ASP.NET过滤HTML字符串方法总结

发布时间:2022-04-16 发布网站:脚本宝典
脚本宝典收集整理的这篇文章主要介绍了ASP.NET过滤HTML字符串方法总结脚本宝典觉得挺不错的,现在分享给大家,也给大家做个参考。

本文实例讲述了ASP.NET过滤HTML字符串的方法,供大家参考使用,具体代码如下:

///  <summary>去除HTML标记 
///     
///  </summary>   
///  <param name="Htmlstring">包括HTML的码</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[^>]*&#63;>.*?</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, @"&amp;(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; 
} 

脚本宝典总结

以上是脚本宝典为你收集整理的ASP.NET过滤HTML字符串方法总结全部内容,希望文章能够帮你解决ASP.NET过滤HTML字符串方法总结所遇到的问题。

如果觉得脚本宝典网站内容还不错,欢迎将脚本宝典推荐好友。

本图文内容来源于网友网络收集整理提供,作为学习参考使用,版权属于原作者。
如您有任何意见或建议可联系处理。小编QQ:384754419,请注明来意。