清除word html标签,剥离Word Html标签

我需要在特定位置删除Word HTML标记。目前我正在这样做：

public string CleanWordStyle(string html)

{

StringCollection sc = new StringCollection();

sc.Add(@"

");

sc.Add(@"(]+>");

sc.Add(@"(]+>");

sc.Add(@"(]+>");

sc.Add(@"(mso-bidi-|mso-fareast|mso-spacerun:|mso-list: ign|mso-ascii|mso-hansi|mso-ansi|mso-element|mso-special|mso-highlight|mso-border|mso-yfti|mso-padding|mso-background|mso-tab|mso-width|mso-height|mso-pagination|mso-theme|mso-outline)[^;]+;");

sc.Add(@"(font-size|font-family):[^;]+;");

sc.Add(@"font:[^;]+;");

sc.Add(@"line-height:[^;]+;");

sc.Add(@"class=""mso[^""]+""");

sc.Add(@"times new roman","serif";");

sc.Add(@"verdana","sans-serif";");

sc.Add(@"

sc.Add(@"

foreach (string s in sc)

{

html = Regex.Replace(html, s, "", RegexOptions.IgnoreCase);

}

html = Regex.Replace(html, @" ", @" "); //can not be read by as XmlDocument if not!

return html;

}

现在我正在使用

剥离sc.Add(@"