From 959b7a379b8e5da059d110a63339c964b6265736 Mon Sep 17 00:00:00 2001 From: Christopher Schreiner Date: Sun, 14 Jul 2024 17:58:05 +0200 Subject: [PATCH 01/69] [ie/adn] Adjust for .com domain change (#10399) Closes #10442 Authored by: infanf --- yt_dlp/extractor/adn.py | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/yt_dlp/extractor/adn.py b/yt_dlp/extractor/adn.py index 7be990b9c..337071794 100644 --- a/yt_dlp/extractor/adn.py +++ b/yt_dlp/extractor/adn.py @@ -16,6 +16,7 @@ float_or_none, int_or_none, intlist_to_bytes, + join_nonempty, long_to_bytes, parse_iso8601, pkcs1pad, @@ -48,9 +49,9 @@ class ADNBaseIE(InfoExtractor): class ADNIE(ADNBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?Pfr|de)/video/[^/?#]+/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?Pde)/)?video/[^/?#]+/(?P\d+)' _TESTS = [{ - 'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir', + 'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir', 'md5': '1c9ef066ceb302c86f80c2b371615261', 'info_dict': { 'id': '9841', @@ -70,10 +71,10 @@ class ADNIE(ADNBaseIE): }, 'skip': 'Only available in French and German speaking Europe', }, { - 'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites', + 'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites', 'only_matching': True, }, { - 'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1', + 'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1', 'md5': '5c5651bf5791fa6fcd7906012b9d94e8', 'info_dict': { 'id': '23550', @@ -217,7 +218,7 @@ def _real_extract(self, url): links_data = self._download_json( links_url, video_id, 'Downloading links JSON metadata', headers={ 'X-Player-Token': authorization, - 'X-Target-Distribution': lang, + 'X-Target-Distribution': lang or 'fr', **self._HEADERS, }, query={ 'freeWithAds': 'true', @@ -298,9 +299,9 @@ def _real_extract(self, url): class ADNSeasonIE(ADNBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?Pfr|de)/video/(?P[^/?#]+)/?(?:$|[#?])' + _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?Pde)/)?video/(?P[^/?#]+)/?(?:$|[#?])' _TESTS = [{ - 'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new', + 'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new', 'playlist_count': 12, 'info_dict': { 'id': '911', @@ -318,7 +319,7 @@ def _real_extract(self, url): episodes = self._download_json( f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug, 'Downloading episode list', headers={ - 'X-Target-Distribution': lang, + 'X-Target-Distribution': lang or 'fr', **self._HEADERS, }, query={ 'order': 'asc', @@ -327,8 +328,8 @@ def _real_extract(self, url): def entries(): for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})): - yield self.url_result( - f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}', - ADNIE, episode_id) + yield self.url_result(join_nonempty( + 'https://animationdigitalnetwork.com', lang, 'video', + video_show_slug, episode_id, delim='/'), ADNIE, episode_id) return self.playlist_result(entries(), show_id, show.get('title')) From 16da8ef9937ff76632dfef02e5062c5ba99c8ea2 Mon Sep 17 00:00:00 2001 From: sepro <4618135+seproDev@users.noreply.github.com> Date: Sun, 14 Jul 2024 20:42:11 +0200 Subject: [PATCH 02/69] [ie/youtube] Fix initial player response usage (Bugfix for 8b8b442cb005a8d85315f301615f83fb736b967a) (#10464) Authored by: seproDev --- yt_dlp/extractor/youtube.py | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index d1d57eb47..7c74ec905 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3702,17 +3702,17 @@ def _invalid_player_response(self, pr, video_id): return pr_id def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data): - initial_pr = None + initial_pr = ignore_initial_response = None if webpage: - experiments = traverse_obj(master_ytcfg, ( - 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {str}, {lambda x: x.split(',')}, ..., {str})) - if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): - self.report_warning( - 'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response') - master_ytcfg = self._get_default_ytcfg() - else: - initial_pr = self._search_json( - self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) + if 'web' in clients: + experiments = traverse_obj(master_ytcfg, ( + 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {lambda x: x.split(',')}, ...)) + if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): + self.report_warning( + 'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response') + ignore_initial_response = True + initial_pr = self._search_json( + self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) prs = [] if initial_pr and not self._invalid_player_response(initial_pr, video_id): @@ -3740,8 +3740,10 @@ def append_client(*client_names): skipped_clients = {} while clients: client, base_client, variant = _split_innertube_client(clients.pop()) - player_ytcfg = master_ytcfg if client == 'web' else {} - if 'configs' not in self._configuration_arg('player_skip') and client != 'web': + player_ytcfg = {} + if client == 'web': + player_ytcfg = self._get_default_ytcfg() if ignore_initial_response else master_ytcfg + elif 'configs' not in self._configuration_arg('player_skip'): player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) @@ -3754,7 +3756,7 @@ def append_client(*client_names): player_url = self._download_player_url(video_id) tried_iframe_fallback = True - pr = initial_pr if client == 'web' and initial_pr else None + pr = initial_pr if client == 'web' and not ignore_initial_response else None for retry in self.RetryManager(fatal=False): try: pr = pr or self._extract_player_response( @@ -3765,7 +3767,7 @@ def append_client(*client_names): break experiments = traverse_obj(pr, ( 'responseContext', 'serviceTrackingParams', lambda _, v: v['service'] == 'GFEEDBACK', - 'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ..., {str})) + 'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ...)) if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): pr = None retry.error = ExtractorError('API returned broken formats (poToken experiment detected)', expected=True) From b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sun, 14 Jul 2024 13:57:07 -0500 Subject: [PATCH 03/69] [ie/generic] Fix direct video link extensions (#10468) Fixes regression in the generic extractor due in 5ce582448ececb8d9c30c8c31f58330090ced03a Closes #10459 Authored by: bashonly --- yt_dlp/extractor/generic.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index 3b8e1e957..04cffaa86 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -43,6 +43,7 @@ xpath_text, xpath_with_ns, ) +from ..utils._utils import _UnsafeExtensionError class GenericIE(InfoExtractor): @@ -2446,9 +2447,13 @@ def _real_extract(self, url): if not is_html(first_bytes): self.report_warning( 'URL could be a direct video link, returning it as such.') + ext = determine_ext(url) + if ext not in _UnsafeExtensionError.ALLOWED_EXTENSIONS: + ext = 'unknown_video' info_dict.update({ 'direct': True, 'url': url, + 'ext': ext, }) return info_dict From 22870b81bad97dfa6307a7add44753b2dffc76a9 Mon Sep 17 00:00:00 2001 From: DunnesH <88340380+DunnesH@users.noreply.github.com> Date: Sun, 14 Jul 2024 19:01:50 +0000 Subject: [PATCH 04/69] [ie/soundcloud:user:permalink] Extract tracks only (#10463) Closes #10242 Authored by: DunnesH --- yt_dlp/extractor/soundcloud.