mirror of
https://github.com/C9Glax/tranga.git
synced 2025-07-07 03:14:17 +02:00
Rename Connectors -> MangaConnectors
This commit is contained in:
256
Tranga/MangaConnectors/Connector.cs
Normal file
256
Tranga/MangaConnectors/Connector.cs
Normal file
@ -0,0 +1,256 @@
|
||||
using System.Globalization;
|
||||
using System.IO.Compression;
|
||||
using System.Net;
|
||||
using System.Runtime.InteropServices;
|
||||
using System.Text.RegularExpressions;
|
||||
using static System.IO.UnixFileMode;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
/// <summary>
|
||||
/// Base-Class for all Connectors
|
||||
/// Provides some methods to be used by all Connectors, as well as a DownloadClient
|
||||
/// </summary>
|
||||
public abstract class Connector : TBaseObject
|
||||
{
|
||||
internal DownloadClient downloadClient { get; init; } = null!;
|
||||
|
||||
protected Connector(TBaseObject clone) : base(clone)
|
||||
{
|
||||
if (!Directory.Exists(settings.coverImageCache))
|
||||
Directory.CreateDirectory(settings.coverImageCache);
|
||||
}
|
||||
|
||||
public abstract string name { get; } //Name of the Connector (e.g. Website)
|
||||
|
||||
/// <summary>
|
||||
/// Returns all Publications with the given string.
|
||||
/// If the string is empty or null, returns all Publication of the Connector
|
||||
/// </summary>
|
||||
/// <param name="publicationTitle">Search-Query</param>
|
||||
/// <returns>Publications matching the query</returns>
|
||||
protected abstract Publication[] GetPublications(string publicationTitle = "");
|
||||
|
||||
/// <summary>
|
||||
/// Returns all Chapters of the publication in the provided language.
|
||||
/// If the language is empty or null, returns all Chapters in all Languages.
|
||||
/// </summary>
|
||||
/// <param name="publication">Publication to get Chapters for</param>
|
||||
/// <param name="language">Language of the Chapters</param>
|
||||
/// <returns>Array of Chapters matching Publication and Language</returns>
|
||||
public abstract Chapter[] GetChapters(Publication publication, string language = "");
|
||||
|
||||
/// <summary>
|
||||
/// Updates the available Chapters of a Publication
|
||||
/// </summary>
|
||||
/// <param name="publication">Publication to check</param>
|
||||
/// <param name="language">Language to receive chapters for</param>
|
||||
/// <param name="collection"></param>
|
||||
/// <returns>List of Chapters that were previously not in collection</returns>
|
||||
public List<Chapter> GetNewChaptersList(Publication publication, string language, ref HashSet<Publication> collection)
|
||||
{
|
||||
Log($"Getting new Chapters for {publication}");
|
||||
Chapter[] newChapters = this.GetChapters(publication, language);
|
||||
collection.Add(publication);
|
||||
NumberFormatInfo decimalPoint = new (){ NumberDecimalSeparator = "." };
|
||||
Log($"Checking for duplicates {publication}");
|
||||
List<Chapter> newChaptersList = newChapters.Where(nChapter =>
|
||||
float.Parse(nChapter.chapterNumber, decimalPoint) > publication.ignoreChaptersBelow &&
|
||||
!nChapter.CheckChapterIsDownloaded(settings.downloadLocation)).ToList();
|
||||
Log($"{newChaptersList.Count} new chapters. {publication}");
|
||||
|
||||
return newChaptersList;
|
||||
}
|
||||
|
||||
public Chapter[] SelectChapters(Publication publication, string searchTerm, string? language = null)
|
||||
{
|
||||
Chapter[] availableChapters = this.GetChapters(publication, language??"en");
|
||||
Regex volumeRegex = new ("((v(ol)*(olume)*){1} *([0-9]+(-[0-9]+)?){1})", RegexOptions.IgnoreCase);
|
||||
Regex chapterRegex = new ("((c(h)*(hapter)*){1} *([0-9]+(-[0-9]+)?){1})", RegexOptions.IgnoreCase);
|
||||
Regex singleResultRegex = new("([0-9]+)", RegexOptions.IgnoreCase);
|
||||
Regex rangeResultRegex = new("([0-9]+(-[0-9]+))", RegexOptions.IgnoreCase);
|
||||
Regex allRegex = new("a(ll)?", RegexOptions.IgnoreCase);
|
||||
if (volumeRegex.IsMatch(searchTerm) && chapterRegex.IsMatch(searchTerm))
|
||||
{
|
||||
string volume = singleResultRegex.Match(volumeRegex.Match(searchTerm).Value).Value;
|
||||
string chapter = singleResultRegex.Match(chapterRegex.Match(searchTerm).Value).Value;
|
||||
return availableChapters.Where(aCh => aCh.volumeNumber is not null &&
|
||||
aCh.volumeNumber.Equals(volume, StringComparison.InvariantCultureIgnoreCase) &&
|
||||
aCh.chapterNumber.Equals(chapter, StringComparison.InvariantCultureIgnoreCase))
|
||||
.ToArray();
|
||||
}
|
||||
else if (volumeRegex.IsMatch(searchTerm))
|
||||
{
|
||||
string volume = volumeRegex.Match(searchTerm).Value;
|
||||
if (rangeResultRegex.IsMatch(volume))
|
||||
{
|
||||
string range = rangeResultRegex.Match(volume).Value;
|
||||
int start = Convert.ToInt32(range.Split('-')[0]);
|
||||
int end = Convert.ToInt32(range.Split('-')[1]);
|
||||
return availableChapters.Where(aCh => aCh.volumeNumber is not null &&
|
||||
Convert.ToInt32(aCh.volumeNumber) >= start &&
|
||||
Convert.ToInt32(aCh.volumeNumber) <= end).ToArray();
|
||||
}
|
||||
else if (singleResultRegex.IsMatch(volume))
|
||||
{
|
||||
string volumeNumber = singleResultRegex.Match(volume).Value;
|
||||
return availableChapters.Where(aCh =>
|
||||
aCh.volumeNumber is not null &&
|
||||
aCh.volumeNumber.Equals(volumeNumber, StringComparison.InvariantCultureIgnoreCase)).ToArray();
|
||||
}
|
||||
|
||||
}
|
||||
else if (chapterRegex.IsMatch(searchTerm))
|
||||
{
|
||||
string chapter = chapterRegex.Match(searchTerm).Value;
|
||||
if (rangeResultRegex.IsMatch(chapter))
|
||||
{
|
||||
string range = rangeResultRegex.Match(chapter).Value;
|
||||
int start = Convert.ToInt32(range.Split('-')[0]);
|
||||
int end = Convert.ToInt32(range.Split('-')[1]);
|
||||
return availableChapters.Where(aCh => Convert.ToInt32(aCh.chapterNumber) >= start &&
|
||||
Convert.ToInt32(aCh.chapterNumber) <= end).ToArray();
|
||||
}
|
||||
else if (singleResultRegex.IsMatch(chapter))
|
||||
{
|
||||
string chapterNumber = singleResultRegex.Match(chapter).Value;
|
||||
return availableChapters.Where(aCh =>
|
||||
aCh.chapterNumber.Equals(chapterNumber, StringComparison.InvariantCultureIgnoreCase)).ToArray();
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
if (rangeResultRegex.IsMatch(searchTerm))
|
||||
{
|
||||
int start = Convert.ToInt32(searchTerm.Split('-')[0]);
|
||||
int end = Convert.ToInt32(searchTerm.Split('-')[1]);
|
||||
return availableChapters[start..(end + 1)];
|
||||
}
|
||||
else if(singleResultRegex.IsMatch(searchTerm))
|
||||
return new [] { availableChapters[Convert.ToInt32(searchTerm)] };
|
||||
else if (allRegex.IsMatch(searchTerm))
|
||||
return availableChapters;
|
||||
}
|
||||
|
||||
return Array.Empty<Chapter>();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Retrieves the Chapter (+Images) from the website.
