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

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 = "
tag
";
    var expected = "tag";
    var actual = HtmlUtilities.StripTags(input, "p");

    Assert.AreEqual(expected, actual);
}

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

    Assert.AreEqual(expected, actual);
}

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

    Assert.AreEqual(expected, actual);
}

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

    Assert.AreEqual(expected, actual);
}

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

    Assert.AreEqual(expected, actual);
}

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

    Assert.AreEqual(expected, actual);

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

    Assert.AreEqual(expected, actual);
}

[TestMethod]
public void StripTags_CanStripSelfClosingAndUnclosedTagsLikeBr()
{
    var input = "
tag


";
    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.