提取html内的文字1
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; }
郑重声明:本站内容如果来自互联网及其他传播媒体,其版权均属原媒体及文章作者所有。转载目的在于传递更多信息及用于网络分享,并不代表本站赞同其观点和对其真实性负责,也不构成任何其他建议。