|
||||
/// Should later call DownloadChapterImages to retrieve the individual Images of the Chapter and create .cbz archive.
|
||||
/// </summary>
|
||||
/// <param name="publication">Publication that contains Chapter</param>
|
||||
/// <param name="chapter">Chapter with Images to retrieve</param>
|
||||
/// <param name="cancellationToken"></param>
|
||||
public abstract HttpStatusCode DownloadChapter(Publication publication, Chapter chapter, CancellationToken? cancellationToken = null);
|
||||
|
||||
/// <summary>
|
||||
/// Copies the already downloaded cover from cache to downloadLocation
|
||||
/// </summary>
|
||||
/// <param name="publication">Publication to retrieve Cover for</param>
|
||||
public void CopyCoverFromCacheToDownloadLocation(Publication publication)
|
||||
{
|
||||
Log($"Copy cover {publication}");
|
||||
//Check if Publication already has a Folder and cover
|
||||
string publicationFolder = publication.CreatePublicationFolder(settings.downloadLocation);
|
||||
DirectoryInfo dirInfo = new (publicationFolder);
|
||||
if (dirInfo.EnumerateFiles().Any(info => info.Name.Contains("cover", StringComparison.InvariantCultureIgnoreCase)))
|
||||
{
|
||||
Log($"Cover exists {publication}");
|
||||
return;
|
||||
}
|
||||
|
||||
string fileInCache = Path.Join(settings.coverImageCache, publication.coverFileNameInCache);
|
||||
string newFilePath = Path.Join(publicationFolder, $"cover.{Path.GetFileName(fileInCache).Split('.')[^1]}" );
|
||||
Log($"Cloning cover {fileInCache} -> {newFilePath}");
|
||||
File.Copy(fileInCache, newFilePath, true);
|
||||
if(RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
|
||||
File.SetUnixFileMode(newFilePath, GroupRead | GroupWrite | OtherRead | OtherWrite | UserRead | UserWrite);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Downloads Image from URL and saves it to the given path(incl. fileName)
|
||||
/// </summary>
|
||||
/// <param name="imageUrl"></param>
|
||||
/// <param name="fullPath"></param>
|
||||
/// <param name="requestType">RequestType for Rate-Limit</param>
|
||||
/// <param name="referrer">referrer used in html request header</param>
|
||||
private HttpStatusCode DownloadImage(string imageUrl, string fullPath, byte requestType, string? referrer = null)
|
||||
{
|
||||
DownloadClient.RequestResult requestResult = downloadClient.MakeRequest(imageUrl, requestType, referrer);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.result == Stream.Null)
|
||||
return requestResult.statusCode;
|
||||
byte[] buffer = new byte[requestResult.result.Length];
|
||||
requestResult.result.ReadExactly(buffer, 0, buffer.Length);
|
||||
File.WriteAllBytes(fullPath, buffer);
|
||||
return requestResult.statusCode;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Downloads all Images from URLs, Compresses to zip(cbz) and saves.
|
||||
/// </summary>
|
||||
/// <param name="imageUrls">List of URLs to download Images from</param>
|
||||
/// <param name="saveArchiveFilePath">Full path to save archive to (without file ending .cbz)</param>
|
||||
/// <param name="comicInfoPath">Path of the generate Chapter ComicInfo.xml, if it was generated</param>
|
||||
/// <param name="requestType">RequestType for RateLimits</param>
|
||||
/// <param name="referrer">Used in http request header</param>
|
||||
/// <param name="cancellationToken"></param>
|
||||
protected HttpStatusCode DownloadChapterImages(string[] imageUrls, string saveArchiveFilePath, byte requestType, string? comicInfoPath = null, string? referrer = null, CancellationToken? cancellationToken = null)
|
||||
{
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
Log($"Downloading Images for {saveArchiveFilePath}");
|
||||
//Check if Publication Directory already exists
|
||||
string directoryPath = Path.GetDirectoryName(saveArchiveFilePath)!;
|
||||
if (!Directory.Exists(directoryPath))
|
||||
Directory.CreateDirectory(directoryPath);
|
||||
|
||||
if (File.Exists(saveArchiveFilePath)) //Don't download twice.
|
||||
return HttpStatusCode.OK;
|
||||
|
||||
//Create a temporary folder to store images
|
||||
string tempFolder = Directory.CreateTempSubdirectory().FullName;
|
||||
|
||||
int chapter = 0;
|
||||
//Download all Images to temporary Folder
|
||||
foreach (string imageUrl in imageUrls)
|
||||
{
|
||||
string[] split = imageUrl.Split('.');
|
||||
string extension = split[^1];
|
||||
Log($"Downloading image {chapter + 1:000}/{imageUrls.Length:000}"); //TODO
|
||||
HttpStatusCode status = DownloadImage(imageUrl, Path.Join(tempFolder, $"{chapter++}.{extension}"), requestType, referrer);
|
||||
if ((int)status < 200 || (int)status >= 300)
|
||||
return status;
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
}
|
||||
|
||||
if(comicInfoPath is not null)
|
||||
File.Copy(comicInfoPath, Path.Join(tempFolder, "ComicInfo.xml"));
|
||||
|
||||
Log($"Creating archive {saveArchiveFilePath}");
|
||||
//ZIP-it and ship-it
|
||||
ZipFile.CreateFromDirectory(tempFolder, saveArchiveFilePath);
|
||||
if(RuntimeInformation.IsOSPlatform(OSPlatform.Linux))
|
||||
File.SetUnixFileMode(saveArchiveFilePath, GroupRead | GroupWrite | OtherRead | OtherWrite | UserRead | UserWrite);
|
||||
Directory.Delete(tempFolder, true); //Cleanup
|
||||
return HttpStatusCode.OK;
|
||||
}
|
||||
|
||||
protected string SaveCoverImageToCache(string url, byte requestType)
|
||||
{
|
||||
string[] split = url.Split('/');
|
||||
string filename = split[^1];
|
||||
string saveImagePath = Path.Join(settings.coverImageCache, filename);
|
||||
|
||||
if (File.Exists(saveImagePath))
|
||||
return filename;
|
||||
|
||||
DownloadClient.RequestResult coverResult = downloadClient.MakeRequest(url, requestType);
|
||||
using MemoryStream ms = new();
|
||||
coverResult.result.CopyTo(ms);
|
||||
File.WriteAllBytes(saveImagePath, ms.ToArray());
|
||||
Log($"Saving cover to {saveImagePath}");
|
||||
return filename;
|
||||
}
|
||||
}
|
98
Tranga/MangaConnectors/DownloadClient.cs
Normal file
98
Tranga/MangaConnectors/DownloadClient.cs
Normal file
@ -0,0 +1,98 @@
|
||||
using System.Net;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
internal class DownloadClient : TBaseObject
|
||||
{
|
||||
private static readonly HttpClient Client = new()
|
||||
{
|
||||
Timeout = TimeSpan.FromSeconds(60)
|
||||
};
|
||||
|
||||
private readonly Dictionary<byte, DateTime> _lastExecutedRateLimit;
|
||||
private readonly Dictionary<byte, TimeSpan> _rateLimit;
|
||||
|
||||
public DownloadClient(Dictionary<byte, int> rateLimitRequestsPerMinute, TBaseObject clone) : base(clone)
|
||||
{
|
||||
_lastExecutedRateLimit = new();
|
||||
_rateLimit = new();
|
