Merge pull request #283 from C9Glax/cuttingedge-merge-candiate

AsuraToon merge

Tranga/Chapter.cs

@@ -121,6 +121,8 @@ public readonly struct Chapter : IComparable
     
     public void CreateChapterMarker()
     {
+        if (this.id is null)
+            return;
         string path = Path.Join(TrangaSettings.downloadLocation, parentManga.folderName, $".{id}");
         File.WriteAllText(path, GetArchiveFilePath());
         File.SetAttributes(path, FileAttributes.Hidden);

Tranga/MangaConnectors/AsuraToon.cs

@@ -0,0 +1,208 @@
+using System.Net;
+using System.Text.RegularExpressions;
+using HtmlAgilityPack;
+using Tranga.Jobs;
+
+namespace Tranga.MangaConnectors;
+
+public class AsuraToon : MangaConnector
+{
+	
+	public AsuraToon(GlobalBase clone) : base(clone, "AsuraToon", ["en"])
+	{
+		this.downloadClient = new HttpDownloadClient(clone);
+	}
+
+	public override Manga[] GetManga(string publicationTitle = "")
+	{
+		Log($"Searching Publications. Term=\"{publicationTitle}\"");
+		string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(m => m.Value.Length > 0)).ToLower();
+		string requestUrl = $"https://asuracomic.net/series?name={sanitizedTitle}";
+		RequestResult requestResult =
+			downloadClient.MakeRequest(requestUrl, RequestType.Default);
+		if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+			return Array.Empty<Manga>();
+
+		if (requestResult.htmlDocument is null)
+		{
+			Log($"Failed to retrieve site");
+			return Array.Empty<Manga>();
+		}
+			
+		Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
+		Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\"");
+		return publications;
+	}
+
+	public override Manga? GetMangaFromId(string publicationId)
+	{
+		return GetMangaFromUrl($"https://asuracomic.net/series/{publicationId}");
+	}
+
+	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;
+		}
+		return ParseSinglePublicationFromHtml(requestResult.htmlDocument, url.Split('/')[^1], url);
+	}
+
+	private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
+	{
+		HtmlNodeCollection mangaList = document.DocumentNode.SelectNodes("//a[starts-with(@href,'series')]");
+		if (mangaList.Count < 1)
+			return Array.Empty<Manga>();
+
+		IEnumerable<string> urls = mangaList.Select(a => $"https://asuracomic.net/{a.GetAttributeValue("href", "")}");
+		
+		List<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 Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
+	{
+		string? originalLanguage = null;
+		Dictionary<string, string> altTitles = new(), links = new();
+
+		HtmlNodeCollection genreNodes = document.DocumentNode.SelectNodes("//h3[text()='Genres']/../div/button");
+		string[] tags = genreNodes.Select(b => b.InnerText).ToArray();
+		
+		HtmlNode statusNode = document.DocumentNode.SelectSingleNode("//h3[text()='Status']/../h3[2]");
+		Manga.ReleaseStatusByte releaseStatus = statusNode.InnerText.ToLower() switch
+		{
+			"ongoing" => Manga.ReleaseStatusByte.Continuing,
+			"hiatus" => Manga.ReleaseStatusByte.OnHiatus,
+			"completed" => Manga.ReleaseStatusByte.Completed,
+			"dropped" => Manga.ReleaseStatusByte.Cancelled,
+			"season end" => Manga.ReleaseStatusByte.Continuing,
+			"coming soon" => Manga.ReleaseStatusByte.Unreleased,
+			_ => Manga.ReleaseStatusByte.Unreleased
+		};
+		
+		HtmlNode coverNode = 
+			document.DocumentNode.SelectSingleNode("//img[@alt='poster']");
+		string coverUrl = coverNode.GetAttributeValue("src", "");
+		string coverFileNameInCache = SaveCoverImageToCache(coverUrl, publicationId, RequestType.MangaCover);
+		
+		HtmlNode titleNode = 
+			document.DocumentNode.SelectSingleNode("//title");
+		string sortName = Regex.Match(titleNode.InnerText, @"(.*) - Asura Scans").Groups[1].Value;
+		
+		HtmlNode descriptionNode =
+			document.DocumentNode.SelectSingleNode("//h3[starts-with(text(),'Synopsis')]/../span");
+		string description = descriptionNode.InnerText;
+		
+		HtmlNodeCollection authorNodes = document.DocumentNode.SelectNodes("//h3[text()='Author']/../h3[not(text()='Author' or text()='_')]");
+		HtmlNodeCollection artistNodes = document.DocumentNode.SelectNodes("//h3[text()='Artist']/../h3[not(text()='Author' or text()='_')]");
+		List<string> authors = authorNodes.Select(a => a.InnerText).Concat(artistNodes.Select(a => a.InnerText)).ToList();
+
+		HtmlNode? firstChapterNode = document.DocumentNode.SelectSingleNode("//a[contains(@href, 'chapter/1')]/../following-sibling::h3");
+		int? year = int.Parse(firstChapterNode?.InnerText.Split(' ')[^1] ?? "2000");
+		
+		Manga manga = new (sortName, authors, description, altTitles, tags, coverUrl, coverFileNameInCache, links,
+			year, originalLanguage, publicationId, releaseStatus, websiteUrl);
+		AddMangaToCache(manga);
+		return manga;
+	}
+
+	public override Chapter[] GetChapters(Manga manga, string language="en")
+	{
+		Log($"Getting chapters {manga}");
+		string requestUrl = $"https://asuracomic.net/series/{manga.publicationId}";
+		// Leaving this in for verification if the page exists
+		RequestResult requestResult =
+			downloadClient.MakeRequest(requestUrl, RequestType.Default);
+		if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+			return Array.Empty<Chapter>();
+
+		//Return Chapters ordered by Chapter-Number
+		List<Chapter> chapters = ParseChaptersFromHtml(manga, requestUrl);
+		Log($"Got {chapters.Count} chapters. {manga}");
+		return chapters.Order().ToArray();
+	}
+
+	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();
+
+		HtmlNodeCollection chapterURLNodes = result.htmlDocument.DocumentNode.SelectNodes("//a[contains(@href, '/chapter/')]");
+		Regex infoRex = new(@"Chapter ([0-9]+)(.*)?");
+
+		foreach (HtmlNode chapterInfo in chapterURLNodes)
+		{
+			string chapterUrl = chapterInfo.GetAttributeValue("href", "");
+
+			Match match = infoRex.Match(chapterInfo.InnerText);
+			string chapterNumber = match.Groups[1].Value;
+			string? chapterName = match.Groups[2].Success && match.Groups[2].Length > 1 ? match.Groups[2].Value : null;
+			string url = $"https://asuracomic.net/series/{chapterUrl}";
+			ret.Add(new Chapter(manga, chapterName, null, chapterNumber, url));
+		}
+		
+		return ret;
+	}
+
+	public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null)
+	{
+		if (progressToken?.cancellationRequested ?? false)
+		{
+			progressToken.Cancel();
+			return HttpStatusCode.RequestTimeout;
+		}
+
+		Manga chapterParentManga = chapter.parentManga;
+		Log($"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);
+	}
+
+	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>();
+		}
+
+		HtmlNodeCollection images =
+			requestResult.htmlDocument.DocumentNode.SelectNodes("//img[contains(@alt, 'chapter page')]");
+
+		return images.Select(i => i.GetAttributeValue("src", "")).ToArray();
+	}
+}

