# -*- coding: utf-8 -*- # Copyright 2017-2021 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://fanfox.net/""" from .common import ChapterExtractor, MangaExtractor from .. import text import re BASE_PATTERN = r"(?:https?://)?(?:www\.|m\.)?(?:fanfox\.net|mangafox\.me)" class MangafoxChapterExtractor(ChapterExtractor): """Extractor for manga chapters from fanfox.net""" category = "mangafox" root = "https://m.fanfox.net" pattern = BASE_PATTERN + \ r"(/manga/[^/?#]+/((?:v([^/?#]+)/)?c(\d+)([^/?#]*)))" test = ( ("http://fanfox.net/manga/kidou_keisatsu_patlabor/v05/c006.2/1.html", { "keyword": "5661dab258d42d09d98f194f7172fb9851a49766", "content": "5c50c252dcf12ffecf68801f4db8a2167265f66c", }), ("http://mangafox.me/manga/kidou_keisatsu_patlabor/v05/c006.2/"), ("http://fanfox.net/manga/black_clover/vTBD/c295/1.html"), ) def __init__(self, match): base, self.cstr, self.volume, self.chapter, self.minor = match.groups() self.urlbase = self.root + base ChapterExtractor.__init__(self, match, self.urlbase + "/1.html") def metadata(self, page): manga, pos = text.extract(page, "
', '
') author, pos = text.extract(page, 'Author(s):', '
', pos) data = { "manga" : text.unescape(manga), "author" : text.remove_html(author), "lang" : "en", "language": "English", } results = [] pos = page.index('