||||
foreach(KeyValuePair<byte, int> limit in rateLimitRequestsPerMinute)
|
||||
_rateLimit.Add(limit.Key, TimeSpan.FromMinutes(1).Divide(limit.Value));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Request Webpage
|
||||
/// </summary>
|
||||
/// <param name="url"></param>
|
||||
/// <param name="requestType">For RateLimits: Same Endpoints use same type</param>
|
||||
/// <param name="referrer">Used in http request header</param>
|
||||
/// <returns>RequestResult with StatusCode and Stream of received data</returns>
|
||||
public RequestResult MakeRequest(string url, byte requestType, string? referrer = null)
|
||||
{
|
||||
if (_rateLimit.TryGetValue(requestType, out TimeSpan value))
|
||||
_lastExecutedRateLimit.TryAdd(requestType, DateTime.Now.Subtract(value));
|
||||
else
|
||||
{
|
||||
Log("RequestType not configured for rate-limit.");
|
||||
return new RequestResult(HttpStatusCode.NotAcceptable, Stream.Null);
|
||||
}
|
||||
|
||||
TimeSpan rateLimitTimeout = _rateLimit[requestType]
|
||||
.Subtract(DateTime.Now.Subtract(_lastExecutedRateLimit[requestType]));
|
||||
|
||||
if(rateLimitTimeout > TimeSpan.Zero)
|
||||
Thread.Sleep(rateLimitTimeout);
|
||||
|
||||
HttpResponseMessage? response = null;
|
||||
while (response is null)
|
||||
{
|
||||
try
|
||||
{
|
||||
HttpRequestMessage requestMessage = new(HttpMethod.Get, url);
|
||||
if(referrer is not null)
|
||||
requestMessage.Headers.Referrer = new Uri(referrer);
|
||||
_lastExecutedRateLimit[requestType] = DateTime.Now;
|
||||
response = Client.Send(requestMessage);
|
||||
}
|
||||
catch (HttpRequestException e)
|
||||
{
|
||||
Log("Exception:\n\t{0}\n\tWaiting {1} before retrying.", e.Message, _rateLimit[requestType] * 2);
|
||||
Thread.Sleep(_rateLimit[requestType] * 2);
|
||||
}
|
||||
}
|
||||
if (!response.IsSuccessStatusCode)
|
||||
{
|
||||
Log($"Request-Error {response.StatusCode}: {response.ReasonPhrase}");
|
||||
return new RequestResult(response.StatusCode, Stream.Null);
|
||||
}
|
||||
|
||||
// Request has been redirected to another page. For example, it redirects directly to the results when there is only 1 result
|
||||
if(response.RequestMessage is not null && response.RequestMessage.RequestUri is not null)
|
||||
{
|
||||
return new RequestResult(response.StatusCode, response.Content.ReadAsStream(), true, response.RequestMessage.RequestUri.AbsoluteUri);
|
||||
}
|
||||
|
||||
return new RequestResult(response.StatusCode, response.Content.ReadAsStream());
|
||||
}
|
||||
|
||||
public struct RequestResult
|
||||
{
|
||||
public HttpStatusCode statusCode { get; }
|
||||
public Stream result { get; }
|
||||
public bool hasBeenRedirected { get; }
|
||||
public string? redirectedToUrl { get; }
|
||||
|
||||
public RequestResult(HttpStatusCode statusCode, Stream result)
|
||||
{
|
||||
this.statusCode = statusCode;
|
||||
this.result = result;
|
||||
}
|
||||
|
||||
public RequestResult(HttpStatusCode statusCode, Stream result, bool hasBeenRedirected, string redirectedTo)
|
||||
: this(statusCode, result)
|
||||
{
|
||||
this.hasBeenRedirected = hasBeenRedirected;
|
||||
redirectedToUrl = redirectedTo;
|
||||
}
|
||||
}
|
||||
}
|
280
Tranga/MangaConnectors/MangaDex.cs
Normal file
280
Tranga/MangaConnectors/MangaDex.cs
Normal file
@ -0,0 +1,280 @@
|
||||
using System.Globalization;
|
||||
using System.Net;
|
||||
using System.Text.Json;
|
||||
using System.Text.Json.Nodes;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
public class MangaDex : Connector
|
||||
{
|
||||
public override string name { get; }
|
||||
|
||||
private enum RequestType : byte
|
||||
{
|
||||
Manga,
|
||||
Feed,
|
||||
AtHomeServer,
|
||||
CoverUrl,
|
||||
Author,
|
||||
}
|
||||
|
||||
public MangaDex(TBaseObject clone) : base(clone)
|
||||
{
|
||||
name = "MangaDex";
|
||||
this.downloadClient = new DownloadClient(new Dictionary<byte, int>()
|
||||
{
|
||||
{(byte)RequestType.Manga, 250},
|
||||
{(byte)RequestType.Feed, 250},
|
||||
{(byte)RequestType.AtHomeServer, 40},
|
||||
{(byte)RequestType.CoverUrl, 250},
|
||||
{(byte)RequestType.Author, 250}
|
||||
}, clone);
|
||||
}
|
||||
|
||||
protected override Publication[] GetPublications(string publicationTitle = "")
|
||||
{
|
||||
Log($"Searching Publications. Term=\"{publicationTitle}\"");
|
||||
const int limit = 100; //How many values we want returned at once
|
||||
int offset = 0; //"Page"
|
||||
int total = int.MaxValue; //How many total results are there, is updated on first request
|
||||
HashSet<Publication> publications = new();
|
||||
int loadedPublicationData = 0;
|
||||
while (offset < total) //As long as we haven't requested all "Pages"
|
||||
{
|
||||
//Request next Page
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(
|
||||
$"https://api.mangadex.org/manga?limit={limit}&title={publicationTitle}&offset={offset}", (byte)RequestType.Manga);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
break;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
|
||||
offset += limit;
|
||||
if (result is null)
|
||||
break;
|
||||
|
||||
total = result["total"]!.GetValue<int>(); //Update the total number of Publications
|
||||
|
||||
JsonArray mangaInResult = result["data"]!.AsArray(); //Manga-data-Array
|
||||
//Loop each Manga and extract information from JSON
|
||||
foreach (JsonNode? mangeNode in mangaInResult)
|
||||
{
|
||||
Log($"Getting publication data. {++loadedPublicationData}/{total}");
|
||||
JsonObject manga = (JsonObject)mangeNode!;
|
||||
JsonObject attributes = manga["attributes"]!.AsObject();
|
||||
|
||||
string publicationId = manga["id"]!.GetValue<string>();
|
||||
|
||||
string title = attributes["title"]!.AsObject().ContainsKey("en") && attributes["title"]!["en"] is not null
|
||||
? attributes["title"]!["en"]!.GetValue<string>()
|
||||
: attributes["title"]![((IDictionary<string, JsonNode?>)attributes["title"]!.AsObject()).Keys.First()]!.GetValue<string>();
|
||||
|
||||
string? description = attributes["description"]!.AsObject().ContainsKey("en") && attributes["description"]!["en"] is not null
|
||||
? attributes["description"]!["en"]!.GetValue<string?>()
|
||||
: null;
|
||||
|
||||
JsonArray altTitlesObject = attributes["altTitles"]!.AsArray();
|
||||
Dictionary<string, string> altTitlesDict = new();
|
||||
foreach (JsonNode? altTitleNode in altTitlesObject)
|
||||
{
|
||||
JsonObject altTitleObject = (JsonObject)altTitleNode!;
|
||||
string key = ((IDictionary<string, JsonNode?>)altTitleObject).Keys.ToArray()[0];
|
||||
altTitlesDict.TryAdd(key, altTitleObject[key]!.GetValue<string>());
|
||||
}
|
||||
|
||||
JsonArray tagsObject = attributes["tags"]!.AsArray();
