C#提取HTML中文字的函数

最新推荐文章于 2024-07-21 16:29:46 发布

aa76789762

最新推荐文章于 2024-07-21 16:29:46 发布

阅读量109

点赞数

文章标签： c#

原文链接：http://www.cnblogs.com/breezeblew/archive/2009/03/10/1408214.html

版权

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;
              }

转载于:https://www.cnblogs.com/breezeblew/archive/2009/03/10/1408214.html