zoukankan      html  css  js  c++  java

  • asp.net如何去掉HTML标记

    ///   <summary>   
          ///   去除HTML标记   
          ///   </summary>   
          ///   <param   name="NoHTML">包括HTML的源码   </param>   
          ///   <returns>已经去除后的文字</returns>   
      public   static   string   NoHTML(string   Htmlstring)   
          {   
          //删除脚本   
      Htmlstring   =   Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",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.Replace(    "<","");   
      Htmlstring.Replace(    ">","");   
      Htmlstring.Replace(    "\r\n","");   
      Htmlstring    =HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();   
        
          return   Htmlstring;   
      }



    ///提取HTML代码中文字的C#函数     
          ///   <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>   
      using   System;   
          using   System.Text.RegularExpressions;   
          public   class   StripHTMLTest{   
              public   static   void   Main(){   
                  string   s=StripHTML("<HTML><HEAD><TITLE>中国石龙信息平台</TITLE></HEAD><BODY>faddfs龙信息平台</BODY></HTML>");   
              Console.WriteLine(s);   
          }       
        
              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;   
          }       
      }


    写一个静态方法   
          移除HTML标签   
        
                          取出文本中的图片地址
  • 相关阅读:
    JavaScript ---Function
    win7(x64)安装scrapy框架
    [转]mysql性能优化-慢查询分析、优化索引和配置
    [原创]win7环境下搭建eclipse+python+django开发环境
    [原创]Python/Django使用富文本编辑器XHeditor上传本地图片
    Ubuntu下mysql使用
    [整理] mysql操作
    [原创]Sql2008 使用TVP批量插入数据
    一个js获取数组下标的函数
    深入理解js的prototype以及prototype的一些应用
  • 原文地址：https://www.cnblogs.com/goody9807/p/961195.html
Copyright © 2011-2022 走看看