mirror of
https://github.com/C9Glax/tranga.git
synced 2025-05-07 15:42:10 +02:00
Compare commits
23 Commits
d0b775444d
...
e6d40a7b36
Author | SHA1 | Date | |
---|---|---|---|
e6d40a7b36 | |||
a95cb90561 | |||
603e1b41d9 | |||
bb8a514830 | |||
edacaaba8a | |||
d97da26994 | |||
8b923d73c4 | |||
814efd3528 | |||
2cd5d8bc4f | |||
5a864ab9b7 | |||
![]() |
7f13d9b1e6 | ||
![]() |
0c9e3205c2 | ||
4f7031ecfc | |||
![]() |
f7a285aabd | ||
786482398c | |||
![]() |
7921dcb1cb | ||
280d715a7c | |||
b4edcccafe | |||
1701881f4b | |||
e5be5703f8 | |||
ce217aae4f | |||
3abf7224d0 | |||
![]() |
b39dbd5671 |
@ -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/).
|
||||
|
@ -167,9 +167,10 @@ public class JobBoss : GlobalBase
|
||||
Log($"Adding Job {job}");
|
||||
if (!AddJob(job, file.FullName)) //If we detect a duplicate, delete the file.
|
||||
{
|
||||
string path = string.Concat(file.FullName, ".duplicate");
|
||||
file.MoveTo(path);
|
||||
Log($"Duplicate detected or otherwise not able to add job to list.\nMoved job {job} to {path}");
|
||||
//string path = string.Concat(file.FullName, ".duplicate");
|
||||
//file.MoveTo(path);
|
||||
//Log($"Duplicate detected or otherwise not able to add job to list.\nMoved job {job} to {path}");
|
||||
Log($"Duplicate detected or otherwise not able to add job to list. Removed the file {file.FullName} {job}");
|
||||
}
|
||||
}
|
||||
catch (Exception e)
|
||||
|
@ -73,6 +73,7 @@ internal class ChromiumDownloadClient : DownloadClient
|
||||
return new RequestResult(HttpStatusCode.InternalServerError, null, Stream.Null);
|
||||
IPage page = _browser.NewPageAsync().Result;
|
||||
page.DefaultTimeout = TrangaSettings.ChromiumPageTimeoutMs;
|
||||
page.SetExtraHttpHeadersAsync(new() { { "Referer", referrer } });
|
||||
IResponse response;
|
||||
try
|
||||
{
|
||||
|
@ -60,7 +60,7 @@ public abstract class MangaConnector : GlobalBase
|
||||
return Array.Empty<Chapter>();
|
||||
|
||||
Log($"Checking for duplicates {manga}");
|
||||
List<Chapter> newChaptersList = allChapters.Where(nChapter => nChapter.chapterNumber > manga.ignoreChaptersBelow
|
||||
List<Chapter> newChaptersList = allChapters.Where(nChapter => nChapter.chapterNumber >= manga.ignoreChaptersBelow
|
||||
&& !nChapter.CheckChapterIsDownloaded()).ToList();
|
||||
Log($"{newChaptersList.Count} new chapters. {manga}");
|
||||
try
|
||||
@ -213,7 +213,7 @@ public abstract class MangaConnector : GlobalBase
|
||||
return HttpStatusCode.OK;
|
||||
}
|
||||
|
||||
protected string SaveCoverImageToCache(string url, string mangaInternalId, RequestType requestType)
|
||||
protected string SaveCoverImageToCache(string url, string mangaInternalId, RequestType requestType, string? referrer = null)
|
||||
{
|
||||
Regex urlRex = new (@"https?:\/\/((?:[a-zA-Z0-9-]+\.)+[a-zA-Z0-9]+)\/(?:.+\/)*(.+\.([a-zA-Z]+))");
|
||||
//https?:\/\/[a-zA-Z0-9-]+\.([a-zA-Z0-9-]+\.[a-zA-Z0-9]+)\/(?:.+\/)*(.+\.([a-zA-Z]+)) for only second level domains
|
||||
@ -224,7 +224,7 @@ public abstract class MangaConnector : GlobalBase
|
||||
if (File.Exists(saveImagePath))
|
||||
return saveImagePath;
|
||||
|
||||
RequestResult coverResult = downloadClient.MakeRequest(url, requestType);
|
||||
RequestResult coverResult = downloadClient.MakeRequest(url, requestType, referrer);
|
||||
using MemoryStream ms = new();
|
||||
coverResult.result.CopyTo(ms);
|
||||
Directory.CreateDirectory(TrangaSettings.coverImageCache);
|
||||
|
@ -34,11 +34,11 @@ public class MangaConnectorJsonConverter : JsonConverter
|
||||
"MangaKatana" => this._connectors.First(c => c is MangaKatana),
|
||||
"Mangaworld" => this._connectors.First(c => c is Mangaworld),
|
||||
"Bato" => this._connectors.First(c => c is Bato),
|
||||
"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),
|
||||
"Weebcentral" => this._connectors.First(c => c is Weebcentral),
|
||||
"Webtoons" => this._connectors.First(c => c is Webtoons),
|
||||
_ => throw new UnreachableException($"Could not find Connector with name {connectorName}")
|
||||
};
|
||||
}
|
||||
|
@ -1,206 +0,0 @@
