提取HTML代码中文字的C#函数

网络编程 2024/9/25 佚名

3 2 1

无为清净楼资源网 Design By www.qnjia.com

/// <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)
"<script[^>]*?>.*?</script>",

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

         "",
           "",
           "",
           "\"",
           "&",
           "<",
           ">",
           " ",
           "\xa1",//chr(161),
           "\xa2",//chr(162),
           "\xa3",//chr(163),
           "\xa9",//chr(169),
           "",
           "\r\n",
           ""
          "<","");
   strOutput.Replace(">","");
   strOutput.Replace("\r\n","");