Merge branch 'cuttingedge-merge-ServerV2' into postgres-Server-V2

# Conflicts:
#	API/Schema/MangaConnectors/Webtoons.cs
#	Tranga/MangaConnectors/MangaConnector.cs
#	Tranga/MangaConnectors/MangaConnectorJsonConverter.cs
#	Tranga/MangaConnectors/WeebCentral.cs
#	Tranga/Tranga.cs

API/Schema/MangaConnectors/Webtoons.cs

@@ -0,0 +1,272 @@
+using System.Net;
+using System.Text.RegularExpressions;
+using HtmlAgilityPack;
+using Tranga.Jobs;
+
+namespace Tranga.MangaConnectors;
+
+public class Webtoons : MangaConnector
+{
+
+    public Webtoons(GlobalBase clone) : base(clone, "Webtoons", ["en"])
+    {
+        this.downloadClient = new HttpDownloadClient(clone);
+    }
+
+    // Done
+    public override Manga[] GetManga(string publicationTitle = "")
+    {
+        string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(m => m.Value.Length > 0)).ToLower();
+        Log($"Searching Publications. Term=\"{publicationTitle}\"");
+        string requestUrl = $"https://www.webtoons.com/en/search?keyword={sanitizedTitle}&searchType=WEBTOON";
+        RequestResult requestResult =
+            downloadClient.MakeRequest(requestUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) {
+            Log($"Failed to retrieve site");
+            return Array.Empty<Manga>();
+        }
+
+        if (requestResult.htmlDocument is null)
+        {
+            Log($"Failed to retrieve site");
+            return Array.Empty<Manga>();
+        }
+
+        Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
+        Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\"");
+        return publications;
+    }
+
+    // Done
+    public override Manga? GetMangaFromId(string publicationId)
+    {
+        PublicationManager pb = new PublicationManager(publicationId);
+        return GetMangaFromUrl($"https://www.webtoons.com/en/{pb.Category}/{pb.Title}/list?title_no={pb.Id}");
+    }
+
+    // Done
+    public override Manga? GetMangaFromUrl(string url)
+    {
+        RequestResult requestResult = downloadClient.MakeRequest(url, RequestType.MangaInfo);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300) {
+            return null;
+        }
+        if (requestResult.htmlDocument is null)
+        {
+            Log($"Failed to retrieve site");
+            return null;
+        }
+        Regex regex = new Regex(@".*webtoons\.com/en/(?<category>[^/]+)/(?<title>[^/]+)/list\?title_no=(?<id>\d+).*");
+        Match match = regex.Match(url);
+
+        if(match.Success) {
+            PublicationManager pm = new PublicationManager(match.Groups["title"].Value, match.Groups["category"].Value, match.Groups["id"].Value);
+            return ParseSinglePublicationFromHtml(requestResult.htmlDocument, pm.getPublicationId(), url);
+        }
+        Log($"Failed match Regex ID");
+        return null;
+    }
+
+    // Done
+    private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
+    {
+        HtmlNode mangaList = document.DocumentNode.SelectSingleNode("//ul[contains(@class, 'card_lst')]");
+        if (!mangaList.ChildNodes.Any(node => node.Name == "li")) {
+            Log($"Failed to parse publication");
+            return Array.Empty<Manga>();
+        }
+
+        List<string> urls = document.DocumentNode
+                            .SelectNodes("//ul[contains(@class, 'card_lst')]/li/a")
+                            .Select(node => node.GetAttributeValue("href", "https://www.webtoons.com"))
+                            .ToList();
+
+        HashSet<Manga> ret = new();
+        foreach (string url in urls)
+        {
+            Manga? manga = GetMangaFromUrl(url);
+            if (manga is not null)
+                ret.Add((Manga)manga);
+        }
+
+        return ret.ToArray();
+    }
+
+    private string capitalizeString(string str = "") {
+        if(str.Length == 0) return "";
+        if(str.Length == 1) return str.ToUpper();
+        return char.ToUpper(str[0]) + str.Substring(1).ToLower();
+    }
+
+    // Done
+    private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
+    {
+        HtmlNode infoNode1 = document.DocumentNode.SelectSingleNode("//*[@id='content']/div[2]/div[1]/div[1]");
+        HtmlNode infoNode2 = document.DocumentNode.SelectSingleNode("//*[@id='content']/div[2]/div[2]/div[2]");
+
+        string sortName = infoNode1.SelectSingleNode(".//h1[contains(@class, 'subj')]").InnerText;
+        string description = infoNode2.SelectSingleNode(".//p[contains(@class, 'summary')]")
+                            .InnerText.Trim();
+
+        HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//div[contains(@class, 'detail_body') and contains(@class, 'banner')]");
+
+        Regex regex = new Regex(@"url\((?<url>.*?)\)");
+        Match match = regex.Match(posterNode.GetAttributeValue("style", ""));
+
+        string posterUrl = match.Groups["url"].Value;
+        string coverFileNameInCache = SaveCoverImageToCache(posterUrl, publicationId, RequestType.MangaCover, websiteUrl);
+
+        string genre = infoNode1.SelectSingleNode(".//h2[contains(@class, 'genre')]")
+                            .InnerText.Trim();
+        string[] tags = [ genre ];
+
+        List<HtmlNode> authorsNodes = infoNode1.SelectSingleNode(".//div[contains(@class, 'author_area')]").Descendants("a").ToList();
+        List<string> authors = authorsNodes.Select(node => node.InnerText.Trim()).ToList();
+
+        string originalLanguage = "";
+
+        int year = DateTime.Now.Year;
+