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using HtmlAgilityPack;
|
||||
using Tranga.Jobs;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
public class MangaLife : MangaConnector
|
||||
{
|
||||
public MangaLife(GlobalBase clone) : base(clone, "Manga4Life", ["en"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient(clone);
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
Log($"Searching Publications. Term=\"{publicationTitle}\"");
|
||||
string sanitizedTitle = WebUtility.UrlEncode(publicationTitle);
|
||||
string requestUrl = $"https://manga4life.com/search/?name={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return Array.Empty<Manga>();
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
Log($"Retrieved {publications.Length} publications. Term=\"{publicationTitle}\"");
|
||||
return publications;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://manga4life.com/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
Regex publicationIdRex = new(@"https:\/\/(www\.)?manga4life.com\/manga\/(.*)(\/.*)*");
|
||||
string publicationId = publicationIdRex.Match(url).Groups[2].Value;
|
||||
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if(requestResult.htmlDocument is not null)
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, publicationId, url);
|
||||
return null;
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
HtmlNode resultsNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']/div[last()]/div[1]/div");
|
||||
if (resultsNode.Descendants("div").Count() == 1 && resultsNode.Descendants("div").First().HasClass("NoResults"))
|
||||
{
|
||||
Log("No results.");
|
||||
return Array.Empty<Manga>();
|
||||
}
|
||||
Log($"{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 websiteUrl)
|
||||
{
|
||||
string originalLanguage = "", status = "";
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
HashSet<string> tags = new();
|
||||
Manga.ReleaseStatusByte releaseStatus = Manga.ReleaseStatusByte.Unreleased;
|
||||
|
||||
HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']//div[@class='row']//img");
|
||||
string posterUrl = posterNode.GetAttributeValue("src", "");
|
||||
string coverFileNameInCache = SaveCoverImageToCache(posterUrl, publicationId, RequestType.MangaCover);
|
||||
|
||||
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];
|
||||
switch (status.ToLower())
|
||||
{
|
||||
case "cancelled": releaseStatus = Manga.ReleaseStatusByte.Cancelled; break;
|
||||
case "hiatus": releaseStatus = Manga.ReleaseStatusByte.OnHiatus; break;
|
||||
case "discontinued": releaseStatus = Manga.ReleaseStatusByte.Cancelled; break;
|
||||
case "complete": releaseStatus = Manga.ReleaseStatusByte.Completed; break;
|
||||
case "ongoing": releaseStatus = Manga.ReleaseStatusByte.Continuing; break;
|
||||
}
|
||||
|
||||
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, publicationId, releaseStatus, websiteUrl: websiteUrl);
|
||||
AddMangaToCache(manga);
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
Log($"Getting chapters {manga}");
|
||||
RequestResult result = downloadClient.MakeRequest($"https://manga4life.com/manga/{manga.publicationId}", RequestType.Default, clickButton:"[class*='ShowAllChapters']");
|
||||
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();
|
||||
Regex urlRex = new (@"-chapter-([0-9\\.]+)(-index-([0-9\\.]+))?");
|
||||
|
||||
List<Chapter> chapters = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Match rexMatch = urlRex.Match(url);
|
||||
|
||||
string volumeNumber = "1";
|
||||
if (rexMatch.Groups[3].Value.Length > 0)
|
||||
volumeNumber = rexMatch.Groups[3].Value;
|
||||
string chapterNumber = rexMatch.Groups[1].Value;
|
||||
string fullUrl = $"https://manga4life.com{url}";
|
||||
fullUrl = fullUrl.Replace(Regex.Match(url,"(-page-[0-9])").Value,"");
|
||||
try
|
||||
{
|
||||
chapters.Add(new Chapter(manga, "", volumeNumber, chapterNumber, fullUrl));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
Log($"Failed to load chapter {chapterNumber}: {e.Message}");
|
||||
}
|
||||
}
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
