C#抓取网页的几种方法

清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>

/// <summary>  
 
        /// 用HttpWebRequest取得网页源码  
        /// 对于带BOM的网页很有效,不管是什么编码都能正确识别  
        /// </summary>  
        /// <param name="url">网页地址" </param>   
        /// <returns>返回网页源文件</returns>  
        public static string GetHtmlSource2(string  url)
        {
            //处理内容  
            string html = "";
            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
            request.Accept = "*/*"; //接受任意文件
            request.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.1.4322)"; // 模拟使用IE在浏览 http://www.52mvc.com
            request.AllowAutoRedirect = true;//是否允许302
            //request.CookieContainer = new CookieContainer();//cookie容器,
            request.Referer = url; //当前页面的引用
 
 
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            Stream stream = response.GetResponseStream();
            StreamReader reader = new StreamReader(stream, Encoding.Default);
            html = reader.ReadToEnd();
            stream.Close();
 
 
            return html;
        }