+        string status1 = infoNode2.SelectSingleNode(".//p").InnerText;
+        string status2 = infoNode2.SelectSingleNode(".//p/span").InnerText;
+        Manga.ReleaseStatusByte releaseStatus = Manga.ReleaseStatusByte.Unreleased;
+        if(status2.Length == 0 || status1.ToLower() == "completed") {
+            releaseStatus = Manga.ReleaseStatusByte.Completed;
+        } else if(status2.ToLower() == "up") {
+            releaseStatus = Manga.ReleaseStatusByte.Continuing;
+        }
+
+        Manga manga = new(sortName, authors, description, new Dictionary<string, string>(), tags, posterUrl, coverFileNameInCache, new Dictionary<string, string>(),
+            year, originalLanguage, publicationId, releaseStatus, websiteUrl: websiteUrl);
+        AddMangaToCache(manga);
+        return manga;
+    }
+
+    // Done
+    public override Chapter[] GetChapters(Manga manga, string language = "en")
+    {
+        PublicationManager pm = new PublicationManager(manga.publicationId);
+        string requestUrl = $"https://www.webtoons.com/en/{pm.Category}/{pm.Title}/list?title_no={pm.Id}";
+        // Leaving this in for verification if the page exists
+        RequestResult requestResult =
+            downloadClient.MakeRequest(requestUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+            return Array.Empty<Chapter>();
+
+        // Get number of pages
+        int pages = requestResult.htmlDocument.DocumentNode.SelectSingleNode("//div[contains(@class, 'paginate')]").ChildNodes.ToArray().Length;
+        List<Chapter> chapters = new List<Chapter>();
+        
+        for(int page = 1; page <= pages; page++) {
+            string pageRequestUrl = $"{requestUrl}&page={page}";
+
+            chapters.AddRange(ParseChaptersFromHtml(manga, pageRequestUrl));
+        }
+
+        Log($"Got {chapters.Count} chapters. {manga}");
+        return chapters.Order().ToArray();
+    }
+
+    // Done
+    private List<Chapter> ParseChaptersFromHtml(Manga manga, string mangaUrl)
+    {
+        RequestResult result = downloadClient.MakeRequest(mangaUrl, RequestType.Default);
+        if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
+        {
+            Log("Failed to load site");
+            return new List<Chapter>();
+        }
+
+        List<Chapter> ret = new();
+
+        foreach (HtmlNode chapterInfo in result.htmlDocument.DocumentNode.SelectNodes("//ul/li[contains(@class, '_episodeItem')]"))
+        {
+            HtmlNode infoNode = chapterInfo.SelectSingleNode(".//a");
+            string url = infoNode.GetAttributeValue("href", "");
+
+            string id = chapterInfo.GetAttributeValue("id", "");
+            if(id == "") continue;
+            string? volumeNumber = null;
+            string chapterNumber = chapterInfo.GetAttributeValue("data-episode-no", "");
+            if(chapterNumber == "") continue;
+            string chapterName = infoNode.SelectSingleNode(".//span[contains(@class, 'subj')]/span").InnerText.Trim();
+            ret.Add(new Chapter(manga, chapterName, volumeNumber, chapterNumber, url));
+        }
+
+        return ret;
+    }
+
+    public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null)
+    {
+        if (progressToken?.cancellationRequested ?? false)
+        {
+            progressToken.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        Manga chapterParentManga = chapter.parentManga;
+        Log($"Retrieving chapter-info {chapter} {chapterParentManga}");
+        string requestUrl = chapter.url;
+        // Leaving this in to check if the page exists
+        RequestResult requestResult =
+            downloadClient.MakeRequest(requestUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+        {
+            progressToken?.Cancel();
+            return requestResult.statusCode;
+        }
+
+        string[] imageUrls = ParseImageUrlsFromHtml(requestUrl);
+		return DownloadChapterImages(imageUrls, chapter, RequestType.MangaImage, progressToken:progressToken, referrer: requestUrl);
+    }
+
+    private string[] ParseImageUrlsFromHtml(string mangaUrl)
+    {
+        RequestResult requestResult =
+            downloadClient.MakeRequest(mangaUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+        {
+            return Array.Empty<string>();
+        }
+        if (requestResult.htmlDocument is null)
+        {
+            Log($"Failed to retrieve site");
+            return Array.Empty<string>();
+        }
+
+        return requestResult.htmlDocument.DocumentNode
+        .SelectNodes("//*[@id='_imageList']/img")
+        .Select(node =>
+            node.GetAttributeValue("data-url", ""))
+        .ToArray();
+    }
+}
+
+internal class PublicationManager {
+    public PublicationManager(string title = "", string category = "", string id = "") {
+        this.Title = title;
+        this.Category = category;
+        this.Id = id;
+    }
+
+    public PublicationManager(string publicationId) {
+        string[] parts = publicationId.Split("|");
+        if(parts.Length == 3) {
+            this.Title = parts[0];
+            this.Category = parts[1];
+            this.Id = parts[2];
+        } else {
+            this.Title = "";
+            this.Category = "";
+            this.Id = "";
+        }
+    }
+
+    public string getPublicationId() {
+        return $"{this.Title}|{this.Category}|{this.Id}";
+    }
+
+    public string Title { get; set; }
+    public string Category { get; set; }
+    public string Id { get; set; }
+}

