Reputation: 12002
I have a c# code that will read an html file and return it content as string/text.
One thing that I need to do is parse the html string, look for all <embed>
tags, get the value in the "src" attribute then replace the entire <embed>
tag with the content of the file that is found in the src
tag.
I am trying to use the HtmlAgilityPack
to allow me to parse the html code.
The only thing that I am not able to do is how to replace the <embed>
tag with another string and finally return the new string with no <embed>
tag to the user.
Here is what I have done
protected string ParseContent(string content)
{
if (content != null)
{
//Create a new document parser object
HtmlAgilityPack.HtmlDocument document = new HtmlAgilityPack.HtmlDocument();
//load the content
document.LoadHtml(content);
//Get all embed tags
IEnumerable<HtmlNode> embedNodes = document.DocumentNode.Descendants("embed");
//Make sure the content contains at least one <embed> tag
if (embedNodes.Count() > 0)
{
// Outputs the href for external links
foreach (HtmlNode embedNode in embedNodes)
{
//Mak sure there is a source
if (embedNode.Attributes.Contains("src"))
{
//If the file ends with ".html"
if (embedNode.Attributes["src"].Value.EndsWith(".html"))
{
var newContent = GetContent(embedNode.Attributes["src"].Value);
//Here I need to be able to replace the entireembedNode with the newContent
}
}
}
}
return content;
}
return null;
}
protected string GetContent(string path)
{
if (System.IO.File.Exists(path))
{
//The file exists, read its content
return System.IO.File.ReadAllText(path);
}
return null;
}
How can I replace the <embed>
tag with a string?
Upvotes: 1
Views: 2682
Reputation: 13599
I think you can try to get the parent node of the current node which is <embed>
then replace the child node of the parent which is <embed>
var newContent = GetContent(embedNode.Attributes["src"].Value);
var ParentNodeT =embedNode.ParentNode;
var newNodeTtext = "<p>"+newContent+"</p>";
var newNodeT = HtmlNode.CreateNode(newNodeStr);
ParentNodeT.ReplaceChild(newNodeT, embedNode);
Upvotes: 2
Reputation: 12002
I figured it out. Thanks to @COlD TOLD he advised me to convert enumerable to list
Here is what I have done.
protected string ParseContent(string content)
{
if (content != null)
{
//Create a new document parser object
HtmlAgilityPack.HtmlDocument document = new HtmlAgilityPack.HtmlDocument();
//load the content
document.LoadHtml(content);
//Get all embed tags
List<HtmlNode> embedNodes = document.DocumentNode.Descendants("embed").ToList();
//Make sure the content contains at least one <embed> tag
if (embedNodes.Count() > 0)
{
// Outputs the href for external links
foreach (HtmlNode embedNode in embedNodes)
{
//Mak sure there is a source
if (embedNode.Attributes.Contains("src"))
{
if (embedNode.Attributes["src"].Value.EndsWith(".html"))
{
//At this point we know that the source of the embed tag is set and it is an html file
//Get the full path
string embedPath = customBase + embedNode.Attributes["src"].Value;
//Get the
string newContent = GetContent(embedPath);
if (newContent != null)
{
//Create place holder div node
HtmlNode newNode = document.CreateElement("div");
//At this point we know the file exists, load it's content
newNode.InnerHtml = HtmlDocument.HtmlEncode(newContent);
//Here I need to be able to replace the entireembedNode with the newContent
document.DocumentNode.InsertAfter(newNode, embedNode);
//Remove the code after converting it
embedNode.Remove();
}
}
}
}
return document.DocumentNode.OuterHtml;
}
return content;
}
return null;
}
Upvotes: 2