提取HTML代码中文字的C#函数

 

        ///提取HTML代码中文字的函数
        ///  

        ///   去除HTML标记
        ///  

        ///   包括HTML的源码  
        ///   已经去除后的文字
        using   System;
        using   System.Text.RegularExpressions;
        public   class   StripHTMLTest{
              public   static   void   Main(){
                  string   s=StripHTML("faddfs龙信息平台 ");
                  Console.WriteLine(s);
              }
              public   static   string   StripHTML(string   strHtml){
                  string   []   aryReg   ={
                              @"]*?>.*?",
                              @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(*)?>",
                              @"([\r\n])[\s]+",
                              @"&(quot|#34);",
                              @"&(amp|#38);",
                              @"&(lt|#60);",
                              @"&(gt|#62);",
                              @"&(nbsp|#160);",
                              @"&(iexcl|#161);",
                              @"&(cent|#162);",
                              @"&(pound|#163);",
                              @"&(copy|#169);",
                              @"&#(\d+);",
                              @"-->",
                              @"