public IEnumerable<Ebookdz_Forum> LoadMainForum(Predicate<string> filter = null, bool reload = false)
{
LoadDataFromWeb_v4 loadDataFromWeb = Load(new RequestFromWeb_v4(new HttpRequest { Url = __urlForum }, reload: reload));
if (loadDataFromWeb.LoadResult)
{
XXElement xeSource = new XXElement(loadDataFromWeb.Http.zGetXDocument().Root);
//HtmlRun.Select("//ol[@id='forums']/li:.:EmptyRow", ".//text()", ".//a//text()", ".//a/@href");
// <ol id="forums" class="floatcontainer">
foreach (XXElement xe in xeSource.XPathElements("//ol[@id='forums']/li"))
{
// Accueil de la Board, Forum de l'entraide, Journaux, MAGAZINES, Les Livres, Sujet supprimés ou à supprimer
// http://www.ebookdz.com/forum/forumdisplay.php?f=1&s=1fdf76d35a57d09aa11e75ff6f0d9985
XXElement xe2 = xe.XPathElement(".//a");
string name = xe2.XPathValue(".//text()");
if (filter != null && !filter(name))
continue;
string url = Ebookdz.GetUrl(zurl.GetUrl(loadDataFromWeb.WebRequest.HttpRequest.Url, xe2.XPathValue("@href")));
//if (url != null)
//{
// PBUriBuilder uriBuilder = new PBUriBuilder(url);
// uriBuilder.RemoveQueryValue("s");
// url = uriBuilder.ToString();
//}
yield return new Ebookdz_Forum { Forum = name, Url = url };
}
}
}
protected override IEnumDataPages<IHeaderData> GetDataPage(WebResult webResult)
{
XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root);
string url = webResult.WebRequest.HttpRequest.Url;
PostHeaderDataPage_v1 data = new PostHeaderDataPage_v1();
data.SourceUrl = url;
data.LoadFromWebDate = webResult.LoadFromWebDate;
data.Id = GetPageKey(webResult.WebRequest.HttpRequest);
data.UrlNextPage = null;
Predicate<string> filter = __forumFilter;
List<EbookdzForumData> forums = new List<EbookdzForumData>();
//HtmlRun.Select("//ol[@id='forums']/li:.:EmptyRow", ".//text()", ".//a//text()", ".//a/@href");
// <ol id="forums" class="floatcontainer">
foreach (XXElement xe in xeSource.XPathElements("//ol[@id='forums']/li"))
{
// Accueil de la Board, Forum de l'entraide, Journaux, MAGAZINES, Les Livres, Sujet supprimés ou à supprimer
// http://www.ebookdz.com/forum/forumdisplay.php?f=1&s=1fdf76d35a57d09aa11e75ff6f0d9985
XXElement xe2 = xe.XPathElement(".//a");
string name = xe2.XPathValue(".//text()");
if (filter != null && !filter(name))
continue;
EbookdzForumData forum = new EbookdzForumData();
forum.SourceUrl = url;
forum.LoadFromWebDate = webResult.LoadFromWebDate;
forum.Name = name;
forum.UrlDetail = GetUrl(zurl.GetUrl(url, xe2.XPathValue("@href")));
forums.Add(forum);
}
data.Headers = forums.ToArray();
return data;
}
public static TelechargementPlus_HeaderPage LoadHeaderFromWeb_GetData(LoadDataFromWeb_v1<TelechargementPlus_HeaderPage> loadDataFromWeb, bool loadImage = false)
{
XXElement xeSource = new XXElement(loadDataFromWeb.GetXmlDocument().Root);
string url = loadDataFromWeb.Url;
TelechargementPlus_HeaderPage data = new TelechargementPlus_HeaderPage();
// post list :
// <div class="base shortstory">
// _hxr.ReadSelect("//div[@class='base shortstory']:.:EmptyRow", ".//text()");
// next page :
// <div class="navigation">
// <div align="center">
// <span>Prev.</span>
// <span>1</span>
// <a href="http://www.telechargement-plus.com/e-book-magazines/page/2/">2</a>
// ...
