private static Ebookdz_ForumPage_v1 GetData(WebResult webResult) { XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root); string url = webResult.WebRequest.HttpRequest.Url; Ebookdz_ForumPage_v1 data = new Ebookdz_ForumPage_v1(); data.SourceUrl = url; data.LoadFromWebDate = webResult.LoadFromWebDate; //data.Id = _GetPageKey(webResult.WebRequest.HttpRequest); //data.UrlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='basenavi']//span[@class='nnext']//a/@href")); data.UrlNextPage = null; List <Ebookdz_Forum_v1> forums = new List <Ebookdz_Forum_v1>(); Predicate <string> filter = null; // <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()"); string urlCategory = Ebookdz_v1.GetUrl(zurl.GetUrl(url, xe2.XPathValue("@href"))); // Forum = forum //forums.Add(new Ebookdz_Forum { Category = category, Url = urlCategory }); 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; } string urlSubForum = Ebookdz_v1.GetUrl(zurl.GetUrl(url, xe3.XPathValue("@href"))); // Forum = forum forums.Add(new Ebookdz_Forum_v1 { SourceUrl = url, LoadFromWebDate = webResult.LoadFromWebDate, Category = category, Name = name, Url = urlSubForum }); } } data.Forums = forums.ToArray(); return(data); }
private static Ebookdz_ForumPage_v1 GetData(WebResult webResult) { XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root); string url = webResult.WebRequest.HttpRequest.Url; Ebookdz_ForumPage_v1 data = new Ebookdz_ForumPage_v1(); data.SourceUrl = url; data.LoadFromWebDate = webResult.LoadFromWebDate; data.Id = _GetPageKey(webResult.WebRequest.HttpRequest); //data.UrlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='basenavi']//span[@class='nnext']//a/@href")); data.UrlNextPage = null; Predicate <string> filter = __forumFilter; List <Ebookdz_Forum_v1> forums = new List <Ebookdz_Forum_v1>(); //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; } Ebookdz_Forum_v1 forum = new Ebookdz_Forum_v1(); forum.SourceUrl = url; forum.LoadFromWebDate = webResult.LoadFromWebDate; forum.Name = name; forum.Url = Ebookdz_v1.GetUrl(zurl.GetUrl(url, xe2.XPathValue("@href"))); forums.Add(forum); } data.Forums = forums.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); }
private static Ebookdz_HeaderPage_v1 GetData(WebResult webResult) { XXElement xeSource = new XXElement(webResult.Http.zGetXDocument().Root); string url = webResult.WebRequest.HttpRequest.Url; Ebookdz_HeaderPage_v1 data = new Ebookdz_HeaderPage_v1(); 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"))); //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(); //Trace.WriteLine(data.zToJson()); return(data); }