HTML格式化为标准XML

第三方

SgmlReaderDll   

/// <summary>

        /// 把html转成XML

        /// </summary>

        /// <param name="html"></param>

        /// <returns></returns>

        private static XElement Html2XML(string html)

        {

            Sgml.SgmlReader sgmlReader = new Sgml.SgmlReader();

            sgmlReader.DocType = "HTML";

            sgmlReader.WhitespaceHandling = WhitespaceHandling.All;

            sgmlReader.CaseFolding = Sgml.CaseFolding.ToLower;

            sgmlReader.InputStream = new StringReader(html);

            return XElement.Load(sgmlReader);

        }           

转载于:https://www.cnblogs.com/kklldog/archive/2011/08/08/2130980.html