// <a href="http://www.telechargement-plus.com/e-book-magazines/page/2/">Next</a>
// </div>
// </div>
// _hxr.ReadSelect("//div[@class='navigation']//a[text()='Next']:.:EmptyRow", "text()", "@href");
data.urlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='navigation']//a[text()='Next']/@href"));
IEnumerable<XXElement> xeHeaders = xeSource.XPathElements("//div[@class='base shortstory']");
List<TelechargementPlus_PostHeader> headers = new List<TelechargementPlus_PostHeader>();
foreach (XXElement xeHeader in xeHeaders)
{
TelechargementPlus_PostHeader header = new TelechargementPlus_PostHeader();
//_postHeader.sourceUrl = _sourceUrl;
header.sourceUrl = url;
header.loadFromWebDate = DateTime.Now;
//<h1 class="shd">
// <a href="http://www.telechargement-plus.com/e-book-magazines/magazines/86236-multi-ici-paris-n3562-9-au-15-octobre-2013.html">
// [Multi] Ici Paris N°3562 - 9 au 15 Octobre 2013
// </a>
//</h1>
XXElement xe = xeHeader.XPathElement(".//*[@class='shd']//a");
header.urlDetail = zurl.GetUrl(url, xe.XPathValue("@href"));
//header.title = TelechargementPlus.TrimString(TelechargementPlus.ExtractTextValues(header.infos, xe.XPathValue(".//text()")));
// xe.XPathValue(".//text()", TelechargementPlus.TrimFunc1)
header.title = TelechargementPlus.ExtractTextValues(header.infos, TelechargementPlus.TrimFunc1(xe.XPathValue(".//text()")));
//<div class="shdinf">
// <div class="shdinf">
// <span class="rcol">Auteur:
// <a onclick="ShowProfile('bakafa', 'http://www.telechargement-plus.com/user/bakafa/', '0'); return false;" href="http://www.telechargement-plus.com/user/bakafa/">
// bakafa
// </a>
// </span>
// <span class="date">
// <b><a href="http://www.telechargement-plus.com/2013/10/09/">Aujourd'hui, 17:13</a></b>
// </span>
// <span class="lcol">Catégorie:
// <a href="http://www.telechargement-plus.com/e-book-magazines/">
// E-Book / Magazines
// </a> »
// <a href="http://www.telechargement-plus.com/e-book-magazines/magazines/">
// Magazines
// </a>
// </span>
// </div>
//</div>
xe = xeHeader.XPathElement(".//div[@class='shdinf']/div[@class='shdinf']");
header.postAuthor = xe.XPathValue(".//span[@class='rcol']//a//text()");
//string postDate = xe.XPathValue(".//span[@class='date']//text()");
// Aujourd'hui, 17:13
//if (postDate != null)
// _postHeader.infos.SetValue("postDate", new ZString(postDate));
header.creationDate = TelechargementPlus.ParseDateTime(xe.XPathValue(".//span[@class='date']//text()"));
//header.category = xe.DescendantTextList(".//span[@class='lcol']").Select(TelechargementPlus.TrimFunc1).Where(s => s != "E-Book / Magazines" && s != "Catégorie:" && s != "").zToStringValues("/");
header.category = xe.XPathElements(".//span[@class='lcol']").DescendantTexts().Select(TelechargementPlus.TrimFunc1).Where(s => s != "E-Book / Magazines" && s != "Catégorie:" && s != "").zToStringValues("/");
//Trace.CurrentTrace.WriteLine("post header category \"{0}\"", _postHeader.category);
//.zForEach(s => s.Trim())
//<span id="post-img">
// <div id="news-id-86236" style="display: inline;">
// <div style="text-align: center;">
