解决httpurlconnection获取网页数据部分中文乱码问题

“`
public void doGet(final String urlStr) throws CommonException {
final StringBuffer sb = new StringBuffer();
new Thread(new Runnable() {

        @Override
        public void run() {
            // TODO Auto-generated method stub
            try {
                URL url = new URL(urlStr);
                HttpURLConnection conn = (HttpURLConnection) url
                        .openConnection();
                conn.setRequestProperty("Charset", "UTF-8");
                conn.setRequestMethod("GET");
                conn.setConnectTimeout(5000);
                conn.setDoInput(true);
                conn.setDoOutput(true);
                if (conn.getResponseCode() == 200) {
                    InputStream is = conn.getInputStream();
                    int len = 0;
                    //原因就出在这里，直接我开的字节1024这回造成如果是一个中文字符正好在这个1024的临界点，这样就会出现中文乱码，所以我就直接将大小开到60000，哈哈哈。
                    byte[] buf = new byte[60000];
                    while ((len = is.read(buf)) != -1) {
                        sb.append(new String(buf, 0, len, "UTF-8"));
                    }
                    jsoup_jiexi(sb.toString());
                    is.close();
                } else {
                    throw new CommonException("访问网络失败00");
                }

            } catch (Exception e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
                try {
                    throw new CommonException("访问网络失败11");
                } catch (CommonException e1) {
                    // TODO Auto-generated catch block
                    e1.printStackTrace();
                }
            }
        }
    }).start();
}```