提取HTML代码中文字的C#函数

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Node.js›Node.js教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

/// <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;
}