Esempio n. 1
0
 public static void Test_01(string file)
 {
     file = zPath.Combine(GetDirectory(), file);
     foreach (BsonDocument doc in zMongo.BsonRead <BsonDocument>(file))
     {
         PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(doc.zGet("Texts").zAsBsonArray().zAsStrings(), doc.zGet("Title").zAsString());
         Trace.WriteLine("Texts :");
         Trace.WriteLine(doc.zGet("Texts").zToJson());
         Trace.WriteLine("PrintTextValues :");
         Trace.WriteLine(textValues.zToJson());
         Trace.WriteLine();
     }
 }
Esempio n. 2
0
        protected override RapideDdl_HeaderPage GetDataFromWeb(LoadDataFromWeb_v3 loadDataFromWeb)
        {
            XXElement            xeSource = new XXElement(loadDataFromWeb.GetXmlDocument().Root);
            string               url      = loadDataFromWeb.request.Url;
            RapideDdl_HeaderPage data     = new RapideDdl_HeaderPage();

            data.sourceUrl       = url;
            data.loadFromWebDate = loadDataFromWeb.loadFromWebDate;
            data.id = RapideDdl_LoadHeaderPagesManager.GetHeaderPageKey(url);

            data.urlNextPage = zurl.GetUrl(url, xeSource.XPathValue("//div[@class='basenavi']//span[@class='nnext']//a/@href"));
            IEnumerable <XXElement>     xeHeaders = xeSource.XPathElements("//div[@class='base shortstory']");
            List <RapideDdl_PostHeader> headers   = new List <RapideDdl_PostHeader>();

            foreach (XXElement xeHeader in xeHeaders)
            {
                RapideDdl_PostHeader header = new RapideDdl_PostHeader();
                header.sourceUrl       = url;
                header.loadFromWebDate = loadDataFromWeb.loadFromWebDate;

                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));
                //header.title = xe.XPathValue(".//text()", DownloadPrint.Trim);
                header.title = xe.XPathValue(".//text()").Trim(DownloadPrint.TrimChars);
                PrintTitleInfos titleInfos = DownloadPrint.PrintTextValuesManager.ExtractTitleInfos(header.title);
                if (titleInfos.foundInfo)
                {
                    //header.originalTitle = header.title;
                    header.title = titleInfos.title;
                    header.infos.SetValues(titleInfos.infos);
                }

                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);
                string date = xe.XPathValue(".//span[@class='date']//text()");
                header.creationDate = zdate.ParseDateTimeLikeToday(date, loadDataFromWeb.loadFromWebDate, "d-M-yyyy, HH:mm", "d M yyyy", "d MMMM yyyy");
                if (header.creationDate == null)
                {
                    pb.Trace.WriteLine("unknow date time \"{0}\"", date);
                }
                if (__trace)
                {
                    pb.Trace.WriteLine("creationDate {0} - \"{1}\"", header.creationDate, date);
                }

                xe = xeHeader.XPathElement(".//div[@class='maincont']");
                //header.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToArray();
                header.images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new WebImage(zurl.GetUrl(url, xeImg.zAttribValue("src")))).ToArray();

                //if (request.LoadImage)
                //    Http2.LoadImageFromWeb(header.images);

                //RapideDdl.SetTextValues(header, xe.DescendantTextList());
                // get infos, description, language, size, nbPages
                // xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a")
                PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(xe.DescendantTexts(node => !(node is XElement) || ((XElement)node).Name != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode), header.title);
                header.description = textValues.description;
                header.language    = textValues.language;
                header.size        = textValues.size;
                header.nbPages     = textValues.nbPages;
                header.infos.SetValues(textValues.infos);

                xe = xeHeader.XPathElement(".//div[@class='morelink']//span[@class='arg']");
                //header.category = xe.DescendantTextList(".//a").Select(DownloadPrint.TrimFunc1).Where(s => !s.StartsWith("Commentaires")).zToStringValues("/");
                header.category = xe.XPathElements(".//a").DescendantTexts().Select(DownloadPrint.Trim).Where(s => !s.StartsWith("Commentaires")).zToStringValues("/");

