一段我自己常用的c#读取页面源码的方法

一段我自己常用的c#读取页面源码的方法

	/// <summary>
        /// 根据URL获取页面内容
         /// </summary>
        /// <param name="sUrl">页面的URL</param>
        /// <returns>页面内容</returns>
        public static string getHtmlContents(string sUrl)
        {
            string returnHtml = string.Empty;
            try
            {
                //创建HttpWebRequest对象
                HttpWebRequest rqst = (HttpWebRequest)WebRequest.Create(sUrl);
                rqst.AllowAutoRedirect = false;
                rqst.UserAgent = "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)";
                rqst.KeepAlive = true;
                rqst.Timeout = 30000;

                //响应头
                HttpWebResponse rsps = (HttpWebResponse)rqst.GetResponse();

                //获取主体
                Stream sm = rsps.GetResponseStream();

                //设置默认
                Encoding cding = System.Text.Encoding.Default;

                //响应头中的文档格式
                string contenttype = rsps.ContentType.ToLower();
                //判断格式中是否包含编码
                int ix = contenttype.IndexOf("charset=");
                if (ix != -1)
                {

                    try
                    {
                        cding = System.Text.Encoding.GetEncoding(rsps.ContentType.Substring(ix + "charset".Length + 1));
                    }
                    catch
                    {
                        cding = Encoding.Default;
                    }
                    returnHtml = new StreamReader(sm, cding).ReadToEnd();
                }
                else
                {
                    returnHtml = new StreamReader(sm, cding).ReadToEnd();
                    Regex regex = new Regex("charset=(?<cding>[^=]+)?\"", RegexOptions.IgnoreCase);
                    string strcding = regex.Match(returnHtml).Groups["cding"].Value;
                    try
                    {
                        cding = Encoding.GetEncoding(strcding);
                    }
                    catch
                    {
                        cding = Encoding.Default;
                    }
                    byte[] bytes = Encoding.Default.GetBytes(returnHtml.ToCharArray());
                    returnHtml = cding.GetString(bytes);
                    if (returnHtml.Split('?').Length > 100)
                    {
                        returnHtml = Encoding.Default.GetString(bytes);
                    }
                }
                rsps.Close();
                return returnHtml;
            }
            catch
            {
                return "";
            }
        }