• C#中如何去除HTML标记


     /// <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 string NoHTML(string Htmlstring)
      {
       //删除脚本
       Htmlstring = Htmlstring.Replace("\r\n","");
       Htmlstring = Regex.Replace(Htmlstring,@"<script.*?</script>","",RegexOptions.IgnoreCase);
       Htmlstring = Regex.Replace(Htmlstring,@"<style.*?</style>","",RegexOptions.IgnoreCase);
       Htmlstring = Regex.Replace(Htmlstring,@"<.*?>","",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 = Htmlstring.Replace("<","");
       Htmlstring = Htmlstring.Replace(">","");
       Htmlstring = Htmlstring.Replace("\r\n","");   
       Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
       return Htmlstring;
      }
  • 相关阅读:
    [LeetCode] Search a 2D Matrix
    [LeetCode] Merge Sorted Array
    [LeetCode] Remove Duplicates from Sorted Array
    [LeetCode] Convert Sorted Array to Binary Search Tree
    [LeetCode] Remove Element
    [LeetCode] Search Insert Position
    [LeetCode] Remove Duplicates from Sorted List
    [LeetCode] Merge Two Sorted Lists
    [LeetCode] Best Time to Buy and Sell Stock II
    [LeetCode] Reverse Integer
  • 原文地址:https://www.cnblogs.com/zoupeiyang/p/1508039.html
Copyright © 2020-2023  润新知