利用java的net包来实在数据采集的功能

package net.xinhudong.html;

import java.io.ByteArrayOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;

public class htmlRequest {
    /**
    * @param args
    * @throws MalformedURLException 
    */
    public static void main(String[] args) throws Exception{
        URL url = new URL("http://roll.news.sina.com.cn/news/gnxw/gdxw1/index.shtml"); 
        HttpURLConnection conn = (HttpURLConnection)url.openConnection();
        conn.setRequestMethod("GET");
        conn.setConnectTimeout(5 * 1000);
        InputStream inStream =  conn.getInputStream();//通过输入流获取html数据	
        byte[] data = readInputStream(inStream);//得到html的二进制数据
        String html = new String(data);
        System.out.println(html);//在控制台输入得到的html代码
    }
    public static byte[] readInputStream(InputStream instream) throws Exception{
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        byte[]  buffer = new byte[1204];
        int len = 0;
        while ((len = instream.read(buffer)) != -1) {
            outStream.write(buffer,0,len);
        }
        instream.close();
        return outStream.toByteArray();    
    }
}