private static void MyFunction(HtmlDocument doc, Uri docUri, out List <string> foundItems, out List <Uri> newUris)
{
foundItems = new List <string>();
newUris = new List <Uri>();
IEnumerable <HtmlNode> nodes = doc.DocumentNode.Descendants();// SelectNodes("//link[(@type='application/rss+xml' or @type='application/atom+xml') and @rel='alternate']");
if (nodes != null)
{
foreach (var node in nodes)
{
if (node.HasAttributes)
{
var href = node.Attributes["href"];
var type = node.Attributes["type"];
var rel = node.Attributes["rel"];
if (href != null && type != null &&
rel != null && IsRss(type, rel))
{
try
{
Uri rssUri = new Uri(docUri, href.Value);
foundItems.Add(rssUri.ToString());
}
catch
{
}
}
}
}
}
foreach (Uri link in s_extractor.ExtractLinks(docUri, doc))
{
newUris.Add(link);
}
}
private void ProcessPageForImageLinks(PageData obPageData, Int32 iLevel, Int32 iStopLevel, bool bFlatHierarchy)
{
LinkDataCollection obLinks = new LinkDataCollection();
LinkExtractor obLinkExtractor = new LinkExtractor(obPageData.Url, iLevel);
do
{
LinkStatus status = obLinkExtractor.ExtractLinks();
LinkDataCollection tempColl = obLinkExtractor.Links;
ICollectionSupport.AddAll(obPageData.m_Outlinks, tempColl);
if (iLevel >= iStopLevel)
{
break;
}
iLevel++;
tempColl = new LinkDataCollection();
foreach (LinkData obLinkData in obPageData.m_Outlinks)
{
if (obLinkData.LinkType == LinkType.Outlink)
{
PageData obPage = new PageData();
obPage.m_strUrl = obLinkData.Url;
ProcessPageForLinks(obPage, iLevel, iStopLevel, bFlatHierarchy);
if (bFlatHierarchy)
{
ICollectionSupport.AddAll(tempColl, obPage.OutLinks);
}
}
}
if (bFlatHierarchy)
{
ICollectionSupport.AddAll(obPageData.m_Outlinks, tempColl);
}
}while(true);
}
