diff options
Diffstat (limited to 'gallery_dl/extractor/komikcast.py')
| -rw-r--r-- | gallery_dl/extractor/komikcast.py | 37 |
1 files changed, 16 insertions, 21 deletions
diff --git a/gallery_dl/extractor/komikcast.py b/gallery_dl/extractor/komikcast.py index 89a1b5e..816bc3d 100644 --- a/gallery_dl/extractor/komikcast.py +++ b/gallery_dl/extractor/komikcast.py @@ -1,36 +1,32 @@ # -*- coding: utf-8 -*- -# Copyright 2018-2023 Mike Fährmann +# Copyright 2018-2025 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://komikcast.la/""" +"""Extractors for https://komikcast.li/""" from .common import ChapterExtractor, MangaExtractor -from .. import text -import re +from .. import text, util BASE_PATTERN = (r"(?:https?://)?(?:www\.)?" - r"komikcast\.(?:la|cz|lol|site|mo?e|com)") + r"komikcast\d*\.(?:l(?:i|a|ol)|com|cz|site|mo?e)") class KomikcastBase(): """Base class for komikcast extractors""" category = "komikcast" - root = "https://komikcast.la" + root = "https://komikcast.li" - @staticmethod - def parse_chapter_string(chapter_string, data=None): + def parse_chapter_string(self, chapter_string, data=None): """Parse 'chapter_string' value and add its info to 'data'""" - if not data: + if data is None: data = {} - match = re.match( - r"(?:(.*) Chapter )?0*(\d+)([^ ]*)(?: (?:- )?(.+))?", - text.unescape(chapter_string), - ) + pattern = util.re(r"(?:(.*) Chapter )?0*(\d+)([^ ]*)(?: (?:- )?(.+))?") + match = pattern.match(text.unescape(chapter_string)) manga, chapter, data["chapter_minor"], title = match.groups() if manga: @@ -49,27 +45,27 @@ class KomikcastBase(): class KomikcastChapterExtractor(KomikcastBase, ChapterExtractor): """Extractor for komikcast manga chapters""" pattern = BASE_PATTERN + r"(/chapter/[^/?#]+/)" - example = "https://komikcast.la/chapter/TITLE/" + example = "https://komikcast.li/chapter/TITLE/" def metadata(self, page): info = text.extr(page, "<title>", " - Komikcast<") return self.parse_chapter_string(info) - @staticmethod - def images(page): + def images(self, page): readerarea = text.extr( page, '<div class="main-reading-area', '</div') + pattern = util.re(r"<img[^>]* src=[\"']([^\"']+)") return [ (text.unescape(url), None) - for url in re.findall(r"<img[^>]* src=[\"']([^\"']+)", readerarea) + for url in pattern.findall(readerarea) ] class KomikcastMangaExtractor(KomikcastBase, MangaExtractor): """Extractor for komikcast manga""" chapterclass = KomikcastChapterExtractor - pattern = BASE_PATTERN + r"(/(?:komik/)?[^/?#]+)/?$" - example = "https://komikcast.la/komik/TITLE" + pattern = BASE_PATTERN + r"(/(?:komik/)?[^/?#]+/?)$" + example = "https://komikcast.li/komik/TITLE" def chapters(self, page): results = [] @@ -84,8 +80,7 @@ class KomikcastMangaExtractor(KomikcastBase, MangaExtractor): results.append((url, data.copy())) return results - @staticmethod - def metadata(page): + def metadata(self, page): """Return a dict with general metadata""" manga , pos = text.extract(page, "<title>" , " - Komikcast<") genres, pos = text.extract( |