|
||||
HashSet<string> tags = new();
|
||||
foreach (JsonNode? tagNode in tagsObject)
|
||||
{
|
||||
JsonObject tagObject = (JsonObject)tagNode!;
|
||||
if(tagObject["attributes"]!["name"]!.AsObject().ContainsKey("en"))
|
||||
tags.Add(tagObject["attributes"]!["name"]!["en"]!.GetValue<string>());
|
||||
}
|
||||
|
||||
string? posterId = null;
|
||||
HashSet<string> authorIds = new();
|
||||
if (manga.ContainsKey("relationships") && manga["relationships"] is not null)
|
||||
{
|
||||
JsonArray relationships = manga["relationships"]!.AsArray();
|
||||
posterId = relationships.FirstOrDefault(relationship => relationship!["type"]!.GetValue<string>() == "cover_art")!["id"]!.GetValue<string>();
|
||||
foreach (JsonNode? node in relationships.Where(relationship =>
|
||||
relationship!["type"]!.GetValue<string>() == "author"))
|
||||
authorIds.Add(node!["id"]!.GetValue<string>());
|
||||
}
|
||||
string? coverUrl = GetCoverUrl(publicationId, posterId);
|
||||
string? coverCacheName = null;
|
||||
if (coverUrl is not null)
|
||||
coverCacheName = SaveCoverImageToCache(coverUrl, (byte)RequestType.AtHomeServer);
|
||||
|
||||
List<string> authors = GetAuthors(authorIds);
|
||||
|
||||
Dictionary<string, string> linksDict = new();
|
||||
if (attributes.ContainsKey("links") && attributes["links"] is not null)
|
||||
{
|
||||
JsonObject linksObject = attributes["links"]!.AsObject();
|
||||
foreach (string key in ((IDictionary<string, JsonNode?>)linksObject).Keys)
|
||||
{
|
||||
linksDict.Add(key, linksObject[key]!.GetValue<string>());
|
||||
}
|
||||
}
|
||||
|
||||
int? year = attributes.ContainsKey("year") && attributes["year"] is not null
|
||||
? attributes["year"]!.GetValue<int?>()
|
||||
: null;
|
||||
|
||||
string? originalLanguage = attributes.ContainsKey("originalLanguage") && attributes["originalLanguage"] is not null
|
||||
? attributes["originalLanguage"]!.GetValue<string?>()
|
||||
: null;
|
||||
|
||||
string status = attributes["status"]!.GetValue<string>();
|
||||
|
||||
Publication pub = new (
|
||||
title,
|
||||
authors,
|
||||
description,
|
||||
altTitlesDict,
|
||||
tags.ToArray(),
|
||||
coverUrl,
|
||||
coverCacheName,
|
||||
linksDict,
|
||||
year,
|
||||
originalLanguage,
|
||||
status,
|
||||
publicationId
|
||||
);
|
||||
publications.Add(pub); //Add Publication (Manga) to result
|
||||
}
|
||||
}
|
||||
|
||||
Log($"Retrieved {publications.Count} publications.");
|
||||
return publications.ToArray();
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Publication publication, string language = "")
|
||||
{
|
||||
Log($"Getting chapters {publication}");
|
||||
const int limit = 100; //How many values we want returned at once
|
||||
int offset = 0; //"Page"
|
||||
int total = int.MaxValue; //How many total results are there, is updated on first request
|
||||
List<Chapter> chapters = new();
|
||||
//As long as we haven't requested all "Pages"
|
||||
while (offset < total)
|
||||
{
|
||||
//Request next "Page"
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(
|
||||
$"https://api.mangadex.org/manga/{publication.publicationId}/feed?limit={limit}&offset={offset}&translatedLanguage%5B%5D={language}", (byte)RequestType.Feed);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
break;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
|
||||
offset += limit;
|
||||
if (result is null)
|
||||
break;
|
||||
|
||||
total = result["total"]!.GetValue<int>();
|
||||
JsonArray chaptersInResult = result["data"]!.AsArray();
|
||||
//Loop through all Chapters in result and extract information from JSON
|
||||
foreach (JsonNode? jsonNode in chaptersInResult)
|
||||
{
|
||||
JsonObject chapter = (JsonObject)jsonNode!;
|
||||
JsonObject attributes = chapter["attributes"]!.AsObject();
|
||||
string chapterId = chapter["id"]!.GetValue<string>();
|
||||
|
||||
string? title = attributes.ContainsKey("title") && attributes["title"] is not null
|
||||
? attributes["title"]!.GetValue<string>()
|
||||
: null;
|
||||
|
||||
string? volume = attributes.ContainsKey("volume") && attributes["volume"] is not null
|
||||
? attributes["volume"]!.GetValue<string>()
|
||||
: null;
|
||||
|
||||
string chapterNum = attributes.ContainsKey("chapter") && attributes["chapter"] is not null
|
||||
? attributes["chapter"]!.GetValue<string>()
|
||||
: "null";
|
||||
|
||||
if(chapterNum is not "null")
|
||||
chapters.Add(new Chapter(publication, title, volume, chapterNum, chapterId));
|
||||
}
|
||||
}
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
NumberFormatInfo chapterNumberFormatInfo = new() { NumberDecimalSeparator = "." };
|
||||
Log($"Got {chapters.Count} chapters. {publication}");
|
||||
return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, chapterNumberFormatInfo)).ToArray();
|
||||
}
|
||||
|
||||
public override HttpStatusCode DownloadChapter(Publication publication, Chapter chapter, CancellationToken? cancellationToken = null)
|
||||
{
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
Log($"Retrieving chapter-info {chapter} {publication}");
|
||||
//Request URLs for Chapter-Images
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://api.mangadex.org/at-home/server/{chapter.url}?forcePort443=false'", (byte)RequestType.AtHomeServer);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return requestResult.statusCode;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
if (result is null)
|
||||
return HttpStatusCode.NoContent;
|
||||
|
||||
string baseUrl = result["baseUrl"]!.GetValue<string>();
|
||||
string hash = result["chapter"]!["hash"]!.GetValue<string>();
|
||||
JsonArray imageFileNames = result["chapter"]!["data"]!.AsArray();
|
||||
//Loop through all imageNames and construct urls (imageUrl)
|
||||
HashSet<string> imageUrls = new();
|
||||
foreach (JsonNode? image in imageFileNames)
|
||||
imageUrls.Add($"{baseUrl}/data/{hash}/{image!.GetValue<string>()}");
|
||||
|
||||
string comicInfoPath = Path.GetTempFileName();
|
||||
File.WriteAllText(comicInfoPath, chapter.GetComicInfoXmlString());
|
||||
|
||||
//Download Chapter-Images
|
||||
return DownloadChapterImages(imageUrls.ToArray(), chapter.GetArchiveFilePath(settings.downloadLocation), (byte)RequestType.AtHomeServer, comicInfoPath, cancellationToken:cancellationToken);
|
||||
}
|
||||
|
||||
private string? GetCoverUrl(string publicationId, string? posterId)
|
||||
{
|
||||
Log($"Getting CoverUrl for Publication {publicationId}");
|
||||
if (posterId is null)
|
||||
{
|
||||
Log("No cover.");
|
||||
return null;
|
||||
}
|
||||
|
||||
//Request information where to download Cover
