mirror of
https://github.com/C9Glax/tranga.git
synced 2025-06-13 06:47:54 +02:00
Add API
This commit is contained in:
184
API/Schema/MangaConnectors/AsuraToon.cs
Normal file
184
API/Schema/MangaConnectors/AsuraToon.cs
Normal file
@ -0,0 +1,184 @@
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class AsuraToon : MangaConnector
|
||||
{
|
||||
|
||||
public AsuraToon() : base("AsuraToon", ["en"], ["https://asuracomic.net"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(m => m.Value.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://asuracomic.net/series?name={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://asuracomic.net/series/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult = downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
if (requestResult.htmlDocument is null)
|
||||
{
|
||||
return null;
|
||||
}
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, url.Split('/')[^1], url);
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
HtmlNodeCollection mangaList = document.DocumentNode.SelectNodes("//a[starts-with(@href,'series')]");
|
||||
if (mangaList is null || mangaList.Count < 1)
|
||||
return [];
|
||||
|
||||
IEnumerable<string> urls = mangaList.Select(a => $"https://asuracomic.net/{a.GetAttributeValue("href", "")}");
|
||||
|
||||
List<Manga> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? manga = GetMangaFromUrl(url);
|
||||
if (manga is not null)
|
||||
ret.Add((Manga)manga);
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
string? originalLanguage = null;
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
|
||||
HtmlNodeCollection genreNodes = document.DocumentNode.SelectNodes("//h3[text()='Genres']/../div/button");
|
||||
string[] tags = genreNodes.Select(b => b.InnerText).ToArray();
|
||||
|
||||
HtmlNode statusNode = document.DocumentNode.SelectSingleNode("//h3[text()='Status']/../h3[2]");
|
||||
MangaReleaseStatus releaseStatus = statusNode.InnerText.ToLower() switch
|
||||
{
|
||||
"ongoing" => MangaReleaseStatus.Continuing,
|
||||
"hiatus" => MangaReleaseStatus.OnHiatus,
|
||||
"completed" => MangaReleaseStatus.Completed,
|
||||
"dropped" => MangaReleaseStatus.Cancelled,
|
||||
"season end" => MangaReleaseStatus.Continuing,
|
||||
"coming soon" => MangaReleaseStatus.Unreleased,
|
||||
_ => MangaReleaseStatus.Unreleased
|
||||
};
|
||||
|
||||
HtmlNode coverNode =
|
||||
document.DocumentNode.SelectSingleNode("//img[@alt='poster']");
|
||||
string coverUrl = coverNode.GetAttributeValue("src", "");
|
||||
|
||||
HtmlNode titleNode =
|
||||
document.DocumentNode.SelectSingleNode("//title");
|
||||
string sortName = Regex.Match(titleNode.InnerText, @"(.*) - Asura Scans").Groups[1].Value;
|
||||
|
||||
HtmlNode descriptionNode =
|
||||
document.DocumentNode.SelectSingleNode("//h3[starts-with(text(),'Synopsis')]/../span");
|
||||
string description = descriptionNode?.InnerText??"";
|
||||
|
||||
HtmlNodeCollection authorNodes = document.DocumentNode.SelectNodes("//h3[text()='Author']/../h3[not(text()='Author' or text()='_')]");
|
||||
HtmlNodeCollection artistNodes = document.DocumentNode.SelectNodes("//h3[text()='Artist']/../h3[not(text()='Artist' or text()='_')]");
|
||||
IEnumerable<string> authorNames = authorNodes is null ? [] : authorNodes.Select(a => a.InnerText);
|
||||
IEnumerable<string> artistNames = artistNodes is null ? [] : artistNodes.Select(a => a.InnerText);
|
||||
List<string> authors = authorNames.Concat(artistNames).ToList();
|
||||
|
||||
HtmlNode? firstChapterNode = document.DocumentNode.SelectSingleNode("//a[contains(@href, 'chapter/1')]/../following-sibling::h3");
|
||||
uint year = uint.Parse(firstChapterNode?.InnerText.Split(' ')[^1] ?? "2000");
|
||||
|
||||
Manga manga = new Manga(publicationId, sortName, description, websiteUrl, coverUrl, null, year,
|
||||
originalLanguage, releaseStatus, -1, null, null,
|
||||
this.Name, authors, tags, links, altTitles); //TODO
|
||||
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
string requestUrl = $"https://asuracomic.net/series/{manga.MangaId}";
|
||||
// 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 [];
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(manga, requestUrl);
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Manga manga, string mangaUrl)
|
||||
{
|
||||
RequestResult result = downloadClient.MakeRequest(mangaUrl, RequestType.Default);
|
||||
if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
|
||||
{
|
||||
return new List<Chapter>();
|
||||
}
|
||||
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNodeCollection chapterURLNodes = result.htmlDocument.DocumentNode.SelectNodes("//a[contains(@href, '/chapter/')]");
|
||||
Regex infoRex = new(@"Chapter ([0-9]+)(.*)?");
|
||||
|
||||
foreach (HtmlNode chapterInfo in chapterURLNodes)
|
||||
{
|
||||
string chapterUrl = chapterInfo.GetAttributeValue("href", "");
|
||||
|
||||
Match match = infoRex.Match(chapterInfo.InnerText);
|
||||
float chapterNumber = float.Parse(match.Groups[1].Value);
|
||||
string? chapterName = match.Groups[2].Success && match.Groups[2].Length > 1 ? match.Groups[2].Value : null;
|
||||
string url = $"https://asuracomic.net/series/{chapterUrl}";
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, url, chapterNumber, null, chapterName));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
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 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument);
|
||||
return imageUrls;
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
HtmlNodeCollection images = document.DocumentNode.SelectNodes("//img[contains(@alt, 'chapter page')]");
|
||||
|
||||
return images.Select(i => i.GetAttributeValue("src", "")).ToArray();
|
||||
}
|
||||
}
|
||||
194
API/Schema/MangaConnectors/Bato.cs
Normal file
194
API/Schema/MangaConnectors/Bato.cs
Normal file
@ -0,0 +1,194 @@
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class Bato : MangaConnector
|
||||
{
|
||||
|
||||
public Bato() : base("Bato", ["en"], ["bato.to"])
|
||||
{
|
||||
this.downloadClient = new HttpDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(m => m.Value.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://bato.to/v3x-search?word={sanitizedTitle}&lang=en";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://bato.to/title/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult = downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
if (requestResult.htmlDocument is null)
|
||||
{
|
||||
return null;
|
||||
}
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, url.Split('/')[^1], url);
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
HtmlNode mangaList = document.DocumentNode.SelectSingleNode("//div[@data-hk='0-0-2']");
|
||||
if (!mangaList.ChildNodes.Any(node => node.Name == "div"))
|
||||
return [];
|
||||
|
||||
List<string> urls = mangaList.ChildNodes
|
||||
.Select(node => $"https://bato.to{node.Descendants("div").First().FirstChild.GetAttributeValue("href", "")}").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 Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
HtmlNode infoNode = document.DocumentNode.SelectSingleNode("/html/body/div/main/div[1]/div[2]");
|
||||
|
||||
string sortName = infoNode.Descendants("h3").First().InnerText;
|
||||
string description = document.DocumentNode
|
||||
.SelectSingleNode("//div[contains(concat(' ',normalize-space(@class),' '),'prose')]").InnerText;
|
||||
|
||||
string[] altTitlesList = infoNode.ChildNodes[1].ChildNodes[2].InnerText.Split('/');
|
||||
int i = 0;
|
||||
Dictionary<string, string> altTitles = altTitlesList.ToDictionary(s => i++.ToString(), s => s);
|
||||
|
||||
string posterUrl = document.DocumentNode.SelectNodes("//img")
|
||||
.First(child => child.GetAttributeValue("data-hk", "") == "0-1-0").GetAttributeValue("src", "").Replace("&", "&");
|
||||
|
||||
List<HtmlNode> genreNodes = document.DocumentNode.SelectSingleNode("//b[text()='Genres:']/..").SelectNodes("span").ToList();
|
||||
string[] tags = genreNodes.Select(node => node.FirstChild.InnerText).ToArray();
|
||||
|
||||
List<HtmlNode> authorsNodes = infoNode.ChildNodes[1].ChildNodes[3].Descendants("a").ToList();
|
||||
List<string> authors = authorsNodes.Select(node => node.InnerText.Replace("amp;", "")).ToList();
|
||||
|
||||
HtmlNode? originalLanguageNode = document.DocumentNode.SelectSingleNode("//span[text()='Tr From']/..");
|
||||
string originalLanguage = originalLanguageNode is not null ? originalLanguageNode.LastChild.InnerText : "";
|
||||
|
||||
if (!int.TryParse(
|
||||
document.DocumentNode.SelectSingleNode("//span[text()='Original Publication:']/..").LastChild.InnerText.Split('-')[0],
|
||||
out int year))
|
||||
year = DateTime.Now.Year;
|
||||
|
||||
string status = document.DocumentNode.SelectSingleNode("//span[text()='Original Publication:']/..")