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/soundcloud.py b/yt_dlp/extractor/soundcloud.py index afb512d90..4f8d96407 100644 --- a/yt_dlp/extractor/soundcloud.py +++ b/yt_dlp/extractor/soundcloud.py @@ -871,7 +871,7 @@ class SoundcloudUserPermalinkIE(SoundcloudPagedPlaylistBaseIE): 'id': '30909869', 'title': 'neilcic', }, - 'playlist_mincount': 23, + 'playlist_mincount': 22, }] def _real_extract(self, url): @@ -880,7 +880,7 @@ def _real_extract(self, url): self._resolv_url(url), user_id, 'Downloading user info', headers=self._HEADERS) return self._extract_playlist( - f'{self._API_V2_BASE}stream/users/{user["id"]}', str(user['id']), user.get('username')) + f'{self._API_V2_BASE}users/{user["id"]}/tracks', str(user['id']), user.get('username')) class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): From b85eef0a615a01304f88a3847309c667e09a20df Mon Sep 17 00:00:00 2001 From: sepro <4618135+seproDev@users.noreply.github.com> Date: Sun, 14 Jul 2024 21:10:29 +0200 Subject: [PATCH 05/69] [ie/youtube] Reduce android client priority (#10467) Authored by: seproDev --- yt_dlp/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 7c74ec905..53aca3816 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -270,7 +270,7 @@ def build_innertube_clients(): THIRD_PARTY = { 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL } - BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb') + BASE_CLIENTS = ('ios', 'web', 'tv', 'mweb', 'android') priority = qualities(BASE_CLIENTS[::-1]) for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): From cc0070f6496e501d77352bad475fb02d6a86846a Mon Sep 17 00:00:00 2001 From: bashonly Date: Sun, 14 Jul 2024 14:58:07 -0500 Subject: [PATCH 06/69] [utils] `parse_codecs`: Fix parsing of mixed case codec strings Authored by: bashonly --- test/test_utils.py | 5 +++++ yt_dlp/utils/_utils.py | 1 + 2 files changed, 6 insertions(+) diff --git a/test/test_utils.py b/test/test_utils.py index 3ff1f8b55..e82f551bc 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -929,6 +929,11 @@ def test_parse_codecs(self): 'acodec': 'none', 'dynamic_range': 'DV', }) + self.assertEqual(parse_codecs('fLaC'), { + 'vcodec': 'none', + 'acodec': 'flac', + 'dynamic_range': None, + }) self.assertEqual(parse_codecs('theora, vorbis'), { 'vcodec': 'theora', 'acodec': 'vorbis', diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index b582b7d4e..2c23b3ed5 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -2984,6 +2984,7 @@ def parse_codecs(codecs_str): str.strip, codecs_str.strip().strip(',').split(',')))) vcodec, acodec, scodec, hdr = None, None, None, None for full_codec in split_codecs: + full_codec = re.sub(r'^([^.]+)', lambda m: m.group(1).lower(), full_codec) parts = re.sub(r'0+(?=\d)', '', full_codec).split('.') if parts[0] in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av1', 'theora', 'dvh1', 'dvhe'): From e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1 Mon Sep 17 00:00:00 2001 From: bashonly Date: Sat, 13 Jul 2024 22:42:17 -0500 Subject: [PATCH 07/69] [ie/digitalconcerthall] Extract HEVC and FLAC formats (#10470) Authored by: bashonly --- README.md | 3 ++ yt_dlp/extractor/digitalconcerthall.py | 42 ++++++++++++++++++-------- 2 files changed, 33 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 08cca0a45..243b44344 100644 --- a/README.md +++ b/README.md @@ -1859,6 +1859,9 @@ #### orfon (orf:on) #### bilibili * `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats +#### digitalconcerthall +* `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats + **Note**: These options may be changed/removed in the future without concern for backward compatibility diff --git a/yt_dlp/extractor/digitalconcerthall.py b/yt_dlp/extractor/digitalconcerthall.py index 8b4d5c0fc..edb6fa9c0 100644 --- a/yt_dlp/extractor/digitalconcerthall.py +++ b/yt_dlp/extractor/digitalconcerthall.py @@ -1,6 +1,8 @@ from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, + parse_codecs, try_get, url_or_none, urlencode_postdata, @@ -12,6 +14,7 @@ class DigitalConcertHallIE(InfoExtractor): IE_DESC = 'DigitalConcertHall extractor' _VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P[a-z]+)/(?Pfilm|concert|work)/(?P[0-9]+)-?(?P[0-9]+)?' _OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token' + _USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Safari/605.1.15' _ACCESS_TOKEN = None _NETRC_MACHINE = 'digitalconcerthall' _TESTS = [{ @@ -68,33 +71,42 @@ class DigitalConcertHallIE(InfoExtractor): }] def _perform_login(self, username, password): - token_response = self._download_json( + login_token = self._download_json( self._OAUTH_URL, None, 'Obtaining token', errnote='Unable to obtain token', data=urlencode_postdata({ 'affiliate': 'none', 'grant_type': 'device', 'device_vendor': 'unknown', + # device_model 'Safari' gets split streams of 4K/HEVC video and lossless/FLAC audio + 'device_model': 'unknown' if self._configuration_arg('prefer_combined_hls') else 'Safari', 'app_id': 'dch.webapp', - 'app_version': '1.0.0', + 'app_distributor': 'berlinphil', + 'app_version': '1.84.0', 'client_secret': '2ySLN+2Fwb', }), headers={ - 'Content-Type': 'application/x-www-form-urlencoded', - }) - self._ACCESS_TOKEN = token_response['access_token'] + 'Accept': 'application/json', + 'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8', + 'User-Agent': self._USER_AGENT, + })['access_token'] try: - self._download_json( + login_response = self._download_json( self._OAUTH_URL, None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({ 'grant_type': 'password', 'username': username, 'password': password, }), headers={ - 'Content-Type': 'application/x-www-form-urlencoded', + 'Accept': 'application/json', + 'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8', 'Referer': 'https://www.digitalconcerthall.com', - 'Authorization': f'Bearer {self._ACCESS_TOKEN}', + 'Authorization': f'Bearer {login_token}', + 'User-Agent': self._USER_AGENT, }) - except ExtractorError: - self.raise_login_required(msg='Login info incorrect') + except ExtractorError as error: + if isinstance(error.cause, HTTPError) and error.cause.status == 401: + raise ExtractorError('Invalid username or password', expected=True) + raise + self._ACCESS_TOKEN = login_response['access_token'] def _real_initialize(self): if not self._ACCESS_TOKEN: @@ -108,11 +120,15 @@ def _entries(self, items, language, type_, **kwargs): 'Accept': 'application/json', 'Authorization': f'Bearer {self._ACCESS_TOKEN}', 'Accept-Language': language, + 'User-Agent': self._USER_AGENT, }) formats = [] for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})): - formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False)) + formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + for fmt in formats: + if fmt.get('format_note') and fmt.get('vcodec') == 'none': + fmt.update(parse_codecs(fmt['format_note'])) yield { 'id': video_id, @@ -140,13 +156,15 @@ def _real_extract(self, url): f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={ 'Accept': 'application/json', 'Accept-Language': language, + 'User-Agent': self._USER_AGENT, + 'Authorization': f'Bearer {self._ACCESS_TOKEN}', }) - album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...)) if type_ == 'work': videos = [videos[int(part) - 1]] + album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name', {str})) thumbnail = traverse_obj(vid_info, ( 'image', ..., {self._proto_relative_url}, {url_or_none}, {lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size From 39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 15 Jul 2024 17:30:43 -0500 Subject: [PATCH 08/69] [ie/dplay] Fix extractors (#10471) Closes #1623, Closes #2138, Closes #2361, Closes #3841, Closes #8026, Closes #10421 Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 5 - yt_dlp/extractor/discovery.py | 115 --------- yt_dlp/extractor/discoverygo.py | 171 ------------ yt_dlp/extractor/dplay.py | 442 ++++++++++++++++++++------------ 4 files changed, 283 insertions(+), 450 deletions(-) delete mode 100644 yt_dlp/extractor/discovery.py delete mode 100644 yt_dlp/extractor/discoverygo.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index fc917ff06..d2140bc52 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -504,7 +504,6 @@ from .digitalconcerthall import DigitalConcertHallIE from .digiteka import DigitekaIE from .discogs import DiscogsReleasePlaylistIE -from .discovery import DiscoveryIE from .disney import DisneyIE from .dispeak import DigitallySpeakingIE from .dlf import ( @@ -532,16 +531,12 @@ DiscoveryPlusIndiaShowIE, DiscoveryPlusItalyIE, DiscoveryPlusItalyShowIE, - DIYNetworkIE, DPlayIE, FoodNetworkIE, - GlobalCyclingNetworkPlusIE, GoDiscoveryIE, HGTVDeIE, HGTVUsaIE, InvestigationDiscoveryIE, - MotorTrendIE, - MotorTrendOnDemandIE, ScienceChannelIE, TravelChannelIE, ) diff --git a/yt_dlp/extractor/discovery.py b/yt_dlp/extractor/discovery.py deleted file mode 100644 index b98279d67..000000000 --- a/yt_dlp/extractor/discovery.py +++ /dev/null @@ -1,115 +0,0 @@ -import random -import string -import urllib.parse - -from .discoverygo import DiscoveryGoBaseIE -from ..networking.exceptions import HTTPError -from ..utils import ExtractorError - - -class DiscoveryIE(DiscoveryGoBaseIE): - _VALID_URL = r'''(?x)https?:// - (?P - go\.discovery| - www\. - (?: - investigationdiscovery| - discoverylife| - animalplanet| - ahctv| - destinationamerica| - sciencechannel| - tlc - )| - watch\. - (?: - hgtv| - foodnetwork| - travelchannel| - diynetwork| - cookingchanneltv| - motortrend - ) - )\.com/tv-shows/(?P[^/]+)/(?:video|full-episode)s/(?P[^./?#]+)''' - _TESTS = [{ - 'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry', - 'info_dict': { - 'id': '5a2f35ce6b66d17a5026e29e', - 'ext': 'mp4', - 'title': 'Riding with Matthew Perry', - 'description': 'md5:a34333153e79bc4526019a5129e7f878', - 'duration': 84, - }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, - }, { - 'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision', - 'only_matching': True, - }, { - 'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road', - 'only_matching': True, - }, { - # using `show_slug` is important to get the correct video data - 'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special', - 'only_matching': True, - }] - _GEO_COUNTRIES = ['US'] - _GEO_BYPASS = False - _API_BASE_URL = 'https://api.discovery.com/v1/' - - def _real_extract(self, url): - site, show_slug, display_id = self._match_valid_url(url).groups() - - access_token = None - cookies = self._get_cookies(url) - - # prefer Affiliate Auth Token over Anonymous Auth Token - auth_storage_cookie = cookies.get('eosAf') or cookies.get('eosAn') - if auth_storage_cookie and auth_storage_cookie.value: - auth_storage = self._parse_json(urllib.parse.unquote( - urllib.parse.unquote(auth_storage_cookie.value)), - display_id, fatal=False) or {} - access_token = auth_storage.get('a') or auth_storage.get('access_token') - - if not access_token: - access_token = self._download_json( - f'https://{site}.com/anonymous', display_id, - 'Downloading token JSON metadata', query={ - 'authRel': 'authorization', - 'client_id': '3020a40c2356a645b4b4', - 'nonce': ''.join(random.choices(string.ascii_letters, k=32)), - 'redirectUri': 'https://www.discovery.com/', - })['access_token'] - - headers = self.geo_verification_headers() - headers['Authorization'] = 'Bearer ' + access_token - - try: - video = self._download_json( - self._API_BASE_URL + 'content/videos', - display_id, 'Downloading content JSON metadata', - headers=headers, query={ - 'embed': 'show.name', - 'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags', - 'slug': display_id, - 'show_slug': show_slug, - })[0] - video_id = video['id'] - stream = self._download_json( - self._API_BASE_URL + 'streaming/video/' + video_id, - display_id, 'Downloading streaming JSON metadata', headers=headers) - except ExtractorError as e: - if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403): - e_description = self._parse_json( - e.cause.response.read().decode(), display_id)['description'] - if 'resource not available for country' in e_description: - self.raise_geo_restricted(countries=self._GEO_COUNTRIES) - if 'Authorized Networks' in e_description: - raise ExtractorError( - 'This video is only available via cable service provider subscription that' - ' is not currently supported. You may want to use --cookies.', expected=True) - raise ExtractorError(e_description) - raise - - return self._extract_video_info(video, stream, display_id) diff --git a/yt_dlp/extractor/discoverygo.py b/yt_dlp/extractor/discoverygo.py deleted file mode 100644 index 964948548..000000000 --- a/yt_dlp/extractor/discoverygo.py +++ /dev/null @@ -1,171 +0,0 @@ -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - determine_ext, - extract_attributes, - int_or_none, - parse_age_limit, - remove_end, - unescapeHTML, - url_or_none, -) - - -class DiscoveryGoBaseIE(InfoExtractor): - _VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?: - discovery| - investigationdiscovery| - discoverylife| - animalplanet| - ahctv| - destinationamerica| - sciencechannel| - tlc| - velocitychannel - )go\.com/%s(?P[^/?