Converting from MS Word to HTML / XHML

The below C# .net code helps you to clean your HTML which you may have copied from Microsoft word. This .Net code will remove the unwanted XML and other word specific symbols and gives you a clean and tidy HTML which you can then easily convert to XHTML. In short this C# code will help you to convert MS Word specific HTML document to HTML and there by XHTML

static string CleanHtml(string html)

{

     StringCollection sc = new StringCollection();

     html = Regex.Replace(html, @"<(o:p|\/o:p)>", "", RegexOptions.IgnoreCase|RegexOptions.Compiled|RegexOptions.Compiled);

     html = Regex.Replace(html, @"\s*mso-[^:]+:[^;\x22]+;?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"\s*MARGIN-\w{3,6}:\s*0\w{2}\s*;?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"\s*MARGIN\s*:(\s*0\w{2}){3}\s*;?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"\s*TEXT-INDENT: 0.{2}\s*;", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = html.Replace("
", "
");

     html = html.Replace(" ", "\t");

     html = html.Replace("align=\"middle\"", "align=\"center\"");

     Application.DoEvents();

     html = Regex.Replace(html, @"<\\?\?xml[^>]*>", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

    html = Regex.Replace(html, @"<\/?\w+:[^>]*>", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     //html = Regex.Replace(html, @", "$1", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"-->\s*\r*( )", "$1", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(<\w[^>]*style=)(')([^ |>]*)'", "$1$3$5$7", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(font-family:)\s*(\x22)([\w\s-]*)\s*(\x22)(,)\s*(\x22)([\w\s-]*)\s*(\x22)(,)\s*(\x22)([\w\s-]*)\s*(\x22)(,)\s*(\x22)([\w\s-]*)\s*(\x22)", "$1$3$5$7$9$11$13$15", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(font-family:)\s*(\x22)([\w\s-]*)\s*(\x22)(,)\s*(\x22)([\w\s-]*)\s*(\x22)(,)\s*(\x22)([\w\s-]*)\s*(\x22)", "$1$3$5$7$9$11",RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(font-family:)\s*\x22([\w\s-]*)\s*\x22(,)\s*\x22([\w\s-]*)\s*\x22", "$1$2$3$4",RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(font-family:)\s*(\x22)([\w\s-]*)\s*(\x22)", "$1$3", RegexOptions.IgnoreCase|RegexOptions.Compiled);

      Application.DoEvents();

  

     html = html.Replace("·", "\xB7");

   

     if (Quotes)

     {

  html = Regex.Replace(html, @"(]*)([^/]>)\s*()?", "$1\"/>", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     }

     else

     {

  html = Regex.Replace(html, @"(]*)([^/]>)\s*()?", "$1/>", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     }

     html = Regex.Replace(html, @"(]*)([^/]>)\s*()?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"Style\s*=\x22?\s*mso-?\w*\s*\x22?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*>\s*", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

 

     html = Regex.Replace(html, @"]*/>", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"]*/>", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"(style\s*=\s*\x22[^\x22]*)(\s*\x22\s*Style\s*=\s*\x22)", "$1;", RegexOptions.IgnoreCase|RegexOptions.Compiled);

 

     html = Regex.Replace(html, @"Class\s*=\x22?\s*\d*-\d*\s*\x22?", "", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = Regex.Replace(html, @"()([\s\w]*)()", "$2", RegexOptions.IgnoreCase|RegexOptions.Compiled);

     html = html.Replace("®", "®");

     html = html.Replace("©", "©");

     html = html.Replace("™", "™");

     return html;

 }