private IEnumerator <ZoneEbooks_PostHeader> Load(string url, bool reload, bool loadImage)
{
if (url != null)
{
_headerPage = ZoneEbooks_LoadHeader.Load(url, _requestParameters, reload, loadImage);
if (_headerPage != null)
{
return(_headerPage.postHeaders.AsEnumerable <ZoneEbooks_PostHeader>().GetEnumerator());
}
}
return(null);
}
public static ZoneEbooks_HeaderPage LoadHeaderPageFromWeb(pb.Web.v1.RequestFromWeb_v2 request)
{
XXElement xeSource = new XXElement(request.GetXmlDocument().Root);
//string url = request.Url;
ZoneEbooks_HeaderPage data = new ZoneEbooks_HeaderPage();
// post list :
// <div id="post-1838" class="post-1838 post type-post status-publish format-standard hentry category-journaux tag-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-ebook tag-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-ebook-gratuit tag-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-gratuit tag-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-pdf tag-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-telechargement tag-telecharge-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-ddl tag-telecharge-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-uptobox tag-telechargement-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre tag-telecharger-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre tag-telecharger-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-ebook tag-telecharger-le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-pdf clear-block count-1 odd author-admin first">
// _hxr.ReadSelect("//div[starts-with(@id, 'post-')]:.:EmptyRow");
// next page :
// <a href='http://zone-ebooks.com/page/2' class='nextpostslink'>»</a>
// _hxr.ReadSelect("//a[@class='nextpostslink']:.:EmptyRow", "./@href");
data.urlNextPage = zurl.GetUrl(request.Url, xeSource.XPathValue("//a[@class='nextpostslink']/@href"));
Trace.WriteLine("urlNextPage \"{0}\"", data.urlNextPage);
IEnumerable <XXElement> xeHeaders = xeSource.XPathElements("//div[starts-with(@id, 'post-')]");
List <ZoneEbooks_PostHeader> headers = new List <ZoneEbooks_PostHeader>();
foreach (XXElement xeHeader in xeHeaders)
{
ZoneEbooks_PostHeader header = new ZoneEbooks_PostHeader();
header.sourceUrl = request.Url;
header.loadFromWebDate = DateTime.Now;
//<h2 class="title">
// <a href="http://zone-ebooks.com/journaux/le-parisien-journal-de-paris-supp-economie-du-lundi-07-octobre-pdf.html"
// rel="bookmark" title="Lien permanent: Le Parisien + Journal de Paris & supp Economie du lundi 07 octobre">
// Le Parisien + Journal de Paris & supp Economie du lundi 07 octobre</a>
//</h2>
XXElement xe = xeHeader.XPathElement(".//*[@class='title']//a");
header.urlDetail = xe.XPathValue("@href");
header.title = xe.XPathValue(".//text()");
//<div class="post-date">
// <span class="ext">Il y a 2 heures</span>
//</div>
string postDate = xeHeader.XPathValue(".//div[@class='post-date']//text()");
//WriteLine("post date \"{0}\"", postDate);
//Il y a 57 secondes
//Il y a 3 minutes
//Il y a 1 heure
//Il y a 1 jour
//Il y a 2 semaines
//Il y a 2 mois
if (postDate != null)
{
header.infos.Add("postDate", new ZString(postDate));
}
//<div class="post-info">
// <span class="a">par
// <a href="http://zone-ebooks.com/author/admin" title="Articles par admin ">
// admin
// </a>
// </span>
// dans
// <a href="http://zone-ebooks.com/category/journaux" rel="tag" title="Journaux (158 sujets)">Journaux</a>
//</div>
xe = xeHeader.XPathElement(".//div[@class='post-info']");
header.author = xe.XPathValue(".//a//text()");
header.category = xe.XPathValue("./a//text()");
//<div class="post-content clear-block">
xe = xeHeader.XPathElement(".//div[starts-with(@class, 'post-content')]");
//<img title="Le Parisien + Journal de Paris & supp Economie du lundi 07 octobre PDF"
// alt="Le Parisien + Journal de Paris & supp Economie du lundi 07 octobre PDF"
// src="http://i.imgur.com/f7aWDHF.jpg" width="362" height="446" />
//header.images = xe.XPathImages(request.Url, __imagesToSkip);
//header.images = xe.XPathImages(request.Url, imageHtml => !__imagesToSkip.ContainsKey(imageHtml.Source));
//header.images = xe.XPathImages(xeImg => new ImageHtml(xeImg, request.Url), imageHtml => !__imagesToSkip.ContainsKey(imageHtml.Source)).ToList();
//header.images = xe.XPathImages(xeImg => new ImageHtml(xeImg, request.Url), imageHtml => !__imagesToSkip.ContainsKey(imageHtml.Source)).ToList();
header.images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new pb.old.ImageHtml((XElement)xeImg, request.Url)).Where(imageHtml => !__imagesToSkip.ContainsKey(imageHtml.Source)).ToList();
if (request.LoadImage)
{
pb.old.Http_v2.LoadImageFromWeb(header.images);
}
// image "infos sur le livre" http://i.imgur.com/GTPfRoB.png
// image "description" http://i.imgur.com/Ruuh4CP.png
//**********************************************************************************************************************************************************************************
// pb image "infos sur le livre"
// zone-ebooks.com_img_info_livre_02_02.html
// zone-ebooks.com_img_info_livre_02_02.xml
// <div style="text-align: center;">
// image ok
// <img title="Florence Bellot, "Tresses et bracelets bresiliens"" alt="Florence Bellot, Tresses et bracelets bresiliens PDF" src="http://i.imgur.com/RHWAvUQ.jpg" />
// <p>
// image "infos sur le livre"
// <img title="Florence Bellot, "Tresses et bracelets bresiliens"" alt="Florence Bellot, Tresses et bracelets bresiliens PDF" src="http://i.imgur.com/GTPfRoB.png" />
// </p>
// ...
// <p>
// image "description"
// <img title="Florence Bellot, "Tresses et bracelets bresiliens"" alt="Florence Bellot, Tresses et bracelets bresiliens PDF" src="http://i.imgur.com/Ruuh4CP.png" />
// </p>
//**********************************************************************************************************************************************************************************
headers.Add(header);
}
data.postHeaders = headers.ToArray();
return(data);
}
