Fix #72 Chapternumber Parsing Bato

Also fixed the faulty url completion.

README.md

@@ -58,6 +58,7 @@ Tranga can download Chapters and Metadata from "Scanlation" sites such as
 - [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)
 - ❓ Open an [issue](https://github.com/C9Glax/tranga/issues)
 
 and trigger an scan with [Komga](https://komga.org/) and [Kavita](https://www.kavitareader.com/).  

Tranga/MangaConnectors/Bato.cs

@@ -127,26 +127,29 @@ public class Bato : MangaConnector
 
 	private List<Chapter> ParseChaptersFromHtml(Manga manga, string mangaUrl)
 	{
-		// Using HtmlWeb will include the chapters since they are loaded with js 
+		DownloadClient.RequestResult result = downloadClient.MakeRequest(mangaUrl, 1);
-		HtmlWeb web = new();
+		if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
-		HtmlDocument document = web.Load(mangaUrl);
+		{
+			Log("Failed to load site");
+			return new List<Chapter>();
+		}
 
 		List<Chapter> ret = new();
 
 		HtmlNode chapterList =
-			document.DocumentNode.SelectSingleNode("/html/body/div/main/div[3]/astro-island/div/div[2]/div/div/astro-slot");
+			result.htmlDocument.DocumentNode.SelectSingleNode("/html/body/div/main/div[3]/astro-island/div/div[2]/div/div/astro-slot");
 
-		Regex chapterNumberRex = new(@"Chapter ([0-9\.]+)");
+		Regex chapterNumberRex = new(@"\/title\/.+\/[0-9]+-ch_([0-9\.]+)");
 
 		foreach (HtmlNode chapterInfo in chapterList.SelectNodes("div"))
 		{
 			HtmlNode infoNode = chapterInfo.FirstChild.FirstChild;
-			string fullString = infoNode.InnerText;
+			string chapterUrl = infoNode.GetAttributeValue("href", "");
 
 			string? volumeNumber = null;
-			string chapterNumber = chapterNumberRex.Match(fullString).Groups[1].Value;
+			string chapterNumber = chapterNumberRex.Match(chapterUrl).Groups[1].Value;
 			string chapterName = chapterNumber;
-			string url = $"https://bato.to{infoNode.GetAttributeValue("href", "")}?load=2";
+			string url = $"https://bato.to{chapterUrl}?load=2";
 			ret.Add(new Chapter(manga, chapterName, volumeNumber, chapterNumber, url));
 		}
 		

Tranga/MangaConnectors/ChromiumDownloadClient.cs

@@ -62,7 +62,7 @@ internal class ChromiumDownloadClient : DownloadClient
     {
         IPage page = this.browser.NewPageAsync().Result;
         page.DefaultTimeout = 10000;
-        IResponse response = page.GoToAsync(url, WaitUntilNavigation.DOMContentLoaded).Result;
+        IResponse response = page.GoToAsync(url, WaitUntilNavigation.Networkidle0).Result;
         Log("Page loaded.");
 
         Stream stream = Stream.Null;

Tranga/MangaConnectors/MangaConnectorJsonConverter.cs

@@ -36,6 +36,8 @@ public class MangaConnectorJsonConverter : JsonConverter
                 return this._connectors.First(c => c is Mangaworld);
             case "Bato":
                 return this._connectors.First(c => c is Bato);
+            case "Manga4Life":
+                return this._connectors.First(c => c is MangaLife);
         }
 
         throw new Exception();

Tranga/MangaConnectors/MangaKatana.cs

@@ -167,15 +167,20 @@ public class MangaKatana : MangaConnector
 
 		HtmlNode chapterList = document.DocumentNode.SelectSingleNode("//div[contains(@class, 'chapters')]/table/tbody");
 
