161 lines
5.3 KiB
Python
161 lines
5.3 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright 2020 Jake Mannens
|
|
# Copyright 2021-2026 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://www.mangakakalot.gg/ and mirror sites"""
|
|
|
|
from .common import BaseExtractor, ChapterExtractor, MangaExtractor, Message
|
|
from .. import text, util
|
|
|
|
|
|
class ManganeloExtractor(BaseExtractor):
|
|
basecategory = "manganelo"
|
|
|
|
|
|
BASE_PATTERN = ManganeloExtractor.update({
|
|
"nelomanga": {
|
|
"root" : "https://www.nelomanga.net",
|
|
"pattern": r"(?:www\.)?nelomanga\.net",
|
|
},
|
|
"natomanga": {
|
|
"root" : "https://www.natomanga.com",
|
|
"pattern": r"(?:www\.)?natomanga\.com",
|
|
},
|
|
"manganato": {
|
|
"root" : "https://www.manganato.gg",
|
|
"pattern": r"(?:www\.)?manganato\.gg",
|
|
},
|
|
"mangakakalot": {
|
|
"root" : "https://www.mangakakalot.gg",
|
|
"pattern": r"(?:www\.)?mangakakalot\.gg",
|
|
},
|
|
})
|
|
|
|
|
|
class ManganeloChapterExtractor(ManganeloExtractor, ChapterExtractor):
|
|
"""Extractor for manganelo manga chapters"""
|
|
pattern = BASE_PATTERN + r"(/manga/[^/?#]+/chapter-[^/?#]+)"
|
|
example = "https://www.mangakakalot.gg/manga/MANGA_NAME/chapter-123"
|
|
|
|
def __init__(self, match):
|
|
ManganeloExtractor.__init__(self, match)
|
|
self.page_url = self.root + self.groups[-1]
|
|
|
|
def metadata(self, page):
|
|
extr = text.extract_from(page)
|
|
|
|
data = {
|
|
"date" : self.parse_datetime_iso(extr(
|
|
'"datePublished": "', '"')[:19]),
|
|
"date_updated": self.parse_datetime_iso(extr(
|
|
'"dateModified": "', '"')[:19]),
|
|
"manga_id" : text.parse_int(extr("comic_id =", ";")),
|
|
"chapter_id" : text.parse_int(extr("chapter_id =", ";")),
|
|
"manga" : extr("comic_name =", ";").strip('" '),
|
|
"lang" : "en",
|
|
"language" : "English",
|
|
}
|
|
|
|
chapter_name = extr("chapter_name =", ";").strip('" ')
|
|
chapter, sep, minor = chapter_name.rpartition(" ")[2].partition(".")
|
|
data["chapter"] = text.parse_int(chapter)
|
|
data["chapter_minor"] = sep + minor
|
|
data["author"] = extr(". Author:", " already has ").strip()
|
|
|
|
return data
|
|
|
|
def images(self, page):
|
|
extr = text.extract_from(page)
|
|
cdns = util.json_loads(extr("var cdns =", ";"))[0]
|
|
imgs = util.json_loads(extr("var chapterImages =", ";"))
|
|
|
|
if cdns[-1] != "/":
|
|
cdns += "/"
|
|
|
|
return [
|
|
(cdns + path, None)
|
|
for path in imgs
|
|
]
|
|
|
|
|
|
class ManganeloMangaExtractor(ManganeloExtractor, MangaExtractor):
|
|
"""Extractor for manganelo manga"""
|
|
chapterclass = ManganeloChapterExtractor
|
|
pattern = BASE_PATTERN + r"(/manga/[^/?#]+)$"
|
|
example = "https://www.mangakakalot.gg/manga/MANGA_NAME"
|
|
|
|
def __init__(self, match):
|
|
ManganeloExtractor.__init__(self, match)
|
|
self.page_url = self.root + self.groups[-1]
|
|
|
|
def chapters(self, page):
|
|
extr = text.extract_from(page)
|
|
|
|
url = extr('property="og:url" content="', '"')
|
|
slug = url[url.rfind("/")+1:]
|
|
|
|
info = {
|
|
"manga" : text.unescape(extr("<h1>", "<")),
|
|
"manga_url" : url,
|
|
"manga_slug": slug,
|
|
"author": text.remove_html(extr("<li>Author(s) :", "</li>")),
|
|
"status": extr("<li>Status :", "<").strip(),
|
|
"date_updated": self.parse_datetime(extr(
|
|
"<li>Last updated :", "<").strip(), "%b-%d-%Y %I:%M:%S %p"),
|
|
"tags" : text.split_html(extr(">Genres :", "</li>"))[::2],
|
|
"lang" : "en",
|
|
}
|
|
info["tags"].sort()
|
|
|
|
base = url + "/"
|
|
url = f"{self.root}/api/manga/{slug}/chapters?limit=-1"
|
|
|
|
results = []
|
|
data = self.request_json(url)["data"]
|
|
for ch in data["chapters"]:
|
|
slug = ch["chapter_slug"]
|
|
chapter, sep, minor = slug[8:].partition("-")
|
|
results.append((base + slug, {
|
|
**info,
|
|
"chapter": text.parse_int(chapter),
|
|
"chapter_minor": (sep and ".") + minor,
|
|
"date" : self.parse_datetime_iso(ch["updated_at"]),
|
|
"views" : ch["view"],
|
|
}))
|
|
return results
|
|
|
|
|
|
class ManganeloBookmarkExtractor(ManganeloExtractor):
|
|
"""Extractor for manganelo bookmarks"""
|
|
subcategory = "bookmark"
|
|
pattern = BASE_PATTERN + r"/bookmark"
|
|
example = "https://www.mangakakalot.gg/bookmark"
|
|
|
|
def items(self):
|
|
data = {"_extractor": ManganeloMangaExtractor}
|
|
|
|
url = self.root + "/bookmark"
|
|
params = {"page": 1}
|
|
|
|
response = self.request(url, params=params)
|
|
if response.history:
|
|
raise self.exc.AuthRequired(
|
|
"authenticated cookies", "your bookmarks")
|
|
page = response.text
|
|
last = text.parse_int(text.extr(page, ">Last(", ")"))
|
|
|
|
while True:
|
|
for bookmark in text.extract_iter(
|
|
page, 'class="user-bookmark-item ', '</a>'):
|
|
yield Message.Queue, text.extr(bookmark, ' href="', '"'), data
|
|
|
|
if params["page"] >= last:
|
|
break
|
|
params["page"] += 1
|
|
page = self.request(url, params=params).text
|