How do I filter all HTML tags except a certain whitelist?

Question

This is for .NET. IgnoreCase is set and MultiLine is NOT set.

Usually I\'m decent at regex, maybe I\'m running low on caffeine...

Users are allowed to enter

Answer 1

    /// 

    /// Trims the ignoring spacified tags
    /// 
    /// the text from which html is to be removed
    /// specify if you want to remove scripts
    /// specify the tags that are to be ignored while stripping
    /// Stripped Text
    public static string StripHtml(string text, bool isRemoveScript, params string[] ignorableTags)
    {
        if (!string.IsNullOrEmpty(text))
        {
            text = text.Replace("<", "<");
            text = text.Replace(">", ">");
            string ignorePattern = null;

            if (isRemoveScript)
            {
                text = Regex.Replace(text, "", string.Empty, RegexOptions.IgnoreCase);
            }
            if (!ignorableTags.Contains("style"))
            {
                text = Regex.Replace(text, "", string.Empty, RegexOptions.IgnoreCase);
            }
            foreach (string tag in ignorableTags)
            {
                //the character b spoils the regex so replace it with strong
                if (tag.Equals("b"))
                {
                    text = text.Replace("", "");
                    text = text.Replace("", "");
                    if (ignorableTags.Contains("strong"))
                    {
                        ignorePattern = string.Format("{0}(?!strong)(?!/strong)", ignorePattern);
                    }
                }
                else
                {
                    //Create ignore pattern fo the tags to ignore
                    ignorePattern = string.Format("{0}(?!{1})(?!/{1})", ignorePattern, tag);
                }

            }
            //finally add the ignore pattern into regex <[^<]*> which is used to match all html tags
            ignorePattern = string.Format(@"<{0}[^<]*>", ignorePattern);
            text = Regex.Replace(text, ignorePattern, "", RegexOptions.IgnoreCase);
        }

        return text;
    }