/// <summary>
/// Document parser.
/// </summary>
/// <param name="content">The document to parse.</param>
/// <returns>The parsed document.</returns>
public static XHtmlDocument Parse(string content)
{
var strContent = content.Trim(new[] { ' ', '\uFEFF', '\r', '\n' });
if (content.Length == 0)
{
return(new XHtmlDocument(new XDocument()));
}
XDocument doc = XDocument.Parse(strContent);
XHtmlDocument htmDoc = new XHtmlDocument(doc);
if (doc.Root != null)
{
XNamespace ns = "http://www.w3.org/1999/xhtml";
htmDoc.Images = (from img in doc.Root.Descendants(ns + "img")
let xAttribute = img.Attribute("src")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
htmDoc.Links = (from linc in doc.Root.Descendants(ns + "link")
let xAttribute = linc.Attribute("href")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
htmDoc.Scripts = (from script in doc.Root.Descendants(ns + "script")
let xAttribute = script.Attribute("src")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
}
return(htmDoc);
}
/// <summary>
/// Create download list for contents of HTML document
/// </summary>
/// <param name="origdir">Original path</param>
/// <param name="document">The document</param>
private static void MakeDownloadList(string origdir, XHtmlDocument document)
{
foreach (var script in document.Scripts)
{
PriorityRecord pr = new PriorityRecord(PriorityLevel.HighPriority, string.Format("{0}/{1}", origdir.ToLower(), script.ToLower()));
currentStreams.Add(pr);
}
foreach (var link in document.Links)
{
PriorityRecord pr = new PriorityRecord(PriorityLevel.MediumPriority, string.Format("{0}/{1}", origdir.ToLower(), link.ToLower()));
currentStreams.Add(pr);
}
foreach (var image in document.Images)
{
PriorityRecord pr = new PriorityRecord(PriorityLevel.LowPriority, string.Format("{0}/{1}", origdir.ToLower(), image.ToLower()));
currentStreams.Add(pr);
}
// sort by priority, name
currentStreams.SortByPriority();
}
/// <summary>
/// Document parser.
/// </summary>
/// <param name="content">The document to parse.</param>
/// <returns>The parsed document.</returns>
public static XHtmlDocument Parse(string content)
{
XDocument doc = XDocument.Parse(content.Trim(new[] { ' ', '\uFEFF', '\r', '\n' }));
XHtmlDocument htmDoc = new XHtmlDocument(doc);
if (doc.Root != null)
{
XNamespace ns = "http://www.w3.org/1999/xhtml";
htmDoc.Images = (from img in doc.Root.Descendants(ns + "img")
let xAttribute = img.Attribute("src")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
htmDoc.Links = (from linc in doc.Root.Descendants(ns + "link")
let xAttribute = linc.Attribute("href")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
htmDoc.Scripts = (from script in doc.Root.Descendants(ns + "script")
let xAttribute = script.Attribute("src")
where xAttribute != null
select xAttribute.Value).Distinct().ToArray();
}
return htmDoc;
}
