Extract links from a web page

Question

Using Java, how can I extract all the links from a given web page?

Answer 1

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

public class NameOfProgram {
    public static void main(String[] args) {
        URL url;
        InputStream is = null;
        BufferedReader br;
        String line;

        try {
            url = new URL("http://www.stackoverflow.com");
            is = url.openStream();  // throws an IOException
            br = new BufferedReader(new InputStreamReader(is));

            while ((line = br.readLine()) != null) {
                if(line.contains("href="))
                    System.out.println(line.trim());
            }
        } catch (MalformedURLException mue) {
             mue.printStackTrace();
        } catch (IOException ioe) {
             ioe.printStackTrace();
        } finally {
            try {
                if (is != null) is.close();
            } catch (IOException ioe) {
                //exception
            }
        }
    }
}