Html Agility Pack - Remove element, but not innerHtml

Question

I can easily remove the element just by note.Remove() lik this:

HtmlDocument html = new HtmlDocument();

html.Load(Server.MapPath(@\"~\\Site\\themes\\default         


        

Answer 1

How about this?

var removedNodes = document.SelectNodes("//removeme");
if(removedNodes != null)
    foreach(var rn in removedNodes){
        HtmlTextNode innernodes =document.CreateTextNode(rn.InnerHtml);
        rn.ParnetNode.ReplaceChild(innernodes, rn);
    }

Answer 2

Adding my two cents because none of these approaches handled what I wanted (to remove a set of given tags like p and div and handle nesting properly while preserving inner tags).

Here's what I came up with and passes all my unit tests with what I would consider most of the cases I need to deal with:

var htmlDoc = new HtmlDocument();

// load html
htmlDoc.LoadHtml(html);

var tags = (from tag in htmlDoc.DocumentNode.Descendants()
           where tagNames.Contains(tag.Name)
           select tag).Reverse();

// find formatting tags
foreach (var item in tags)
{
    if (item.PreviousSibling == null)
    {
        // Prepend children to parent node in reverse order
        foreach (HtmlNode node in item.ChildNodes.Reverse())
        {
            item.ParentNode.PrependChild(node);
        }                        
    }
    else
    {
        // Insert children after previous sibling
        foreach (HtmlNode node in item.ChildNodes)
        {
            item.ParentNode.InsertAfter(node, item.PreviousSibling);
        }
    }

    // remove from tree
    item.Remove();
}

// return transformed doc
html = htmlDoc.DocumentNode.WriteContentTo().Trim();

Here are the cases I used to test:

[TestMethod]
public void StripTags_CanStripSingleTag()
{
    var input = "<p>tag</p>";
    var expected = "tag";
    var actual = HtmlUtilities.StripTags(input, "p");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripNestedTag()
{
    var input = "<p>tag <p>inner</p></p>";
    var expected = "tag inner";
    var actual = HtmlUtilities.StripTags(input, "p");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripTwoTopLevelTags()
{
    var input = "<p>tag</p> <div>block</div>";
    var expected = "tag block";
    var actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripMultipleNestedTags_2LevelsDeep()
{
    var input = "<p>tag <div>inner</div></p>";
    var expected = "tag inner";
    var actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripMultipleNestedTags_3LevelsDeep()
{
    var input = "<p>tag <div>inner <p>superinner</p></div></p>";
    var expected = "tag inner superinner";
    var actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripTwoTopLevelMultipleNestedTags_3LevelsDeep()
{
    var input = "<p>tag <div>inner <p>superinner</p></div></p> <div><p>inner</p> toplevel</div>";
    var expected = "tag inner superinner inner toplevel";
    var actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_IgnoresTagsThatArentSpecified()
{
    var input = "<p>tag <div>inner <a>superinner</a></div></p>";
    var expected = "tag inner <a>superinner</a>";
    var actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);

    input = "<wrapper><p>tag <div>inner</div></p></wrapper>";
    expected = "<wrapper>tag inner</wrapper>";
    actual = HtmlUtilities.StripTags(input, "p", "div");

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripSelfClosingAndUnclosedTagsLikeBr()
{
    var input = "<p>tag</p><br><br/>";
    var expected = "tag";
    var actual = HtmlUtilities.StripTags(input, "p", "br");

    Assert.AreEqual(expected, actual);
}

It may not handle everything probably but it works for my needs.

Answer 3

Perhaps this might be what you're looking for?

foreach (HtmlNode node in html.DocumentNode.SelectNodes("//removeme"))
{
    HtmlNodeCollection children = node.ChildNodes; //get <removeme>'s children
    HtmlNode parent = node.ParentNode; //get <removeme>'s parent
    node.Remove(); //remove <removeme>
    parent.AppendChildren(children); //append the children to the parent
}

Edit: L.B's answer is much cleaner. Go with his!

Answer 4

HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);

var node = doc.DocumentNode.SelectSingleNode("//removeme");
node.ParentNode.RemoveChild(node, true);