#&]+)''' - - def _extract_video_info(self, video, stream, display_id): - title = video['name'] - - if not stream: - if video.get('authenticated') is True: - raise ExtractorError( - 'This video is only available via cable service provider subscription that' - ' is not currently supported. You may want to use --cookies.', expected=True) - else: - raise ExtractorError('Unable to find stream') - STREAM_URL_SUFFIX = 'streamUrl' - formats = [] - for stream_kind in ('', 'hds'): - suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX - stream_url = stream.get(f'{stream_kind}{suffix}') - if not stream_url: - continue - if stream_kind == '': - formats.extend(self._extract_m3u8_formats( - stream_url, display_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - elif stream_kind == 'hds': - formats.extend(self._extract_f4m_formats( - stream_url, display_id, f4m_id=stream_kind, fatal=False)) - - video_id = video.get('id') or display_id - description = video.get('description', {}).get('detailed') - duration = int_or_none(video.get('duration')) - - series = video.get('show', {}).get('name') - season_number = int_or_none(video.get('season', {}).get('number')) - episode_number = int_or_none(video.get('episodeNumber')) - - tags = video.get('tags') - age_limit = parse_age_limit(video.get('parental', {}).get('rating')) - - subtitles = {} - captions = stream.get('captions') - if isinstance(captions, list): - for caption in captions: - subtitle_url = url_or_none(caption.get('fileUrl')) - if not subtitle_url or not subtitle_url.startswith('http'): - continue - lang = caption.get('fileLang', 'en') - ext = determine_ext(subtitle_url) - subtitles.setdefault(lang, []).append({ - 'url': subtitle_url, - 'ext': 'ttml' if ext == 'xml' else ext, - }) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'duration': duration, - 'series': series, - 'season_number': season_number, - 'episode_number': episode_number, - 'tags': tags, - 'age_limit': age_limit, - 'formats': formats, - 'subtitles': subtitles, - } - - -class DiscoveryGoIE(DiscoveryGoBaseIE): - _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' - _GEO_COUNTRIES = ['US'] - _TEST = { - 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', - 'info_dict': { - 'id': '58c167d86b66d12f2addeb01', - 'ext': 'mp4', - 'title': 'Reaper Madness', - 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', - 'duration': 2519, - 'series': 'Bering Sea Gold', - 'season_number': 8, - 'episode_number': 6, - 'age_limit': 14, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - container = extract_attributes( - self._search_regex( - r'(]+class=["\']video-player-container[^>]+>)', - webpage, 'video container')) - - video = self._parse_json( - container.get('data-video') or container.get('data-json'), - display_id) - - stream = video.get('stream') - - return self._extract_video_info(video, stream, display_id) - - -class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE): - _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % '' - _TEST = { - 'url': 'https://www.discoverygo.com/bering-sea-gold/', - 'info_dict': { - 'id': 'bering-sea-gold', - 'title': 'Bering Sea Gold', - 'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e', - }, - 'playlist_mincount': 6, - } - - @classmethod - def suitable(cls, url): - return False if DiscoveryGoIE.suitable(url) else super().suitable(url) - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - entries = [] - for mobj in re.finditer(r'data-json=(["\'])(?P{.+?})\1', webpage): - data = self._parse_json( - mobj.group('json'), display_id, - transform_source=unescapeHTML, fatal=False) - if not isinstance(data, dict) or data.get('type') != 'episode': - continue - episode_url = data.get('socialUrl') - if not episode_url: - continue - entries.append(self.url_result( - episode_url, ie=DiscoveryGoIE.ie_key(), - video_id=data.get('id'))) - - return self.playlist_result( - entries, display_id, - remove_end(self._og_search_title( - webpage, fatal=False), ' | Discovery GO'), - self._og_search_description(webpage)) diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index 48eae1088..e9f9357ad 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -346,8 +346,16 @@ def _real_extract(self, url): class DiscoveryPlusBaseIE(DPlayBaseIE): + """Subclasses must set _PRODUCT, _DISCO_API_PARAMS""" + + _DISCO_CLIENT_VER = '27.43.0' + def _update_disco_api_headers(self, headers, disco_base, display_id, realm): - headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6' + headers.update({ + 'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}', + 'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:{self._DISCO_CLIENT_VER}', + 'Authorization': self._get_auth(disco_base, display_id, realm), + }) def _download_video_playback_info(self, disco_base, video_id, headers): return self._download_json( @@ -368,6 +376,26 @@ def _real_extract(self, url): class GoDiscoveryIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://go.discovery.com/video/in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister', + 'info_dict': { + 'id': '5352642', + 'display_id': 'in-the-eye-of-the-storm-discovery-atve-us/trapped-in-a-twister', + 'ext': 'mp4', + 'title': 'Trapped in a Twister', + 'description': 'Twisters destroy Midwest towns, trapping spotters in the eye of the storm.', + 'episode_number': 1, + 'episode': 'Episode 1', + 'season_number': 1, + 'season': 'Season 1', + 'series': 'In The Eye Of The Storm', + 'duration': 2490.237, + 'upload_date': '20240715', + 'timestamp': 1721008800, + 'tags': [], + 'creators': ['Discovery'], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/10/5e39637d-cabf-3ab3-8e9a-f4e9d37bc036.jpeg', + }, + }, { 'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer', 'info_dict': { 'id': '4164906', @@ -395,6 +423,26 @@ class GoDiscoveryIE(DiscoveryPlusBaseIE): class TravelChannelIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://watch.travelchannel.com/video/the-dead-files-travel-channel/protect-the-children', + 'info_dict': { + 'id': '4710177', + 'display_id': 'the-dead-files-travel-channel/protect-the-children', + 'ext': 'mp4', + 'title': 'Protect the Children', + 'description': 'An evil presence threatens an Ohio woman\'s children and marriage.', + 'season_number': 14, + 'season': 'Season 14', + 'episode_number': 10, + 'episode': 'Episode 10', + 'series': 'The Dead Files', + 'duration': 2550.481, + 'timestamp': 1664510400, + 'upload_date': '20220930', + 'tags': [], + 'creators': ['Travel Channel'], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/17/5e45eace-de5d-343a-9293-f400a2aa77d5.jpeg', + }, + }, { 'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely', 'info_dict': { 'id': '2220256', @@ -422,6 +470,26 @@ class TravelChannelIE(DiscoveryPlusBaseIE): class CookingChannelIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://watch.cookingchanneltv.com/video/bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson', + 'info_dict': { + 'id': '5350005', + 'ext': 'mp4', + 'display_id': 'bobbys-triple-threat-food-network-atve-us/titans-vs-marcus-samuelsson', + 'title': 'Titans vs Marcus Samuelsson', + 'description': 'Marcus Samuelsson throws his legendary global tricks at the Titans.', + 'episode_number': 1, + 'episode': 'Episode 1', + 'season_number': 3, + 'season': 'Season 3', + 'series': 'Bobby\'s Triple Threat', + 'duration': 2520.851, + 'upload_date': '20240710', + 'timestamp': 1720573200, + 'tags': [], + 