Asp.net 使用正则过滤信息

最新推荐文章于 2018-07-22 09:01:06 发布

追夢秋陽

最新推荐文章于 2018-07-22 09:01:06 发布

阅读量649

点赞数

分类专栏： .Net技术分享文章标签： asp.net 正则过滤

本文链接：https://blog.csdn.net/yimiyuangguang/article/details/42456795

版权

.Net技术分享专栏收录该内容

10 篇文章 0 订阅

订阅专栏

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