                headers.Add(header);
            }
            data.postHeaders = headers.ToArray();
            return(data);
        }
Esempio n. 3
0
        protected override IPost GetData(LoadDataFromWeb_v4 loadDataFromWeb)
        {
            XXElement          xeSource = new XXElement(loadDataFromWeb.Http.zGetXDocument().Root);
            Ebookdz_PostDetail data     = new Ebookdz_PostDetail();

            data.SourceUrl       = loadDataFromWeb.WebRequest.HttpRequest.Url;
            data.LoadFromWebDate = loadDataFromWeb.LoadFromWebDate;
            data.Id = GetPostDetailKey(loadDataFromWeb.WebRequest.HttpRequest);

            // <div class="body_bd">
            XXElement xePost = xeSource.XPathElement("//div[@class='body_bd']");

            // Le Monde + Magazine + 2 suppléments du samedi 03 janvier 2015
            //data.Title = xePost.XPathValue(".//div[@id='pagetitle']//a//text()", DownloadPrint.Trim);
            data.Title = xePost.XPathValue(".//div[@id='pagetitle']//a//text()").Trim(DownloadPrint.TrimChars);
            PrintTitleInfos titleInfos = DownloadPrint.PrintTextValuesManager.ExtractTitleInfos(data.Title);

            if (titleInfos.foundInfo)
            {
                data.OriginalTitle = data.Title;
                data.Title         = titleInfos.title;
                data.Infos.SetValues(titleInfos.infos);
            }

            // Forum / Journaux / Presse quotidienne / Le Monde / Journal Le Monde + Magazine + 2 suppléments du samedi 03 janvier 2015
            string lowerTitle = null;

            if (data.Title != null)
            {
                lowerTitle = data.Title.ToLowerInvariant();
            }
            //data.Category = xePost.DescendantTextList(".//div[@id='breadcrumb']//a").Where(text => { text = text.ToLowerInvariant(); return text != "forum" && !text.EndsWith(lowerTitle); }).Select(DownloadPrint.TrimFunc1).zToStringValues("/");
            data.Category = xePost.XPathElements(".//div[@id='breadcrumb']//a").DescendantTexts().Where(text => { text = text.ToLowerInvariant(); return(text != "forum" && !text.EndsWith(lowerTitle)); }).Select(DownloadPrint.Trim).zToStringValues("/");
            string category = data.Category.ToLowerInvariant();

            data.PrintType = GetPrintType(category);
            //Trace.WriteLine("category \"{0}\" printType {1}", category, data.printType);

            // <div id="postlist" class="postlist restrain">
            XXElement xe = xePost.XPathElement(".//div[@id='postlist']");

            // Aujourd'hui, 07h32 - Aujourd'hui, 10h51 - Hier, 12h55 - 22/02/2014, 21h09
            //string date = xe.DescendantTextList(".//div[@class='posthead']//text()", nodeFilter: node => node.zGetName() != "a").zToStringValues("");
            XXElement xe2 = xe.XPathElement(".//div[@class='posthead']");
            //string date = xe2.DescendantTextList(nodeFilter: node => node.zGetName() != "a").zToStringValues("");
            string date = xe2.DescendantTexts(node => node.zGetName() != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode).zToStringValues("");

            date = date.Replace('\xA0', ' ');
            data.PostCreationDate = zdate.ParseDateTimeLikeToday(date, loadDataFromWeb.LoadFromWebDate, @"d/M/yyyy, HH\hmm", @"d-M-yyyy, HH\hmm");
            if (data.PostCreationDate == null)
            {
                pb.Trace.WriteLine("unknow post creation date \"{0}\"", date);
            }
            if (__trace)
            {
                pb.Trace.WriteLine("post creation date {0} - \"{1}\"", data.PostCreationDate, date);
            }

            //data.PostAuthor = xe.XPathValue(".//div[@class='userinfo']//a//text()", DownloadPrint.Trim);
            data.PostAuthor = xe.XPathValue(".//div[@class='userinfo']//a//text()").Trim(DownloadPrint.TrimChars);

