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);
using (WebClient client = new WebClient())
{
client.Headers[HttpRequestHeader.UserAgent] = resolver.UserAgent;
HtmlDocument xmlDoc = new HtmlDocument();
xmlDoc.Load(client.OpenRead(url));
string xsltUrl = xmlDoc.DocumentNode.SelectSingleNode("//*[name()='?xml-stylesheet']").GetAttributeValue("href", null);
client.Headers[HttpRequestHeader.UserAgent] = resolver.UserAgent;
XslCompiledTransform xslt = new XslCompiledTransform();
xslt.Load(new XmlTextReader(client.OpenRead(url + xsltUrl)), new XsltSettings(true, false), null);
xslt.Transform(xmlDoc, null, output, resolver);
}
}
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");