diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 34c98b537..861e36f92 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -229,7 +229,6 @@ from .beatport import BeatportIE from .beeg import BeegIE from .behindkink import BehindKinkIE -from .bellmedia import BellMediaIE from .berufetv import BerufeTVIE from .bet import BetIE from .bfi import BFIPlayerIE @@ -446,7 +445,6 @@ CSpanIE, ) from .ctsnews import CtsNewsIE -from .ctv import CTVIE from .ctvnews import CTVNewsIE from .cultureunplugged import CultureUnpluggedIE from .curiositystream import ( @@ -1382,7 +1380,6 @@ from .noice import NoicePodcastIE from .nonktube import NonkTubeIE from .noodlemagazine import NoodleMagazineIE -from .noovo import NoovoIE from .nosnl import NOSNLArticleIE from .nova import ( NovaEmbedIE, diff --git a/yt_dlp/extractor/bellmedia.py b/yt_dlp/extractor/bellmedia.py deleted file mode 100644 index ac45dd477..000000000 --- a/yt_dlp/extractor/bellmedia.py +++ /dev/null @@ -1,91 +0,0 @@ -from .common import InfoExtractor - - -class BellMediaIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)? - (?P - (?: - ctv| - tsn| - bnn(?:bloomberg)?| - thecomedynetwork| - discovery| - discoveryvelocity| - sciencechannel| - investigationdiscovery| - animalplanet| - bravo| - mtv| - space| - etalk| - marilyn - )\.ca| - (?:much|cp24)\.com - )/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6,})''' - _TESTS = [{ - 'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070', - 'md5': '3e5b8e38370741d5089da79161646635', - 'info_dict': { - 'id': '1403070', - 'ext': 'flv', - 'title': 'David Cockfield\'s Top Picks', - 'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3', - 'upload_date': '20180525', - 'timestamp': 1527288600, - 'season_id': '73997', - 'season': '2018', - 'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg', - 'tags': [], - 'categories': ['ETFs'], - 'season_number': 8, - 'duration': 272.038, - 'series': 'Market Call Tonight', - }, - }, { - 'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582', - 'only_matching': True, - }, { - 'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549', - 'only_matching': True, - }, { - 'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654', - 'only_matching': True, - }, { - 'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009', - 'only_matching': True, - }, { - 'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016', - 'only_matching': True, - }, { - 'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6', - 'only_matching': True, - }, { - 'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430', - 'only_matching': True, - }, { - 'url': 'http://www.etalk.ca/video?videoid=663455', - 'only_matching': True, - }, { - 'url': 'https://www.cp24.com/video?clipId=1982548', - 'only_matching': True, - }] - _DOMAINS = { - 'thecomedynetwork': 'comedy', - 'discoveryvelocity': 'discvel', - 'sciencechannel': 'discsci', - 'investigationdiscovery': 'invdisc', - 'animalplanet': 'aniplan', - 'etalk': 'ctv', - 'bnnbloomberg': 'bnn', - 'marilyn': 'ctv_marilyn', - } - - def _real_extract(self, url): - domain, video_id = self._match_valid_url(url).groups() - domain = domain.split('.')[0] - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': f'9c9media:{self._DOMAINS.get(domain, domain)}_web:{video_id}', - 'ie_key': 'NineCNineMedia', - } diff --git a/yt_dlp/extractor/ctv.py b/yt_dlp/extractor/ctv.py deleted file mode 100644 index a41dab11b..000000000 --- a/yt_dlp/extractor/ctv.py +++ /dev/null @@ -1,49 +0,0 @@ -from .common import InfoExtractor - - -class CTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ctv\.ca/(?P(?:show|movie)s/[^/]+/[^/?#&]+)' - _TESTS = [{ - 'url': 'https://www.ctv.ca/shows/your-morning/wednesday-december-23-2020-s5e88', - 'info_dict': { - 'id': '2102249', - 'ext': 'flv', - 'title': 'Wednesday, December 23, 2020', - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': 'Your Morning delivers original perspectives and unique insights into the headlines of the day.', - 'timestamp': 1608732000, - 'upload_date': '20201223', - 'series': 'Your Morning', - 'season': '2020-2021', - 'season_number': 5, - 'episode_number': 88, - 'tags': ['Your Morning'], - 'categories': ['Talk Show'], - 'duration': 7467.126, - }, - }, { - 'url': 