            // <div class="postbody">
            xe = xePost.XPathElement(".//div[@class='postbody']//div[@class='content']//blockquote/div");

            //data.Images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(data.SourceUrl, xeImg.zAttribValue("src")))).ToArray();
            data.Images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new WebImage(zurl.GetUrl(data.SourceUrl, xeImg.zAttribValue("src")))).ToArray();

            // force load image to get image width and height
            if (loadDataFromWeb.WebRequest.LoadImage)
            {
                data.Images = DownloadPrint.LoadImages(data.Images).ToArray();
            }

            // get infos, description, language, size, nbPages
            // xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a")
            PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(xe.DescendantTexts(node => !(node is XElement) || ((XElement)node).Name != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode), data.Title);

            data.Description = textValues.description;
            data.Language    = textValues.language;
            data.Size        = textValues.size;
            data.NbPages     = textValues.nbPages;
            data.Infos.SetValues(textValues.infos);

            data.DownloadLinks = xe.XPathValues(".//a/@href").ToArray();

            if (__trace)
            {
                pb.Trace.WriteLine(data.zToJson());
            }

            return(data);
        }
Esempio n. 4
0
        protected override RapideDdl_PostDetail GetDataFromWeb(LoadDataFromWeb_v3 loadDataFromWeb)
        {
            XXElement            xeSource = new XXElement(loadDataFromWeb.GetXmlDocument().Root);
            RapideDdl_PostDetail data     = new RapideDdl_PostDetail();

            data.sourceUrl       = loadDataFromWeb.request.Url;
            data.loadFromWebDate = loadDataFromWeb.loadFromWebDate;
            data.id = GetPostDetailKey(data.sourceUrl);

            XXElement xePost = xeSource.XPathElement("//div[@class='lcolomn mainside']");

            //data.category = xePost.DescendantTextList(".//div[@class='spbar']//a").Select(DownloadPrint.TrimFunc1).Where(
            data.category = xePost.XPathElements(".//div[@class='spbar']//a").DescendantTexts().Select(DownloadPrint.Trim).Where(
                s =>
            {
                s = s.ToLowerInvariant();
                return(s != "" && !s.Contains("acceuil") && !s.Contains("accueil"));
            }
                ).zToStringValues("/");
            string category = data.category.ToLowerInvariant();

            data.printType = GetPostType(category);

            //data.title = xePost.DescendantTextList(".//div[@class='spbar']", func: DownloadPrint.TrimFunc1).LastOrDefault();
            data.title = xePost.XPathElements(".//div[@class='spbar']").DescendantTexts().Select(DownloadPrint.Trim).LastOrDefault();
            //ExtractTitleInfos(data);
            PrintTitleInfos titleInfos = DownloadPrint.PrintTextValuesManager.ExtractTitleInfos(data.title);

            if (titleInfos.foundInfo)
            {
                data.originalTitle = data.title;
                data.title         = titleInfos.title;
                data.infos.SetValues(titleInfos.infos);
            }

            XXElement xe   = xePost.XPathElement(".//div[@class='shdinfo']");
            string    date = xe.XPathValue(".//span[@class='date']//text()");

            //data.creationDate = Download.Print.RapideDdl.RapideDdl.ParseDateTime(date, loadDataFromWeb.loadFromWebDate);
            data.creationDate = zdate.ParseDateTimeLikeToday(date, loadDataFromWeb.loadFromWebDate, "d-M-yyyy, HH:mm", "d M yyyy", "d MMMM yyyy");
            if (data.creationDate == null)
            {
                pb.Trace.WriteLine("unknow date time \"{0}\"", date);
            }
            if (__trace)
            {
                pb.Trace.WriteLine("creationDate {0} - \"{1}\"", data.creationDate, date);
            }
            data.postAuthor = xe.XPathValue(".//span[@class='arg']//a//text()");

            xe = xePost.XPathElement(".//div[@class='maincont']");
            //data.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).ToArray();
            data.images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new WebImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).ToArray();

            if (loadDataFromWeb.request.LoadImage)
            {
                data.images = DownloadPrint.LoadImages(data.images).ToArray();
            }

