提取HTML代码中文字的C#函数

最新推荐文章于 2024-04-15 00:05:43 发布

cansee

最新推荐文章于 2024-04-15 00:05:43 发布

阅读量807

点赞数

分类专栏： C#文档文章标签： html c# string regex

本文链接：https://blog.csdn.net/cansee/article/details/265438

版权

C#文档专栏收录该内容

26 篇文章 0 订阅

订阅专栏

转自：http://goaler.xicp.net/ShowLog.asp?ID=477

/// <summary>
  /// 去除HTML标记
  /// </summary>
  /// <param name="strHtml">包括HTML的源码 </param>
  /// <returns>已经去除后的文字</returns>
  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;
}