JAVA通过网站域名URL获取该网站的源码(2018

import java.io.ByteArrayOutputStream;  

import java.io.InputStream;  

import java.net.HttpURLConnection;  

import java.net.URL;  

  

  

public class HtmlRequest {  

      

    public static void main(String[] args) throws Exception{  

    String HttpUrl = "http://www.baidu.com";

        URL url = new URL(HttpUrl);   

        String urlsource = getURLSource(url);  

        System.out.println(urlsource);  

    }  

      

      

    public static String getURLSource(URL url) throws Exception    {  

        HttpURLConnection conn = (HttpURLConnection)url.openConnection();  

        conn.setRequestMethod("GET");  

        conn.setConnectTimeout(5 * 1000);  

        InputStream inStream =  conn.getInputStream();  //通过输入流获取html二进制数据  

        byte[] data = readInputStream(inStream);        //把二进制数据转化为byte字节数据  

        String htmlSource = new String(data,"UTF-8");  

        return htmlSource;  

    }  

      

      

    public static byte[] readInputStream(InputStream instream) throws Exception {  

        ByteArrayOutputStream outStream = new ByteArrayOutputStream();  

        byte[]  buffer = new byte[10000];  

        int len = 0;  

        while ((len = instream.read(buffer)) != -1){  

            outStream.write(buffer,0,len);  

        }  

        instream.close();  

        return outStream.toByteArray();           

    }  

}  

 

来自  http://blog.sina.com.cn/s/blog_e762d3d20102z4lr.html