README.md

@@ -45,14 +45,13 @@ Tranga can download Chapters and Metadata from "Scanlation" sites such as
 
 - [MangaDex.org](https://mangadex.org/) (Multilingual)
 - [Manganato.com](https://manganato.com/) (en)
-- [Mangasee.com](https://mangasee123.com/) (en)
 - [MangaKatana.com](https://mangakatana.com) (en)
 - [Mangaworld.bz](https://www.mangaworld.bz/) (it)
 - [Bato.to](https://bato.to/v3x) (en)
-- [Manga4Life](https://manga4life.com) (en)
 - [ManhuaPlus](https://manhuaplus.org/) (en)
 - [MangaHere](https://www.mangahere.cc/) (en) (Their covers aren't scrapeable.)
 - [Weebcentral](https://weebcentral.com) (en)
+- [Webtoons](https://www.webtoons.com/en/)
 - ❓ Open an [issue](https://github.com/C9Glax/tranga/issues/new?assignees=&labels=New+Connector&projects=&template=new_connector.yml&title=%5BNew+Connector%5D%3A+)
 
 and trigger a library-scan with [Komga](https://komga.org/) and [Kavita](https://www.kavitareader.com/).  

Tranga/MangaConnectors/WeebCentral.cs

@@ -0,0 +1,243 @@
+using System.Net;
+using System.Text.RegularExpressions;
+using HtmlAgilityPack;
+using Soenneker.Utils.String.NeedlemanWunsch;
+using Tranga.Jobs;
+
+namespace Tranga.MangaConnectors;
+
+public class Weebcentral : MangaConnector
+{
+    private readonly string _baseUrl = "https://weebcentral.com";
+
+    private readonly string[] _filterWords =
+        { "a", "the", "of", "as", "to", "no", "for", "on", "with", "be", "and", "in", "wa", "at", "be", "ni" };
+
+    public Weebcentral(GlobalBase clone) : base(clone, "Weebcentral", ["en"])
+    {
+        downloadClient = new ChromiumDownloadClient(clone);
+    }
+
+    public override Manga[] GetManga(string publicationTitle = "")
+    {
+        Log($"Searching Publications. Term=\"{publicationTitle}\"");
+        const int limit = 32; //How many values we want returned at once
+        var offset = 0; //"Page"
+        var requestUrl =
+            $"{_baseUrl}/search/data?limit={limit}&offset={offset}&text={publicationTitle}&sort=Best+Match&order=Ascending&official=Any&display_mode=Minimal%20Display";
+        var requestResult =
+            downloadClient.MakeRequest(requestUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 ||
+            requestResult.htmlDocument == null)
+        {
+            Log($"Failed to retrieve search: {requestResult.statusCode}");
+            return [];
+        }
+
+        var publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
+        Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\"");
+
+        return publications;
+    }
+
+    private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
+    {
+        if (document.DocumentNode.SelectNodes("//article") == null)
+            return Array.Empty<Manga>();
+
+        var urls = document.DocumentNode.SelectNodes("/html/body/article/a[@class='link link-hover']")
+            .Select(elem => elem.GetAttributeValue("href", "")).ToList();
+
+        HashSet<Manga> ret = new();
+        foreach (var url in urls)
+        {
+            var manga = GetMangaFromUrl(url);
+            if (manga is not null)
+                ret.Add((Manga)manga);
+        }
+
+        return ret.ToArray();
+    }
+
+    public override Manga? GetMangaFromUrl(string url)
+    {
+        Regex publicationIdRex = new(@"https:\/\/weebcentral\.com\/series\/(\w*)\/(.*)");
+        var publicationId = publicationIdRex.Match(url).Groups[1].Value;
+
+        var requestResult = downloadClient.MakeRequest(url, RequestType.MangaInfo);
+        if ((int)requestResult.statusCode < 300 && (int)requestResult.statusCode >= 200 &&
+            requestResult.htmlDocument is not null)
+            return ParseSinglePublicationFromHtml(requestResult.htmlDocument, publicationId, url);
