1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-24 03:32:33 +01:00
gallery-dl/gallery_dl/extractor/mangakakalot.py
2022-07-12 15:49:22 +02:00

109 lines
4.0 KiB
Python

# -*- coding: utf-8 -*-
# Copyright 2020 Jake Mannens
# Copyright 2021-2022 Mike Fährmann
#
# 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
# published by the Free Software Foundation.
"""Extractors for https://mangakakalot.tv/"""
from .common import ChapterExtractor, MangaExtractor
from .. import text
import re
BASE_PATTERN = r"(?:https?://)?(?:ww[\dw]?\.)?mangakakalot\.tv"
class MangakakalotBase():
"""Base class for mangakakalot extractors"""
category = "mangakakalot"
root = "https://ww3.mangakakalot.tv"
class MangakakalotChapterExtractor(MangakakalotBase, ChapterExtractor):
"""Extractor for manga chapters from mangakakalot.tv"""
pattern = BASE_PATTERN + r"(/chapter/[^/?#]+/chapter[_-][^/?#]+)"
test = (
("https://ww3.mangakakalot.tv/chapter/manga-jk986845/chapter-34.2", {
"pattern": r"https://cm\.blazefast\.co"
r"/[0-9a-f]{2}/[0-9a-f]{2}/[0-9a-f]{32}\.jpg",
"keyword": "0f1586ff52f0f9cbbb25306ae64ab718f8a6a633",
"count": 9,
}),
("https://mangakakalot.tv/chapter"
"/hatarakanai_futari_the_jobless_siblings/chapter_20.1"),
)
def __init__(self, match):
self.path = match.group(1)
ChapterExtractor.__init__(self, match, self.root + self.path)
self.session.headers['Referer'] = self.root
def metadata(self, page):
_ , pos = text.extract(page, '<span itemprop="title">', '<')
manga , pos = text.extract(page, '<span itemprop="title">', '<', pos)
info , pos = text.extract(page, '<span itemprop="title">', '<', pos)
author, pos = text.extract(page, '. Author:', ' already has ', pos)
match = re.match(
r"(?:[Vv]ol\. *(\d+) )?"
r"[Cc]hapter *([^:]*)"
r"(?:: *(.+))?", info)
volume, chapter, title = match.groups() if match else ("", "", info)
chapter, sep, minor = chapter.partition(".")
return {
"manga" : text.unescape(manga),
"title" : text.unescape(title) if title else "",
"author" : text.unescape(author).strip() if author else "",
"volume" : text.parse_int(volume),
"chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor,
"lang" : "en",
"language" : "English",
}
def images(self, page):
return [
(url, None)
for url in text.extract_iter(page, '<img data-src="', '"')
]
class MangakakalotMangaExtractor(MangakakalotBase, MangaExtractor):
"""Extractor for manga from mangakakalot.tv"""
chapterclass = MangakakalotChapterExtractor
pattern = BASE_PATTERN + r"(/manga/[^/?#]+)"
test = (
("https://ww3.mangakakalot.tv/manga/manga-jk986845", {
"pattern": MangakakalotChapterExtractor.pattern,
"count": ">= 30",
}),
("https://mangakakalot.tv/manga/lk921810"),
)
def chapters(self, page):
data = {"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)
results = []
for chapter in text.extract_iter(page, '<div class="row">', '</div>'):
url, pos = text.extract(chapter, '<a href="', '"')
title, pos = text.extract(chapter, '>', '</a>', pos)
data["title"] = title.partition(": ")[2]
data["date"] , pos = text.extract(
chapter, '<span title=" ', '"', pos)
chapter, sep, minor = url.rpartition("/chapter-")[2].partition(".")
data["chapter"] = text.parse_int(chapter)
data["chapter_minor"] = sep + minor
if url.startswith("/"):
url = self.root + url
results.append((url, data.copy()))
return results