java读取网页内容乱码

1.首先判断网页的编码

URL url = new URL("http://www.qq.com");

URLConnection connection = url.openConnection();

Map<String,List<String>> headers = connection.getHeaderFields();

String ctype = headers.get("Content-Type").get(0); //判断获取网页编码 text/html; charset=GB2312

String charset = ctype.substring(ctype.lastIndexOf("=") +1 ); // GB2312

 2.读取网页内容

InputStreamReader isr = new InputStreamReader(url.openStream(),charset);

StringBuffer sb = new StringBuffer();

InputStreamReader isr=new InputStreamReader(url.openStream());

BufferedReader br=new BufferedReader(isr);

String str;

while((str=br.readLine())!=null)

{

  sb.append(str);

}

br.close();

isr.close();