Log($"Got {chapters.Count} chapters. {manga}");
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
public override HttpStatusCode DownloadChapter(Chapter chapter, ProgressToken? progressToken = null)
|
||||
{
|
||||
if (progressToken?.cancellationRequested ?? false)
|
||||
{
|
||||
progressToken.Cancel();
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
}
|
||||
|
||||
Manga chapterParentManga = chapter.parentManga;
|
||||
if (progressToken?.cancellationRequested ?? false)
|
||||
{
|
||||
progressToken.Cancel();
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
}
|
||||
|
||||
Log($"Retrieving chapter-info {chapter} {chapterParentManga}");
|
||||
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(chapter.url, RequestType.Default);
|
||||
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, RequestType.MangaImage, progressToken:progressToken);
|
||||
}
|
||||
}
|
272
Tranga/MangaConnectors/Webtoons.cs
Normal file
272
Tranga/MangaConnectors/Webtoons.cs
Normal file
@ -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 $"{this.Title}|{this.Category}|{this.Id}";
|
||||
}
|
||||
|
||||
public string Title { get; set; }
|
||||
public string Category { get; set; }
|
||||
public string Id { get; set; }
|
||||
}
|
@ -43,7 +43,7 @@ public class Weebcentral : MangaConnector
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
if (document.DocumentNode.SelectNodes("//article") == null)
|
||||
return Array.Empty<Manga>();
|
||||
return [];
|
||||
|
||||
var urls = document.DocumentNode.SelectNodes("/html/body/article/a[@class='link link-hover']")
|
||||
.Select(elem => elem.GetAttributeValue("href", "")).ToList();
|
||||
@ -127,33 +127,6 @@ public class Weebcentral : MangaConnector
|
||||
return GetMangaFromUrl($"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($"Getting chapters {manga}");
|
||||
@ -161,11 +134,11 @@ public class Weebcentral : MangaConnector
|
||||
var requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Chapter>();
|
||||
return [];
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
if (requestResult.htmlDocument is null)
|
||||
return Array.Empty<Chapter>();
|
||||
return [];
|
||||
var chapters = ParseChaptersFromHtml(manga, requestResult.htmlDocument);
|
||||
Log($"Got {chapters.Count} chapters. {manga}");
|
||||
return chapters.Order().ToArray();
|
||||
@ -175,7 +148,7 @@ public class Weebcentral : MangaConnector
|
||||
{
|
||||
var chaptersWrapper = document.DocumentNode.SelectSingleNode("/html/body");
|
||||
|
||||
Regex chapterRex = new(@".* (\d+)");
|
||||
Regex chapterRex = new(@"(\d+(?:\.\d+)*)");
|
||||
Regex idRex = new(@"https:\/\/weebcentral\.com\/chapters\/(\w*)");
|
||||
|
||||
var ret = chaptersWrapper.Descendants("a").Select(elem =>
|
||||
@ -233,11 +206,4 @@ public class Weebcentral : MangaConnector
|
||||
|
||||
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; }
|
||||
}
|
||||
}
|
@ -22,11 +22,11 @@ public partial class Tranga : GlobalBase
|
||||
new MangaKatana(this),
|
||||
new Mangaworld(this),
|
||||
new Bato(this),
|
||||
new MangaLife(this),
|
||||
new ManhuaPlus(this),
|
||||
new MangaHere(this),
|
||||
new AsuraToon(this),
|
||||
new Weebcentral(this)
|
||||
new Weebcentral(this),
|
||||
new Webtoons(this),
|
||||
};
|
||||
foreach(DirectoryInfo dir in new DirectoryInfo(Path.GetTempPath()).GetDirectories("trangatemp"))//Cleanup old temp folders
|
||||
dir.Delete();
|
||||
|
@ -10,9 +10,9 @@
|
||||
|
||||
<ItemGroup>
|
||||
<PackageReference Include="GlaxArguments" Version="1.1.0" />
|
||||
<PackageReference Include="HtmlAgilityPack" Version="1.11.71" />
|
||||
<PackageReference Include="HtmlAgilityPack" Version="1.11.72" />
|
||||
<PackageReference Include="Newtonsoft.Json" Version="13.0.3" />
|
||||
<PackageReference Include="PuppeteerSharp" Version="20.0.5" />
|
||||
<PackageReference Include="PuppeteerSharp" Version="20.1.0" />
|
||||
<PackageReference Include="Soenneker.Utils.String.NeedlemanWunsch" Version="2.1.301" />
|
||||
</ItemGroup>
|
||||
|
||||
|
Loading…
x
Reference in New Issue
Block a user