// <!--dle_image_begin:http://zupimages.net/up/3/1515486591.jpeg|-->
// <img src="http://zupimages.net/up/3/1515486591.jpeg" alt="[Multi] Ici Paris N°3562 - 9 au 15 Octobre 2013"
// title="[Multi] Ici Paris N°3562 - 9 au 15 Octobre 2013" /><!--dle_image_end-->
// <br />
// <b>
// <br />
// Ici Paris N°3562 - 9 au 15 Octobre 2013<br />
// French | 52 pages | HQ PDF | 101 MB
// </b>
// <br />
// <br />
// Ici Paris vous fait partager la vie publique et privée de celles et ceux qui font
// l'actualité : exclusivités, interviews, enquêtes (la face cachée du showbiz, les
// coulisses de la télé) indiscrétions, potins.<br />
// </div>
// </div>
//</span>
xe = xeHeader.XPathElement(".//span[@id='post-img']//div[starts-with(@id, 'news-id')]");
//_postHeader.images = xe.XPathImages(".//img", _url, TelechargementPlus.ImagesToSkip);
//header.images = xe.XPathImages(url, TelechargementPlus.ImagesToSkip);
//header.images = xe.XPathImages(url, imageHtml => !TelechargementPlus.ImagesToSkip.ContainsKey(imageHtml.Source));
//header.images = xe.XPathImages(xeImg => new ImageHtml(xeImg, url), imageHtml => !TelechargementPlus.ImagesToSkip.ContainsKey(imageHtml.Source)).ToList();
header.images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new pb.old.ImageHtml((XElement)xeImg, url)).Where(imageHtml => !TelechargementPlus.ImagesToSkip.ContainsKey(imageHtml.Source)).ToList();
if (loadImage)
pb.old.Http_v2.LoadImageFromWeb(header.images);
//header.SetTextValues(xe.DescendantTextList());
header.SetTextValues(xe.DescendantTexts());
headers.Add(header);
}
data.postHeaders = headers.ToArray();
return data;
}
//private static Ebookdz_HeaderPage GetData(WebResult webResult)
private static IEnumDataPages<IHeaderData> GetData(WebResult webResult)
{
XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root);
string url = webResult.WebRequest.HttpRequest.Url;
Ebookdz_HeaderPage_v2 data = new Ebookdz_HeaderPage_v2();
data.SourceUrl = url;
data.LoadFromWebDate = webResult.LoadFromWebDate;
//data.Id = _GetPageKey(webResult.WebRequest.HttpRequest);
// <div class="threadpagenav">
// <span class="prev_next">
// <a rel="next" href="forumdisplay.php?f=157&page=2&s=fec27f3bac2b58debbb727ab8725c8a4" title="Page suivante - Résultats de 21 à 40 sur 61">
data.UrlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='threadpagenav']//span[@class='prev_next']//a[@rel='next']/@href"));
List<Ebookdz_PostHeader> headers = new List<Ebookdz_PostHeader>();
// <div class="body_bd">
// <div id="threadlist" class="threadlist">
// <ol id="threads" class="threads">
// <li class="threadbit " id="thread_111977">
// <h3 class="threadtitle">
// <a title="" class="title" href="showthread.php?t=111977&s=fec27f3bac2b58debbb727ab8725c8a4" id="thread_title_111977">La Provence Marseille du lundi 26 janvier 2015</a>
foreach (XXElement xeHeader in xeSource.XPathElements("//div[@id='threadlist']//ol[@id='threads']/li"))
{
Ebookdz_PostHeader header = new Ebookdz_PostHeader();
header.SourceUrl = url;
header.LoadFromWebDate = webResult.LoadFromWebDate;
XXElement xe = xeHeader.XPathElement(".//h3[@class='threadtitle']//a[@class='title']");
