使用SgmlReader将HTML转换为合法的XML

 public static string Convert(string html)
{
    if (string.IsNullOrEmpty(html.Trim()))
    {
        return string.Empty;
    }
    using (SgmlReader reader = new SgmlReader())
    {
        reader.DocType = "HTML";
        reader.InputStream = new StringReader(html);
        using (StringWriter stringWriter = new StringWriter())
        {
            using (XmlTextWriter writer = new XmlTextWriter(stringWriter))
            {
                reader.WhitespaceHandling = WhitespaceHandling.None;
                writer.Formatting = Formatting.Indented;
                XmlDocument doc = new XmlDocument();
                doc.Load(reader);
                if (doc.DocumentElement == null)
                {
                    return string.Empty;
                }
                else
               {
                    doc.DocumentElement.WriteContentTo(writer);
                }
                writer.Close();
                string xhtml = stringWriter.ToString();
                return xhtml;
            }
        }
    }
}

其他相关资料：http://www.kaiyuan8.org/Article/KLNvXMQhmKeyQyVGCfBZ.aspx

                     http://www.eggheadcafe.com/articles/20030317.asp