脚本之家 服务器常用软件
快捷导航
您的位置：首页 → 网络编程 → ASP.NET → 自学过程 → c#过滤html

c#中过滤html的正则表达式

 更新时间：2006年10月13日 00:00:00   投稿：mdxy-dxy  
这篇文章主要为大家介绍c#中过滤html的正则表达式，需要的朋友可以参考一下

实现代码

///  <summary>
///  去除HTML标记
///  </summary>
///  <param  name=”NoHTML”>包括HTML的源码  </param>
///  <returns>已经去除后的文字</returns>
public static string NoHTML(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;
}

C#过滤Html标签及空格

public static string FilterHTML(string HTMLStr)
    {
      if (!string.IsNullOrEmpty(HTMLStr))
        return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>|&nbsp;", "");
      else
        return "";
    }

写一个静态方法移除HTML标签

#region
///  <summary>
///  移除HTML标签
///  </summary>
///  <param  name="HTMLStr">HTMLStr</param>
public static string ParseTags(string HTMLStr)
{
 return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
}
#endregion

取出文本中的图片地址

#region
///  <summary>
///  取出文本中的图片地址
///  </summary>
///  <param  name="HTMLStr">HTMLStr</param>
public static string GetImgUrl(string HTMLStr)
{
 string str = string.Empty;
 string sPattern = @"^<img\s+[^>]*>";
 Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>",
  RegexOptions.Compiled);
 Match m = r.Match(HTMLStr.ToLower());
 if (m.Success)
  str = m.Result("${url}");
 return str;
}
#endregion

提取HTML代码中文字的C#函数

///  <summary>
///  提取HTML代码中文字的C#函数
///  </summary>
///  <param  name="strHtml">包括HTML的源码  </param>
///  <returns>已经去除后的文字</returns>
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest
{
 public static void Main()
 {
  string s = StripHTML(
   "<HTML><HEAD><TITLE>中国石龙信息平台</TITLE></HEAD><BODY>faddfs龙信息平台</BODY></HTML>");
  Console.WriteLine(s);
 }

 public static string StripHTML(string strHtml)
 {
  string[]aryReg =
  {
   @"<script[^>]*?>.*?</script>",

   @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\["
    "'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @
    "&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @
    "&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);",
    @"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.*\n"
  };

  string[]aryRep =
  {
   "", "", "", "\"", "&", "<", ">", "  ", "\xa1", //chr(161),
   "\xa2", //chr(162),
   "\xa3", //chr(163),
   "\xa9", //chr(169),
   "", "\r\n", ""
  };

  string newReg = aryReg[0];
  string strOutput = strHtml;
  for (int i = 0; i < aryReg.Length; i++)
  {
   Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
   strOutput = regex.Replace(strOutput, aryRep[i]);
  }
  strOutput.Replace("<", "");
  strOutput.Replace(">", "");
  strOutput.Replace("\r\n", "");
  return strOutput;
 }
}

TempContent 表示包含有html的字符串；
TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]+>","");至少一个
TempContent = System.Text.RegularExpressions.Regex.Replace(TempContent,"<[^>]*>","");任意个 

您可能感兴趣的文章:

相关文章

最新评论