mikf/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[mangakakalot] update domain and fix extraction

Browse Source
This commit is contained in:
Mike Fährmann 2021-10-31 02:11:56 +02:00
parent 69cd573809
commit 4c49174579
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
2 changed files with 44 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/supportedsites.md
View File

@ -447,7 +447,7 @@ Consider all sites to be NSFW unless otherwise known.
</tr> </tr>
<tr> <tr>
<td>MangaKakalot</td> <td>MangaKakalot</td>
<td>https://mangakakalot.com/</td> <td>https://mangakakalot.tv/</td>
<td>Chapters, Manga</td> <td>Chapters, Manga</td>
<td></td> <td></td>
</tr> </tr>

91
gallery_dl/extractor/mangakakalot.py
View File

@ -1,12 +1,13 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2020 Jake Mannens # Copyright 2020 Jake Mannens
# Copyright 2021 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as # it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation. # published by the Free Software Foundation.
"""Extract manga-chapters and entire manga from https://mangakakalot.com/""" """Extractors for https://mangakakalot.tv/"""
from .common import ChapterExtractor, MangaExtractor from .common import ChapterExtractor, MangaExtractor
from .. import text from .. import text
@ -16,34 +17,24 @@ import re
class MangakakalotBase(): class MangakakalotBase():
"""Base class for mangakakalot extractors""" """Base class for mangakakalot extractors"""
category = "mangakakalot" category = "mangakakalot"
root = "https://mangakakalot.com" root = "https://ww.mangakakalot.tv"
@staticmethod
def parse_page(page, data):
"""Parse metadata on 'page' and add it to 'data'"""
text.extract_all(page, (
("manga" , '<h1>', '</h1>'),
('author' , '<li>Author(s) :\n', '</a>'),
), values=data)
data["author"] = text.remove_html(data["author"])
return data
class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor): class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor):
"""Extractor for manga-chapters from mangakakalot.com""" """Extractor for manga chapters from mangakakalot.tv"""
pattern = (r"(?:https?://)?(?:www\.)?mangakakalot\.com" pattern = (r"(?:https?://)?(?:www?\.)?mangakakalot\.tv"
r"(/chapter/\w+/chapter_[^/?#]+)") r"(/chapter/[^/?#]+/chapter[_-][^/?#]+)")
test = ( test = (
("https://mangakakalot.com/chapter/rx922077/chapter_6", { ("https://ww.mangakakalot.tv/chapter/manga-hl984546/chapter-6", {
"pattern": r"https://s\d+\.\w+\.com/mangakakalot/r\d+/rx922077/" "pattern": r"https://cm\.blazefast\.co"
r"chapter_6_master_help_me_out/\d+\.jpg", r"/[0-9a-f]{2}/[0-9a-f]{2}/[0-9a-f]{32}\.jpg",
"keyword": "80fde46d2210a6c17f0b2f7c1c89f0f56b65e157", "keyword": "e9646a76a210f1eb4a71b4134664814c99d65d48",
"count": 14, "count": 14,
}), }),
(("https://mangakakalot.com/chapter" (("https://mangakakalot.tv/chapter"
"/hatarakanai_futari_the_jobless_siblings/chapter_20.1"), { "/hatarakanai_futari_the_jobless_siblings/chapter_20.1"), {
"keyword": "6b24349bb16f41ef1c4350200c1ccda5f09ae136", "keyword": "14c430737ff600b26a3811815905f34dd6a6c8c6",
"content": "7196aed8bb1536806bf55033ed1f2ed172c86f9a", "content": "b3eb1f139caef98d9dcd8ba6a5ee146a13deebc4",
"count": 2, "count": 2,
}), }),
) )
@ -54,10 +45,10 @@ class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor):
self.session.headers['Referer'] = self.root self.session.headers['Referer'] = self.root
def metadata(self, page): def metadata(self, page):
_ , pos = text.extract(page, '<span itemprop="name">', '<') _ , pos = text.extract(page, '<span itemprop="title">', '<')
manga , pos = text.extract(page, '<span itemprop="name">', '<', pos) manga , pos = text.extract(page, '<span itemprop="title">', '<', pos)