header.Title = xe.XPathValue(".//text()");
header.UrlDetail = Ebookdz_v1.GetUrl(zurl.GetUrl(url, xe.XPathValue("@href")));
headers.Add(header);
}
data.PostHeaders = headers.ToArray();
//Trace.WriteLine(data.zToJson());
return data;
}
public static IEnumDataPages<PostHeader> GetHeaderPageData(WebResult webResult)
{
XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root);
string url = webResult.WebRequest.HttpRequest.Url;
PostHeaderDataPage<PostHeader> data = new PostHeaderDataPage<PostHeader>();
data.SourceUrl = url;
data.LoadFromWebDate = webResult.LoadFromWebDate;
data.Id = GetPageKey(webResult.WebRequest.HttpRequest);
data.UrlNextPage = null;
// <div id="vba_news4">
IEnumerable<XXElement> xeHeaders = xeSource.XPathElements("//div[@id='vba_news4']//div[@class='collapse']");
List<PostHeader> headers = new List<PostHeader>();
foreach (XXElement xeHeader in xeHeaders)
{
PostHeader header = new PostHeader();
header.SourceUrl = url;
header.LoadFromWebDate = webResult.LoadFromWebDate;
//XXElement xe = xeHeader.XPathElement(".//h2[@class='blockhead']//a[@class!='mcbadge mcbadge_r']");
XXElement xe = xeHeader.XPathElement(".//h2[@class='blockhead']//a[2]");
header.Title = xe.XPathValue(".//text()");
header.UrlDetail = xe.XPathValue("./@href");
//header.images = xeHeader.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//XXElement xe = xeHeader.XPathElement(".//*[@class='shd']//a");
//header.urlDetail = zurl.GetUrl(url, xe.XPathValue("@href"));
//header.title = RapideDdl.ExtractTextValues(header.infos, xe.XPathValue(".//text()", RapideDdl.TrimFunc1));
//xe = xeHeader.XPathElement(".//div[@class='shdinfo']");
//header.postAuthor = xe.XPathValue(".//span[@class='arg']//a//text()");
//// Aujourd'hui, 17:13
//header.creationDate = RapideDdl.ParseDateTime(xe.XPathValue(".//span[@class='date']//text()"), loadDataFromWeb.loadFromWebDate);
//xe = xeHeader.XPathElement(".//div[@class='maincont']");
//header.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//RapideDdl.SetTextValues(header, xe.DescendantTextList());
//xe = xeHeader.XPathElement(".//div[@class='morelink']//span[@class='arg']");
//header.category = xe.DescendantTextList(".//a").Select(RapideDdl.TrimFunc1).Where(s => !s.StartsWith("Commentaires")).zToStringValues("/");
//pb.Trace.WriteLine(header.Title);
headers.Add(header);
}
data.Headers = headers.ToArray();
return data;
}
public static IKeyData<int> GetForumHeaderPageData(LoadDataFromWeb_v4 loadDataFromWeb)
{
XXElement xeSource = new XXElement(loadDataFromWeb.Http.zGetXDocument().Root);
string url = loadDataFromWeb.WebRequest.HttpRequest.Url;
Ebookdz_HeaderPage data = new Ebookdz_HeaderPage();
data.SourceUrl = url;
data.LoadFromWebDate = loadDataFromWeb.LoadFromWebDate;
//data.Id = Ebookdz_LoadHeaderPagesManager.GetHeaderPageKey(loadDataFromWeb.WebRequest.HttpRequest);
// <div id="above_threadlist" class="above_threadlist">
// <div class="threadpagenav">
// <span class="prev_next">
// <a rel="next" href="forumdisplay.php?f=74&page=2&s=4807e931448c05da34dd54fbd0308479" title="Page suivante - Résultats de 21 à 40 sur 66">
