如果需要清除后台获得的网页源文件中的HMTL标记,那么需要使用正则表达式,下面这个直接编写为函数的程序,各位可以直接使用,也可以在这里先测试一下。看看效果如何。
- using System.Text.RegularExpressions; //包含正则表达式
- public static string NoHTML(string Htmlstring) //去除HTML标记
- {
- //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;
- }
或者
- /// <summary>
- /// 将所有HTML标签替换成""
- /// </summary>
- /// <param name="strHtml"></param>
- /// <returns></returns>
- public static string StripHTML(string strHtml)
- {
- string[] aryReg ={
- @"<script[^>]*?>.*?</script>",
- @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(file://[""'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;
- }
用起来很是不错。我用的第一个,第二个没有测试。原文链接:http://jhxk.javaeye.com/blog/436867