java html抓取_JAVA抓取一个HTML源代码

package com.hyq.src;

import java.io.InputStream;

import java.net.URL;

public class Test {

/**

* @param args

*/

public static void main(String[] args) {

try{

Test.testNetStream();

}catch(Exception e){

e.printStackTrace();

}

}

public static void testNetStream()throws Exception{

URL url=new URL("http://www.imust.cn/");

InputStream in=url.openStream();

byte[] b=new byte[100000];

in.read(b);

in.close();

String s=new String(b);

System.out.println(s);

}

}package com.hyq.src;

import java.io.BufferedReader;

import java.io.InputStreamReader;

import java.net.URL;

import java.net.URLConnection;

public class Test {

public static void main(String[] args)

{

System.out.println(Test.getHtmlSource("http://sports.163.com/zc/"));

}

public static String getHtmlSource(String url){

StringBuffer stb=new StringBuffer();

try{

URLConnection uc=new URL(url).openConnection();

BufferedReader br=new BufferedReader(new InputStreamReader(uc.getInputStream(),"gb2312"));

String temp=null;

while((temp=br.readLine())!=null){

stb.append(temp).append("\n");

}

br.close();

}catch(Exception e){

e.printStackTrace();

}

return stb.toString();

}

}

本文原创发布php中文网，转载请注明出处，感谢您的尊重！