+        return null;
+    }
+
+    private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
+    {
+        var posterNode =
+            document.DocumentNode.SelectSingleNode("//section[@class='flex items-center justify-center']/picture/img");
+        var posterUrl = posterNode?.GetAttributeValue("src", "") ?? "";
+        var coverFileNameInCache = SaveCoverImageToCache(posterUrl, publicationId, RequestType.MangaCover);
+
+        var titleNode = document.DocumentNode.SelectSingleNode("//section/h1");
+        var sortName = titleNode?.InnerText ?? "Undefined";
+
+        HtmlNode[] authorsNodes =
+            document.DocumentNode.SelectNodes("//ul/li[strong/text() = 'Author(s): ']/span")?.ToArray() ?? [];
+        var authors = authorsNodes.Select(n => n.InnerText).ToList();
+
+        HtmlNode[] genreNodes =
+            document.DocumentNode.SelectNodes("//ul/li[strong/text() = 'Tags(s): ']/span")?.ToArray() ?? [];
+        HashSet<string> tags = genreNodes.Select(n => n.InnerText).ToHashSet();
+
+        var statusNode = document.DocumentNode.SelectSingleNode("//ul/li[strong/text() = 'Status: ']/a");
+        var status = statusNode?.InnerText ?? "";
+        Log("unable to parse status");
+        var releaseStatus = Manga.ReleaseStatusByte.Unreleased;
+        switch (status.ToLower())
+        {
+            case "cancelled": releaseStatus = Manga.ReleaseStatusByte.Cancelled; break;
+            case "hiatus": releaseStatus = Manga.ReleaseStatusByte.OnHiatus; break;
+            case "complete": releaseStatus = Manga.ReleaseStatusByte.Completed; break;
+            case "ongoing": releaseStatus = Manga.ReleaseStatusByte.Continuing; break;
+        }
+
+        var yearNode = document.DocumentNode.SelectSingleNode("//ul/li[strong/text() = 'Released: ']/span");
+        var year = Convert.ToInt32(yearNode?.InnerText ?? "0");
+
+        var descriptionNode = document.DocumentNode.SelectSingleNode("//ul/li[strong/text() = 'Description']/p");
+        var description = descriptionNode?.InnerText ?? "Undefined";
+
+        HtmlNode[] altTitleNodes = document.DocumentNode
+            .SelectNodes("//ul/li[strong/text() = 'Associated Name(s)']/ul/li")?.ToArray() ?? [];
+        Dictionary<string, string> altTitles = new(), links = new();
+        for (var i = 0; i < altTitleNodes.Length; i++)
+            altTitles.Add(i.ToString(), altTitleNodes[i].InnerText);
+
+        var originalLanguage = "";
+
+        Manga manga = new(sortName, authors.ToList(), description, altTitles, tags.ToArray(), posterUrl,
+            coverFileNameInCache, links,
+            year, originalLanguage, publicationId, releaseStatus, websiteUrl);
+        AddMangaToCache(manga);
+        return manga;
+    }
+
+    public override Manga? GetMangaFromId(string publicationId)
+    {
+        return GetMangaFromUrl($"https://weebcentral.com/series/{publicationId}");
+    }
+
+    private string ToFilteredString(string input)
+    {
+        return string.Join(' ', input.ToLower().Split(' ').Where(word => _filterWords.Contains(word) == false));
+    }
+
+    private SearchResult[] FilteredResults(string publicationTitle, SearchResult[] unfilteredSearchResults)
+    {
+        Dictionary<SearchResult, int> similarity = new();
+        foreach (var sr in unfilteredSearchResults)
+        {
+            List<int> scores = new();
+            var filteredPublicationString = ToFilteredString(publicationTitle);
+            var filteredSString = ToFilteredString(sr.s);
+            scores.Add(NeedlemanWunschStringUtil.CalculateSimilarity(filteredSString, filteredPublicationString));
+            foreach (var srA in sr.a)
+            {
+                var filteredAString = ToFilteredString(srA);
