您的位置:首页 > 编程语言 > ASP

Asp.net 使用正则过滤信息

2015-01-06 12:09 232 查看

Asp.net 使用正则过滤信息

学习参考案例如下:
#region 去除HTML标记
/// <summary>
/// 去除HTML标记
/// </summary>
/// <param name="Htmlstring">需要处理的字符串</param>
/// <returns></returns>
private static string NoHTML(string Htmlstring = "")
{
//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 = Regex.Replace(Htmlstring, ">", "");
Htmlstring = Regex.Replace(Htmlstring, "<", "");
Htmlstring = Regex.Replace(Htmlstring, "\r\n", "");
Htmlstring = Htmlstring.Substring(Htmlstring.IndexOf("\n") + 1);
if (Htmlstring.LastIndexOf("'") >= 0)
Htmlstring = Htmlstring.Substring(Htmlstring.LastIndexOf("'") + 1);
if (Htmlstring.IndexOf("class='tdbk'") >= 0)
Htmlstring = Htmlstring.Substring(Htmlstring.IndexOf("class='tdbk'") + "class='tdbk'".Length);
Htmlstring = Htmlstring.Replace("<span>(* 本数据由中国外汇交易中心授权转载)</span>", "");

return Htmlstring;
}
#endregion
内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签:  asp.net 正则 过滤