java的正则匹配网站(Spider)

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


public class Testspider {
    public static void main(String args[]) throws IOException{
        String regex = "src=\"(/\\w{1,6}_\\w{1,5}/\\w{1,6}/\\d\\.\\w{1,3})\"/>";
//        例如:匹配          src="/games_html/images/1.gif"
        String webAddress = "http://www.shua123.com";
        String sCurrentLine; 

        String sTotalString; 

        sCurrentLine=""; 

        sTotalString=""; 

        java.io.InputStream l_urlStream; 

        java.net.URL l_url = new java.net.URL(webAddress); 

        java.net.HttpURLConnection l_connection = (java.net.HttpURLConnection) l_url.openConnection(); 

        l_connection.connect(); 

        l_urlStream = l_connection.getInputStream(); 

        java.io.BufferedReader l_reader = new java.io.BufferedReader(new java.io.InputStreamReader(l_urlStream)); 

        while ((sCurrentLine = l_reader.readLine()) != null) 

        { 

        sTotalString+=sCurrentLine; 

        }      
        Pattern p = Pattern.compile(regex);
        Matcher m = p.matcher(sTotalString);
        while (m.find()){
            System.out.println(webAddress + m.group(1));
        }
    }


打印出:

http://www.shua123.com/games_html/images/1.gif
http://www.shua123.com/games_html/images/2.gif
http://www.shua123.com/games_html/images/3.gif
http://www.shua123.com/games_html/images/4.gif
http://www.shua123.com/games_html/images/5.gif
http://www.shua123.com/games_html/images/6.gif
http://www.shua123.com/games_html/images/7.gif
http://www.shua123.com/games_html/images/8.gif
http://www.shua123.com/games_html/images/9.gif