C#去除HTML标签方法

原文链接：http://www.cnblogs.com/TSPWater/archive/2011/10/11/2206814.html public static string ExecRepaceHTML(string Htmlstring) 
{ 
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase); 
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, @"<!--.*\n", "", 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 = Regex.Replace(Htmlstring, @"\s", ""); Htmlstring.Replace("<", ""); Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", ""); 
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}

转载于:https://www.cnblogs.com/TSPWater/archive/2011/10/11/2206814.html

标签：Regex,Htmlstring,C#,标签,www,Replace,IgnoreCase,HTML,RegexOptions
来源： https://blog.csdn.net/weixin_30906185/article/details/95302678