|
||||
.ChildNodes[2].InnerText;
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
switch (status.ToLower())
|
||||
{
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
case "completed": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "hiatus": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "cancelled": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "pending": releaseStatus = MangaReleaseStatus.Unreleased; break;
|
||||
}
|
||||
|
||||
Manga manga = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
string requestUrl = $"https://bato.to/title/{manga.MangaId}";
|
||||
// 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 [];
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(manga, requestUrl);
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Manga manga, string mangaUrl)
|
||||
{
|
||||
RequestResult result = downloadClient.MakeRequest(mangaUrl, RequestType.Default);
|
||||
if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
|
||||
{
|
||||
return new List<Chapter>();
|
||||
}
|
||||
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNode chapterList =
|
||||
result.htmlDocument.DocumentNode.SelectSingleNode("/html/body/div/main/div[3]/astro-island/div/div[2]/div/div/astro-slot");
|
||||
|
||||
Regex numberRex = new(@"\/title\/.+\/([0-9])+(?:-vol_([0-9]+))?-ch_([0-9\.]+)");
|
||||
|
||||
foreach (HtmlNode chapterInfo in chapterList.SelectNodes("div"))
|
||||
{
|
||||
HtmlNode infoNode = chapterInfo.FirstChild.FirstChild;
|
||||
string chapterUrl = infoNode.GetAttributeValue("href", "");
|
||||
|
||||
Match match = numberRex.Match(chapterUrl);
|
||||
string id = match.Groups[1].Value;
|
||||
float? volumeNumber = match.Groups[2].Success ? float.Parse(match.Groups[2].Value) : null;
|
||||
float chapterNumber = float.Parse(match.Groups[3].Value);
|
||||
string url = $"https://bato.to{chapterUrl}?load=2";
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, url, chapterNumber, volumeNumber, null));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
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 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument);
|
||||
return imageUrls;
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
HtmlNode images = document.DocumentNode.SelectNodes("//astro-island").First(node =>
|
||||
node.GetAttributeValue("component-url", "").Contains("/_astro/ImageList."));
|
||||
|
||||
string weirdString = images.OuterHtml;
|
||||
string weirdString2 = Regex.Match(weirdString, @"props=\""(.*)}\""").Groups[1].Value;
|
||||
string[] urls = Regex.Matches(weirdString2, @"(https:\/\/[A-z\-0-9\.\?\&\;\=\/]+)\\")
|
||||
.Select(match => match.Groups[1].Value.Replace("&", "&")).ToArray();
|
||||
|
||||
return urls;
|
||||
}
|
||||
}
|
||||
43
API/Schema/MangaConnectors/MangaConnector.cs
Normal file
43
API/Schema/MangaConnectors/MangaConnector.cs
Normal file
@ -0,0 +1,43 @@
|
||||
using System.ComponentModel.DataAnnotations;
|
||||
using System.ComponentModel.DataAnnotations.Schema;
|
||||
using API.MangaDownloadClients;
|
||||
using Microsoft.EntityFrameworkCore;
|
||||
using Newtonsoft.Json;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
[PrimaryKey("Name")]
|
||||
public abstract class MangaConnector(string name, string[] supportedLanguages, string[] baseUris)
|
||||
{
|
||||
[MaxLength(32)]
|
||||
public string Name { get; init; } = name;
|
||||
public string[] SupportedLanguages { get; init; } = supportedLanguages;
|
||||
public string[] BaseUris { get; init; } = baseUris;
|
||||
|
||||
[ForeignKey("MangaIds")]
|
||||
public virtual Manga[] Mangas { get; internal set; } = [];
|
||||
|
||||
|
||||
public abstract Manga[] GetManga(string publicationTitle = "");
|
||||
|
||||
public abstract Manga? GetMangaFromUrl(string url);
|
||||
|
||||
public abstract Manga? GetMangaFromId(string publicationId);
|
||||
|
||||
public abstract Chapter[] GetChapters(Manga manga, string language="en");
|
||||
|
||||
[JsonIgnore]
|
||||
[NotMapped]
|
||||
internal DownloadClient downloadClient { get; init; } = null!;
|
||||
|
||||
public Chapter[] GetNewChapters(Manga manga)
|
||||
{
|
||||
Chapter[] allChapters = GetChapters(manga);
|
||||
if (allChapters.Length < 1)
|
||||
return [];
|
||||
|
||||
return allChapters.Where(chapter => !chapter.IsDownloaded()).ToArray();
|
||||
}
|
||||
|
||||
internal abstract string[] GetChapterImageUrls(Chapter chapter);
|
||||
}
|
||||
267
API/Schema/MangaConnectors/MangaDex.cs
Normal file
267
API/Schema/MangaConnectors/MangaDex.cs
Normal file
@ -0,0 +1,267 @@
|
||||
using System.Net;
|
||||
using System.Text.Json.Nodes;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using JsonSerializer = System.Text.Json.JsonSerializer;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class MangaDex : MangaConnector
|
||||
{
|
||||
//https://api.mangadex.org/docs/3-enumerations/#language-codes--localization
|
||||
//https://en.wikipedia.org/wiki/List_of_ISO_639_language_codes
|
||||
//https://gist.github.com/Josantonius/b455e315bc7f790d14b136d61d9ae469
|
||||
public MangaDex() : base("MangaDex", ["en","pt","pt-br","it","de","ru","aa","ab","ae","af","ak","am","an","ar-ae","ar-bh","ar-dz","ar-eg","ar-iq","ar-jo","ar-kw","ar-lb","ar-ly","ar-ma","ar-om","ar-qa","ar-sa","ar-sy","ar-tn","ar-ye","ar","as","av","ay","az","ba","be","bg","bh","bi","bm","bn","bo","br","bs","ca","ce","ch","co","cr","cs","cu","cv","cy","da","de-at","de-ch","de-de","de-li","de-lu","div","dv","dz","ee","el","en-au","en-bz","en-ca","en-cb","en-gb","en-ie","en-jm","en-nz","en-ph","en-tt","en-us","en-za","en-zw","eo","es-ar","es-bo","es-cl","es-co","es-cr","es-do","es-ec","es-es","es-gt","es-hn","es-la","es-mx","es-ni","es-pa","es-pe","es-pr","es-py","es-sv","es-us","es-uy","es-ve","es","et","eu","fa","ff","fi","fj","fo","fr-be","fr-ca","fr-ch","fr-fr","fr-lu","fr-mc","fr","fy","ga","gd","gl","gn","gu","gv","ha","he","hi","ho","hr-ba","hr-hr","hr","ht","hu","hy","hz","ia","id","ie","ig","ii","ik","in","io","is","it-ch","it-it","iu","iw","ja","ja-ro","ji","jv","jw","ka","kg","ki","kj","kk","kl","km","kn","ko","ko-ro","kr","ks","ku","kv","kw","ky","kz","la","lb","lg","li","ln","lo","ls","lt","lu","lv","mg","mh","mi","mk","ml","mn","mo","mr","ms-bn","ms-my","ms","mt","my","na","nb","nd","ne","ng","nl-be","nl-nl","nl","nn","no","nr","ns","nv","ny","oc","oj","om","or","os","pa","pi","pl","ps","pt-pt","qu-bo","qu-ec","qu-pe","qu","rm","rn","ro","rw","sa","sb","sc","sd","se-fi","se-no","se-se","se","sg","sh","si","sk","sl","sm","sn","so","sq","sr-ba","sr-sp","sr","ss","st","su","sv-fi","sv-se","sv","sw","sx","syr","ta","te","tg","th","ti","tk","tl","tn","to","tr","ts","tt","tw","ty","ug","uk","ur","us","uz","ve","vi","vo","wa","wo","xh","yi","yo","za","zh-cn","zh-hk","zh-mo","zh-ro","zh-sg","zh-tw","zh","zu"], ["mangadex.org"])
|
||||
{
|
||||
this.downloadClient = new HttpDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string 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<Manga> retManga = new();
|
||||
int loadedPublicationData = 0;
|
||||
List<JsonNode> results = new();
|
||||
|
||||
//Request all search-results
|
||||
while (offset < total) //As long as we haven't requested all "Pages"
|
||||
{
|
||||
//Request next Page
|
||||
RequestResult requestResult = downloadClient.MakeRequest(
|
||||
$"https://api.mangadex.org/manga?limit={limit}&title={publicationTitle}&offset={offset}" +
|
||||
$"&contentRating%5B%5D=safe&contentRating%5B%5D=suggestive&contentRating%5B%5D=erotica" +
|
||||
$"&contentRating%5B%5D=pornographic" +
|
||||
$"&includes%5B%5D=manga&includes%5B%5D=cover_art&includes%5B%5D=author" +
|
||||
$"&includes%5B%5D=artist&includes%5B%5D=tag", RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
