C#中如何去除HTML標記
來源:互聯網
上載者:User
/// <summary>
/// 去除HTML標記
/// </summary>
/// <param name="Htmlstring">包括HTML的源碼 </param>
/// <returns>已經去除後的文字</returns>
public string NoHTML(string Htmlstring)
{
//刪除指令碼
Htmlstring = Htmlstring.Replace("\r\n","");
Htmlstring = Regex.Replace(Htmlstring,@"<script.*?</script>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<style.*?</style>","",RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring,@"<.*?>","",RegexOptions.IgnoreCase);
//刪除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 = Htmlstring.Replace("<","");
Htmlstring = Htmlstring.Replace(">","");
Htmlstring = Htmlstring.Replace("\r\n","");
Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}