用java获取网页源文件

package com.xust.bao.test;

import java.io.InputStream;
import java.net.URL;
import java.util.regex.Pattern;
import java.util.regex.Matcher;

public class test2 {
    public test2() {
        String sCurrentLine;
        String sTotalString;
        sCurrentLine = "";
        sTotalString = "";

        InputStream l_urlStream;
        URL l_url;
        try {

//*********************************以下是获取源文件的代码******************************

            l_url = new java.net.URL("http://www.sina.com");
            l_urlStream = l_url.openStream();
            java.io.BufferedReader l_reader = new java.io.BufferedReader(new
                    java.io.InputStreamReader(l_urlStream));

            while ((sCurrentLine = l_reader.readLine()) != null) {
                sTotalString += sCurrentLine;
            }

//*******************************以下是获取源文件中超级链接的方法********************
//String regEx = "href=([^/"']*)>";
            String regEx = "href=/"([^/"]*)/""; //找出href="****"的链接
            Pattern p = Pattern.compile(regEx, Pattern.CASE_INSENSITIVE);
            Matcher m = p.matcher(sTotalString);
            int j = 0;
            while (m.find()) {
                j++;
                System.out.println("m.group(" + j + "): " + m.group(0) + "<br>");
            }
            regEx = "href='([^']*)'"; //找出href='****'的链接
            p = Pattern.compile(regEx, Pattern.CASE_INSENSITIVE); //Pattern.CASE_INSENSITIVE查找忽略大小写
            m = p.matcher(sTotalString);
            while (m.find()) {
                j++;
                System.out.println("m.group(" + j + "): " + m.group(0) + "<br>");
            }

        } catch (Exception e) {
            e.printStackTrace();
        }

    }

/************************************本文修改于月光软件的http://www.moon-soft.com/doc/50290.htm*******

    public static void main(String[] args) {
        test2 test2 = new test2();
    }
}