break;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
|
||||
offset += limit;
|
||||
if (result is null)
|
||||
break;
|
||||
|
||||
if(result.ContainsKey("total"))
|
||||
total = result["total"]!.GetValue<int>(); //Update the total number of Publications
|
||||
else continue;
|
||||
|
||||
if (result.ContainsKey("data"))
|
||||
results.AddRange(result["data"]!.AsArray()!);//Manga-data-Array
|
||||
}
|
||||
|
||||
foreach (JsonNode mangaNode in results)
|
||||
{
|
||||
if(MangaFromJsonObject(mangaNode.AsObject()) is { } manga)
|
||||
retManga.Add(manga); //Add Publication (Manga) to result
|
||||
}
|
||||
return retManga.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://api.mangadex.org/manga/{publicationId}?includes%5B%5D=manga&includes%5B%5D=cover_art&includes%5B%5D=author&includes%5B%5D=artist&includes%5B%5D=tag", RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
if(result is not null)
|
||||
return MangaFromJsonObject(result["data"]!.AsObject());
|
||||
return null;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
Regex idRex = new (@"https:\/\/mangadex.org\/title\/([A-z0-9-]*)\/.*");
|
||||
string id = idRex.Match(url).Groups[1].Value;
|
||||
return GetMangaFromId(id);
|
||||
}
|
||||
|
||||
private Manga? MangaFromJsonObject(JsonObject manga)
|
||||
{
|
||||
if (!manga.TryGetPropertyValue("id", out JsonNode? idNode))
|
||||
return null;
|
||||
string publicationId = idNode!.GetValue<string>();
|
||||
|
||||
if (!manga.TryGetPropertyValue("attributes", out JsonNode? attributesNode))
|
||||
return null;
|
||||
JsonObject attributes = attributesNode!.AsObject();
|
||||
|
||||
if (!attributes.TryGetPropertyValue("title", out JsonNode? titleNode))
|
||||
return null;
|
||||
string title = titleNode!.AsObject().ContainsKey("en") switch
|
||||
{
|
||||
true => titleNode.AsObject()["en"]!.GetValue<string>(),
|
||||
false => titleNode.AsObject().First().Value!.GetValue<string>()
|
||||
};
|
||||
|
||||
Dictionary<string, string> altTitlesDict = new();
|
||||
if (attributes.TryGetPropertyValue("altTitles", out JsonNode? altTitlesNode))
|
||||
{
|
||||
foreach (JsonNode? altTitleNode in altTitlesNode!.AsArray())
|
||||
{
|
||||
JsonObject altTitleNodeObject = altTitleNode!.AsObject();
|
||||
altTitlesDict.TryAdd(altTitleNodeObject.First().Key, altTitleNodeObject.First().Value!.GetValue<string>());
|
||||
}
|
||||
}
|
||||
|
||||
if (!attributes.TryGetPropertyValue("description", out JsonNode? descriptionNode))
|
||||
return null;
|
||||
string description = descriptionNode!.AsObject().ContainsKey("en") switch
|
||||
{
|
||||
true => descriptionNode.AsObject()["en"]!.GetValue<string>(),
|
||||
false => descriptionNode.AsObject().FirstOrDefault().Value?.GetValue<string>() ?? ""
|
||||
};
|
||||
|
||||
Dictionary<string, string> linksDict = new();
|
||||
if (attributes.TryGetPropertyValue("links", out JsonNode? linksNode) && linksNode is not null)
|
||||
foreach (KeyValuePair<string, JsonNode?> linkKv in linksNode!.AsObject())
|
||||
linksDict.TryAdd(linkKv.Key, linkKv.Value.GetValue<string>());
|
||||
|
||||
string? originalLanguage =
|
||||
attributes.TryGetPropertyValue("originalLanguage", out JsonNode? originalLanguageNode) switch
|
||||
{
|
||||
true => originalLanguageNode?.GetValue<string>(),
|
||||
false => null
|
||||
};
|
||||
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
if (attributes.TryGetPropertyValue("status", out JsonNode? statusNode))
|
||||
{
|
||||
releaseStatus = statusNode?.GetValue<string>().ToLower() switch
|
||||
{
|
||||
"ongoing" => MangaReleaseStatus.Continuing,
|
||||
"completed" => MangaReleaseStatus.Completed,
|
||||
"hiatus" => MangaReleaseStatus.OnHiatus,
|
||||
"cancelled" => MangaReleaseStatus.Cancelled,
|
||||
_ => MangaReleaseStatus.Unreleased
|
||||
};
|
||||
}
|
||||
|
||||
int? year = attributes.TryGetPropertyValue("year", out JsonNode? yearNode) switch
|
||||
{
|
||||
true => yearNode?.GetValue<int>(),
|
||||
false => null
|
||||
};
|
||||
|
||||
HashSet<string> tags = new(128);
|
||||
if (attributes.TryGetPropertyValue("tags", out JsonNode? tagsNode))
|
||||
foreach (JsonNode? tagNode in tagsNode!.AsArray())
|
||||
tags.Add(tagNode!["attributes"]!["name"]!["en"]!.GetValue<string>());
|
||||
|
||||
|
||||
if (!manga.TryGetPropertyValue("relationships", out JsonNode? relationshipsNode))
|
||||
return null;
|
||||
|
||||
JsonNode? coverNode = relationshipsNode!.AsArray()
|
||||
.FirstOrDefault(rel => rel!["type"]!.GetValue<string>().Equals("cover_art"));
|
||||
if (coverNode is null)
|
||||
return null;
|
||||
string fileName = coverNode["attributes"]!["fileName"]!.GetValue<string>();
|
||||
string coverUrl = $"https://uploads.mangadex.org/covers/{publicationId}/{fileName}";
|
||||
|
||||
List<string> authors = new();
|
||||
JsonNode?[] authorNodes = relationshipsNode.AsArray()
|
||||
.Where(rel => rel!["type"]!.GetValue<string>().Equals("author") || rel!["type"]!.GetValue<string>().Equals("artist")).ToArray();
|
||||
foreach (JsonNode? authorNode in authorNodes)
|
||||
{
|
||||
string authorName = authorNode!["attributes"]!["name"]!.GetValue<string>();
|
||||
if(!authors.Contains(authorName))
|
||||
authors.Add(authorName);
|
||||
}
|
||||
|
||||
Manga pub = //TODO
|
||||
return pub;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
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"
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(
|
||||
$"https://api.mangadex.org/manga/{manga.MangaId}/feed?limit={limit}&offset={offset}&translatedLanguage%5B%5D={language}&contentRating%5B%5D=safe&contentRating%5B%5D=suggestive&contentRating%5B%5D=erotica&contentRating%5B%5D=pornographic", RequestType.MangaDexFeed);
|
||||
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 url = $"https://mangadex.org/chapter/{chapterId}";
|
||||
|
||||
string? title = attributes.ContainsKey("title") && attributes["title"] is not null
|
||||
? attributes["title"]!.GetValue<string>()
|
||||
: null;
|
||||
|
||||
float? volume = attributes.ContainsKey("volume") && attributes["volume"] is not null
|
||||
? float.Parse(attributes["volume"]!.GetValue<string>())
|
||||
: null;
|
||||
|
||||
float chapterNum = attributes.ContainsKey("chapter") && attributes["chapter"] is not null
|
||||
? float.Parse(attributes["chapter"]!.GetValue<string>())
|
||||
: 0;
|
||||
|
||||
|
||||
if (attributes.ContainsKey("pages") && attributes["pages"] is not null &&
|
||||
attributes["pages"]!.GetValue<int>() < 1)
|
||||
{
|
||||
continue;
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
Chapter newChapter = new Chapter(manga, url, chapterNum, volume, title);
|
||||
if(!chapters.Contains(newChapter))
|
||||
chapters.Add(newChapter);
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{//Request URLs for Chapter-Images
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"https://api.mangadex.org/at-home/server/{chapter.ChapterId}?forcePort443=false", RequestType.MangaDexImage);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
JsonObject? result = JsonSerializer.Deserialize<JsonObject>(requestResult.result);
|
||||
if (result is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
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)
|
||||
List<string> imageUrls = new();
|
||||
foreach (JsonNode? image in imageFileNames)
|
||||
imageUrls.Add($"{baseUrl}/data/{hash}/{image!.GetValue<string>()}");
|
||||
return imageUrls.ToArray();
|
||||
}
|
||||
}
|
||||
174
API/Schema/MangaConnectors/MangaHere.cs
Normal file
174
API/Schema/MangaConnectors/MangaHere.cs
Normal file
@ -0,0 +1,174 @@
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class MangaHere : MangaConnector
|
||||
{
|
||||