info , pos = text.extract(page, '<span itemprop="name">', '<', pos) info , pos = text.extract(page, '<span itemprop="title">', '<', pos)
author, pos = text.extract(page, '. Author: ', ' already has ', pos) author, pos = text.extract(page, '. Author:', ' already has ', pos)
match = re.match( match = re.match(
r"(?:[Vv]ol\. *(\d+) )?" r"(?:[Vv]ol\. *(\d+) )?"
@ -69,7 +60,7 @@ class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor):
return { return {
"manga" : text.unescape(manga), "manga" : text.unescape(manga),
"title" : text.unescape(title) if title else "", "title" : text.unescape(title) if title else "",
"author" : text.unescape(author) if author else "", "author" : text.unescape(author).strip() if author else "",
"volume" : text.parse_int(volume), "volume" : text.parse_int(volume),
"chapter" : text.parse_int(chapter), "chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor, "chapter_minor": sep + minor,
@ -78,42 +69,46 @@ class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor):
} }
def images(self, page): def images(self, page):
page = text.extract(
page, 'class="container-chapter-reader', '\n<div')[0]
return [ return [
(url, None) (url, None)
for url in text.extract_iter(page, '<img src="', '"') for url in text.extract_iter(page, '<img data-src="', '"')
] ]
class MangakakalotMangaExtractor(MangakakalotBase, MangaExtractor): class MangakakalotMangaExtractor(MangakakalotBase, MangaExtractor):
"""Extractor for manga from mangakakalot.com""" """Extractor for manga from mangakakalot.tv"""
chapterclass = MangakakalotChapterExtractor chapterclass = MangakakalotChapterExtractor
pattern = (r"(?:https?://)?(?:www\.)?mangakakalot\.com" pattern = (r"(?:https?://)?(?:www?\.)?mangakakalot\.tv"
r"(/(?:manga/|read-)\w+)") r"(/manga/[^/?#]+)")
test = ( test = (
("https://mangakakalot.com/manga/lk921810", { ("https://ww.mangakakalot.tv/manga/lk921810", {
"url": "d262134b65993b031406f7b9d9442c9afd321a27", "url": "654d040c17728c9c8756fce7092b084e8dcf67d2",
}), }),
("https://mangakakalot.com/read-ry3sw158504884246", { ("https://mangakakalot.tv/manga/manga-jk986845", {
"pattern": MangakakalotChapterExtractor.pattern, "pattern": MangakakalotChapterExtractor.pattern,
"count": ">= 40" "count": ">= 30",
}), }),
) )
def chapters(self, page): def chapters(self, page):
results = [] data = {"lang": "en", "language": "English"}
data = self.parse_page(page, {"lang": "en", "language": "English"}) data["manga"], pos = text.extract(page, "<h1>", "<")
author, pos = text.extract(page, "<li>Author(s) :", "</a>", pos)
data["author"] = text.remove_html(author)
needle = '<div class="row">\n<span><a href="' results = []
pos = page.index('<div class="chapter-list">') for chapter in text.extract_iter(page, '<div class="row">', '</div>'):
while True: url, pos = text.extract(chapter, '<a href="', '"')
url, pos = text.extract(page, needle, '"', pos) title, pos = text.extract(chapter, '>', '</a>', pos)
if not url: data["title"] = title.partition(": ")[2]
return results data["date"] , pos = text.extract(
data["title"], pos = text.extract(page, '>', '</a>', pos) chapter, '<span title=" ', '"', pos)
data["date"] , pos = text.extract(page, '<span title="', '">', pos)
chapter, sep, minor = url.rpartition("/chapter_")[2].partition(".") chapter, sep, minor = url.rpartition("/chapter-")[2].partition(".")
data["chapter"] = text.parse_int(chapter) data["chapter"] = text.parse_int(chapter)
data["chapter_minor"] = sep + minor data["chapter_minor"] = sep + minor
if url.startswith("/"):
url = self.root + url
results.append((url, data.copy())) results.append((url, data.copy()))
return results