+		Regex volumeRex = new(@"Volume ([0-9]+)");
+		Regex chapterNumRex = new(@"https:\/\/mangakatana\.com\/manga\/.+\/c([0-9\.]+)");
+		Regex chapterNameRex = new(@"Chapter [0-9\.]+: (.*)");
+		
+
 		foreach (HtmlNode chapterInfo in chapterList.Descendants("tr"))
 		{
 			string fullString = chapterInfo.Descendants("a").First().InnerText;
-
-			string? volumeNumber = fullString.Contains("Vol.") ? fullString.Replace("Vol.", "").Split(' ')[0] : null;
-			string chapterNumber = fullString.Split(':')[0].Split("Chapter ")[1].Split(" ")[0].Replace('-', '.');
-			string chapterName = string.Concat(fullString.Split(':')[1..]);
 			string url = chapterInfo.Descendants("a").First()
 				.GetAttributeValue("href", "");
+
+			string? volumeNumber = volumeRex.IsMatch(fullString) ? volumeRex.Match(fullString).Groups[1].Value : null;
+			string chapterNumber = chapterNumRex.Match(url).Groups[1].Value;
+			string chapterName = chapterNameRex.Match(fullString).Groups[1].Value;
 			ret.Add(new Chapter(manga, chapterName, volumeNumber, chapterNumber, url));
 		}
 		