'creators': ['Food Network'], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2024/07/04/529cd095-27ec-35c5-84e9-90ebd3e5d2da.jpeg', + }, + }, { 'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634', 'info_dict': { 'id': '2348634', @@ -449,6 +517,22 @@ class CookingChannelIE(DiscoveryPlusBaseIE): class HGTVUsaIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://watch.hgtv.com/video/flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip', + 'info_dict': { + 'id': '5025585', + 'display_id': 'flip-or-flop-the-final-flip-hgtv-atve-us/flip-or-flop-the-final-flip', + 'ext': 'mp4', + 'title': 'Flip or Flop: The Final Flip', + 'description': 'Tarek and Christina are going their separate ways after one last flip!', + 'series': 'Flip or Flop: The Final Flip', + 'duration': 2580.644, + 'upload_date': '20231101', + 'timestamp': 1698811200, + 'tags': [], + 'creators': ['HGTV'], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2022/11/27/455caa6c-1462-3f14-b63d-a026d7a5e6d3.jpeg', + }, + }, { 'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house', 'info_dict': { 'id': '4289736', @@ -476,6 +560,26 @@ class HGTVUsaIE(DiscoveryPlusBaseIE): class FoodNetworkIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://watch.foodnetwork.com/video/guys-grocery-games-food-network/wild-in-the-aisles', + 'info_dict': { + 'id': '2152549', + 'display_id': 'guys-grocery-games-food-network/wild-in-the-aisles', + 'ext': 'mp4', + 'title': 'Wild in the Aisles', + 'description': 'The chefs make spaghetti and meatballs with "Out of Stock" ingredients.', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': 'Guy\'s Grocery Games', + 'tags': [], + 'creators': ['Food Network'], + 'duration': 2520.651, + 'upload_date': '20230623', + 'timestamp': 1687492800, + 'thumbnail': 'https://us1-prod-images.disco-api.com/2022/06/15/37fb5333-cad2-3dbb-af7c-c20ec77c89c6.jpeg', + }, + }, { 'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly', 'info_dict': { 'id': '4116449', @@ -503,6 +607,26 @@ class FoodNetworkIE(DiscoveryPlusBaseIE): class DestinationAmericaIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.destinationamerica.com/video/bbq-pit-wars-destination-america/smoke-on-the-water', + 'info_dict': { + 'id': '2218409', + 'display_id': 'bbq-pit-wars-destination-america/smoke-on-the-water', + 'ext': 'mp4', + 'title': 'Smoke on the Water', + 'description': 'The pitmasters head to Georgia for the Smoke on the Water BBQ Festival.', + 'season_number': 2, + 'season': 'Season 2', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': 'BBQ Pit Wars', + 'tags': [], + 'creators': ['Destination America'], + 'duration': 2614.878, + 'upload_date': '20230623', + 'timestamp': 1687492800, + 'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/c0f8e85d-9a10-3e6f-8e43-f6faafa81ba2.jpeg', + }, + }, { 'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot', 'info_dict': { 'id': '4210904', @@ -530,6 +654,26 @@ class DestinationAmericaIE(DiscoveryPlusBaseIE): class InvestigationDiscoveryIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.investigationdiscovery.com/video/deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca', + 'info_dict': { + 'id': '5341132', + 'display_id': 'deadly-influence-the-social-media-murders-investigation-discovery-atve-us/rip-bianca', + 'ext': 'mp4', + 'title': 'RIP Bianca', + 'description': 'A teenage influencer discovers an online world of threat, harm and danger.', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 3, + 'episode': 'Episode 3', + 'series': 'Deadly Influence: The Social Media Murders', + 'creators': ['Investigation Discovery'], + 'tags': [], + 'duration': 2490.888, + 'upload_date': '20240618', + 'timestamp': 1718672400, + 'thumbnail': 'https://us1-prod-images.disco-api.com/2024/06/15/b567c774-9e44-3c6c-b0ba-db860a73e812.jpeg', + }, + }, { 'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown', 'info_dict': { 'id': '2139409', @@ -557,6 +701,26 @@ class InvestigationDiscoveryIE(DiscoveryPlusBaseIE): class AmHistoryChannelIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.ahctv.com/video/blood-and-fury-americas-civil-war-ahc/battle-of-bull-run', + 'info_dict': { + 'id': '2139199', + 'display_id': 'blood-and-fury-americas-civil-war-ahc/battle-of-bull-run', + 'ext': 'mp4', + 'title': 'Battle of Bull Run', + 'description': 'Two untested armies clash in the first real battle of the Civil War.', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': 'Blood and Fury: America\'s Civil War', + 'duration': 2612.509, + 'upload_date': '20220923', + 'timestamp': 1663905600, + 'creators': ['AHC'], + 'tags': [], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2020/05/11/4af61bd7-d705-3108-82c4-1a6e541e20fa.jpeg', + }, + }, { 'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army', 'info_dict': { 'id': '2309730', @@ -584,6 +748,26 @@ class AmHistoryChannelIE(DiscoveryPlusBaseIE): class ScienceChannelIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.sciencechannel.com/video/spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets', + 'info_dict': { + 'id': '2347335', + 'display_id': 'spaces-deepest-secrets-science-atve-us/mystery-of-the-dead-planets', + 'ext': 'mp4', + 'title': 'Mystery of the Dead Planets', + 'description': 'Astronomers unmask the truly destructive nature of the cosmos.', + 'season_number': 7, + 'season': 'Season 7', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': 'Space\'s Deepest Secrets', + 'duration': 2524.989, + 'upload_date': '20230128', + 'timestamp': 1674882000, + 'creators': ['Science'], + 'tags': [], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/30/3796829d-aead-3f9a-bd8d-e49048b3cdca.jpeg', + }, + }, { 'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine', 'info_dict': { 'id': '2842849', @@ -608,36 +792,29 @@ class ScienceChannelIE(DiscoveryPlusBaseIE): } -class DIYNetworkIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayBaseIE._PATH_REGEX - _TESTS = [{ - 'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas', - 'info_dict': { - 'id': '2309730', - 'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas', - 'ext': 'mp4', - 'title': 'Bringing Beach Life to Texas', - 'description': 'The Pool Kings give a family a day at the beach in their own backyard.', - 'season_number': 10, - 'episode_number': 2, - }, - 'skip': 'Available for Premium users', - }, { - 'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas', - 'only_matching': True, - }] - - _PRODUCT = 'diy' - _DISCO_API_PARAMS = { - 'disco_host': 'us1-prod-direct.watch.diynetwork.com', - 'realm': 'go', - 'country': 'us', - } - - class DiscoveryLifeIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.discoverylife.com/video/er-files-discovery-life-atve-us/sweet-charity', + 'info_dict': { + 'id': '2347614', + 'display_id': 'er-files-discovery-life-atve-us/sweet-charity', + 'ext': 'mp4', + 'title': 'Sweet Charity', + 'description': 'The staff at Charity Hospital treat a serious foot