首页 > > 程序设计 > delphi >

在ASP.NET中过滤HTML字符串总结

2018-06-17 20:25:04来源：未知阅读 ()

先记下来，以作备用！

C#代码

/// <summary>去除HTML标记
///
/// </summary>
/// <param name="Htmlstring">包括HTML的源码</param>
/// <returns>已经去除后的文字</returns>
public static string GetNoHTMLString(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;
}
/// <summary>获取显示的字符串，可显示HTML标签，但把危险的HTML标签过滤，如iframe,script等。
///
/// </summary>
/// <param name="str">未处理的字符串</param>
/// <returns></returns>
public static string GetSafeHTMLString(string str)
{
str = Regex.Replace(str, @"<applet[^>]*?>.*?</applet>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<body[^>]*?>.*?</body>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<embed[^>]*?>.*?</embed>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<frame[^>]*?>.*?</frame>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<frameset[^>]*?>.*?</frameset>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<html[^>]*?>.*?</html>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<iframe[^>]*?>.*?</iframe>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<style[^>]*?>.*?</style>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<layer[^>]*?>.*?</layer>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<link[^>]*?>.*?</link>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<ilayer[^>]*?>.*?</ilayer>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<meta[^>]*?>.*?</meta>", "", RegexOptions.IgnoreCase);
str = Regex.Replace(str, @"<object[^>]*?>.*?</object>", "", RegexOptions.IgnoreCase);
return str;
}