data.UrlNextPage = GetUrl(zurl.GetUrl(url, xeSource.XPathValue("//div[@id='above_threadlist']//span[@class='prev_next']//a[@rel='next']/@href")));
// <div class="body_bd">
XXElement xePost = xeSource.XPathElement("//div[@class='body_bd']");
// <div id="breadcrumb" class="breadcrumb">
// <ul class="floatcontainer">
// <li class="navbit">
// Forum / Journaux / Presse quotidienne / Autres Journaux
// <div id="threadlist" class="threadlist">
// <ol id="threads" class="threads">
IEnumerable<XXElement> xeHeaders = xeSource.XPathElements("//div[@id='threadlist']//ol[@id='threads']/li");
List<Ebookdz_PostHeader> headers = new List<Ebookdz_PostHeader>();
foreach (XXElement xeHeader in xeHeaders)
{
Ebookdz_PostHeader header = new Ebookdz_PostHeader();
header.SourceUrl = url;
header.LoadFromWebDate = loadDataFromWeb.LoadFromWebDate;
// <div class="threadinfo" title="">
// <div class="inner">
// <a title="" class="title" href="showthread.php?t=111210&s=4807e931448c05da34dd54fbd0308479" id="thread_title_111210">L'OPINION du mardi 20 janvier 2015</a>
XXElement xe = xeHeader.XPathElement(".//div[@class='threadinfo']//a[@class='title']");
header.Title = xe.XPathValue(".//text()");
header.UrlDetail = GetUrl(zurl.GetUrl(loadDataFromWeb.WebRequest.HttpRequest.Url, xe.XPathValue("@href")));
//header.images = xeHeader.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//XXElement xe = xeHeader.XPathElement(".//*[@class='shd']//a");
//header.urlDetail = zurl.GetUrl(url, xe.XPathValue("@href"));
//header.title = RapideDdl.ExtractTextValues(header.infos, xe.XPathValue(".//text()", RapideDdl.TrimFunc1));
//xe = xeHeader.XPathElement(".//div[@class='shdinfo']");
//header.postAuthor = xe.XPathValue(".//span[@class='arg']//a//text()");
//// Aujourd'hui, 17:13
//header.creationDate = RapideDdl.ParseDateTime(xe.XPathValue(".//span[@class='date']//text()"), loadDataFromWeb.loadFromWebDate);
//xe = xeHeader.XPathElement(".//div[@class='maincont']");
//header.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//RapideDdl.SetTextValues(header, xe.DescendantTextList());
//xe = xeHeader.XPathElement(".//div[@class='morelink']//span[@class='arg']");
//header.category = xe.DescendantTextList(".//a").Select(RapideDdl.TrimFunc1).Where(s => !s.StartsWith("Commentaires")).zToStringValues("/");
headers.Add(header);
}
data.PostHeaders = headers.ToArray();
//return (IEnumDataPages_new2<int, IHeaderData_new>)data;
return (IKeyData<int>)data;
}
private static IEnumDataPages<IHeaderData> GetHeaderPageData(WebResult webResult)
{
XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root);
string url = webResult.WebRequest.HttpRequest.Url;
Vosbooks_HeaderPage_v2 data = new Vosbooks_HeaderPage_v2();
data.SourceUrl = url;
data.LoadFromWebDate = webResult.LoadFromWebDate;
data.Id = GetPageKey(webResult.WebRequest.HttpRequest);
// <div id="page">
// <div id="wrapper">
// <table id="layout">
// <tr>
// <td></td>
// <td>
// <div id="left-col">
// <div id="content-padding">
// <div id="content">
// <div style="height:264px;" class="cover_global" data-zt="divbyzt">...</div>
// ...