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://api.mangadex.org/cover/{posterId}", (byte)RequestType.CoverUrl);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
if (result is null)
|
||||
return null;
|
||||
|
||||
string fileName = result["data"]!["attributes"]!["fileName"]!.GetValue<string>();
|
||||
|
||||
string coverUrl = $"https://uploads.mangadex.org/covers/{publicationId}/{fileName}";
|
||||
Log($"Cover-Url {publicationId} -> {coverUrl}");
|
||||
return coverUrl;
|
||||
}
|
||||
|
||||
private List<string> GetAuthors(IEnumerable<string> authorIds)
|
||||
{
|
||||
Log("Retrieving authors.");
|
||||
List<string> ret = new();
|
||||
foreach (string authorId in authorIds)
|
||||
{
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://api.mangadex.org/author/{authorId}", (byte)RequestType.Author);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return ret;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
if (result is null)
|
||||
return ret;
|
||||
|
||||
string authorName = result["data"]!["attributes"]!["name"]!.GetValue<string>();
|
||||
ret.Add(authorName);
|
||||
Log($"Got author {authorId} -> {authorName}");
|
||||
}
|
||||
return ret;
|
||||
}
|
||||
}
|
222
Tranga/MangaConnectors/MangaKatana.cs
Normal file
222
Tranga/MangaConnectors/MangaKatana.cs
Normal file
@ -0,0 +1,222 @@
|
||||
using System.Globalization;
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
public class MangaKatana : Connector
|
||||
{
|
||||
public override string name { get; }
|
||||
|
||||
public MangaKatana(TBaseObject clone) : base(clone)
|
||||
{
|
||||
this.name = "MangaKatana";
|
||||
this.downloadClient = new DownloadClient(new Dictionary<byte, int>()
|
||||
{
|
||||
{1, 60}
|
||||
}, clone);
|
||||
}
|
||||
|
||||
protected override Publication[] GetPublications(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 = $"https://mangakatana.com/?search={sanitizedTitle}&search_by=book_name";
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Publication>();
|
||||
|
||||
// ReSharper disable once MergeIntoPattern
|
||||
// If a single result is found, the user will be redirected to the results directly instead of a result page
|
||||
if(requestResult.hasBeenRedirected
|
||||
&& requestResult.redirectedToUrl is not null
|
||||
&& requestResult.redirectedToUrl.Contains("mangakatana.com/manga"))
|
||||
{
|
||||
return new [] { ParseSinglePublicationFromHtml(requestResult.result, requestResult.redirectedToUrl.Split('/')[^1]) };
|
||||
}
|
||||
|
||||
Publication[] publications = ParsePublicationsFromHtml(requestResult.result);
|
||||
Log($"Retrieved {publications.Length} publications.");
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Publication[] ParsePublicationsFromHtml(Stream html)
|
||||
{
|
||||
StreamReader reader = new(html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new();
|
||||
document.LoadHtml(htmlString);
|
||||
IEnumerable<HtmlNode> searchResults = document.DocumentNode.SelectNodes("//*[@id='book_list']/div");
|
||||
if (searchResults is null || !searchResults.Any())
|
||||
return Array.Empty<Publication>();
|
||||
List<string> urls = new();
|
||||
foreach (HtmlNode mangaResult in searchResults)
|
||||
{
|
||||
urls.Add(mangaResult.Descendants("a").First().GetAttributes()
|
||||
.First(a => a.Name == "href").Value);
|
||||
}
|
||||
|
||||
HashSet<Publication> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Publication>();
|
||||
|
||||
ret.Add(ParseSinglePublicationFromHtml(requestResult.result, url.Split('/')[^1]));
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
private Publication ParseSinglePublicationFromHtml(Stream html, string publicationId)
|
||||
{
|
||||
StreamReader reader = new(html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new();
|
||||
document.LoadHtml(htmlString);
|
||||
string status = "";
|
||||
Dictionary<string, string> altTitles = new();
|
||||
Dictionary<string, string>? links = null;
|
||||
HashSet<string> tags = new();
|
||||
string[] authors = Array.Empty<string>();
|
||||
string originalLanguage = "";
|
||||
|
||||
HtmlNode infoNode = document.DocumentNode.SelectSingleNode("//*[@id='single_book']");
|
||||
string sortName = infoNode.Descendants("h1").First(n => n.HasClass("heading")).InnerText;
|
||||
HtmlNode infoTable = infoNode.SelectSingleNode("//*[@id='single_book']/div[2]/div/ul");
|
||||
|
||||
foreach (HtmlNode row in infoTable.Descendants("li"))
|
||||
{
|
||||
string key = row.SelectNodes("div").First().InnerText.ToLower();
|
||||
string value = row.SelectNodes("div").Last().InnerText;
|
||||
string keySanitized = string.Concat(Regex.Matches(key, "[a-z]"));
|
||||
|
||||
switch (keySanitized)
|
||||
{
|
||||
case "altnames":
|
||||
string[] alts = value.Split(" ; ");
|
||||
for (int i = 0; i < alts.Length; i++)
|
||||
altTitles.Add(i.ToString(), alts[i]);
|
||||
break;
|
||||
case "authorsartists":
|
||||
authors = value.Split(',');
|
||||
break;
|
||||
case "status":
|
||||
status = value;
|
||||
break;
|
||||
case "genres":
|
||||
tags = row.SelectNodes("div").Last().Descendants("a").Select(a => a.InnerText).ToHashSet();
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
string posterUrl = document.DocumentNode.SelectSingleNode("//*[@id='single_book']/div[1]/div").Descendants("img").First()
|
||||
.GetAttributes().First(a => a.Name == "src").Value;
|
||||
|
||||
string coverFileNameInCache = SaveCoverImageToCache(posterUrl, 1);
|
||||
|
||||
string description = document.DocumentNode.SelectSingleNode("//*[@id='single_book']/div[3]/p").InnerText;
|
||||
while (description.StartsWith('\n'))
|
||||
description = description.Substring(1);
|
||||
|
||||
int year = DateTime.Now.Year;
|
||||
string yearString = infoTable.Descendants("div").First(d => d.HasClass("updateAt"))
|
||||
.InnerText.Split('-')[^1];
|
||||
|
||||
if(yearString.Contains("ago") == false)
|
||||
{
|
||||
year = Convert.ToInt32(yearString);
|
||||
}
|
||||
|
||||
return new Publication(sortName, authors.ToList(), description, altTitles, tags.ToArray(), posterUrl, coverFileNameInCache, links,
|
||||
year, originalLanguage, status, publicationId);
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Publication publication, string language = "")
|
||||
{
|
||||
Log($"Getting chapters {publication}");
|
||||
string requestUrl = $"https://mangakatana.com/manga/{publication.publicationId}";
|
||||
// Leaving this in for verification if the page exists
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Chapter>();
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
NumberFormatInfo chapterNumberFormatInfo = new()
|
||||
{
|
||||
NumberDecimalSeparator = "."
