From 3cea5fb4317d265c310a8fa94dcd40254c7b66d8 Mon Sep 17 00:00:00 2001 From: glax Date: Wed, 13 Sep 2023 23:00:52 +0200 Subject: [PATCH] #50 Added Mangaworld.bz connector --- .../MangaConnectorJsonConverter.cs | 2 + Tranga/MangaConnectors/Mangaworld.cs | 181 ++++++++++++++++++ Tranga/Tranga.cs | 3 +- 3 files changed, 185 insertions(+), 1 deletion(-) create mode 100644 Tranga/MangaConnectors/Mangaworld.cs diff --git a/Tranga/MangaConnectors/MangaConnectorJsonConverter.cs b/Tranga/MangaConnectors/MangaConnectorJsonConverter.cs index 5b98845..b9f3af0 100644 --- a/Tranga/MangaConnectors/MangaConnectorJsonConverter.cs +++ b/Tranga/MangaConnectors/MangaConnectorJsonConverter.cs @@ -32,6 +32,8 @@ public class MangaConnectorJsonConverter : JsonConverter return this.connectors.First(c => c is MangaKatana); case "Mangasee": return this.connectors.First(c => c is Mangasee); + case "Mangaworld": + return this.connectors.First(c => c is Mangaworld); } throw new Exception(); diff --git a/Tranga/MangaConnectors/Mangaworld.cs b/Tranga/MangaConnectors/Mangaworld.cs new file mode 100644 index 0000000..2e74b2e --- /dev/null +++ b/Tranga/MangaConnectors/Mangaworld.cs @@ -0,0 +1,181 @@ +using System.Net; +using System.Text.RegularExpressions; +using HtmlAgilityPack; +using Tranga.Jobs; + +namespace Tranga.MangaConnectors; + +public class Mangaworld: MangaConnector +{ + public Mangaworld(GlobalBase clone) : base(clone, "Mangaworld") + { + this.downloadClient = new HttpDownloadClient(clone, new Dictionary() + { + {1, 60} + }); + } + + public override Manga[] GetManga(string publicationTitle = "") + { + Log($"Searching Publications. Term=\"{publicationTitle}\""); + string sanitizedTitle = string.Join('_', Regex.Matches(publicationTitle, "[A-z]*").Where(str => str.Length > 0)).ToLower(); + string requestUrl = $"https://www.mangaworld.bz/archive?keyword={sanitizedTitle}"; + DownloadClient.RequestResult requestResult = + downloadClient.MakeRequest(requestUrl, 1); + if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) + return Array.Empty(); + + if (requestResult.htmlDocument is null) + return Array.Empty(); + Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument); + Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\""); + return publications; + } + + private Manga[] ParsePublicationsFromHtml(HtmlDocument document) + { + + List urls = document.DocumentNode + .SelectNodes( + "//div[@class='comics-grid']//div[@class='entry']//a[contains(concat(' ',normalize-space(@class),' '),'thumb')]") + .Select(thumb => thumb.GetAttributeValue("href", "")).ToList(); + + HashSet ret = new(); + foreach (string url in urls) + { + Manga? manga = GetMangaFromUrl(url); + if (manga is not null) + ret.Add((Manga)manga); + } + + return ret.ToArray(); + } + + public override Manga? GetMangaFromUrl(string url) + { + DownloadClient.RequestResult requestResult = + downloadClient.MakeRequest(url, 1); + if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) + return null; + + if (requestResult.htmlDocument is null) + return null; + + return ParseSinglePublicationFromHtml(requestResult.htmlDocument, url.Split('/')[^2]); + } + + private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId) + { + string status = ""; + Dictionary altTitles = new(); + Dictionary? links = null; + HashSet tags = new(); + string[] authors = Array.Empty(); + string originalLanguage = ""; + + HtmlNode infoNode = document.DocumentNode.Descendants("div").First(d => d.HasClass("info")); + + string sortName = infoNode.Descendants("h1").First().InnerText; + + HtmlNode metadata = infoNode.Descendants().First(d => d.HasClass("meta-data")); + + HtmlNode altTitlesNode = metadata.SelectSingleNode("//span[text()='Titoli alternativi: ']/..").ChildNodes[1]; + + string[] alts = altTitlesNode.InnerText.Split(", "); + for(int i = 0; i < alts.Length; i++) + altTitles.Add(i.ToString(), alts[i]); + + HtmlNode genresNode = + metadata.SelectSingleNode("//span[text()='Generi: ']/.."); + tags = genresNode.SelectNodes("a").Select(node => node.InnerText).ToHashSet(); + + HtmlNode authorsNode = + metadata.SelectSingleNode("//span[text()='Autore: ']/.."); + authors = new[] { authorsNode.SelectNodes("a").First().InnerText }; + + status = metadata.SelectSingleNode("//span[text()='Stato: ']/..").SelectNodes("a").First().InnerText; + + string posterUrl = document.DocumentNode.SelectSingleNode("//img[@class='rounded']").GetAttributeValue("src", ""); + + string coverFileNameInCache = SaveCoverImageToCache(posterUrl, 1); + + string description = document.DocumentNode.SelectSingleNode("//div[@id='noidungm']").InnerText; + + string yearString = metadata.SelectSingleNode("//span[text()='Anno di uscita: ']/..").SelectNodes("a").First().InnerText; + int year = Convert.ToInt32(yearString); + + Manga manga = new (sortName, authors.ToList(), description, altTitles, tags.ToArray(), posterUrl, coverFileNameInCache, links, + year, originalLanguage, status, publicationId); + cachedPublications.Add(manga); + return manga; + } + + public override Chapter[] GetChapters(Manga manga, string language="en") + { + Log($"Getting chapters {manga}"); + string requestUrl = $"https://www.mangaworld.bz/manga/{manga.publicationId}"; + DownloadClient.RequestResult requestResult = + downloadClient.MakeRequest(requestUrl, 1); + if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) + return Array.Empty(); + + //Return Chapters ordered by Chapter-Number + if (requestResult.htmlDocument is null) + return Array.Empty(); + List chapters = ParseChaptersFromHtml(manga, requestResult.htmlDocument); + Log($"Got {chapters.Count} chapters. {manga}"); + return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, numberFormatDecimalPoint)).ToArray(); + } + + private List ParseChaptersFromHtml(Manga manga, HtmlDocument document) + { + List ret = new(); + + foreach (HtmlNode volNode in document.DocumentNode.SelectNodes( + "//div[contains(concat(' ',normalize-space(@class),' '),'chapters-wrapper')]//div[contains(concat(' ',normalize-space(@class),' '),'volume-element')]")) + { + string volume = volNode.SelectSingleNode("//p[contains(concat(' ',normalize-space(@class),' '),'volume-name')]").InnerText.Split(' ')[^1]; + foreach (HtmlNode chNode in volNode.SelectNodes("//div[contains(concat(' ',normalize-space(@class),' '),'volume-chapters')]/div[@class='chapter']")) + { + string number = chNode.SelectSingleNode("a").SelectSingleNode("span").InnerText.Split(" ")[^1]; + string url = chNode.SelectSingleNode("a").GetAttributeValue("href", ""); + ret.Add(new Chapter(manga, null, volume, number, url)); + } + } + + ret.Reverse(); + return ret; + } + + public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null) + { + if (progressToken?.cancellationRequested ?? false) + return HttpStatusCode.RequestTimeout; + Manga chapterParentManga = chapter.parentManga; + Log($"Retrieving chapter-info {chapter} {chapterParentManga}"); + string requestUrl = $"{chapter.url}?style=list"; + DownloadClient.RequestResult requestResult = + downloadClient.MakeRequest(requestUrl, 1); + if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) + return requestResult.statusCode; + + string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument); + + string comicInfoPath = Path.GetTempFileName(); + File.WriteAllText(comicInfoPath, chapter.GetComicInfoXmlString()); + + return DownloadChapterImages(imageUrls, chapter.GetArchiveFilePath(settings.downloadLocation), 1, comicInfoPath, "https://www.mangaworld.bz/", progressToken:progressToken); + } + + private string[] ParseImageUrlsFromHtml(HtmlDocument document) + { + List ret = new(); + + HtmlNode imageContainer = + document.DocumentNode.SelectSingleNode("//div[@id='page']"); + foreach(HtmlNode imageNode in imageContainer.Descendants("img")) + ret.Add(imageNode.GetAttributeValue("src", "")); + + return ret.ToArray(); + } +} \ No newline at end of file diff --git a/Tranga/Tranga.cs b/Tranga/Tranga.cs index 458c5e2..16f01c3 100644 --- a/Tranga/Tranga.cs +++ b/Tranga/Tranga.cs @@ -19,7 +19,8 @@ public partial class Tranga : GlobalBase new Manganato(this), new Mangasee(this), new MangaDex(this), - new MangaKatana(this) + new MangaKatana(this), + new Mangaworld(this) }; jobBoss = new(this, this._connectors); StartJobBoss();