            //RapideDdl.SetTextValues(data, xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a" ));
            // xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a")
            PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(xe.DescendantTexts(node => !(node is XElement) || ((XElement)node).Name != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode), data.title);

            data.description = textValues.description;
            data.language    = textValues.language;
            data.size        = textValues.size;
            data.nbPages     = textValues.nbPages;
            data.infos.SetValues(textValues.infos);

            List <string> downloadLinks = new List <string>();

            foreach (XXElement xe2 in xe.XPathElements("div/div"))
            {
                // http://prezup.eu http://pixhst.com/avaxhome/27/36/002e3627.jpeg http://www.zupmage.eu/i/R1UgqdXn4F.jpg
                // http://i.imgur.com/Gu7hagN.jpg http://img11.hostingpics.net/pics/591623liens.png http://www.hapshack.com/images/jUfTZ.gif
                // http://pixhst.com/pictures/3029467
                downloadLinks.AddRange(xe2.XPathValues(".//a/@href").Where(url => !url.StartsWith("http://prezup.eu") && !url.StartsWith("http://pixhst.com") &&
                                                                           !url.EndsWith(".jpg") && !url.EndsWith("jpeg") && !url.EndsWith("png") && !url.EndsWith("gif")));
            }
            data.downloadLinks = downloadLinks.ToArray();

            //if (__trace)
            //    RapideDdl_LoadPostDetail.Trace_RapideDdl_PostDetail(data);

            return(data);
        }
Esempio n. 5
0
        //protected override Telechargementz_PostDetail GetDataFromWeb(LoadDataFromWeb loadDataFromWeb)
        protected override IPost GetDataFromWeb(LoadDataFromWeb_v3 loadDataFromWeb)
        {
            XXElement xeSource = new XXElement(loadDataFromWeb.GetXmlDocument().Root);
            Telechargementz_PostDetail data = new Telechargementz_PostDetail();

            data.SourceUrl       = loadDataFromWeb.request.Url;
            data.LoadFromWebDate = loadDataFromWeb.loadFromWebDate;
            data.Id = GetPostDetailKey(data.SourceUrl);

            XXElement xePost = xeSource.XPathElement("//div[@id='dle-content']");

            data.PostAuthor = xePost.XPathValue(".//div[@class='title-info']//a//text()");

            // , 26.12.14
            string date = xePost.XPathValue(".//div[@class='title-info']//a/following-sibling::text()");

            if (date != null)
            {
                data.PostCreationDate = zdate.ParseDateTimeLikeToday(date.Trim(' ', ','), loadDataFromWeb.loadFromWebDate, "dd.MM.yy");
                if (data.PostCreationDate == null)
                {
                    pb.Trace.WriteLine("unknow date time \"{0}\"", date);
                }
                if (__trace)
                {
                    pb.Trace.WriteLine("creationDate {0} - \"{1}\"", data.PostCreationDate, date);
                }
            }
            else
            {
                pb.Trace.WriteLine("creationDate not found \"{0}\"", data.SourceUrl);
            }

            //data.Title = xePost.XPathElement(".//div[@class='post-title']").DescendantTextList(func: DownloadPrint.TrimFunc1).FirstOrDefault();
            data.Title = xePost.XPathElement(".//div[@class='post-title']").DescendantTexts().Select(DownloadPrint.Trim).FirstOrDefault();
            PrintTitleInfos titleInfos = DownloadPrint.PrintTextValuesManager.ExtractTitleInfos(data.Title);

            if (titleInfos.foundInfo)
            {
                data.OriginalTitle = data.Title;
                data.Title         = titleInfos.title;
                data.infos.SetValues(titleInfos.infos);
            }

            XXElement xe = xePost.XPathElement(".//div[starts-with(@id, 'news-id-')]");

            if (xe.XElement == null)
            {
                pb.Trace.WriteLine("element not found \".//div[starts-with(@id, 'news-id-')]\"");
            }

