解码编码问题 求指教

Question

package com.lucene.web;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.net.Socket;

import java.net.UnknownHostException;

public class WebHttpClient {

    /**
     * @param args
     * @throws IOException
     * @throws UnknownHostException
     */
    public static void main(String[] args) throws UnknownHostException,
            IOException {
        Socket webClient = new Socket("www.bnu.edu.cn", 80);
        PrintWriter result = new PrintWriter(webClient.getOutputStream(), true);
        BufferedReader receiver = new BufferedReader(new InputStreamReader(
                webClient.getInputStream()));
        // 解码 编码

        // 发送http请求
        result.println("GET / HTTP/1.1");
        result.println("Host: bnu.edu.cn");
        // 响应完了 告诉服务器关闭连接
        result.println("Connection: Close");
        result.println();
        // 接受请求
        boolean bRet = true;
        StringBuilder sb = new StringBuilder(8096);
        while (bRet) {
            // 有数据进来了
            if (receiver.ready()) {
                String name = null;
                while ((name = receiver.readLine()) != null) { //一行字符地读取 数据
                /**
                 * 解码的关键部分  
                 */
                    String context = new String(name.getBytes(), "utf-8");
                    sb.append(context + "\n");
                }

                bRet = false;
            }
        }
        // 显示获取的正文的网页 打印到控制台
        // String context=URLDecoder.decode(sb.toString(),"utf-8");
        System.out.println(sb.toString());
        if (webClient != null) {
            webClient.close();
        }

    }

}

运行完  抓取下来的网页里面出现了几个不能解码的汉字  以问号的形式出现  但是很少   对此问题表示不解

 

Answer 1

直接把InputStream按照UTF-8，转化成Reader