如何爬取網站代碼

private static String getHtml(String urlInfo) throws Exception {
        //讀取目的網頁URL地址，獲取網頁源碼
        URL url = new URL(urlInfo);
        HttpURLConnection httpUrl = (HttpURLConnection)url.openConnection();
        httpUrl.setConnectTimeout(30000);//連接主機的超時時間(單位：毫秒)
        httpUrl.setReadTimeout(30000);//從主機讀取數據的超時時間(單位：毫秒)
        System.out.println(httpUrl.getContentEncoding());
        InputStream is = httpUrl.getInputStream();
        if("gzip".equals(httpUrl.getContentEncoding())){
            //處理gzip壓縮
            is = new GZIPInputStream(is);
        }
        BufferedReader br = new BufferedReader(new InputStreamReader(is,"gb2312"));
        StringBuilder sb = new StringBuilder();
        String line;
        while ((line = br.readLine()) != null) {
            sb.append(line);
        }
        is.close();
        br.close();
        return sb.toString().trim();

    }