java下载网页源码，content type有问题？（初学，求教）

[chen_q07]

顶
0

踩 按照书上例子写了个GetPageSource的代码，运行结果如下

chenqi@chenqi-laptop ~/MyPro/Java/NetWork $ java GetPageSource http://www.baidu.com/
Date: Wed May 09 00:29:07 CST 2012
Content-Type: text/html;charset=gb2312

但是，我用firefox查看该页源码，发现是这样的：

<meta http-equiv=Content-Type content="text/html;charset=utf-8">

两个内容的charset不一致。。。。有点小无语。不知道为什么。

以下附上源码，求高手分析下：）

import java.net.URL;
import java.net.MalformedURLException;
import java.net.URLConnection;
import java.io.IOException;
import java.io.InputStream;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.util.Date;

class GetPageSource {
    public static void main(String[] args) {
        if (args.length != 1) {
            System.out.println("Usage: GetPageSource URL");
            return;
        }

        String strURL = args[0];
        URL url = null;
        try {
            url = new URL(strURL);
        } catch (MalformedURLException e) {
            System.err.println("Invalid format of URL:" + url + "," + e.getMessage());
            return;
        }

        URLConnection urlCon = null;
        try {
            urlCon = url.openConnection();
        } catch (IOException e) {
            System.err.println("Can't get connection from URL: " + e.getMessage());
        }
        // print properties of this url                                                                                      
        System.out.println("Date: " + new Date(urlCon.getDate()));
        System.out.println("Content-Type: " + urlCon.getContentType());
        System.out.println("Expires: " + urlCon.getExpiration());
        System.out.println("Last-Modified: " + new Date(urlCon.getLastModified()));
        System.out.println("Content-Length: " + urlCon.getContentLength());

        // download page source from this url                                                                                
        InputStream inputStream = null;
        BufferedReader reader = null;
        try {
            inputStream = urlCon.getInputStream();
            reader = new BufferedReader(new InputStreamReader(inputStream));
            int count = 0;
            String tmp = null;
            while ( (tmp = reader.readLine()) != null ) {
                System.out.println(tmp);
                count += tmp.length();
            }
            System.out.println("Count = " + count);
        } catch (IOException e) {
            System.err.println("I/O failed: " + e.getMessage());
        } finally {
            try {
                if (reader != null) reader.close();
            } catch (IOException e) { }
        }
    }
}