ASP.NET过滤HTML字符串方法总结

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; 
}