public MangaHere() : base("MangaHere", ["en"], ["www.mangahere.cc"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join('+', Regex.Matches(publicationTitle, "[A-z]*").Where(str => str.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://www.mangahere.cc/search?title={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
if (document.DocumentNode.SelectNodes("//div[contains(concat(' ',normalize-space(@class),' '),' container ')]").Any(node => node.ChildNodes.Any(cNode => cNode.HasClass("search-keywords"))))
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
List<string> urls = document.DocumentNode
|
||||
.SelectNodes("//a[contains(@href, '/manga/') and not(contains(@href, '.html'))]")
|
||||
.Select(thumb => $"https://www.mangahere.cc{thumb.GetAttributeValue("href", "")}").Distinct().ToList();
|
||||
|
||||
HashSet<Manga> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? manga = GetMangaFromUrl(url);
|
||||
if (manga is not null)
|
||||
ret.Add((Manga)manga);
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://www.mangahere.cc/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
return null;
|
||||
|
||||
Regex idRex = new (@"https:\/\/www\.mangahere\.[a-z]{0,63}\/manga\/([0-9A-z\-]+).*");
|
||||
string id = idRex.Match(url).Groups[1].Value;
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, id, url);
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
string originalLanguage = "", status = "";
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
//We dont get posters, because same origin bs HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//img[contains(concat(' ',normalize-space(@class),' '),' detail-info-cover-img ')]");
|
||||
string posterUrl = "http://static.mangahere.cc/v20230914/mangahere/images/nopicture.jpg";
|
||||
|
||||
HtmlNode titleNode = document.DocumentNode.SelectSingleNode("//span[contains(concat(' ',normalize-space(@class),' '),' detail-info-right-title-font ')]");
|
||||
string sortName = titleNode.InnerText;
|
||||
|
||||
List<string> authors = document.DocumentNode
|
||||
.SelectNodes("//p[contains(concat(' ',normalize-space(@class),' '),' detail-info-right-say ')]/a")
|
||||
.Select(node => node.InnerText)
|
||||
.ToList();
|
||||
|
||||
HashSet<string> tags = document.DocumentNode
|
||||
.SelectNodes("//p[contains(concat(' ',normalize-space(@class),' '),' detail-info-right-tag-list ')]/a")
|
||||
.Select(node => node.InnerText)
|
||||
.ToHashSet();
|
||||
|
||||
status = document.DocumentNode.SelectSingleNode("//span[contains(concat(' ',normalize-space(@class),' '),' detail-info-right-title-tip ')]").InnerText;
|
||||
switch (status.ToLower())
|
||||
{
|
||||
case "cancelled": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "hiatus": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "discontinued": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "complete": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
}
|
||||
|
||||
HtmlNode descriptionNode = document.DocumentNode
|
||||
.SelectSingleNode("//p[contains(concat(' ',normalize-space(@class),' '),' fullcontent ')]");
|
||||
string description = descriptionNode.InnerText;
|
||||
|
||||
Manga manga =//TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
string requestUrl = $"https://www.mangahere.cc/manga/{manga.MangaId}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
return Array.Empty<Chapter>();
|
||||
|
||||
List<string> urls = requestResult.htmlDocument.DocumentNode.SelectNodes("//div[@id='list-1']/ul//li//a[contains(@href, '/manga/')]")
|
||||
.Select(node => node.GetAttributeValue("href", "")).ToList();
|
||||
Regex chapterRex = new(@".*\/manga\/[a-zA-Z0-9\-\._\~\!\$\&\'\(\)\*\+\,\;\=\:\@]+\/v([0-9(TBD)]+)\/c([0-9\.]+)\/.*");
|
||||
|
||||
List<Chapter> chapters = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Match rexMatch = chapterRex.Match(url);
|
||||
|
||||
float? volumeNumber = rexMatch.Groups[1].Value == "TBD" ? null : float.Parse(rexMatch.Groups[1].Value);
|
||||
float chapterNumber = float.Parse(rexMatch.Groups[2].Value);
|
||||
string fullUrl = $"https://www.mangahere.cc{url}";
|
||||
|
||||
try
|
||||
{
|
||||
chapters.Add(new Chapter(manga, fullUrl, chapterNumber, volumeNumber, null));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
List<string> imageUrls = new();
|
||||
|
||||
int downloaded = 1;
|
||||
int images = 1;
|
||||
string url = string.Join('/', chapter.Url.Split('/')[..^1]);
|
||||
do
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest($"{url}/{downloaded}.html", RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
imageUrls.AddRange(ParseImageUrlsFromHtml(requestResult.htmlDocument));
|
||||
|
||||
images = requestResult.htmlDocument.DocumentNode
|
||||
.SelectNodes("//a[contains(@href, '/manga/')]")
|
||||
.MaxBy(node => node.GetAttributeValue("data-page", 0))!.GetAttributeValue("data-page", 0);
|
||||
} while (downloaded++ <= images);
|
||||
|
||||
return imageUrls.ToArray();
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
return document.DocumentNode
|
||||
.SelectNodes("//img[contains(concat(' ',normalize-space(@class),' '),' reader-main-img ')]")
|
||||
.Select(node =>
|
||||
{
|
||||
string url = node.GetAttributeValue("src", "");
|
||||
return url.StartsWith("//") ? $"https:{url}" : url;
|
||||
})
|
||||
.ToArray();
|
||||
}
|
||||
}
|
||||
223
API/Schema/MangaConnectors/MangaKatana.cs
Normal file
223
API/Schema/MangaConnectors/MangaKatana.cs
Normal file
@ -0,0 +1,223 @@
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class MangaKatana : MangaConnector
|
||||
{
|
||||
public MangaKatana() : base("MangaKatana", ["en"], ["mangakatana.com"])
|
||||
{
|
||||
this.downloadClient = new HttpDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join("%20", Regex.Matches(publicationTitle, "[A-z]*").Where(m => m.Value.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://mangakatana.com/?search={sanitizedTitle}&search_by=book_name";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
// ReSharper disable once MergeIntoPattern
|
||||
// If a single result is found, the user will be redirected to the results directly instead of a result page
|
||||
if(requestResult.hasBeenRedirected
|
||||
&& requestResult.redirectedToUrl is not null
|
||||
&& requestResult.redirectedToUrl.Contains("mangakatana.com/manga"))
|
||||
{
|
||||
return new [] { ParseSinglePublicationFromHtml(requestResult.result, requestResult.redirectedToUrl.Split('/')[^1], requestResult.redirectedToUrl) };
|
||||
}
|
||||
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.result);
|
||||
return publications;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://mangakatana.com/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
return ParseSinglePublicationFromHtml(requestResult.result, url.Split('/')[^1], url);
|
||||
}
|
||||
|
||||
private Manga[] 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<Manga>();
|
||||
List<string> urls = new();
|
||||
foreach (HtmlNode mangaResult in searchResults)
|
||||
{
|
||||
urls.Add(mangaResult.Descendants("a").First().GetAttributes()
|
||||
.First(a => a.Name == "href").Value);
|
||||
}
|
||||
|
||||
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 Manga ParseSinglePublicationFromHtml(Stream html, string publicationId, string websiteUrl)
|
||||
{
|
||||
StreamReader reader = new(html);
|
||||
string htmlString = reader.ReadToEnd();
|
||||
HtmlDocument document = new();
|
||||
document.LoadHtml(htmlString);
|
||||
Dictionary<string, string> altTitles = new();
|
||||
Dictionary<string, string>? links = null;
|
||||
HashSet<string> tags = new();
|
||||
string[] authors = Array.Empty<string>();
|
||||
string originalLanguage = "";
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
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":