|
||||
};
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(publication, requestUrl);
|
||||
Log($"Got {chapters.Count} chapters. {publication}");
|
||||
return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, chapterNumberFormatInfo)).ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Publication publication, string mangaUrl)
|
||||
{
|
||||
// Using HtmlWeb will include the chapters since they are loaded with js
|
||||
HtmlWeb web = new();
|
||||
HtmlDocument document = web.Load(mangaUrl);
|
||||
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNode chapterList = document.DocumentNode.SelectSingleNode("//div[contains(@class, 'chapters')]/table/tbody");
|
||||
|
||||
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", "");
|
||||
ret.Add(new Chapter(publication, chapterName, volumeNumber, chapterNumber, url));
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
public override HttpStatusCode DownloadChapter(Publication publication, Chapter chapter, CancellationToken? cancellationToken = null)
|
||||
{
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
Log($"Retrieving chapter-info {chapter} {publication}");
|
||||
string requestUrl = chapter.url;
|
||||
// Leaving this in to check if the page exists
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return requestResult.statusCode;
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestUrl);
|
||||
|
||||
string comicInfoPath = Path.GetTempFileName();
|
||||
File.WriteAllText(comicInfoPath, chapter.GetComicInfoXmlString());
|
||||
|
||||
return DownloadChapterImages(imageUrls, chapter.GetArchiveFilePath(settings.downloadLocation), 1, comicInfoPath, "https://mangakatana.com/", cancellationToken);
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(string mangaUrl)
|
||||
{
|
||||
HtmlWeb web = new();
|
||||
HtmlDocument document = web.Load(mangaUrl);
|
||||
|
||||
// Images are loaded dynamically, but the urls are present in a piece of js code on the page
|
||||
string js = document.DocumentNode.SelectSingleNode("//script[contains(., 'data-src')]").InnerText
|
||||
.Replace("\r", "")
|
||||
.Replace("\n", "")
|
||||
.Replace("\t", "");
|
||||
|
||||
// ReSharper disable once StringLiteralTypo
|
||||
string regexPat = @"(var thzq=\[')(.*)(,];function)";
|
||||
var group = Regex.Matches(js, regexPat).First().Groups[2].Value.Replace("'", "");
|
||||
var urls = group.Split(',');
|
||||
|
||||
return urls;
|
||||
}
|
||||
}
|
205
Tranga/MangaConnectors/Manganato.cs
Normal file
205
Tranga/MangaConnectors/Manganato.cs
Normal file
@ -0,0 +1,205 @@
|
||||
using System.Globalization;
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
public class Manganato : Connector
|
||||
{
|
||||
public override string name { get; }
|
||||
|
||||
public Manganato(TBaseObject clone) : base(clone)
|
||||
{
|
||||
this.name = "Manganato";
|
||||
this.downloadClient = new DownloadClient(new Dictionary<byte, int>()
|
||||
{
|
||||
{1, 60}
|
||||
}, clone);
|
||||
}
|
||||
|
||||
protected override Publication[] GetPublications(string publicationTitle = "")
|
||||
{
|
||||
Log($"Searching Publications. Term=\"{publicationTitle}\"");
|
||||
string sanitizedTitle = string.Join('_', Regex.Matches(publicationTitle, "[A-z]*")).ToLower();
|
||||
string requestUrl = $"https://manganato.com/search/story/{sanitizedTitle}";
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Publication>();
|
||||
|
||||
Publication[] publications = ParsePublicationsFromHtml(requestResult.result);
|
||||
Log($"Retrieved {publications.Length} publications.");
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Publication[] ParsePublicationsFromHtml(Stream html)
|
||||
{
|
||||
StreamReader reader = new (html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(htmlString);
|
||||
IEnumerable<HtmlNode> searchResults = document.DocumentNode.Descendants("div").Where(n => n.HasClass("search-story-item"));
|
||||
List<string> urls = new();
|
||||
foreach (HtmlNode mangaResult in searchResults)
|
||||
{
|
||||
urls.Add(mangaResult.Descendants("a").First(n => n.HasClass("item-title")).GetAttributes()
|
||||
.First(a => a.Name == "href").Value);
|
||||
}
|
||||
|
||||
HashSet<Publication> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Publication>();
|
||||
|
||||
ret.Add(ParseSinglePublicationFromHtml(requestResult.result, url.Split('/')[^1]));
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
private Publication ParseSinglePublicationFromHtml(Stream html, string publicationId)
|
||||
{
|
||||
StreamReader reader = new (html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(htmlString);
|
||||
string status = "";
|
||||
Dictionary<string, string> altTitles = new();
|
||||
Dictionary<string, string>? links = null;
|
||||
HashSet<string> tags = new();
|
||||
string[] authors = Array.Empty<string>();
|
||||
string originalLanguage = "";
|
||||
|
||||
HtmlNode infoNode = document.DocumentNode.Descendants("div").First(d => d.HasClass("story-info-right"));
|
||||
|
||||
string sortName = infoNode.Descendants("h1").First().InnerText;
|
||||
|
||||
HtmlNode infoTable = infoNode.Descendants().First(d => d.Name == "table");
|
||||
|
||||
foreach (HtmlNode row in infoTable.Descendants("tr"))
|
||||
{
|
||||
string key = row.SelectNodes("td").First().InnerText.ToLower();
|
||||
string value = row.SelectNodes("td").Last().InnerText;
|
||||
string keySanitized = string.Concat(Regex.Matches(key, "[a-z]"));
|
||||
|
||||
switch (keySanitized)
|
||||
{
|
||||
case "alternative":
|
||||
string[] alts = value.Split(" ; ");
|
||||
for(int i = 0; i < alts.Length; i++)
|
||||
altTitles.Add(i.ToString(), alts[i]);
|
||||
break;
|
||||
case "authors":
|
||||
authors = value.Split('-');
|
||||
break;
|
||||
case "status":
|
||||
status = value;
|
||||
break;
|
||||
case "genres":
|
||||
string[] genres = value.Split(" - ");
|
||||
tags = genres.ToHashSet();
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
string posterUrl = document.DocumentNode.Descendants("span").First(s => s.HasClass("info-image")).Descendants("img").First()
|
||||
.GetAttributes().First(a => a.Name == "src").Value;
|
||||
|
||||
string coverFileNameInCache = SaveCoverImageToCache(posterUrl, 1);
|
||||
|
||||
string description = document.DocumentNode.Descendants("div").First(d => d.HasClass("panel-story-info-description"))
|
||||
.InnerText.Replace("Description :", "");
|
||||
while (description.StartsWith('\n'))
|
||||
description = description.Substring(1);
|
||||
|
||||
string yearString = document.DocumentNode.Descendants("li").Last(li => li.HasClass("a-h")).Descendants("span")
|
||||
.First(s => s.HasClass("chapter-time")).InnerText;
|
||||
int year = Convert.ToInt32(yearString.Split(',')[^1]) + 2000;
|
||||
|
||||
return new Publication(sortName, authors.ToList(), description, altTitles, tags.ToArray(), posterUrl, coverFileNameInCache, links,
|
||||
year, originalLanguage, status, publicationId);
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Publication publication, string language = "")
|
||||
{
|
||||
Log($"Getting chapters {publication}");
|
||||
string requestUrl = $"https://chapmanganato.com/{publication.publicationId}";
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Chapter>();
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
NumberFormatInfo chapterNumberFormatInfo = new()
|
||||
{
|
||||
NumberDecimalSeparator = "."