Tranga/MangaConnectors/MangaConnector.cs

@@ -281,7 +281,9 @@ public abstract class MangaConnector : GlobalBase
             File.SetUnixFileMode(saveArchiveFilePath, UserRead | UserWrite | UserExecute | GroupRead | GroupWrite | GroupExecute | OtherRead | OtherExecute);
         Directory.Delete(tempFolder, true); //Cleanup
         
+        Log("Created archive.");
         progressToken?.Complete();
+        Log("Download complete.");
         return HttpStatusCode.OK;
     }
     

Tranga/MangaConnectors/MangaConnectorJsonConverter.cs

@@ -38,6 +38,7 @@ public class MangaConnectorJsonConverter : JsonConverter
             "Manga4Life" => this._connectors.First(c => c is MangaLife),
             "ManhuaPlus" => this._connectors.First(c => c is ManhuaPlus),
             "MangaHere" => this._connectors.First(c => c is MangaHere),
+            "AsuraToon" => this._connectors.First(c => c is AsuraToon),
             _ => throw new UnreachableException($"Could not find Connector with name {connectorName}")
         };
     }

Tranga/MangaConnectors/Manganato.cs

@@ -130,13 +130,13 @@ public class Manganato : MangaConnector
         
         string pattern = "MMM dd,yyyy HH:mm";
 
-        HtmlNode oldestChapter = document.DocumentNode
+        HtmlNode? oldestChapter = document.DocumentNode
             .SelectNodes("//span[contains(concat(' ',normalize-space(@class),' '),' chapter-time ')]").MaxBy(
                 node => DateTime.ParseExact(node.GetAttributeValue("title", "Dec 31 2400, 23:59"), pattern,
-                    CultureInfo.InvariantCulture).Millisecond)!;
+                    CultureInfo.InvariantCulture).Millisecond);
 
 
-        int year = DateTime.ParseExact(oldestChapter.GetAttributeValue("title", "Dec 31 2400, 23:59"), pattern,
+        int year = DateTime.ParseExact(oldestChapter?.GetAttributeValue("title", "Dec 31 2400, 23:59")??"Dec 31 2400, 23:59", pattern,
             CultureInfo.InvariantCulture).Year;
         
         Manga manga = new (sortName, authors.ToList(), description, altTitles, tags.ToArray(), posterUrl, coverFileNameInCache, links,

Tranga/Tranga.cs

@@ -26,6 +26,7 @@ public partial class Tranga : GlobalBase
             new MangaLife(this),
             new ManhuaPlus(this),
             new MangaHere(this),
+            new AsuraToon(this),
         };
         foreach(DirectoryInfo dir in new DirectoryInfo(Path.GetTempPath()).GetDirectories("trangatemp"))//Cleanup old temp folders
             dir.Delete();