java抓取网页数据乱码_java抓取网页的乱码问题(通用)

java抓取网页的乱码问题(通用)2010-12-22 13:34//解决抓取页面的乱码问题

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.File;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.InputStreamReader;

import java.io.OutputStreamWriter;

import java.net.URL;

import java.net.URLConnection;

public class DownPage {

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

//抓取的页面地址

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

URL url = new URL(urlStr);

URLConnection connection = url.openConnection();

//获得该网页的编码

String ss = connection.getContentType();

System.out.println(ss);

//查InputStreamReader的构造方法，gb2312为该页面的编码

BufferedReader br = new BufferedReader(new InputStreamReader(url.openStream(),"gb2312"));

File file = new File("d:/a.html");

BufferedWriter bw = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file)));

if(br != null){

String s = null;

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

//String sss = new String(s.getBytes("gb2312"),"windows-31J");

System.out.println(s);

bw.write(s);

bw.flush();

}

bw.close();

br.close();

}

}

}

分享到：

2011-03-17 23:59

浏览 6395

评论