过滤html标签 RemoveHTML
#region =====过滤html标签 RemoveHTML(string html)=====
/// <summary>
/// 过滤html
/// </summary>
/// <param name="html">需要过滤的字符串</param>
/// <returns>过滤html后的字符串</returns>
public static string RemoveHTML(string html)
{
html = Regex.Replace(html, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"-->", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"<!--.*", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"&#(\d+);", "", RegexOptions.IgnoreCase);
html = Regex.Replace(html, @"<img[^>]*>;", "", RegexOptions.IgnoreCase);
html.Replace("<", "");
html.Replace(">", "");
html.Replace("\r\n", "");
//html = HttpContext.Current.Server.HtmlEncode(html).Trim();
//html = HttpContext.Current.Server.HtmlDecode(html).Trim();
return html;
}
#endregion