原文 C#用正则表达式去掉Html中的script脚本和html标签
///
<summary>
/// 用正则表达式去掉Html中的script脚本和html标签 /// </summary> /// <param
name="Htmlstring"></param> /// <returns></returns> public static
string NoHTML(string
Htmlstring) { //删除脚本 Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "",
RegexOptions.IgnoreCase); //删除HTML Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"-->", "",
RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "",
RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", "
", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "",
RegexOptions.IgnoreCase); Htmlstring.Replace("<", ""); Htmlstring.Replace(">", ""); Htmlstring.Replace("\r\n", ""); Htmlstring =
HttpUtility.HtmlDecode(Htmlstring).Replace("<br/>",
"").Replace("<br>",
"").Trim(); return Htmlstring; }C#用正则表达式去掉Html中的script脚本和html标签
原文：http://www.cnblogs.com/lonelyxmas/p/3551624.html