public static void RemoveComments(HtmlNode node)
{
foreach (var n in node.ChildNodes.ToArray())
RemoveComments(n);
if (node.NodeType == HtmlNodeType.Comment)
node.Remove();
}
static void Main(string[] args)
{
var doc = new HtmlDocument();
string html = @"<!--[if gte mso 9]>
...
<![endif]-->
<body>
<span>
<!-- comment -->
</span>
<!-- another comment -->
</body>
<!--[if gte mso 10]>
...
<![endif]-->";
doc.LoadHtml(html);
RemoveComments(doc.DocumentNode);
Console.WriteLine(doc.DocumentNode.OuterHtml);
Console.ReadLine();
}
Or a fun little LINQ-style:
public static IEnumerable<HtmlNode> Walk(HtmlNode node)
{
yield return node;
foreach (var child in node.ChildNodes)
foreach (var x in Walk(child))
yield return x;
}
...
foreach (var n in Walk(doc.DocumentNode).OfType<HtmlCommentNode>().ToArray())
n.Remove();
Even easier (forgot we could use xpath to find comment nodes)
var doc = new HtmlDocument();
string html = @"
<!--[if gte mso 9]>
...
<![endif]-->
<body>
<span>
<!-- comment -->
</span>
<!-- another comment -->
</body>
<!--[if gte mso 10]>
...
<![endif]-->";
doc.LoadHtml(html);
foreach (var n in doc.DocumentNode.SelectNodes("//comment()") ?? new HtmlNodeCollection(doc.DocumentNode))
n.Remove();
与恶龙缠斗过久,自身亦成为恶龙；凝视深渊过久,深渊将回以凝视…