|
||||
};
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(publication, requestResult.result);
|
||||
Log($"Got {chapters.Count} chapters. {publication}");
|
||||
return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, chapterNumberFormatInfo)).ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Publication publication, Stream html)
|
||||
{
|
||||
StreamReader reader = new (html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(htmlString);
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNode chapterList = document.DocumentNode.Descendants("ul").First(l => l.HasClass("row-content-chapter"));
|
||||
|
||||
foreach (HtmlNode chapterInfo in chapterList.Descendants("li"))
|
||||
{
|
||||
string fullString = chapterInfo.Descendants("a").First(d => d.HasClass("chapter-name")).InnerText;
|
||||
|
||||
string? volumeNumber = fullString.Contains("Vol.") ? fullString.Replace("Vol.", "").Split(' ')[0] : null;
|
||||
string chapterNumber = fullString.Split(':')[0].Split("Chapter ")[1].Replace('-','.');
|
||||
string chapterName = string.Concat(fullString.Split(':')[1..]);
|
||||
string url = chapterInfo.Descendants("a").First(d => d.HasClass("chapter-name"))
|
||||
.GetAttributeValue("href", "");
|
||||
ret.Add(new Chapter(publication, chapterName, volumeNumber, chapterNumber, url));
|
||||
}
|
||||
ret.Reverse();
|
||||
return ret;
|
||||
}
|
||||
|
||||
public override HttpStatusCode DownloadChapter(Publication publication, Chapter chapter, CancellationToken? cancellationToken = null)
|
||||
{
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
Log($"Retrieving chapter-info {chapter} {publication}");
|
||||
string requestUrl = chapter.url;
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return requestResult.statusCode;
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.result);
|
||||
|
||||
string comicInfoPath = Path.GetTempFileName();
|
||||
File.WriteAllText(comicInfoPath, chapter.GetComicInfoXmlString());
|
||||
|
||||
return DownloadChapterImages(imageUrls, chapter.GetArchiveFilePath(settings.downloadLocation), 1, comicInfoPath, "https://chapmanganato.com/", cancellationToken);
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(Stream html)
|
||||
{
|
||||
StreamReader reader = new (html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(htmlString);
|
||||
List<string> ret = new();
|
||||
|
||||
HtmlNode imageContainer =
|
||||
document.DocumentNode.Descendants("div").First(i => i.HasClass("container-chapter-reader"));
|
||||
foreach(HtmlNode imageNode in imageContainer.Descendants("img"))
|
||||
ret.Add(imageNode.GetAttributeValue("src", ""));
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
}
|
273
Tranga/MangaConnectors/Mangasee.cs
Normal file
273
Tranga/MangaConnectors/Mangasee.cs
Normal file
@ -0,0 +1,273 @@
|
||||
using System.Globalization;
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using System.Xml.Linq;
|
||||
using HtmlAgilityPack;
|
||||
using Newtonsoft.Json;
|
||||
using PuppeteerSharp;
|
||||
|
||||
namespace Tranga.MangaConnectors;
|
||||
|
||||
public class Mangasee : Connector
|
||||
{
|
||||
public override string name { get; }
|
||||
private IBrowser? _browser;
|
||||
private const string ChromiumVersion = "1154303";
|
||||
|
||||
public Mangasee(TBaseObject clone) : base(clone)
|
||||
{
|
||||
this.name = "Mangasee";
|
||||
this.downloadClient = new DownloadClient(new Dictionary<byte, int>()
|
||||
{
|
||||
{ 1, 60 }
|
||||
}, clone);
|
||||
|
||||
Task d = new Task(DownloadBrowser);
|
||||
d.Start();
|
||||
}
|
||||
|
||||
private async void DownloadBrowser()
|
||||
{
|
||||
BrowserFetcher browserFetcher = new BrowserFetcher();
|
||||
foreach(string rev in browserFetcher.LocalRevisions().Where(rev => rev != ChromiumVersion))
|
||||
browserFetcher.Remove(rev);
|
||||
if (!browserFetcher.LocalRevisions().Contains(ChromiumVersion))
|
||||
{
|
||||
Log("Downloading headless browser");
|
||||
DateTime last = DateTime.Now.Subtract(TimeSpan.FromSeconds(5));
|
||||
browserFetcher.DownloadProgressChanged += (_, args) =>
|
||||
{
|
||||
double currentBytes = Convert.ToDouble(args.BytesReceived) / Convert.ToDouble(args.TotalBytesToReceive);
|
||||
if (args.TotalBytesToReceive == args.BytesReceived)
|
||||
Log("Browser downloaded.");
|
||||
else if (DateTime.Now > last.AddSeconds(1))
|
||||
{
|
||||
Log($"Browser download progress: {currentBytes:P2}");
|
||||
last = DateTime.Now;
|
||||
}
|
||||
|
||||
};
|
||||
if (!browserFetcher.CanDownloadAsync(ChromiumVersion).Result)
|
||||
{
|
||||
Log($"Can't download browser version {ChromiumVersion}");
|
||||
throw new Exception();
|
||||
}
|
||||
await browserFetcher.DownloadAsync(ChromiumVersion);
|
||||
}
|
||||
|
||||
Log("Starting Browser.");
|
||||
this._browser = await Puppeteer.LaunchAsync(new LaunchOptions
|
||||
{
|
||||
Headless = true,
|
||||
ExecutablePath = browserFetcher.GetExecutablePath(ChromiumVersion),
|
||||
Args = new [] {
|
||||
"--disable-gpu",
|
||||
"--disable-dev-shm-usage",
|
||||
"--disable-setuid-sandbox",
|
||||
"--no-sandbox"}
|
||||
});
|
||||
}
|
||||
|
||||
protected override Publication[] GetPublications(string publicationTitle = "")
|
||||
{
|
||||
Log($"Searching Publications. Term=\"{publicationTitle}\"");
|
||||
string requestUrl = $"https://mangasee123.com/_search.php";
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, 1);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Publication>();
|
||||
|
||||
return ParsePublicationsFromHtml(requestResult.result, publicationTitle);
|
||||
}
|
||||
|
||||
private Publication[] ParsePublicationsFromHtml(Stream html, string publicationTitle)
|
||||
{
|
||||
string jsonString = new StreamReader(html).ReadToEnd();
|
||||
List<SearchResultItem> result = JsonConvert.DeserializeObject<List<SearchResultItem>>(jsonString)!;
|
||||
Dictionary<SearchResultItem, int> queryFiltered = new();
|
||||
foreach (SearchResultItem resultItem in result)
|
||||
{
|
||||
int matches = resultItem.GetMatches(publicationTitle);
|
||||
if (matches > 0)
|
||||
queryFiltered.TryAdd(resultItem, matches);
|
||||
}
|
||||
|
||||
queryFiltered = queryFiltered.Where(item => item.Value >= publicationTitle.Split(' ').Length - 1)
|
||||
.ToDictionary(item => item.Key, item => item.Value);
|
||||
|
||||
Log($"Retrieved {queryFiltered.Count} publications.");
|
||||
|
||||
HashSet<Publication> ret = new();
|
||||
List<SearchResultItem> orderedFiltered =
|
||||
queryFiltered.OrderBy(item => item.Value).ToDictionary(item => item.Key, item => item.Value).Keys.ToList();
|
||||
|
||||
uint index = 1;
|
||||
foreach (SearchResultItem orderedItem in orderedFiltered)
|
||||
{
|
||||
DownloadClient.RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://mangasee123.com/manga/{orderedItem.i}", 1);
|
||||