+                scores.Add(NeedlemanWunschStringUtil.CalculateSimilarity(filteredAString, filteredPublicationString));
+            }
+
+            similarity.Add(sr, scores.Sum() / scores.Count);
+        }
+
+        var ret = similarity.OrderBy(s => s.Value).Take(10).Select(s => s.Key).ToList();
+        return ret.ToArray();
+    }
+
+    public override Chapter[] GetChapters(Manga manga, string language = "en")
+    {
+        Log($"Getting chapters {manga}");
+        var requestUrl = $"{_baseUrl}/series/{manga.publicationId}/full-chapter-list";
+        var requestResult =
+            downloadClient.MakeRequest(requestUrl, RequestType.Default);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+            return Array.Empty<Chapter>();
+
+        //Return Chapters ordered by Chapter-Number
+        if (requestResult.htmlDocument is null)
+            return Array.Empty<Chapter>();
+        var chapters = ParseChaptersFromHtml(manga, requestResult.htmlDocument);
+        Log($"Got {chapters.Count} chapters. {manga}");
+        return chapters.Order().ToArray();
+    }
+
+    private List<Chapter> ParseChaptersFromHtml(Manga manga, HtmlDocument document)
+    {
+        var chaptersWrapper = document.DocumentNode.SelectSingleNode("/html/body");
+
+        Regex chapterRex = new(@"(\d+(?:\.\d+)*)");
+        Regex idRex = new(@"https:\/\/weebcentral\.com\/chapters\/(\w*)");
+
+        var ret = chaptersWrapper.Descendants("a").Select(elem =>
+        {
+            var url = elem.GetAttributeValue("href", "") ?? "Undefined";
+
+            if (!url.StartsWith("https://") && !url.StartsWith("http://"))
+                return new Chapter(manga, null, null, "-1", "undefined");
+
+            var idMatch = idRex.Match(url);
+            var id = idMatch.Success ? idMatch.Groups[1].Value : null;
+
+            var chapterNode = elem.SelectSingleNode("span[@class='grow flex items-center gap-2']/span")?.InnerText ??
+                              "Undefined";
+
+            var chapterNumberMatch = chapterRex.Match(chapterNode);
+            var chapterNumber = chapterNumberMatch.Success ? chapterNumberMatch.Groups[1].Value : "-1";
+
+            return new Chapter(manga, null, null, chapterNumber, url, id);
+        }).Where(elem => elem.chapterNumber != -1 && elem.url != "undefined").ToList();
+
+        ret.Reverse();
+        return ret;
+    }
+
+    public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null)
+    {
+        if (progressToken?.cancellationRequested ?? false)
+        {
+            progressToken.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        var chapterParentManga = chapter.parentManga;
+        if (progressToken?.cancellationRequested ?? false)
+        {
+            progressToken.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        Log($"Retrieving chapter-info {chapter} {chapterParentManga}");
+
+        var requestResult = downloadClient.MakeRequest(chapter.url, RequestType.Default);
+        if (requestResult.htmlDocument is null)
+        {
+            progressToken?.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        var document = requestResult.htmlDocument;
+
+        var imageNodes =
+            document.DocumentNode.SelectNodes($"//section[@hx-get='{chapter.url}/images']/img")?.ToArray() ?? [];
+        var urls = imageNodes.Select(imgNode => imgNode.GetAttributeValue("src", "")).ToArray();
+
+        return DownloadChapterImages(urls, chapter, RequestType.MangaImage, progressToken: progressToken);
+    }
+
+    private struct SearchResult
+    {
+        public string i { get; set; }
+        public string s { get; set; }
+        public string[] a { get; set; }
+    }
+}