            //data.Images = new List<UrlImage>();
            //data.Images.Add(xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).FirstOrDefault());
            //data.Images = new UrlImage[] { xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).FirstOrDefault() };
            WebImage image = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new WebImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).FirstOrDefault();

            if (image != null)
            {
                data.Images = new WebImage[] { image }
            }
            ;

            // force load image to get image width and height
            if (loadDataFromWeb.request.LoadImage)
            {
                data.Images = DownloadPrint.LoadImages(data.Images).ToArray();
            }

            data.DownloadLinks = xe.XPathValues(".//a/@href").ToArray();

            //data.category = xePost.DescendantTextList(".//div[@class='hdiin']//a").Select(DownloadPrint.TrimFunc1).zToStringValues("/");
            //string category = data.category.ToLowerInvariant();
            //data.printType = GetPrintType(category);
            ////pb.Trace.WriteLine("category \"{0}\" printType {1}", category, data.printType);


            // get infos, description, language, size, nbPages
            // nodeFilter: not <a> and not <span>
            //   nodeFilter: node => !(node is XElement) || (((XElement)node).Name != "a" && ((XElement)node).Name != "span")
            // nodeFilter: not <a>
            //PrintTextValues_old textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_old(xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a"), data.Title);
            PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(xe.DescendantTexts(node => !(node is XElement) || ((XElement)node).Name != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode), data.Title);

            data.description = textValues.description;
            data.language    = textValues.language;
            data.size        = textValues.size;
            data.nbPages     = textValues.nbPages;
            data.infos.SetValues(textValues.infos);

            data.PrintType = PrintType.UnknowEBook;
            if (data.infos.ContainsKey("Bd") || data.infos.ContainsKey("bd") || data.infos.ContainsKey("BD"))
            {
                data.PrintType = PrintType.Comics;
            }
            // Editeur : Presse fr
            else if (data.infos.ContainsKey("editeur") && data.infos["editeur"] is ZString && ((string)data.infos["editeur"]).ToLowerInvariant() == "presse fr")
            {
                data.PrintType = PrintType.Print;
            }
            else if (data.infos.ContainsKey("isbn"))
            {
                data.PrintType = PrintType.Book;
            }


            //pb.Trace.WriteLine(xe.DescendantNodes(returnNodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a").Select(node => new { type = node.NodeType, name = node is XElement ? ((XElement)node).Name.LocalName : null, value = node is XText ? ((XText)node).Value : null }).zToJson());
            //pb.Trace.WriteLine(xe.DescendantNodes(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a").Select(node => new { type = node.NodeType, name = node is XElement ? ((XElement)node).Name.LocalName : null, value = node is XText ? ((XText)node).Value : null }).zToJson());
            //pb.Trace.WriteLine(xe.DescendantNodes(returnNodeFilter: node => node is XText).Select(node => new { type = node.NodeType, name = node is XElement ? ((XElement)node).Name.LocalName : null, value = node is XText ? ((XText)node).Value : null }).zToJson());
            //pb.Trace.WriteLine(xe.DescendantNodes(nodeFilter: node => !(node is XElement) || (((XElement)node).Name != "a" && ((XElement)node).Name != "span"), returnNodeFilter: node => node is XText).Select(node => new { type = node.NodeType, name = node is XElement ? ((XElement)node).Name.LocalName : null, value = node is XText ? ((XText)node).Value : null }).zToJson());

            if (__trace)
            {
                pb.Trace.WriteLine(data.zToJson());
            }

            return(data);
        }
Esempio n. 6
0
        //protected override GoldenDdl_PostDetail GetDataFromWeb(LoadDataFromWeb loadDataFromWeb)
        protected override IPost GetDataFromWeb(LoadDataFromWeb_v3 loadDataFromWeb)
        {
            XXElement            xeSource = new XXElement(loadDataFromWeb.GetXmlDocument().Root);
            GoldenDdl_PostDetail data     = new GoldenDdl_PostDetail();

            data.sourceUrl       = loadDataFromWeb.request.Url;
            data.loadFromWebDate = loadDataFromWeb.loadFromWebDate;
            data.id = GetPostDetailKey(data.sourceUrl);

