]*?>.*?", "", RegexOption">
 | 注册
请输入搜索内容

热门搜索

Java Linux MySQL PHP JavaScript Hibernate jQuery Nginx
Blake36Q
10年前发布

c#使用正则表达式替换html标签

using System.Text.RegularExpressions;     //包含正则表达式       public static string NoHTML(string Htmlstring) //去除HTML标记     {       //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>     /// 将所有HTML标签替换成""     /// </summary>     /// <param name="strHtml"></param>     /// <returns></returns>     public static string StripHTML(string strHtml)     {       string[] aryReg ={         @"<script[^>]*?>.*?</script>",         @"<(///s*)?!?((/w+:)?/w+)(/w+(/s*=?/s*(([""'])(file://[""'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;     }