// </div>
data.UrlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='page-nav']//li[last()]//a[text()='>']/@href"));
IEnumerable<XXElement> xeHeaders = xeSource.XPathElements("//table[@id='layout']//div[@id='content']/div");
List<Vosbooks_PostHeader_v1> headers = new List<Vosbooks_PostHeader_v1>();
foreach (XXElement xeHeader in xeHeaders)
{
Vosbooks_PostHeader_v1 header = new Vosbooks_PostHeader_v1();
header.SourceUrl = url;
header.LoadFromWebDate = webResult.LoadFromWebDate;
if (xeHeader.XPathValue("@class") == "page-nav")
continue;
// <div style="" data-zt="divbyzt">
// <div data-zt="divbyzt">
// <div data-zt="divbyzt">
// <center>
// <strong>
// <a href="http://www.vosbooks.net/74231-journaux/pack-journaux-francais-du-28-janvier-2015.html" title="">
// Pack Journaux Français Du 28 Janvier 2015
// <span class="detail_release" data-zt="spanbyzt"></span>
// </a>
// </strong>
// </center>
// </div>
// </div>
// </div>
XXElement xe = xeHeader.XPathElement(".//div/div/div//a");
header.Title = xe.XPathValue(".//text()");
header.UrlDetail = xe.XPathValue("./@href");
//header.images = xeHeader.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//XXElement xe = xeHeader.XPathElement(".//*[@class='shd']//a");
//header.urlDetail = zurl.GetUrl(url, xe.XPathValue("@href"));
//header.title = RapideDdl.ExtractTextValues(header.infos, xe.XPathValue(".//text()", RapideDdl.TrimFunc1));
//xe = xeHeader.XPathElement(".//div[@class='shdinfo']");
//header.postAuthor = xe.XPathValue(".//span[@class='arg']//a//text()");
//// Aujourd'hui, 17:13
//header.creationDate = RapideDdl.ParseDateTime(xe.XPathValue(".//span[@class='date']//text()"), loadDataFromWeb.loadFromWebDate);
//xe = xeHeader.XPathElement(".//div[@class='maincont']");
//header.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToList();
//RapideDdl.SetTextValues(header, xe.DescendantTextList());
//xe = xeHeader.XPathElement(".//div[@class='morelink']//span[@class='arg']");
//header.category = xe.DescendantTextList(".//a").Select(RapideDdl.TrimFunc1).Where(s => !s.StartsWith("Commentaires")).zToStringValues("/");
headers.Add(header);
}
data.PostHeaders = headers.ToArray();
return data;
}
public IEnumerable<Ebookdz_Forum> LoadSubForum(string url, string forum, Predicate<string> filter = null, bool reload = false)
{
LoadDataFromWeb_v4 loadDataFromWeb = Load(new RequestFromWeb_v4(new HttpRequest { Url = url }, reload: reload));
if (loadDataFromWeb.LoadResult)
{
XXElement xeSource = new XXElement(loadDataFromWeb.Http.zGetXDocument().Root);
// <div class="body_bd">
// <div id="forumbits" class="forumbits">
// <ol>
// <li id="forum10" class="forumbit_post new L1">
// <div class="forumrow">
// <ol id="childforum_for_161" class="childsubforum">
// <div class="titleline">
foreach (XXElement xe in xeSource.XPathElements("//div[@id='forumbits']/ol/li"))
{
XXElement xe2 = xe.XPathElement(".//div[@class='forumrow']//a");
string category = xe2.XPathValue(".//text()");
url = Ebookdz.GetUrl(zurl.GetUrl(loadDataFromWeb.WebRequest.HttpRequest.Url, xe2.XPathValue("@href")));
yield return new Ebookdz_Forum { Forum = forum, Category = category, Url = url };
foreach (XXElement xe3 in xe.XPathElements(".//ol[@class='childsubforum']/li//div[@class='titleline']//a"))
{
string name = xe3.XPathValue(".//text()");
if (filter != null && !filter(name))
continue;
url = Ebookdz.GetUrl(zurl.GetUrl(loadDataFromWeb.WebRequest.HttpRequest.Url, xe3.XPathValue("@href")));
yield return new Ebookdz_Forum { Forum = forum, Category = category, Name = name, Url = url };
}
}
}
}