博客

asp.net开发中，有时需要对读出的文本进行处理，例如不需要html格式，需要数据直接以文本方式显示，这时就需要一个方法来去除html。

具体代码如下：

因为是利用正则来处理，所以需要添加命名空间：

using System.Text.RegularExpressions;

public static string RemoveHTML(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.Replace(“<“, “”);

Htmlstring.Replace(“>”, “”);

Htmlstring.Replace(“\r\n”, “”);

Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

return Htmlstring;

}

OK!大功告成！