Tranga/MangaConnectors/MangaLife.cs

@@ -0,0 +1,184 @@
+using System.Net;
+using System.Text.RegularExpressions;
+using HtmlAgilityPack;
+using Tranga.Jobs;
+
+namespace Tranga.MangaConnectors;
+
+public class MangaLife : MangaConnector
+{
+    public MangaLife(GlobalBase clone) : base(clone, "Manga4Life")
+    {
+        this.downloadClient = new ChromiumDownloadClient(clone, new Dictionary<byte, int>()
+        {
+            { 1, 60 }
+        });
+    }
+
+    public override Manga[] GetManga(string publicationTitle = "")
+    {
+        Log($"Searching Publications. Term=\"{publicationTitle}\"");
+        string sanitizedTitle = WebUtility.UrlEncode(publicationTitle);
+        string requestUrl = $"https://manga4life.com/search/?name={sanitizedTitle}";
+        DownloadClient.RequestResult requestResult =
+            downloadClient.MakeRequest(requestUrl, 1);
+        if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
+            return Array.Empty<Manga>();
+
+        if (requestResult.htmlDocument is null)
+            return Array.Empty<Manga>();
+        Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
+        Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\"");
+        return publications;
+    }
+
+    public override Manga? GetMangaFromUrl(string url)
+    {
+        Regex publicationIdRex = new(@"https:\/\/manga4life.com\/manga\/(.*)(\/.*)*");
+        string publicationId = publicationIdRex.Match(url).Groups[1].Value;
+
+        DownloadClient.RequestResult requestResult = this.downloadClient.MakeRequest(url, 1);
+        if(requestResult.htmlDocument is not null)
+            return ParseSinglePublicationFromHtml(requestResult.htmlDocument, publicationId);
+        return null;
+    }
+
+    private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
+    {
+        HtmlNode resultsNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']/div[last()]/div[1]/div");
+        if (resultsNode.Descendants("div").Count() == 1 && resultsNode.Descendants("div").First().HasClass("NoResults"))
+        {
+            Log("No results.");
+            return Array.Empty<Manga>();
+        }
+        Log($"{resultsNode.SelectNodes("div").Count} items.");
+
+        HashSet<Manga> ret = new();
+
+        foreach (HtmlNode resultNode in resultsNode.SelectNodes("div"))
+        {
+            string url = resultNode.Descendants().First(d => d.HasClass("SeriesName")).GetAttributeValue("href", "");
+            Manga? manga = GetMangaFromUrl($"https://manga4life.com{url}");
+            if (manga is not null)
+                ret.Add((Manga)manga);
+        }
+        
+        return ret.ToArray();
+    }
+
+
+    private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId)
+    {
+        string originalLanguage = "", status = "";
+        Dictionary<string, string> altTitles = new(), links = new();
+        HashSet<string> tags = new();
+
+        HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']//div[@class='row']//img");
+        string posterUrl = posterNode.GetAttributeValue("src", "");
+        string coverFileNameInCache = SaveCoverImageToCache(posterUrl, 1);
+
+        HtmlNode titleNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']//div[@class='row']//h1");
+        string sortName = titleNode.InnerText;
+
+        HtmlNode[] authorsNodes = document.DocumentNode
+            .SelectNodes("//div[@class='BoxBody']//div[@class='row']//span[text()='Author(s):']/..").Descendants("a")
+            .ToArray();
+        List<string> authors = new();
+        foreach (HtmlNode authorNode in authorsNodes)
+            authors.Add(authorNode.InnerText);
+
+        HtmlNode[] genreNodes = document.DocumentNode
+            .SelectNodes("//div[@class='BoxBody']//div[@class='row']//span[text()='Genre(s):']/..").Descendants("a")
+            .ToArray();
+        foreach (HtmlNode genreNode in genreNodes)
+            tags.Add(genreNode.InnerText);
+
+        HtmlNode yearNode = document.DocumentNode
+            .SelectNodes("//div[@class='BoxBody']//div[@class='row']//span[text()='Released:']/..").Descendants("a")
+            .First();
+        int year = Convert.ToInt32(yearNode.InnerText);
+
+        HtmlNode[] statusNodes = document.DocumentNode
+            .SelectNodes("//div[@class='BoxBody']//div[@class='row']//span[text()='Status:']/..").Descendants("a")
+            .ToArray();
+        foreach (HtmlNode statusNode in statusNodes)
+            if (statusNode.InnerText.Contains("publish", StringComparison.CurrentCultureIgnoreCase))
+                status = statusNode.InnerText.Split(' ')[0];
+
+        HtmlNode descriptionNode = document.DocumentNode
+            .SelectNodes("//div[@class='BoxBody']//div[@class='row']//span[text()='Description:']/..")
+            .Descendants("div").First();
+        string description = descriptionNode.InnerText;
+
+        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($"Getting chapters {manga}");
+        DownloadClient.RequestResult result = downloadClient.MakeRequest($"https://manga4life.com/manga/{manga.publicationId}", 1);
+        if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
+        {
+            return Array.Empty<Chapter>();
+        }
+        
+        HtmlNodeCollection chapterNodes = result.htmlDocument.DocumentNode.SelectNodes(
+            "//a[contains(concat(' ',normalize-space(@class),' '),' ChapterLink ')]");
+        string[] urls = chapterNodes.Select(node => node.GetAttributeValue("href", "")).ToArray();
+        
+        List<Chapter> chapters = new();
+        foreach (string url in urls)
+        {
+            string volumeNumber = "1";
+            string chapterNumber = Regex.Match(url, @"-chapter-([0-9\.]+)").Groups[1].ToString();
+            string fullUrl = $"https://manga4life.com{url}";
+            fullUrl = fullUrl.Replace(Regex.Match(url,"(-page-[0-9])").Value,"");
+            chapters.Add(new Chapter(manga, "", volumeNumber, chapterNumber, fullUrl));
+        }
+        //Return Chapters ordered by Chapter-Number
+        Log($"Got {chapters.Count} chapters. {manga}");
+        return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, numberFormatDecimalPoint)).ToArray();
+    }
+
+    public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null)
+    {
+        if (progressToken?.cancellationRequested ?? false)
+        {
+            progressToken.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        Manga chapterParentManga = chapter.parentManga;
+        if (progressToken?.cancellationRequested ?? false)
+        {
+            progressToken.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        Log($"Retrieving chapter-info {chapter} {chapterParentManga}");
+
+        DownloadClient.RequestResult requestResult = this.downloadClient.MakeRequest(chapter.url, 1);
+        if (requestResult.htmlDocument is null)
+        {
+            progressToken?.Cancel();
+            return HttpStatusCode.RequestTimeout;
+        }
+
+        HtmlDocument document = requestResult.htmlDocument;
+        
+        HtmlNode gallery = document.DocumentNode.Descendants("div").First(div => div.HasClass("ImageGallery"));
+        HtmlNode[] images = gallery.Descendants("img").Where(img => img.HasClass("img-fluid")).ToArray();
+        List<string> urls = new();
+        foreach(HtmlNode galleryImage in images)
+            urls.Add(galleryImage.GetAttributeValue("src", ""));
+            
+        string comicInfoPath = Path.GetTempFileName();
+        File.WriteAllText(comicInfoPath, chapter.GetComicInfoXmlString());
+        
+        return DownloadChapterImages(urls.ToArray(), chapter.GetArchiveFilePath(settings.downloadLocation), 1, comicInfoPath, progressToken:progressToken);
+    }
+}

Tranga/Tranga.cs

@@ -23,7 +23,8 @@ public partial class Tranga : GlobalBase
             new MangaDex(this),
             new MangaKatana(this),
             new Mangaworld(this),
-            new Bato(this)
+            new Bato(this),
+            new MangaLife(this)
         };
         jobBoss = new(this, this._connectors);
         StartJobBoss();