|
||||
switch (value.ToLower())
|
||||
{
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
case "completed": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
}
|
||||
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 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);
|
||||
}
|
||||
|
||||
Manga manga = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
Log($"Getting chapters {manga}");
|
||||
string requestUrl = $"https://mangakatana.com/manga/{manga.MangaId}";
|
||||
// Leaving this in for verification if the page exists
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Chapter>();
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(manga, requestUrl);
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Manga manga, 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");
|
||||
|
||||
Regex volumeRex = new(@"[0-9a-z\-\.]+\/[0-9a-z\-]*v([0-9\.]+)");
|
||||
Regex chapterNumRex = new(@"[0-9a-z\-\.]+\/[0-9a-z\-]*c([0-9\.]+)");
|
||||
Regex chapterNameRex = new(@"Chapter [0-9\.]+:? (.*)");
|
||||
|
||||
foreach (HtmlNode chapterInfo in chapterList.Descendants("tr"))
|
||||
{
|
||||
string fullString = chapterInfo.Descendants("a").First().InnerText;
|
||||
string url = chapterInfo.Descendants("a").First()
|
||||
.GetAttributeValue("href", "");
|
||||
|
||||
float? volumeNumber = volumeRex.IsMatch(url) ? float.Parse(volumeRex.Match(url).Groups[1].Value) : null;
|
||||
float chapterNumber = float.Parse(chapterNumRex.Match(url).Groups[1].Value);
|
||||
string chapterName = chapterNameRex.Match(fullString).Groups[1].Value;
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, url, chapterNumber, volumeNumber, chapterName));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
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 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument);
|
||||
return imageUrls;
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
// 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;
|
||||
}
|
||||
}
|
||||
175
API/Schema/MangaConnectors/MangaLife.cs
Normal file
175
API/Schema/MangaConnectors/MangaLife.cs
Normal file
@ -0,0 +1,175 @@
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class MangaLife : MangaConnector
|
||||
{
|
||||
public MangaLife() : base("Manga4Life", ["en"], ["manga4life.com"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = WebUtility.UrlEncode(publicationTitle);
|
||||
string requestUrl = $"https://manga4life.com/search/?name={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return Array.Empty<Manga>();
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"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"))
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
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();
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']//div[@class='row']//img");
|
||||
string posterUrl = posterNode.GetAttributeValue("src", "");
|
||||
|
||||
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 = MangaReleaseStatus.Cancelled; break;
|
||||
case "hiatus": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "discontinued": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "complete": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.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 = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
RequestResult result = downloadClient.MakeRequest($"https://manga4life.com/manga/{manga.MangaId}", 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);
|
||||
|
||||
float? volumeNumber = rexMatch.Groups[3].Success && rexMatch.Groups[3].Value.Length > 0 ?
|
||||
float.Parse(rexMatch.Groups[3].Value) : null;
|
||||
float chapterNumber = float.Parse(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, fullUrl, chapterNumber, volumeNumber, null));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(chapter.Url, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
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", ""));
|
||||
return urls.ToArray();
|
||||
}
|
||||
}
|
||||
212
API/Schema/MangaConnectors/Manganato.cs
Normal file
212
API/Schema/MangaConnectors/Manganato.cs
Normal file
@ -0,0 +1,212 @@
|
||||
using System.Globalization;
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class Manganato : MangaConnector
|
||||
{
|
||||
public Manganato() : base("Manganato", ["en"], ["manganato.com"])
|
||||
{
|
||||
this.downloadClient = new HttpDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join('_', Regex.Matches(publicationTitle, "[A-z]*").Where(str => str.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://manganato.com/search/story/{sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 ||requestResult.htmlDocument is null)
|
||||
return [];
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
List<HtmlNode> searchResults = document.DocumentNode.Descendants("div").Where(n => n.HasClass("search-story-item")).ToList();
|
||||
List<string> urls = new();
|
||||
foreach (HtmlNode mangaResult in searchResults)
|
||||
{
|
||||
urls.Add(mangaResult.Descendants("a").First(n => n.HasClass("item-title")).GetAttributes()
|
||||
.First(a => a.Name == "href").Value);
|
||||
}
|
||||
|
||||
HashSet<Manga> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? manga = GetMangaFromUrl(url);
|
||||
if (manga is not null)
|
||||
ret.Add(manga);
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://chapmanganato.com/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return null;
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, url.Split('/')[^1], url);
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
Dictionary<string, string> altTitles = new();
|
||||
Dictionary<string, string>? links = null;
|
||||
HashSet<string> tags = new();
|
||||
string[] authors = Array.Empty<string>();
|
||||
string originalLanguage = "";
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
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('-');
|
||||
for (int i = 0; i < authors.Length; i++)
|
||||
authors[i] = authors[i].Replace("\r\n", "");
|
||||
break;
|
||||
case "status":
|
||||
switch (value.ToLower())
|
||||
{
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
case "completed": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
}
|
||||
break;
|
||||
case "genres":
|
||||
string[] genres = value.Split(" - ");
|
||||
for (int i = 0; i < genres.Length; i++)
|
||||
genres[i] = genres[i].Replace("\r\n", "");
|
||||
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 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 pattern = "MMM dd,yyyy HH:mm";
|
||||
|
||||
HtmlNode? oldestChapter = document.DocumentNode
|
||||
.SelectNodes("//span[contains(concat(' ',normalize-space(@class),' '),' chapter-time ')]").MaxBy(
|
||||
node => DateTime.ParseExact(node.GetAttributeValue("title", "Dec 31 2400, 23:59"), pattern,
|
||||
CultureInfo.InvariantCulture).Millisecond);
|
||||
|
||||
|
||||
int year = DateTime.ParseExact(oldestChapter?.GetAttributeValue("title", "Dec 31 2400, 23:59")??"Dec 31 2400, 23:59", pattern,
|
||||
CultureInfo.InvariantCulture).Year;
|
||||
|
||||
Manga manga = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
string requestUrl = $"https://chapmanganato.com/{manga.MangaId}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return [];
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
if (requestResult.htmlDocument is null)
|
||||
return [];
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(manga, requestResult.htmlDocument);
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Manga manga, HtmlDocument document)
|
||||
{
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNode chapterList = document.DocumentNode.Descendants("ul").First(l => l.HasClass("row-content-chapter"));
