第1个回答 2012-04-21
出现乱码了,不知道你是什么意思,如果你是想从html文本中提取出纯文本的话,给你个方法你调用一下:
public string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Htmlstring.Replace("\r\n", "");
Htmlstring = Regex.Replace(Htmlstring, @"<script.*?</script>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<style.*?</style>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<.*?>", "", 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 = Htmlstring.Replace("<", "");
Htmlstring = Htmlstring.Replace(">", "");
Htmlstring = Htmlstring.Replace("\r\n", "");
//Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}