running quick tests
on the local file references to see if they exist or not on the hard
drive and so I got into Java and regular expressions ....

Can the java gurus here (hehe ok I'm not being picky) please comment on
my code and how I can optimize it ? Please don't just say it 'sucks' (I
know it does) .. give me a 'because' and perhaps some pointers on how
to make it not so sucky :)

Thanks.

*******************************
*******************************
import java.io.*;
import java.net.*;
import java.util.*;
import java.util.regex.*;

public class InternalLinkChecker
{
    private static Pattern pattern;
    private static Matcher matcher;
    private static String REGEX;
    private static BufferedReader in = null;
    private static FileWriter out_rep = null;

    public static void main (String [] args)
    {
        try
        {
            if(args.length != 1)
                throw new IllegalArgumentException("Need to let me know which
file.");
            else
            {
                File file = new File(args[0]);

                if (file.exists())
                {
                    in = new BufferedReader(new FileReader(file));
                    StringBuffer buff = new StringBuffer();
                    int c;

                    while((c=in.read())!= -1)
                        buff.append((char) c);

                    StringBuffer temp2 = new StringBuffer();
                    String blah;
                    String [] Split;
                    int count = 0;

                    REGEX = "(<a href=)[^\\s]+(\")";

                    pattern = Pattern.compile(REGEX, Pattern.CASE_INSENSITIVE);
                    matcher = pattern.matcher(buff);

                    while(matcher.find())
                    {
                        System.out.println("----------------------");
                        System.out.println("I found: \' " + matcher.group() + "' \n" +
                                            "Range: " + matcher.start() + " to " + matcher.end());

                        count++;

                        temp2.append(matcher.group());

                    }

                    System.out.println("\n so I found a total of " + count + "
URLS.");

                    blah = temp2.toString();

                    blah = blah.replaceAll("(?i)<A HREF=\"","");

                    Split = blah.split("\"");

                   out_rep = new FileWriter(new File("Rep.txt"));

                   for (int i=0; i<Split.length; i++)
                       out_rep.write(Split[i] + "\n");

                }
                else
                {
                    throw new IllegalArgumentException("Your file does not exist!");
                }
            }
        }
        catch (IOException e)
        {
            System.err.println(e);
            e.printStackTrace();
        }
        finally
        {
            try
            {
                in.close(); out_rep.close();
            }
            catch (IOException ex)
            {
                ex.printStackTrace();
                System.err.println(ex);
            }
        }
           
    }

}

*****************************
******************************