利用ASP.NET怎么对HTML字符串进行过滤

发布时间：2020-12-09 17:27:49 阅读：156 作者：Leah 栏目：开发技术

前端开发者测试专用服务器限时活动，0元免费领，库存有限，领完即止！点击查看>>

这期内容当中小编将会给大家带来有关利用ASP.NET怎么对HTML字符串进行过滤，文章内容丰富且以专业的角度为大家分析和叙述，阅读完这篇文章希望大家可以有所收获。

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[^>]*&#63;>.*&#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, @"&(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[^>]*&#63;>.*&#63;</applet>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<body[^>]*&#63;>.*&#63;</body>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<embed[^>]*&#63;>.*&#63;</embed>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<frame[^>]*&#63;>.*&#63;</frame>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<script[^>]*&#63;>.*&#63;</script>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<frameset[^>]*&#63;>.*&#63;</frameset>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<html[^>]*&#63;>.*&#63;</html>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<iframe[^>]*&#63;>.*&#63;</iframe>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<style[^>]*&#63;>.*&#63;</style>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<layer[^>]*&#63;>.*&#63;</layer>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<link[^>]*&#63;>.*&#63;</link>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<ilayer[^>]*&#63;>.*&#63;</ilayer>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<meta[^>]*&#63;>.*&#63;</meta>", "", RegexOptions.IgnoreCase); 
  str = Regex.Replace(str, @"<object[^>]*&#63;>.*&#63;</object>", "", RegexOptions.IgnoreCase); 
  return str; 
}

上述就是小编为大家分享的利用ASP.NET怎么对HTML字符串进行过滤了，如果刚好有类似的疑惑，不妨参照上述分析进行理解。如果想知道更多相关知识，欢迎关注亿速云行业资讯频道。

亿速云「云服务器」，即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘，价格低至29元/月。点击查看>>

向AI问一下细节

利用ASP.NET怎么对HTML字符串进行过滤

猜你喜欢

最新资讯

相关推荐

开发者交流群：

相关标签