|
||||
|
||||
Regex volRex = new(@"Vol\.([0-9]+).*");
|
||||
Regex chapterRex = new(@"https:\/\/chapmanganato.[A-z]+\/manga-[A-z0-9]+\/chapter-([0-9\.]+)");
|
||||
Regex nameRex = new(@"Chapter ([0-9]+(\.[0-9]+)*){1}:? (.*)");
|
||||
|
||||
foreach (HtmlNode chapterInfo in chapterList.Descendants("li"))
|
||||
{
|
||||
string fullString = chapterInfo.Descendants("a").First(d => d.HasClass("chapter-name")).InnerText;
|
||||
|
||||
string url = chapterInfo.Descendants("a").First(d => d.HasClass("chapter-name"))
|
||||
.GetAttributeValue("href", "");
|
||||
|
||||
float? volumeNumber = volRex.IsMatch(fullString) ? float.Parse(volRex.Match(fullString).Groups[1].Value) : null;
|
||||
float chapterNumber = float.Parse(chapterRex.Match(url).Groups[1].Value);
|
||||
string chapterName = nameRex.Match(fullString).Groups[3].Value;
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, url, chapterNumber, volumeNumber, chapterName));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
ret.Reverse();
|
||||
return ret;
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
string requestUrl = chapter.Url;
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 ||
|
||||
requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument);
|
||||
return imageUrls;
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
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();
|
||||
}
|
||||
}
|
||||
204
API/Schema/MangaConnectors/Mangasee.cs
Normal file
204
API/Schema/MangaConnectors/Mangasee.cs
Normal file
@ -0,0 +1,204 @@
|
||||
using System.Data;
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using System.Xml.Linq;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
using Newtonsoft.Json;
|
||||
using Soenneker.Utils.String.NeedlemanWunsch;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class Mangasee : MangaConnector
|
||||
{
|
||||
public Mangasee() : base("Mangasee", ["en"], ["mangasee123.com"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient();
|
||||
}
|
||||
|
||||
private struct SearchResult
|
||||
{
|
||||
public string i { get; set; }
|
||||
public string s { get; set; }
|
||||
public string[] a { get; set; }
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string requestUrl = "https://mangasee123.com/_search.php";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
SearchResult[] searchResults = JsonConvert.DeserializeObject<SearchResult[]>(requestResult.htmlDocument!.DocumentNode.InnerText) ??
|
||||
throw new NoNullAllowedException();
|
||||
SearchResult[] filteredResults = FilteredResults(publicationTitle, searchResults);
|
||||
|
||||
|
||||
string[] urls = filteredResults.Select(result => $"https://mangasee123.com/manga/{result.i}").ToArray();
|
||||
List<Manga> searchResultManga = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? newManga = GetMangaFromUrl(url);
|
||||
if(newManga is { } manga)
|
||||
searchResultManga.Add(manga);
|
||||
}
|
||||
return searchResultManga.ToArray();
|
||||
}
|
||||
catch (NoNullAllowedException)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
}
|
||||
|
||||
private readonly string[] _filterWords = {"a", "the", "of", "as", "to", "no", "for", "on", "with", "be", "and", "in", "wa", "at", "be", "ni"};
|
||||
private string ToFilteredString(string input) => string.Join(' ', input.ToLower().Split(' ').Where(word => _filterWords.Contains(word) == false));
|
||||
private SearchResult[] FilteredResults(string publicationTitle, SearchResult[] unfilteredSearchResults)
|
||||
{
|
||||
Dictionary<SearchResult, int> similarity = new();
|
||||
foreach (SearchResult sr in unfilteredSearchResults)
|
||||
{
|
||||
List<int> scores = new();
|
||||
string filteredPublicationString = ToFilteredString(publicationTitle);
|
||||
string filteredSString = ToFilteredString(sr.s);
|
||||
scores.Add(NeedlemanWunschStringUtil.CalculateSimilarity(filteredSString, filteredPublicationString));
|
||||
foreach (string srA in sr.a)
|
||||
{
|
||||
string filteredAString = ToFilteredString(srA);
|
||||
scores.Add(NeedlemanWunschStringUtil.CalculateSimilarity(filteredAString, filteredPublicationString));
|
||||
}
|
||||
similarity.Add(sr, scores.Sum() / scores.Count);
|
||||
}
|
||||
|
||||
List<SearchResult> ret = similarity.OrderBy(s => s.Value).Take(10).Select(s => s.Key).ToList();
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://mangasee123.com/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
Regex publicationIdRex = new(@"https:\/\/mangasee123.com\/manga\/(.*)(\/.*)*");
|
||||
string publicationId = publicationIdRex.Match(url).Groups[1].Value;
|
||||
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if((int)requestResult.statusCode < 300 && (int)requestResult.statusCode >= 200 && requestResult.htmlDocument is not null)
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, publicationId, url);
|
||||
return null;
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
string originalLanguage = "", status = "";
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
HashSet<string> tags = new();
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
HtmlNode posterNode = document.DocumentNode.SelectSingleNode("//div[@class='BoxBody']//div[@class='row']//img");
|
||||
string posterUrl = posterNode.GetAttributeValue("src", "");
|
||||
|
||||
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 = MangaReleaseStatus.Cancelled; break;
|
||||
case "hiatus": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "discontinued": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "complete": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.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 = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
try
|
||||
{
|
||||
XDocument doc = XDocument.Load($"https://mangasee123.com/rss/{manga.MangaId}.xml");
|
||||
XElement[] chapterItems = doc.Descendants("item").ToArray();
|
||||
List<Chapter> chapters = new();
|
||||
Regex chVolRex = new(@".*chapter-([0-9\.]+)(?:-index-([0-9\.]+))?.*");
|
||||
foreach (XElement chapter in chapterItems)
|
||||
{
|
||||
string url = chapter.Descendants("link").First().Value;
|
||||
Match m = chVolRex.Match(url);
|
||||
float? volumeNumber = m.Groups[2].Success ? float.Parse(m.Groups[2].Value) : null;
|
||||
float chapterNumber = float.Parse(m.Groups[1].Value);
|
||||
|
||||
string chapterUrl = Regex.Replace(url, @"-page-[0-9]+(\.html)", ".html");
|
||||
try
|
||||
{
|
||||
chapters.Add(new Chapter(manga, chapterUrl,chapterNumber, volumeNumber, null));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
catch (HttpRequestException e)
|
||||
{
|
||||
return Array.Empty<Chapter>();
|
||||
}
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(chapter.Url, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
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", ""));
|
||||
return urls.ToArray();
|
||||
}
|
||||
}
|
||||
211
API/Schema/MangaConnectors/Mangaworld.cs
Normal file
211
API/Schema/MangaConnectors/Mangaworld.cs
Normal file
@ -0,0 +1,211 @@
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class Mangaworld : MangaConnector
|
||||
{
|
||||
public Mangaworld() : base("Mangaworld", ["it"], ["www.mangaworld.ac"])
|
||||
{
|
||||
this.downloadClient = new HttpDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(str => str.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://www.mangaworld.ac/archive?keyword={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return Array.Empty<Manga>();
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
if (!document.DocumentNode.SelectSingleNode("//div[@class='comics-grid']").ChildNodes
|
||||
.Any(node => node.HasClass("entry")))
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
