C# 正则移除所有的Html标记

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
=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

return Htmlstring;
}

转,原文:http://www.csharpwin.com/dotnetspace/12189r6285.shtml



返回导读目录,阅读更多随笔



分割线,以下为博客签名:

软件臭虫情未了
  • 编码一分钟
  • 测试十年功


随笔如有错误或不恰当之处、为希望不误导他人,望大侠们给予批评指正。

原文地址:https://www.cnblogs.com/08shiyan/p/2088975.html