diff --git a/youtube_dl/extractor/metaebene.py b/youtube_dl/extractor/metaebene.py index 26ced89fd..ac916f479 100644 --- a/youtube_dl/extractor/metaebene.py +++ b/youtube_dl/extractor/metaebene.py @@ -13,7 +13,12 @@ class MetaebeneIE(InfoExtractor): |forschergeist\.de/podcast/ |freakshow\.fm/podcast/ |raumzeit-podcast.de/([^/]+/){3} - |fokus-europa.de/podcast/) + |fokus-europa.de/podcast/ + |not-safe-for-work.de/ + |kolophon.oreilly.de/ + |der-lautsprecher.de/ + |newz-of-the-world.com/ + |diegesellschafter.metaebene.me/) (?P[^-]+)[^\s]*''' _TESTS = [{ 'url': 'https://cre.fm/cre217-mythos-68er', @@ -85,6 +90,74 @@ class MetaebeneIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://not-safe-for-work.de/nsfw098-publikationspromiskuitaet/', + 'info_dict': { + 'id': 'nsfw098', + 'ext': 'opus', + 'formats': 'mincount:4', + 'title': 'NSFW098 Publikationspromiskuität', + 'description': 'md5:b4b503a38c1dc37950fd40b7969c28d5', + 'site_name': 'Not Safe For Work', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://kolophon.oreilly.de/kol017-startups/', + 'info_dict': { + 'id': 'kol017', + 'ext': 'opus', + 'formats': 'mincount:4', + 'title': 'KOL017 Startups', + 'description': 'md5:c2db87c7be046c9f3c712584912db999', + 'site_name': 'Kolophon', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://der-lautsprecher.de/ls018-audioformate-fuer-podcasts', + 'info_dict': { + 'id': 'ls018', + 'ext': 'opus', + 'formats': 'mincount:4', + 'title': 'LS018 Audioformate für Podcasts', + 'description': 'md5:9eea235a49b6ed8bf6b11fa112735e47', + 'site_name': 'Der Lautsprecher', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://newz-of-the-world.com/newz088-were-gonna-miss-him-when-hes-gone/', + 'info_dict': { + 'id': 'newz088', + 'ext': 'oga', + 'formats': 'mincount:4', + 'title': 'NEWZ088 We\'re gonna miss him when he\'s gone', + 'description': 'md5:f48c83fc3f10c950307dca5d318ae346', + 'site_name': 'Newz of the World', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://diegesellschafter.metaebene.me/dg024-freiwilliges-soziales-jahr/', + 'info_dict': { + 'id': 'dg024', + 'ext': 'oga', + 'formats': 'mincount:4', + 'title': 'DG024 Freiwilliges Soziales Jahr', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -103,11 +176,18 @@ class MetaebeneIE(InfoExtractor): 'url': audio_url[0], 'format_id': audio_type[0]}) + # The "Die Gesellschafter" series is discontinued and the description can't be extracted easily. + # This is a workaround to suppress the warning and thus make it testable and avoid bug reports. + if re.match(r'https?://(?:www\.)?diegesellschafter.metaebene.me/(?P[^-]+)[^\s]*', url): + description = None + else: + description = self._og_search_description(webpage) + return { 'id': content_id, 'title': self._og_search_title(webpage), 'site_name': self._og_search_property('site_name', webpage), - 'description': self._og_search_description(webpage), + 'description': description, 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, }