如何爬取网站代码

private static String getHtml(String urlInfo) throws Exception {
        //读取目的网页URL地址，获取网页源码
        URL url = new URL(urlInfo);
        HttpURLConnection httpUrl = (HttpURLConnection)url.openConnection();
        httpUrl.setConnectTimeout(30000);//连接主机的超时时间(单位：毫秒)
        httpUrl.setReadTimeout(30000);//从主机读取数据的超时时间(单位：毫秒)
        System.out.println(httpUrl.getContentEncoding());
        InputStream is = httpUrl.getInputStream();
        if("gzip".equals(httpUrl.getContentEncoding())){
            //处理gzip压缩
            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();

    }

标签：String,网站,代码,httpUrl,爬取,URL,br,new,line
来源： https://www.cnblogs.com/xing-nb/p/15226831.html