Question

I have some code using HTML Agility Pack. What i am trying to do is, replace all links in html contents.

For example: I will replace

http://oldserver/Documents/1.pdf 

to

http://newserver/Documents/2.pdf

I can enumerate all links and can get their values but when i do doc.Save() it saves the original html source. Not the updated html. How can i get the updated html from HtmlDocument.

private string FixHyperlinks(string contentHtml, SPWeb web)
    {
        TextReader reader = new StringReader(contentHtml);

        HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
        doc.Load(reader);

        List<string> hrefTags = new List<string>();

        foreach (HtmlNode link in doc.DocumentNode.SelectNodes("//a[@href]"))
        {
            HtmlAttribute att = link.Attributes["href"];
            att.Value = RepairHyperlinkAddress(att.Value, web);
        }

        MemoryStream memoryStream = new MemoryStream();
        doc.Save(memoryStream);
        memoryStream.Seek(0, System.IO.SeekOrigin.Begin);
        StreamReader streamReader = new StreamReader(memoryStream);
        string result = streamReader.ReadToEnd();

        return result;
    }

Answer 1

This should work better:

foreach (HtmlNode link in doc.DocumentNode.SelectNodes("//a[@href]"))
        {
            HtmlAttribute att = link.Attributes["href"];
            att.Value = RepairHyperlinkAddress(att.Value, web);
        }

foreach (HtmlNode link in doc.DocumentNode.SelectNodes("//img[@src]"))
        {
            HtmlAttribute att = link.Attributes["src"];
            att.Value = RepairHyperlinkAddress(att.Value, web);
        }