if ((int)requestResult.statusCode >= 200 || (int)requestResult.statusCode < 300)
|
||||
{
|
||||
Log($"Retrieving Publication info: {orderedItem.s} {index++}/{orderedFiltered.Count}");
|
||||
ret.Add(ParseSinglePublicationFromHtml(requestResult.result, orderedItem.s, orderedItem.i, orderedItem.a));
|
||||
}
|
||||
}
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
|
||||
private Publication ParseSinglePublicationFromHtml(Stream html, string sortName, string publicationId, string[] a)
|
||||
{
|
||||
StreamReader reader = new (html);
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(reader.ReadToEnd());
|
||||
|
||||
string originalLanguage = "", status = "";
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
HashSet<string> tags = new();
|
||||
|
||||
HtmlNode posterNode =
|
||||
document.DocumentNode.Descendants("img").First(img => img.HasClass("img-fluid") && img.HasClass("bottom-5"));
|
||||
string posterUrl = posterNode.GetAttributeValue("src", "");
|
||||
string coverFileNameInCache = SaveCoverImageToCache(posterUrl, 1);
|
||||
|
||||
HtmlNode attributes = document.DocumentNode.Descendants("div")
|
||||
.First(div => div.HasClass("col-md-9") && div.HasClass("col-sm-8") && div.HasClass("top-5"))
|
||||
.Descendants("ul").First();
|
||||
|
||||
HtmlNode[] authorsNodes = attributes.Descendants("li")
|
||||
.First(node => node.InnerText.Contains("author(s):", StringComparison.CurrentCultureIgnoreCase))
|
||||
.Descendants("a").ToArray();
|
||||
List<string> authors = new();
|
||||
foreach(HtmlNode authorNode in authorsNodes)
|
||||
authors.Add(authorNode.InnerText);
|
||||
|
||||
HtmlNode[] genreNodes = attributes.Descendants("li")
|
||||
.First(node => node.InnerText.Contains("genre(s):", StringComparison.CurrentCultureIgnoreCase))
|
||||
.Descendants("a").ToArray();
|
||||
foreach (HtmlNode genreNode in genreNodes)
|
||||
tags.Add(genreNode.InnerText);
|
||||
|
||||
HtmlNode yearNode = attributes.Descendants("li")
|
||||
.First(node => node.InnerText.Contains("released:", StringComparison.CurrentCultureIgnoreCase))
|
||||
.Descendants("a").First();
|
||||
int year = Convert.ToInt32(yearNode.InnerText);
|
||||
|
||||
HtmlNode[] statusNodes = attributes.Descendants("li")
|
||||
.First(node => node.InnerText.Contains("status:", StringComparison.CurrentCultureIgnoreCase))
|
||||
.Descendants("a").ToArray();
|
||||
foreach(HtmlNode statusNode in statusNodes)
|
||||
if (statusNode.InnerText.Contains("publish", StringComparison.CurrentCultureIgnoreCase))
|
||||
status = statusNode.InnerText.Split(' ')[0];
|
||||
|
||||
HtmlNode descriptionNode = attributes.Descendants("li").First(node => node.InnerText.Contains("description:", StringComparison.CurrentCultureIgnoreCase)).Descendants("div").First();
|
||||
string description = descriptionNode.InnerText;
|
||||
|
||||
int i = 0;
|
||||
foreach(string at in a)
|
||||
altTitles.Add((i++).ToString(), at);
|
||||
|
||||
return new Publication(sortName, authors, description, altTitles, tags.ToArray(), posterUrl, coverFileNameInCache, links,
|
||||
year, originalLanguage, status, publicationId);
|
||||
}
|
||||
|
||||
// ReSharper disable once ClassNeverInstantiated.Local Will be instantiated during deserialization
|
||||
private class SearchResultItem
|
||||
{
|
||||
public string i { get; init; }
|
||||
public string s { get; init; }
|
||||
public string[] a { get; init; }
|
||||
|
||||
[JsonConstructor]
|
||||
public SearchResultItem(string i, string s, string[] a)
|
||||
{
|
||||
this.i = i;
|
||||
this.s = s;
|
||||
this.a = a;
|
||||
}
|
||||
|
||||
public int GetMatches(string title)
|
||||
{
|
||||
int ret = 0;
|
||||
Regex cleanRex = new("[A-z0-9]*");
|
||||
string[] badWords = { "a", "an", "no", "ni", "so", "as", "and", "the", "of", "that", "in", "is", "for" };
|
||||
|
||||
string[] titleTerms = title.Split(new[] { ' ', '-' }).Where(str => !badWords.Contains(str)).ToArray();
|
||||
|
||||
foreach (Match matchTerm in cleanRex.Matches(this.i))
|
||||
ret += titleTerms.Count(titleTerm =>
|
||||
titleTerm.Equals(matchTerm.Value, StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
foreach (Match matchTerm in cleanRex.Matches(this.s))
|
||||
ret += titleTerms.Count(titleTerm =>
|
||||
titleTerm.Equals(matchTerm.Value, StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
foreach(string alt in this.a)
|
||||
foreach (Match matchTerm in cleanRex.Matches(alt))
|
||||
ret += titleTerms.Count(titleTerm =>
|
||||
titleTerm.Equals(matchTerm.Value, StringComparison.OrdinalIgnoreCase));
|
||||
|
||||
return ret;
|
||||
}
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Publication publication, string language = "")
|
||||
{
|
||||
Log($"Getting chapters {publication}");
|
||||
XDocument doc = XDocument.Load($"https://mangasee123.com/rss/{publication.publicationId}.xml");
|
||||
XElement[] chapterItems = doc.Descendants("item").ToArray();
|
||||
List<Chapter> chapters = new();
|
||||
foreach (XElement chapter in chapterItems)
|
||||
{
|
||||
string volumeNumber = "1";
|
||||
string chapterName = chapter.Descendants("title").First().Value;
|
||||
string chapterNumber = Regex.Matches(chapterName, "[0-9]+")[^1].ToString();
|
||||
|
||||
string url = chapter.Descendants("link").First().Value;
|
||||
url = url.Replace(Regex.Matches(url,"(-page-[0-9])")[0].ToString(),"");
|
||||
chapters.Add(new Chapter(publication, "", volumeNumber, chapterNumber, url));
|
||||
}
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
NumberFormatInfo chapterNumberFormatInfo = new()
|
||||
{
|
||||
NumberDecimalSeparator = "."
|
||||
};
|
||||
Log($"Got {chapters.Count} chapters. {publication}");
|
||||
return chapters.OrderBy(chapter => Convert.ToSingle(chapter.chapterNumber, chapterNumberFormatInfo)).ToArray();
|
||||
}
|
||||
|
||||
public override HttpStatusCode DownloadChapter(Publication publication, Chapter chapter, CancellationToken? cancellationToken = null)
|
||||
{
|
||||
if (cancellationToken?.IsCancellationRequested ?? false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
while (this._browser is null && !(cancellationToken?.IsCancellationRequested??false))
|
||||
{
|
||||
Log("Waiting for headless browser to download...");
|
||||
Thread.Sleep(1000);
|
||||
}
|
||||
if (cancellationToken?.IsCancellationRequested??false)
|
||||
return HttpStatusCode.RequestTimeout;
|
||||
|
||||
Log($"Retrieving chapter-info {chapter} {publication}");
|
||||
IPage page = _browser!.NewPageAsync().Result;
|
||||
IResponse response = page.GoToAsync(chapter.url).Result;
|
||||
if (response.Ok)
|
||||
{
|
||||
HtmlDocument document = new ();
|
||||
document.LoadHtml(page.GetContentAsync().Result);
|
||||
|
||||
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, cancellationToken:cancellationToken);
|
||||
}
|
||||
return response.Status;
|
||||
}
|
||||
}
|
Reference in New Issue
Block a user