# -*- coding: utf-8 -*- # Copyright 2018 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. """Extract manga-chapters and entire manga from https://komikcast.com/""" from .common import ChapterExtractor, MangaExtractor from .. import text, cloudflare import re class KomikcastBase(): """Base class for komikcast extractors""" category = "komikcast" scheme = "https" root = "https://komikcast.com" request = cloudflare.request_func @staticmethod def parse_chapter_string(chapter_string, data=None): """Parse 'chapter_string' value and add its info to 'data'""" if not data: data = {} match = re.match( r"(?:(.*) Chapter )?0*(\d+)([^ ]*)(?: (?:- )?(.+))?", text.unescape(chapter_string), ) manga, chapter, data["chapter_minor"], title = match.groups() if manga: data["manga"] = manga.partition(" Chapter ")[0] if title and title.lower() != "bahasa indonesia": data["title"] = title.strip() else: data["title"] = "" data["chapter"] = text.parse_int(chapter) data["lang"] = "id" data["language"] = "Indonesian" return data class KomikcastChapterExtractor(KomikcastBase, ChapterExtractor): """Extractor for manga-chapters from komikcast.com""" pattern = [r"(?:https?://)?(?:www\.)?komikcast\.com(/chapter/[^/?&#]+/)"] test = [ (("https://komikcast.com/chapter/" "apotheosis-chapter-02-2-bahasa-indonesia/"), { "url": "978d3c053d34a77f6ea6e60cbba3deda1e369be8", "keyword": "9964a7ce7c8a518aebdccdea0e05858439c7ad92", }), (("https://komikcast.com/chapter/" "tonari-no-kashiwagi-san-chapter-18b/"), { "url": "db5594b025f9d81e4987da538b8599b8dee8851b", "keyword": "94bb85aec6654ab5af0c10419ca388fcd9c73b47", }), ] def __init__(self, match): ChapterExtractor.__init__(self, self.root + match.group(1)) def get_metadata(self, page): info = text.extract(page, '', "")[0] return self.parse_chapter_string(info) @staticmethod def get_images(page): readerarea = text.extract( page, '
', '