            XXElement xePost = xeSource.XPathElement("//div[@id='dle-content']");

            //data.category = xePost.DescendantTextList(".//div[@class='hdiin']//a").Select(DownloadPrint.TrimFunc1).zToStringValues("/");
            data.category = xePost.XPathElements(".//div[@class='hdiin']//a").DescendantTexts().Select(DownloadPrint.Trim).zToStringValues("/");
            string category = data.category.ToLowerInvariant();

            data.printType = GetPrintType(category);
            //pb.Trace.WriteLine("category \"{0}\" printType {1}", category, data.printType);

            //data.title = xePost.XPathValue(".//div[@class='bheading']//text()", DownloadPrint.Trim);
            data.title = xePost.XPathValue(".//div[@class='bheading']//text()").Trim(DownloadPrint.TrimChars);
            PrintTitleInfos titleInfos = DownloadPrint.PrintTextValuesManager.ExtractTitleInfos(data.title);

            if (titleInfos.foundInfo)
            {
                data.originalTitle = data.title;
                data.title         = titleInfos.title;
                data.infos.SetValues(titleInfos.infos);
            }

            string date = xePost.XPathValue(".//div[@class='datenews']//text()");

            data.creationDate = zdate.ParseDateTimeLikeToday(date, loadDataFromWeb.loadFromWebDate, "d-M-yyyy, HH:mm", "d M yyyy", "d MMMM yyyy");
            if (data.creationDate == null)
            {
                pb.Trace.WriteLine("unknow date time \"{0}\"", date);
            }
            if (__trace)
            {
                pb.Trace.WriteLine("creationDate {0} - \"{1}\"", data.creationDate, date);
            }

            data.postAuthor = xePost.XPathValue(".//div[@class='argr']//a//text()");

            XXElement xe = xePost.XPathElement(".//div[@class='maincont']");

            //data.images = xe.XPathImages(xeImg => new UrlImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).ToArray();
            data.images = xe.DescendantNodes(node => XmlDescendant.ImageFilter(node)).Select(xeImg => new WebImage(zurl.GetUrl(loadDataFromWeb.request.Url, xeImg.zAttribValue("src")))).ToArray();


            // force load image to get image width and height
            if (loadDataFromWeb.request.LoadImage)
            {
                data.images = DownloadPrint.LoadImages(data.images).ToArray();
            }

            // get infos, description, language, size, nbPages
            //PrintTextValues_old textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_old(xe.DescendantTextList(nodeFilter: node => !(node is XElement) || ((XElement)node).Name != "a"), data.title);
            PrintTextValues_v1 textValues = DownloadPrint.PrintTextValuesManager.GetTextValues_v1(xe.DescendantTexts(node => !(node is XElement) || ((XElement)node).Name != "a" ? XNodeFilter.SelectNode : XNodeFilter.SkipNode), data.title);

            data.description = textValues.description;
            data.language    = textValues.language;
            data.size        = textValues.size;
            data.nbPages     = textValues.nbPages;
            data.infos.SetValues(textValues.infos);

            List <string> downloadLinks = new List <string>();

            foreach (XXElement xe2 in xe.XPathElements("div/div"))
            {
                // http://prezup.eu http://pixhst.com/avaxhome/27/36/002e3627.jpeg http://www.zupmage.eu/i/R1UgqdXn4F.jpg
                // http://i.imgur.com/Gu7hagN.jpg http://img11.hostingpics.net/pics/591623liens.png http://www.hapshack.com/images/jUfTZ.gif
                // http://pixhst.com/pictures/3029467
                downloadLinks.AddRange(xe2.XPathValues(".//a/@href").Where(url => !url.StartsWith("http://prezup.eu") && !url.StartsWith("http://pixhst.com") &&
                                                                           !url.EndsWith(".jpg") && !url.EndsWith("jpeg") && !url.EndsWith("png") && !url.EndsWith("gif")));
            }
            data.downloadLinks = downloadLinks.ToArray();

            if (__trace)
            {
                pb.Trace.WriteLine(data.zToJson());
            }

            return(data);
        }