我正在使用此处找到的 Jeff Atwood 的代码对我的 Html 进行消毒
但是我遇到的问题是当我在表单中输入 Markdown 链接时（它们被删除了）
<http://www.example.com>
这是我正在使用的代码。
private static Regex _tags = new Regex("<[^>]*(>|$)",
RegexOptions.Singleline | RegexOptions.ExplicitCapture | RegexOptions.Compiled);
private static Regex _whitelist = new Regex(@"
^</?(b(lockquote)?|code|d(d|t|l|el)|em|h(1|2|3)|i|kbd|li|ol|p(re)?|s(ub|up|trong|trike)?|ul)>$|
^<(b|h)r\s?/?>$",
RegexOptions.Singleline | RegexOptions.ExplicitCapture | RegexOptions.Compiled | RegexOptions.IgnorePatternWhitespace);
private static Regex _whitelist_a = new Regex(@"
^<a\s
href=""(\#\d+|(https?|ftp)://[-a-z0-9+&@#/%?=~_|!:,.;\(\)]+)""
(\stitle=""[^""<>]+"")?\s?>$|
^</a>$",
RegexOptions.Singleline | RegexOptions.ExplicitCapture | RegexOptions.Compiled | RegexOptions.IgnorePatternWhitespace);
private static Regex _whitelist_img = new Regex(@"
^<img\s
src=""https?://[-a-z0-9+&@#/%?=~_|!:,.;\(\)]+""
(\swidth=""\d{1,3}"")?
(\sheight=""\d{1,3}"")?
(\salt=""[^""<>]*"")?
(\stitle=""[^""<>]*"")?
\s?/?>$",
RegexOptions.Singleline | RegexOptions.ExplicitCapture | RegexOptions.Compiled | RegexOptions.IgnorePatternWhitespace);
/// <summary>
/// sanitize any potentially dangerous tags from the provided raw HTML input using
/// a whitelist based approach, leaving the "safe" HTML tags
/// CODESNIPPET:4100A61A-1711-4366-B0B0-144D1179A937
/// </summary>
public static string Sanitize(string html)
{
if (String.IsNullOrEmpty(html)) return html;
string tagname;
Match tag;
// match every HTML tag in the input
MatchCollection tags = _tags.Matches(html);
for (int i = tags.Count - 1; i > -1; i--)
{
tag = tags[i];
tagname = tag.Value.ToLowerInvariant();
if(!(_whitelist.IsMatch(tagname) || _whitelist_a.IsMatch(tagname) || _whitelist_img.IsMatch(tagname)))
{
html = html.Remove(tag.Index, tag.Length);
System.Diagnostics.Debug.WriteLine("tag sanitized: " + tagname);
}
}
return html;
}