I am writing a HTML parser with AngleSharp which should input HTML like this:
<p>
Paragraph Text
<a href="https://www.example com" class="external text" target="_new" rel="nofollow">Link Text</a>
Paragraph Text 2
</p>
and output it like this:
<p>
Paragraph Text
<a href="https://www.example com">Link Text</a>
Paragraph Text 2
</p>
I wrote this recursive function to go through the whole document:
using AngleSharp.Dom;
using AngleSharp.Dom.Html;
using AngleSharp.Extensions;
using AngleSharp.Parser.Html;
private void processHTMLNode(IElement node, IElement targetNode)
{
switch (node.NodeName.ToLower())
{
//...
case "a":
if(node.HasAttribute("href") && node.GetAttribute("href").StartsWith("#"))
{
break;
}
var aNew = outputDocument.CreateElement("a");
aNew.SetAttribute("href", node.GetAttribute("href"));
aNew.TextContent = node.TextContent;
targetNode.AppendChild(aNew);
break;
case "p":
var pNew = outputDocument.CreateElement<IHtmlParagraphElement>();
foreach (var childNode in node.Children)
{
processHTMLNode(childNode, pNew);
}
//TODO fix this
pNew.TextContent = node.TextContent;
targetNode.AppendChild(pNew);
break;
}
//...
}
The problem is, that setting the TextContent
Attribute overwrites the a
-Elements which are children of the p
-Node. Also the order (text -> link -> text) is lost.
How do i properly implement this?
Okay, so i managed to solve my problem using the following code:
using AngleSharp.Dom;
using AngleSharp.Dom.Html;
using AngleSharp.Extensions;
using AngleSharp.Parser.Html;
private void processHTMLNode(INode node, IElement targetElement)
{
IElement elementNode;
IText textNode;
if ((elementNode = node as IElement) != null)
{
switch (node.NodeName.ToLower())
{
//...
case "a":
if(node.HasAttribute("href") && node.GetAttribute("href").StartsWith("#"))
{
break;
}
var aNew = outputDocument.CreateElement("a");
aNew.SetAttribute("href", node.GetAttribute("href"));
foreach (var childNode in elementNode.ChildNodes)
{
processHTMLNode(childNode, aNew);
}
targetElement.AppendChild(aNew);
break;
case "p":
var pNew = outputDocument.CreateElement("p");
foreach (var childNode in node.Children)
{
processHTMLNode(childNode, pNew);
}
targetElement.AppendChild(pNew);
break;
//...
}
}
else if ((textNode = node as IText) != null)
{
var newTextNode = outputDocument.CreateTextNode(textNode.Text);
targetElement.AppendChild(newTextNode);
}
}
This image from the AngleSharp Documentation helped me a lot: AngleSharp DOM
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.