List<string> urls = document.DocumentNode
|
||||
.SelectNodes(
|
||||
"//div[@class='comics-grid']//div[@class='entry']//a[contains(concat(' ',normalize-space(@class),' '),'thumb')]")
|
||||
.Select(thumb => thumb.GetAttributeValue("href", "")).ToList();
|
||||
|
||||
HashSet<Manga> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? manga = GetMangaFromUrl(url);
|
||||
if (manga is not null)
|
||||
ret.Add((Manga)manga);
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://www.mangaworld.ac/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return null;
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return null;
|
||||
|
||||
Regex idRex = new (@"https:\/\/www\.mangaworld\.[a-z]{0,63}\/manga\/([0-9]+\/[0-9A-z\-]+).*");
|
||||
string id = idRex.Match(url).Groups[1].Value;
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, id, url);
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
Dictionary<string, string> altTitles = new();
|
||||
Dictionary<string, string>? links = null;
|
||||
string originalLanguage = "";
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
HtmlNode infoNode = document.DocumentNode.Descendants("div").First(d => d.HasClass("info"));
|
||||
|
||||
string sortName = infoNode.Descendants("h1").First().InnerText;
|
||||
|
||||
HtmlNode metadata = infoNode.Descendants().First(d => d.HasClass("meta-data"));
|
||||
|
||||
HtmlNode altTitlesNode = metadata.SelectSingleNode("//span[text()='Titoli alternativi: ' or text()='Titolo alternativo: ']/..").ChildNodes[1];
|
||||
|
||||
string[] alts = altTitlesNode.InnerText.Split(", ");
|
||||
for(int i = 0; i < alts.Length; i++)
|
||||
altTitles.Add(i.ToString(), alts[i]);
|
||||
|
||||
HtmlNode genresNode =
|
||||
metadata.SelectSingleNode("//span[text()='Generi: ' or text()='Genero: ']/..");
|
||||
HashSet<string> tags = genresNode.SelectNodes("a").Select(node => node.InnerText).ToHashSet();
|
||||
|
||||
HtmlNode authorsNode =
|
||||
metadata.SelectSingleNode("//span[text()='Autore: ' or text()='Autori: ']/..");
|
||||
string[] authors = authorsNode.SelectNodes("a").Select(node => node.InnerText).ToArray();
|
||||
|
||||
string status = metadata.SelectSingleNode("//span[text()='Stato: ']/..").SelectNodes("a").First().InnerText;
|
||||
// ReSharper disable 5 times StringLiteralTypo
|
||||
switch (status.ToLower())
|
||||
{
|
||||
case "cancellato": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "in pausa": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "droppato": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "finito": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "in corso": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
}
|
||||
|
||||
string posterUrl = document.DocumentNode.SelectSingleNode("//img[@class='rounded']").GetAttributeValue("src", "");
|
||||
|
||||
string description = document.DocumentNode.SelectSingleNode("//div[@id='noidungm']").InnerText;
|
||||
|
||||
string yearString = metadata.SelectSingleNode("//span[text()='Anno di uscita: ']/..").SelectNodes("a").First().InnerText;
|
||||
int year = Convert.ToInt32(yearString);
|
||||
|
||||
Manga manga = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
string requestUrl = $"https://www.mangaworld.ac/manga/{manga.MangaId}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
return [];
|
||||
|
||||
List<Chapter> chapters = ParseChaptersFromHtml(manga, requestResult.htmlDocument);
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
private List<Chapter> ParseChaptersFromHtml(Manga manga, HtmlDocument document)
|
||||
{
|
||||
List<Chapter> ret = new();
|
||||
|
||||
HtmlNode chaptersWrapper =
|
||||
document.DocumentNode.SelectSingleNode(
|
||||
"//div[contains(concat(' ',normalize-space(@class),' '),'chapters-wrapper')]");
|
||||
|
||||
Regex volumeRex = new(@"[Vv]olume ([0-9]+).*");
|
||||
Regex chapterRex = new(@"[Cc]apitolo ([0-9]+(?:\.[0-9]+)?).*");
|
||||
Regex idRex = new(@".*\/read\/([a-z0-9]+)(?:[?\/].*)?");
|
||||
if (chaptersWrapper.Descendants("div").Any(descendant => descendant.HasClass("volume-element")))
|
||||
{
|
||||
foreach (HtmlNode volNode in document.DocumentNode.SelectNodes("//div[contains(concat(' ',normalize-space(@class),' '),'volume-element')]"))
|
||||
{
|
||||
string volume = volumeRex.Match(volNode.SelectNodes("div").First(node => node.HasClass("volume")).SelectSingleNode("p").InnerText).Groups[1].Value;
|
||||
foreach (HtmlNode chNode in volNode.SelectNodes("div").First(node => node.HasClass("volume-chapters")).SelectNodes("div"))
|
||||
{
|
||||
|
||||
string number = chapterRex.Match(chNode.SelectSingleNode("a").SelectSingleNode("span").InnerText).Groups[1].Value;
|
||||
string url = chNode.SelectSingleNode("a").GetAttributeValue("href", "");
|
||||
string id = idRex.Match(chNode.SelectSingleNode("a").GetAttributeValue("href", "")).Groups[1].Value;
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, null, volume, number, url, id));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
foreach (HtmlNode chNode in chaptersWrapper.SelectNodes("div").Where(node => node.HasClass("chapter")))
|
||||
{
|
||||
string number = chapterRex.Match(chNode.SelectSingleNode("a").SelectSingleNode("span").InnerText).Groups[1].Value;
|
||||
string url = chNode.SelectSingleNode("a").GetAttributeValue("href", "");
|
||||
string id = idRex.Match(chNode.SelectSingleNode("a").GetAttributeValue("href", "")).Groups[1].Value;
|
||||
try
|
||||
{
|
||||
ret.Add(new Chapter(manga, null, null, number, url, id));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ret.Reverse();
|
||||
return ret;
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
string requestUrl = $"{chapter.Url}?style=list";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
string[] imageUrls = ParseImageUrlsFromHtml(requestResult.htmlDocument);
|
||||
return imageUrls;
|
||||
}
|
||||
|
||||
private string[] ParseImageUrlsFromHtml(HtmlDocument document)
|
||||
{
|
||||
List<string> ret = new();
|
||||
|
||||
HtmlNode imageContainer =
|
||||
document.DocumentNode.SelectSingleNode("//div[@id='page']");
|
||||
foreach(HtmlNode imageNode in imageContainer.Descendants("img"))
|
||||
ret.Add(imageNode.GetAttributeValue("src", ""));
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
}
|
||||
173
API/Schema/MangaConnectors/ManhuaPlus.cs
Normal file
173
API/Schema/MangaConnectors/ManhuaPlus.cs
Normal file
@ -0,0 +1,173 @@
|
||||
using System.Net;
|
||||
using System.Text.RegularExpressions;
|
||||
using API.MangaDownloadClients;
|
||||
using HtmlAgilityPack;
|
||||
|
||||
namespace API.Schema.MangaConnectors;
|
||||
|
||||
public class ManhuaPlus : MangaConnector
|
||||
{
|
||||
public ManhuaPlus() : base("ManhuaPlus", ["en"], ["manhuaplus.org"])
|
||||
{
|
||||
this.downloadClient = new ChromiumDownloadClient();
|
||||
}
|
||||
|
||||
public override Manga[] GetManga(string publicationTitle = "")
|
||||
{
|
||||
string sanitizedTitle = string.Join(' ', Regex.Matches(publicationTitle, "[A-z]*").Where(str => str.Length > 0)).ToLower();
|
||||
string requestUrl = $"https://manhuaplus.org/search?keyword={sanitizedTitle}";
|
||||
RequestResult requestResult =
|
||||
downloadClient.MakeRequest(requestUrl, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300)
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
if (requestResult.htmlDocument is null)
|
||||
return Array.Empty<Manga>();
|
||||
Manga[] publications = ParsePublicationsFromHtml(requestResult.htmlDocument);
|
||||
return publications;
|
||||
}
|
||||
|
||||
private Manga[] ParsePublicationsFromHtml(HtmlDocument document)
|
||||
{
|
||||
if (document.DocumentNode.SelectSingleNode("//h1/../..").ChildNodes//I already want to not.
