学步园

首先读取头部信息，读到字符编码就停止，设定字符编码后继续读取网页内容。

package test;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

public class Main {
	static String[] coding={"utf-8", "gb2312", "gbk", "unicode"};
    public static void main(String args[]) throws IOException{

        String urlStr = "http://www.sina.com.cn";
        URL url = new URL(urlStr);
        URLConnection connection = url.openConnection();

        String ss = connection.getContentType();
        System.out.println(ss);

        BufferedReader br = new BufferedReader(new InputStreamReader(url.openStream()));
        System.out.println("build connection");
        String s = null;
        String pageCoding = null;
        while((s = br.readLine())!=null){
            if(s.contains("charset")){
            	br.close();
            	
            	for(int i=0;i<coding.length;i++){
            		if(s.contains(coding[i])){
            			pageCoding=coding[i];
            			System.out.println(pageCoding);
            			br=new BufferedReader(new InputStreamReader(url.openStream(), pageCoding));
            			System.out.println("build connection2");
            			break;
            		}
            	}
            	if(pageCoding==null){
            		System.out.println("error"+s);
            	}
            	break;
            }
        }
        while((s=br.readLine())!=null){
        	System.out.println(s);
        }
    }
}