Can HtmlAgilityPack process the xml file that comes with the xsl file for html rendering?

I was wondering how the HtmlAgilityPack is best to read the xml file containing the xsl file for html rendering. Are there any settings in the HtmlDocument class that will help with this, or do I need to find a way to perform the conversion before loading it with HtmlAgiliyPack? If so for the latter, does anyone know a good library or method for such a conversion? Below is an example of a website that returns xml with an xls file and code that I would like to use.

var uri = new Uri("http://www.skechers.com/");
var request = (HttpWebRequest)WebRequest.Create(url);
var cookieContainer = new CookieContainer();

request.CookieContainer = cookieContainer;
request.UserAgent = @"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.5) Gecko/20091102 Firefox/3.5.5";
request.Method = "GET";
request.AllowAutoRedirect = true;
request.Timeout = 15000;

var response = (HttpWebResponse)request.GetResponse();
var page = new HtmlDocument();
page.OptionReadEncoding = false;
var stream = response.GetResponseStream();
page.Load(stream); 

This code does not cause any errors, but XML is what gets the parsing, not the conversion I want.

+5
3

Html Agility Pack :

1) Xml, PI Html,

2) HtmlDocument IXPathNavigable, .NET Xslt.

, . XmlResover Xslt, , .

public static void DownloadAndProcessXml(string url, string userAgent, string outputFilePath)
{
    using (XmlTextWriter writer = new XmlTextWriter(outputFilePath, Encoding.UTF8))
    {
        DownloadAndProcessXml(url, userAgent, writer);
    }
}

public static void DownloadAndProcessXml(string url, string userAgent, XmlWriter output)
{
    UserAgentXmlUrlResolver resolver = new UserAgentXmlUrlResolver(url, userAgent);

    // WebClient is an easy to use class.
    using (WebClient client = new WebClient())
    {
        // download Xml doc. set User-Agent header or the site won't answer us...
        client.Headers[HttpRequestHeader.UserAgent] = resolver.UserAgent;
        HtmlDocument xmlDoc = new HtmlDocument();
        xmlDoc.Load(client.OpenRead(url));

        // determine xslt (note the xpath trick as Html Agility Pack does not support xml processing instructions)
        string xsltUrl = xmlDoc.DocumentNode.SelectSingleNode("//*[name()='?xml-stylesheet']").GetAttributeValue("href", null);

        // download Xslt doc
        client.Headers[HttpRequestHeader.UserAgent] = resolver.UserAgent;
        XslCompiledTransform xslt = new XslCompiledTransform();
        xslt.Load(new XmlTextReader(client.OpenRead(url + xsltUrl)), new XsltSettings(true, false), null);

        // transform Html/Xml doc into new Xml doc, easy as HtmlDocument implements IXPathNavigable
        // note the use of a custom resolver to overcome this Xslt resolve requests
        xslt.Transform(xmlDoc, null, output, resolver);
    }
}

// This class is needed during transformation otherwise there are errors.
// This is probably due to this very specific Xslt file that needs to go back to the root document itself.
public class UserAgentXmlUrlResolver : XmlUrlResolver
{
    public UserAgentXmlUrlResolver(string rootUrl, string userAgent)
    {
        RootUrl = rootUrl;
        UserAgent = userAgent;
    }

    public string RootUrl { get; set; }
    public string UserAgent { get; set; }

    public override object GetEntity(Uri absoluteUri, string role, Type ofObjectToReturn)
    {
        WebClient client = new WebClient();
        if (!string.IsNullOrEmpty(UserAgent))
        {
            client.Headers[HttpRequestHeader.UserAgent] = UserAgent;
        }
        return client.OpenRead(absoluteUri);
    }

    public override Uri ResolveUri(Uri baseUri, string relativeUri)
    {
        if ((relativeUri == "/") && (!string.IsNullOrEmpty(RootUrl)))
            return new Uri(RootUrl);

        return base.ResolveUri(baseUri, relativeUri);
    }
}

:

    string url = "http://www.skechers.com/";
    string ua = @"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.5) Gecko/20091102 Firefox/3.5.5";
    DownloadAndProcessXml(url, ua, "skechers.html");
+3

XML XSLT. XML, . XML XSL. XSL XML-.

+2

, , . , , "application/xml", . , FormAssetSrc , href , , , uri.

var xmlStream = response.GetResponseStream();
var xmlDocument = new XPathDocument(xmlStream);
var styleNode = xmlDocument.CreateNavigator().SelectSingleNode("processing-instruction('xml-stylesheet')");
var hrefValue = Regex.Match((styleNode).Value, "href=(\"|')(?<url>.*?)(\"|')");
if(hrefValue.Success)
{
    var xslHref = FormAssetSrc(hrefValue.Groups["url"].Value, response.ResponseUri);
    var xslUri = new Uri(xslHref);
    var xslRequest = CreateWebRequest(xslUri);
    var xslResponse = (HttpWebResponse)xslRequest.GetResponse();
    var xslStream = new XPathDocument(xslResponse.GetResponseStream());
    var xslTransorm = new XslTransform();
    var sw = new System.IO.StringWriter();
    xslTransorm.Load(xslStream);
    xslTransorm.Transform(xmlDocument.CreateNavigator(), null, sw);
    page.Html.LoadHtml(sw.ToString());
}
0

All Articles