HTML到XML转换方法探讨

 #region  HTML转换XML,并保存
        /// <summary>
        /// HTML转换XML,并保存
        /// </summary>
        /// <param name="htmlRUL">ip地址</param>
        /// <param name="xmlURL">XML路径</param>
        public static void SetStreamXML(string htmlRUL, string xmlURL)
        {
            if (File.Exists(xmlURL))
                File.Delete(xmlURL);
            else
                File.Create(xmlURL);
            WebClient client = new WebClient();
            client.Headers.Add("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705;)");

            Stream data = client.OpenRead(htmlRUL);
            StreamReader reader = new StreamReader(data);
            string s = reader.ReadToEnd();   ///将页面返回结果生成一个字符串
            TextWriter tw = new StreamWriter(xmlURL, false, Encoding.UTF8);
            using (SgmlReader readers = new SgmlReader())  //HTML转换为XML格式
            {
                readers.DocType = "HTML";  //指定文件类型
                readers.InputStream = new StringReader(s); //将HTML转化为输出流
                using (StringWriter stringwriter = new StringWriter()) //创建一个输出字符串，并保存
                {
                    using (XmlTextWriter writer = new XmlTextWriter(stringwriter))//创建一个XML文件，并将下面字符串转换为XML文件
                    {
                        readers.WhitespaceHandling = WhitespaceHandling.None;
                        writer.Formatting = Formatting.Indented;//设置文本格式
                        XmlDocument doc = new XmlDocument();