C# 字符串去除HTML格式

最新推荐文章于 2021-06-17 01:43:33 发布

weixin_33670713

最新推荐文章于 2021-06-17 01:43:33 发布

阅读量78

点赞数

CC 4.0 BY-SA版权

文章标签： c#

原文链接：http://www.cnblogs.com/Yellowshorts/archive/2013/03/09/2951503.html

本文介绍了一个用于去除HTML字符串中的所有HTML标签、特殊字符和脚本的C#方法。该方法通过正则表达式来实现，可以有效清理HTML内容，使其仅保留纯文本信息。

public static string NoHTML(string Htmlstring)
{
if (Htmlstring.Length > 0)
{
//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, @"“", "\"", RegexOptions.IgnoreCase);//保留【 “ 】的标点符合
Htmlstring = Regex.Replace(Htmlstring, @"”", "\"", RegexOptions.IgnoreCase);//保留【 ” 】的标点符合
Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
}
return Htmlstring;
}