'https://www.ctv.ca/movies/adam-sandlers-eight-crazy-nights/adam-sandlers-eight-crazy-nights', - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - content = self._download_json( - 'https://www.ctv.ca/space-graphql/graphql', display_id, query={ - 'query': '''{ - resolvedPath(path: "/%s") { - lastSegment { - content { - ... on AxisContent { - axisId - videoPlayerDestCode - } - } - } - } -}''' % display_id, # noqa: UP031 - })['data']['resolvedPath']['lastSegment']['content'] - video_id = content['axisId'] - return self.url_result( - '9c9media:{}:{}'.format(content['videoPlayerDestCode'], video_id), - 'NineCNineMedia', video_id) diff --git a/yt_dlp/extractor/noovo.py b/yt_dlp/extractor/noovo.py deleted file mode 100644 index 772d4ed9e..000000000 --- a/yt_dlp/extractor/noovo.py +++ /dev/null @@ -1,100 +0,0 @@ -from .brightcove import BrightcoveNewIE -from .common import InfoExtractor -from ..utils import ( - int_or_none, - js_to_json, - smuggle_url, - try_get, -) - - -class NoovoIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P[^/]+/[^/?#&]+)' - _TESTS = [{ - # clip - 'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial', - 'info_dict': { - 'id': '5386045029001', - 'ext': 'mp4', - 'title': 'Chrysler Imperial', - 'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056', - 'timestamp': 1491399228, - 'upload_date': '20170405', - 'uploader_id': '618566855001', - 'series': 'RPM+', - }, - 'params': { - 'skip_download': True, - }, - }, { - # episode - 'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8', - 'info_dict': { - 'id': '5395865725001', - 'title': 'Épisode 13 : Les retrouvailles', - 'description': 'md5:888c3330f0c1b4476c5bc99a1c040473', - 'ext': 'mp4', - 'timestamp': 1492019320, - 'upload_date': '20170412', - 'uploader_id': '618566855001', - 'series': "L'amour est dans le pré", - 'season_number': 5, - 'episode': 'Épisode 13', - 'episode_number': 13, - }, - 'params': { - 'skip_download': True, - }, - }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - brightcove_id = self._search_regex( - r'data-video-id=["\'](\d+)', webpage, 'brightcove id') - - data = self._parse_json( - self._search_regex( - r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data', - default='{}'), - video_id, transform_source=js_to_json, fatal=False) - - title = try_get( - data, lambda x: x['video']['nom'], - str) or self._html_search_meta( - 'dcterms.Title', webpage, 'title', fatal=True) - - description = self._html_search_meta( - ('dcterms.Description', 'description'), webpage, 'description') - - series = try_get( - data, lambda x: x['emission']['nom']) or self._search_regex( - r']+class="banner-card__subtitle h4"[^>]*>([^<]+)', - webpage, 'series', default=None) - - season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {} - season = try_get(season_el, lambda x: x['nom'], str) - season_number = int_or_none(try_get(season_el, lambda x: x['numero'])) - - episode_el = try_get(season_el, lambda x: x['episode'], dict) or {} - episode = try_get(episode_el, lambda x: x['nom'], str) - episode_number = int_or_none(try_get(episode_el, lambda x: x['numero'])) - - return { - '_type': 'url_transparent', - 'ie_key': BrightcoveNewIE.ie_key(), - 'url': smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, - {'geo_countries': ['CA']}), - 'id': brightcove_id, - 'title': title, - 'description': description, - 'series': series, - 'season': season, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - } diff --git a/yt_dlp/extractor/unsupported.py b/yt_dlp/extractor/unsupported.py index 31393b02a..7da3c54dd 100644 --- a/yt_dlp/extractor/unsupported.py +++ b/yt_dlp/extractor/unsupported.py @@ -53,6 +53,9 @@ class KnownDRMIE(UnsupportedInfoExtractor): r'(?:beta\.)?crunchyroll\.com', r'viki\.com', r'deezer\.com', + r'ctv\.ca', + r'noovo\.ca', + r'tsn\.ca', ) _TESTS = [{ @@ -168,6 +171,15 @@ class KnownDRMIE(UnsupportedInfoExtractor): }, { 'url': 'http://www.deezer.com/playlist/176747451', 'only_matching': True, + }, { + 'url': 'https://www.ctv.ca/shows/masterchef-53506/the-audition-battles-s15e1', + 'only_matching': True, + }, { + 'url': 'https://www.noovo.ca/emissions/lamour-est-dans-le-pre/prets-pour-lamour-s10e1', + 'only_matching': True, + }, { + 'url': 'https://www.tsn.ca/video/relaxed-oilers-look-to-put-emotional-game-2-loss-in-the-rearview%7E3148747', + 'only_matching': True, }] def _real_extract(self, url):