C#去掉HTML标记
using System.Text.RegularExpressions; /// <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) { string[] aryReg ={ @"<script[^>]*?>.*?</script>", @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([ ])[\s]+", @"&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @"&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);", @"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.* " }; string[] aryRep = { "", "", "", "\"", "&", "<", ">", " ", "\xa1",//chr(161), "\xa2",//chr(162), "\xa3",//chr(163), "\xa9",//chr(169), "", " ", "" }; string newReg = aryReg; string strOutput = strHtml; for (int i = 0; i < aryReg.Length; i++) { Regex regex = new Regex(aryReg, RegexOptions.IgnoreCase); strOutput = regex.Replace(strOutput, aryRep); } strOutput.Replace("<", ""); strOutput.Replace(">", ""); strOutput.Replace(" ", ""); return strOutput; }
页:
[1]