|
||||
.Any(node => node.InnerText.Contains("No manga found")))
|
||||
return Array.Empty<Manga>();
|
||||
|
||||
List<string> urls = document.DocumentNode
|
||||
.SelectNodes("//h1/../..//a[contains(@href, 'https://manhuaplus.org/manga/') and contains(concat(' ',normalize-space(@class),' '),' clamp ') and not(contains(@href, '/chapter'))]")
|
||||
.Select(mangaNode => mangaNode.GetAttributeValue("href", "")).ToList();
|
||||
|
||||
HashSet<Manga> ret = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Manga? manga = GetMangaFromUrl(url);
|
||||
if (manga is not null)
|
||||
ret.Add((Manga)manga);
|
||||
}
|
||||
|
||||
return ret.ToArray();
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromId(string publicationId)
|
||||
{
|
||||
return GetMangaFromUrl($"https://manhuaplus.org/manga/{publicationId}");
|
||||
}
|
||||
|
||||
public override Manga? GetMangaFromUrl(string url)
|
||||
{
|
||||
Regex publicationIdRex = new(@"https:\/\/manhuaplus.org\/manga\/(.*)(\/.*)*");
|
||||
string publicationId = publicationIdRex.Match(url).Groups[1].Value;
|
||||
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(url, RequestType.MangaInfo);
|
||||
if((int)requestResult.statusCode < 300 && (int)requestResult.statusCode >= 200 && requestResult.htmlDocument is not null && requestResult.redirectedToUrl != "https://manhuaplus.org/home") //When manga doesnt exists it redirects to home
|
||||
return ParseSinglePublicationFromHtml(requestResult.htmlDocument, publicationId, url);
|
||||
return null;
|
||||
}
|
||||
|
||||
private Manga ParseSinglePublicationFromHtml(HtmlDocument document, string publicationId, string websiteUrl)
|
||||
{
|
||||
string originalLanguage = "", status = "";
|
||||
Dictionary<string, string> altTitles = new(), links = new();
|
||||
HashSet<string> tags = new();
|
||||
MangaReleaseStatus releaseStatus = MangaReleaseStatus.Unreleased;
|
||||
|
||||
HtmlNode posterNode = document.DocumentNode.SelectSingleNode("/html/body/main/div/div/div[2]/div[1]/figure/a/img");//BRUH
|
||||
Regex posterRex = new(@".*(\/uploads/covers/[a-zA-Z0-9\-\._\~\!\$\&\'\(\)\*\+\,\;\=\:\@]+).*");
|
||||
string posterUrl = $"https://manhuaplus.org/{posterRex.Match(posterNode.GetAttributeValue("src", "")).Groups[1].Value}";
|
||||
|
||||
HtmlNode titleNode = document.DocumentNode.SelectSingleNode("//h1");
|
||||
string sortName = titleNode.InnerText.Replace("\n", "");
|
||||
|
||||
List<string> authors = new();
|
||||
try
|
||||
{
|
||||
HtmlNode[] authorsNodes = document.DocumentNode
|
||||
.SelectNodes("//a[contains(@href, 'https://manhuaplus.org/authors/')]")
|
||||
.ToArray();
|
||||
foreach (HtmlNode authorNode in authorsNodes)
|
||||
authors.Add(authorNode.InnerText);
|
||||
}
|
||||
catch (ArgumentNullException e)
|
||||
{
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
HtmlNode[] genreNodes = document.DocumentNode
|
||||
.SelectNodes("//a[contains(@href, 'https://manhuaplus.org/genres/')]").ToArray();
|
||||
foreach (HtmlNode genreNode in genreNodes)
|
||||
tags.Add(genreNode.InnerText.Replace("\n", ""));
|
||||
}
|
||||
catch (ArgumentNullException e)
|
||||
{
|
||||
}
|
||||
|
||||
Regex yearRex = new(@"(?:[0-9]{1,2}\/){2}([0-9]{2,4}) [0-9]{1,2}:[0-9]{1,2}");
|
||||
HtmlNode yearNode = document.DocumentNode.SelectSingleNode("//aside//i[contains(concat(' ',normalize-space(@class),' '),' fa-clock ')]/../span");
|
||||
Match match = yearRex.Match(yearNode.InnerText);
|
||||
int year = match.Success && match.Groups[1].Success ? int.Parse(match.Groups[1].Value) : 1960;
|
||||
|
||||
status = document.DocumentNode.SelectSingleNode("//aside//i[contains(concat(' ',normalize-space(@class),' '),' fa-rss ')]/../span").InnerText.Replace("\n", "");
|
||||
switch (status.ToLower())
|
||||
{
|
||||
case "cancelled": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "hiatus": releaseStatus = MangaReleaseStatus.OnHiatus; break;
|
||||
case "discontinued": releaseStatus = MangaReleaseStatus.Cancelled; break;
|
||||
case "complete": releaseStatus = MangaReleaseStatus.Completed; break;
|
||||
case "ongoing": releaseStatus = MangaReleaseStatus.Continuing; break;
|
||||
}
|
||||
|
||||
HtmlNode descriptionNode = document.DocumentNode
|
||||
.SelectSingleNode("//div[@id='syn-target']");
|
||||
string description = descriptionNode.InnerText;
|
||||
|
||||
Manga manga = //TODO
|
||||
return manga;
|
||||
}
|
||||
|
||||
public override Chapter[] GetChapters(Manga manga, string language="en")
|
||||
{
|
||||
RequestResult result = downloadClient.MakeRequest($"https://manhuaplus.org/manga/{manga.MangaId}", RequestType.Default);
|
||||
if ((int)result.statusCode < 200 || (int)result.statusCode >= 300 || result.htmlDocument is null)
|
||||
{
|
||||
return Array.Empty<Chapter>();
|
||||
}
|
||||
|
||||
HtmlNodeCollection chapterNodes = result.htmlDocument.DocumentNode.SelectNodes("//li[contains(concat(' ',normalize-space(@class),' '),' chapter ')]//a");
|
||||
string[] urls = chapterNodes.Select(node => node.GetAttributeValue("href", "")).ToArray();
|
||||
Regex urlRex = new (@".*\/chapter-([0-9\-]+).*");
|
||||
|
||||
List<Chapter> chapters = new();
|
||||
foreach (string url in urls)
|
||||
{
|
||||
Match rexMatch = urlRex.Match(url);
|
||||
|
||||
float chapterNumber = float.Parse(rexMatch.Groups[1].Value);
|
||||
string fullUrl = url;
|
||||
try
|
||||
{
|
||||
chapters.Add(new Chapter(manga, fullUrl, chapterNumber, null, null));
|
||||
}
|
||||
catch (Exception e)
|
||||
{
|
||||
}
|
||||
}
|
||||
//Return Chapters ordered by Chapter-Number
|
||||
return chapters.Order().ToArray();
|
||||
}
|
||||
|
||||
internal override string[] GetChapterImageUrls(Chapter chapter)
|
||||
{
|
||||
RequestResult requestResult = this.downloadClient.MakeRequest(chapter.Url, RequestType.Default);
|
||||
if ((int)requestResult.statusCode < 200 || (int)requestResult.statusCode >= 300 || requestResult.htmlDocument is null)
|
||||
{
|
||||
return [];
|
||||
}
|
||||
|
||||
HtmlDocument document = requestResult.htmlDocument;
|
||||
|
||||
HtmlNode[] images = document.DocumentNode.SelectNodes("//a[contains(concat(' ',normalize-space(@class),' '),' readImg ')]/img").ToArray();
|
||||
List<string> urls = images.Select(node => node.GetAttributeValue("src", "")).ToList();
|
||||
return urls.ToArray();
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user