infection.', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': 'ER Files', + 'duration': 2364.261, + 'upload_date': '20230721', + 'timestamp': 1689912000, + 'creators': ['Discovery Life'], + 'tags': [], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/16/4b6f0124-360b-3546-b6a4-5552db886b86.jpeg', + }, + }, { 'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma', 'info_dict': { 'id': '2218238', @@ -665,6 +842,26 @@ class DiscoveryLifeIE(DiscoveryPlusBaseIE): class AnimalPlanetIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://www.animalplanet.com/video/mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru', + 'info_dict': { + 'id': '4650835', + 'display_id': 'mysterious-creatures-with-forrest-galante-animal-planet-atve-us/the-demon-of-peru', + 'ext': 'mp4', + 'title': 'The Demon of Peru', + 'description': 'In Peru, a farming village is being terrorized by a “man-like beast.”', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 4, + 'episode': 'Episode 4', + 'series': 'Mysterious Creatures with Forrest Galante', + 'duration': 2490.488, + 'upload_date': '20230111', + 'timestamp': 1673413200, + 'creators': ['Animal Planet'], + 'tags': [], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2022/03/01/6dbaa833-9a2e-3fee-9381-c19eddf67c0c.jpeg', + }, + }, { 'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown', 'info_dict': { 'id': '3338923', @@ -692,6 +889,26 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE): class TLCIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ + 'url': 'https://go.tlc.com/video/90-day-the-last-resort-tlc-atve-us/the-last-chance', + 'info_dict': { + 'id': '5186422', + 'display_id': '90-day-the-last-resort-tlc-atve-us/the-last-chance', + 'ext': 'mp4', + 'title': 'The Last Chance', + 'description': 'Infidelity shakes Kalani and Asuelu\'s world, and Angela threatens divorce.', + 'season_number': 1, + 'season': 'Season 1', + 'episode_number': 1, + 'episode': 'Episode 1', + 'series': '90 Day: The Last Resort', + 'duration': 5123.91, + 'upload_date': '20230815', + 'timestamp': 1692061200, + 'creators': ['TLC'], + 'tags': [], + 'thumbnail': 'https://us1-prod-images.disco-api.com/2023/08/08/0ee367e2-ac76-334d-bf23-dbf796696a24.jpeg', + }, + }, { 'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1', 'info_dict': { 'id': '2206540', @@ -716,93 +933,8 @@ class TLCIE(DiscoveryPlusBaseIE): } -class MotorTrendIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:watch\.)?motortrend\.com/video' + DPlayBaseIE._PATH_REGEX - _TESTS = [{ - 'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas', - 'info_dict': { - 'id': '"4859182"', - 'display_id': 'double-dakotas', - 'ext': 'mp4', - 'title': 'Double Dakotas', - 'description': 'Tylers buy-one-get-one Dakota deal has the Wizard pulling double duty.', - 'season_number': 2, - 'episode_number': 3, - }, - 'skip': 'Available for Premium users', - }, { - 'url': 'https://watch.motortrend.com/video/car-issues-motortrend-atve-us/double-dakotas', - 'only_matching': True, - }] - - _PRODUCT = 'vel' - _DISCO_API_PARAMS = { - 'disco_host': 'us1-prod-direct.watch.motortrend.com', - 'realm': 'go', - 'country': 'us', - } - - -class MotorTrendOnDemandIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:www\.)?motortrend(?:ondemand\.com|\.com/plus)/detail' + DPlayBaseIE._PATH_REGEX - _TESTS = [{ - 'url': 'https://www.motortrendondemand.com/detail/wheelstanding-dump-truck-stubby-bobs-comeback/37699/784', - 'info_dict': { - 'id': '37699', - 'display_id': 'wheelstanding-dump-truck-stubby-bobs-comeback/37699', - 'ext': 'mp4', - 'title': 'Wheelstanding Dump Truck! Stubby Bob’s Comeback', - 'description': 'md5:996915abe52a1c3dfc83aecea3cce8e7', - 'season_number': 5, - 'episode_number': 52, - 'episode': 'Episode 52', - 'season': 'Season 5', - 'thumbnail': r're:^https?://.+\.jpe?g$', - 'timestamp': 1388534401, - 'duration': 1887.345, - 'creator': 'Originals', - 'series': 'Roadkill', - 'upload_date': '20140101', - 'tags': [], - }, - }, { - 'url': 'https://www.motortrend.com/plus/detail/roadworthy-rescues-teaser-trailer/4922860/', - 'info_dict': { - 'id': '4922860', - 'ext': 'mp4', - 'title': 'Roadworthy Rescues | Teaser Trailer', - 'description': 'Derek Bieri helps Freiburger and Finnegan with their \'68 big-block Dart.', - 'display_id': 'roadworthy-rescues-teaser-trailer/4922860', - 'creator': 'Originals', - 'series': 'Roadworthy Rescues', - 'thumbnail': r're:^https?://.+\.jpe?g$', - 'upload_date': '20220907', - 'timestamp': 1662523200, - 'duration': 1066.356, - 'tags': [], - }, - }, { - 'url': 'https://www.motortrend.com/plus/detail/ugly-duckling/2450033/12439', - 'only_matching': True, - }] - - _PRODUCT = 'MTOD' - _DISCO_API_PARAMS = { - 'disco_host': 'us1-prod-direct.motortrendondemand.com', - 'realm': 'motortrend', - 'country': 'us', - } - - def _update_disco_api_headers(self, headers, disco_base, display_id, realm): - headers.update({ - 'x-disco-params': f'realm={realm}', - 'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:4.39.1-gi1', - 'Authorization': self._get_auth(disco_base, display_id, realm), - }) - - class DiscoveryPlusIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P[a-z]{2})/)?video(?:/sport)?' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family', 'info_dict': { @@ -823,14 +955,42 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE): }, { 'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers', 'only_matching': True, + }, { + 'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review', + 'only_matching': True, }] - _PRODUCT = 'dplus_us' - _DISCO_API_PARAMS = { - 'disco_host': 'us1-prod-direct.discoveryplus.com', - 'realm': 'go', - 'country': 'us', - } + _PRODUCT = None + _DISCO_API_PARAMS = None + + def _update_disco_api_headers(self, headers, disco_base, display_id, realm): + headers.update({ + 'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}', + 'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}', + 'Authorization': self._get_auth(disco_base, display_id, realm), + }) + + def _real_extract(self, url): + video_id, country = self._match_valid_url(url).group('id', 'country') + if not country: + country = 'us' + + self._PRODUCT = f'dplus_{country}' + + if country in ('br', 'ca', 'us'): + self._DISCO_API_PARAMS = { + 'disco_host': 'us1-prod-direct.discoveryplus.com', + 'realm': 'go', + 'country': country, + } + else: + self._DISCO_API_PARAMS = { + 'disco_host': 'eu1-prod-direct.discoveryplus.com', + 'realm': 'dplay', + 'country': country, + } + + return self._get_disco_api_info(url, video_id, **self._DISCO_API_PARAMS) class DiscoveryPlusIndiaIE(DiscoveryPlusBaseIE): @@ -993,7 +1153,7 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE): 'only_matching': True, }] - _PRODUCT = 'dplus_us' + _PRODUCT = 'dplus_it' _DISCO_API_PARAMS = { 'disco_host': 'eu1-prod-direct.discoveryplus.com', 'realm': 'dplay', @@ -1002,8 +1162,8 @@ class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE): def _update_disco_api_headers(self, headers, disco_base, display_id, realm): headers.update({ - 'x-disco-params': f'realm={realm}', - 'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6', + 'x-disco-params': f'realm={realm},siteLookupKey={self._PRODUCT}', + 'x-disco-client': f'WEB:UNKNOWN:dplus_us:{self._DISCO_CLIENT_VER}', 'Authorization': self._get_auth(disco_base, display_id, realm), }) @@ -1044,39 +1204,3 @@ class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE): _SHOW_STR = 'show' _INDEX = 4 _VIDEO_IE = DiscoveryPlusIndiaIE - - -class GlobalCyclingNetworkPlusIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://plus\.globalcyclingnetwork\.com/watch/(?P\d+)' - _TESTS = [{ - 'url': 'https://plus.globalcyclingnetwork.com/watch/1397691', - 'info_dict': { - 'id': '1397691', - 'ext': 'mp4', - 'title': 'The Athertons: Mountain Biking\'s Fastest Family', - 'description': 'md5:75a81937fcd8b989eec6083a709cd837', - 'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/04/eb9e3026-4849-3001-8281-9356466f0557.png', - 'series': 'gcn', - 'creator': 'Gcn', - 'upload_date': '20210309', - 'timestamp': 1615248000, - 'duration': 2531.0, - 'tags': [], - }, - 'skip': 'Subscription required', - 'params': {'skip_download': 'm3u8'}, - }] - - _PRODUCT = 'web' - _DISCO_API_PARAMS = { - 'disco_host': 'disco-api-prod.globalcyclingnetwork.com', - 'realm': 'gcn', - 'country': 'us', - } - - def _update_disco_api_headers(self, headers, disco_base, display_id, realm): - headers.update({ - 'x-disco-params': f'realm={realm}', - 'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:27.3.2', - 'Authorization': self._get_auth(disco_base, display_id, realm), - }) From 66ce3d76d87af3f81cc9dfec4be4704016cb1cdb Mon Sep 17 00:00:00 2001 From: Simon Sawicki Date: Tue, 16 Jul 2024 21:48:45 +0200 Subject: [PATCH 09/69] [core] Fix `noprogress` if `test=True` with `--quiet` and `--verbose` (#10454) Authored by: Grub4K --- yt_dlp/YoutubeDL.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index fd5aa0118..503dcb112 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -3168,11 +3168,12 @@ def dl(self, name, info, subtitle=False, test=False): if test: verbose = self.params.get('verbose') + quiet = self.params.get('quiet') or not verbose params = { 'test': True, - 'quiet': self.params.get('quiet') or not verbose, + 'quiet': quiet, 'verbose': verbose, - 'noprogress': not verbose, + 'noprogress': quiet, 'nopart': True, 'skip_unavailable_fragments': False, 'keep_fragments': False, From d9cbced493cae2008508d94a2db5dd98be7c01fc Mon Sep 17 00:00:00 2001 From: Simon Sawicki Date: Tue, 16 Jul 2024 21:51:56 +0200 Subject: [PATCH 10/69] [core] Support `auto-tty` and `no_color-tty` for `--color` (#10453) Authored by: Grub4K --- yt_dlp/YoutubeDL.py | 12 ++++++++---- yt_dlp/__init__.py | 2 +- yt_dlp/options.py | 1 + 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index 503dcb112..9691a1ea7 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -452,7 +452,8 @@ class YoutubeDL: Can also just be a single color policy, in which case it applies to all outputs. Valid stream names are 'stdout' and 'stderr'. - Valid color policies are one of 'always', 'auto', 'no_color' or 'never'. + Valid color policies are one of 'always', 'auto', + 'no_color', 'never', 'auto-tty' or 'no_color-tty'. geo_bypass: Bypass geographic restriction via faking X-Forwarded-For HTTP header geo_bypass_country: @@ -659,12 +660,15 @@ def __init__(self, params=None, auto_init=True): self.params['color'] = 'no_color' term_allow_color = os.getenv('TERM', '').lower() != 'dumb' - no_color = bool(os.getenv('NO_COLOR')) + base_no_color = bool(os.getenv('NO_COLOR')) def process_color_policy(stream): stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream] - policy = traverse_obj(self.params, ('color', (stream_name, None), {str}), get_all=False) - if policy in ('auto', None): + policy = traverse_obj(self.params, ('color', (stream_name, None), {str}, any)) or 'auto' + if policy in ('auto', 'auto-tty', 'no_color-tty'): + no_color = base_no_color + if policy.endswith('tty'): + no_color = policy.startswith('no_color') if term_allow_color and supports_terminal_sequences(stream): return 'no_color' if no_color else True return False diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index 0e48569e3..c0b8e3b50 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -468,7 +468,7 @@ def metadataparser_actions(f): default_downloader = ed.get_basename() for policy in opts.color.values(): - if policy not in ('always', 'auto', 'no_color', 'never'): + if policy not in ('always', 'auto', 'auto-tty', 'no_color', 'no_color-tty', 'never'): raise ValueError(f'"{policy}" is not a valid color policy') warnings, deprecation_warnings = [], [] diff --git a/yt_dlp/options.py b/yt_dlp/options.py index 76db06c85..ffe2463fe 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -462,6 +462,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs): 'the STREAM (stdout or stderr) to apply the setting to. ' 'Can be one of "always", "auto" (default), "never", or ' '"no_color" (use non color terminal sequences). ' + 'Use "auto-tty" or "no_color-tty" to decide based on terminal support only. ' 'Can be used multiple times')) general.add_option( '--compat-options', From ed1b9ed93dd90d2cc960c0d8eaa9d919db224203 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 16 Jul 2024 16:10:50 -0500 Subject: [PATCH 11/69] [update] Fix network error handling (#10486) Authored by: bashonly --- yt_dlp/update.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/yt_dlp/update.py b/yt_dlp/update.py index 8c6790d61..72ae29084 100644 --- a/yt_dlp/update.py +++ b/yt_dlp/update.py @@ -310,6 +310,7 @@ def _download_update_spec(self, source_tags): if isinstance(error, HTTPError) and error.status == 404: continue self._report_network_error(f'fetch update spec: {error}') + return None self._report_error( f'The requested tag {self.requested_tag} does not exist for {self.requested_repo}', True) @@ -557,9 +558,10 @@ def _report_permission_error(self, file): def _report_network_error(self, action, delim=';', tag=None): if not tag: tag = self.requested_tag + path = tag if tag == 'latest' else f'tag/{tag}' self._report_error( - f'Unable to {action}{delim} visit https://github.com/{self.requested_repo}/releases/' - + tag if tag == 'latest' else f'tag/{tag}', True) + f'Unable to {action}{delim} visit ' + f'https://github.com/{self.requested_repo}/releases/{path}', True) # XXX: Everything below this line in this class is deprecated / for compat only @property From 89a161e8c62569a662deda1c948664152efcb6b4 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 16 Jul 2024 17:01:01 -0500 Subject: [PATCH 12/69] [cleanup] Misc (#10487) Closes #10483 Authored by: bashonly --- pyproject.toml | 1 + yt_dlp/utils/_utils.py | 1 + 2 files changed, 2 insertions(+) diff --git a/pyproject.toml b/pyproject.toml index 54755da48..e4c06d271 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -9,6 +9,7 @@ maintainers = [ {name = "Grub4K", email = "contact@grub4k.xyz"}, {name = "bashonly", email = "bashonly@protonmail.com"}, {name = "coletdjnz", email = "coletdjnz@protonmail.com"}, + {name = "sepro", email = "sepro@sepr0.com"}, ] description = "A feature-rich command-line audio/video downloader" readme = "README.md" diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 2c23b3ed5..3e3b285a4 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -5111,6 +5111,7 @@ class _UnsafeExtensionError(Exception): 'gif', 'heic', 'ico', + 'image', 'jng', 'jpeg', 'jxl', From 37c233562db26dd3401fa188dbeb9cabdb284a62 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Tue, 16 Jul 2024 22:08:42 +0000 Subject: [PATCH 13/69] Release 2024.07.16 Created by: bashonly :ci skip all :ci run dl --- CONTRIBUTORS | 3 +++ Changelog.md | 35 +++++++++++++++++++++++++++++++++++ README.md | 4 +++- supportedsites.md | 5 ----- yt_dlp/version.py | 6 +++--- 5 files changed, 44 insertions(+), 9 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 60e25d0ab..01c07aab9 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -650,3 +650,6 @@ DinhHuy2010 exterrestris harbhim LeSuisse +DunnesH +iancmy +mokrueger diff --git a/Changelog.md b/Changelog.md index 6d3033efc..194d75e8a 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,41 @@ # Changelog # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.07.16 + +#### Core changes +- [Fix `noprogress` if `test=True` with `--quiet` and `--verbose`](https://github.com/yt-dlp/yt-dlp/commit/66ce3d76d87af3f81cc9dfec4be4704016cb1cdb) ([#10454](https://github.com/yt-dlp/yt-dlp/issues/10454)) by [Grub4K](https://github.com/Grub4K) +- [Support `auto-tty` and `no_color-tty` for `--color`](https://github.com/yt-dlp/yt-dlp/commit/d9cbced493cae2008508d94a2db5dd98be7c01fc) ([#10453](https://github.com/yt-dlp/yt-dlp/issues/10453)) by [Grub4K](https://github.com/Grub4K) +- **update**: [Fix network error handling](https://github.com/yt-dlp/yt-dlp/commit/ed1b9ed93dd90d2cc960c0d8eaa9d919db224203) ([#10486](https://github.com/yt-dlp/yt-dlp/issues/10486)) by [bashonly](https://github.com/bashonly) +- **utils**: `parse_codecs`: [Fix parsing of mixed case codec strings](https://github.com/yt-dlp/yt-dlp/commit/cc0070f6496e501d77352bad475fb02d6a86846a) by [bashonly](https://github.com/bashonly) + +#### Extractor changes +- **adn**: [Adjust for .com domain change](https://github.com/yt-dlp/yt-dlp/commit/959b7a379b8e5da059d110a63339c964b6265736) ([#10399](https://github.com/yt-dlp/yt-dlp/issues/10399)) by [infanf](https://github.com/infanf) +- **afreecatv**: [Fix login and use `legacy_ssl`](https://github.com/yt-dlp/yt-dlp/commit/4cd41469243624d90b7a2009b95cbe0609343efe) ([#10440](https://github.com/yt-dlp/yt-dlp/issues/10440)) by [bashonly](https://github.com/bashonly) +- **box**: [Support enterprise URLs](https://github.com/yt-dlp/yt-dlp/commit/705f5b84dec75cc7af97f42fd1530e8062735970) ([#10419](https://github.com/yt-dlp/yt-dlp/issues/10419)) by [seproDev](https://github.com/seproDev) +- **digitalconcerthall**: [Extract HEVC and FLAC formats](https://github.com/yt-dlp/yt-dlp/commit/e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1) ([#10470](https://github.com/yt-dlp/yt-dlp/issues/10470)) by [bashonly](https://github.com/bashonly) +- **dplay**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f) ([#10471](https://github.com/yt-dlp/yt-dlp/issues/10471)) by [bashonly](https://github.com/bashonly) +- **epidemicsound**: [Support sound effects URLs](https://github.com/yt-dlp/yt-dlp/commit/8531d2b03bac9cc746f2ee8098aaf8f115505f5b) ([#10436](https://github.com/yt-dlp/yt-dlp/issues/10436)) by [iancmy](https://github.com/iancmy) +- **generic**: [Fix direct video link extensions](https://github.com/yt-dlp/yt-dlp/commit/b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e) ([#10468](https://github.com/yt-dlp/yt-dlp/issues/10468)) by [bashonly](https://github.com/bashonly) +- **picarto**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bacd18b7df08b4995644fd12cee1f8c8e8636bc7) ([#10414](https://github.com/yt-dlp/yt-dlp/issues/10414)) by [Frankgoji](https://github.com/Frankgoji) +- **soundcloud**: permalink, user: [Extract tracks only](https://github.com/yt-dlp/yt-dlp/commit/22870b81bad97dfa6307a7add44753b2dffc76a9) ([#10463](https://github.com/yt-dlp/yt-dlp/issues/10463)) by [DunnesH](https://github.com/DunnesH) +- **tiktok**: live: [Fix room ID extraction](https://github.com/yt-dlp/yt-dlp/commit/d2189d3d36987ebeac426fd70a60a5fe86325a2b) ([#10408](https://github.com/yt-dlp/yt-dlp/issues/10408)) by [mokrueger](https://github.com/mokrueger) +- **tv5monde**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/9b95a6765a5f6325af99c4aca961587f0c426e8c) ([#10417](https://github.com/yt-dlp/yt-dlp/issues/10417)) by [bashonly](https://github.com/bashonly) (With fixes in [cc1a309](https://github.com/yt-dlp/yt-dlp/commit/cc1a3098c00995c6aebc2a16bd1050a66bad64db)) +- **youtube** + - [Avoid poToken experiment player responses](https://github.com/yt-dlp/yt-dlp/commit/8b8b442cb005a8d85315f301615f83fb736b967a) ([#10456](https://github.com/yt-dlp/yt-dlp/issues/10456)) by [seproDev](https://github.com/seproDev) (With fixes in [16da8ef](https://github.com/yt-dlp/yt-dlp/commit/16da8ef9937ff76632dfef02e5062c5ba99c8ea2)) + - [Invalidate nsig cache from < 2024.07.09](https://github.com/yt-dlp/yt-dlp/commit/04e17ba20a139f1b3e30ec4bafa3fba26888f0b3) ([#10401](https://github.com/yt-dlp/yt-dlp/issues/10401)) by [bashonly](https://github.com/bashonly) + - [Reduce android client priority](https://github.com/yt-dlp/yt-dlp/commit/b85eef0a615a01304f88a3847309c667e09a20df) ([#10467](https://github.com/yt-dlp/yt-dlp/issues/10467)) by [seproDev](https://github.com/seproDev) + +#### Networking changes +- [Add `legacy_ssl` request extension](https://github.com/yt-dlp/yt-dlp/commit/150ecc45d9cacc919550c13b04fd998ac5103a6b) ([#10448](https://github.com/yt-dlp/yt-dlp/issues/10448)) by [coletdjnz](https://github.com/coletdjnz) +- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.7.X](https://github.com/yt-dlp/yt-dlp/commit/42bfca00a6b460fc053514cdd7ac6f5b5daddf0c) by [coletdjnz](https://github.com/coletdjnz) + +#### Misc. changes +- **build** + - [Include `curl_cffi` in `yt-dlp_linux`](https://github.com/yt-dlp/yt-dlp/commit/4521f30d1479315cd5c3bf4abdad19391952df98) by [bashonly](https://github.com/bashonly) + - [Pin `curl-cffi` to 0.5.10 for Windows](https://github.com/yt-dlp/yt-dlp/commit/ac30941ae682f71eab010877c9a977736a61d3cf) by [bashonly](https://github.com/bashonly) +- **cleanup**: Miscellaneous: [89a161e](https://github.com/yt-dlp/yt-dlp/commit/89a161e8c62569a662deda1c948664152efcb6b4) by [bashonly](https://github.com/bashonly) + ### 2024.07.09 #### Core changes diff --git a/README.md b/README.md index 243b44344..3ed8717f0 100644 --- a/README.md +++ b/README.md @@ -368,7 +368,9 @@ ## General Options: stderr) to apply the setting to. Can be one of "always", "auto" (default), "never", or "no_color" (use non color terminal - sequences). Can be used multiple times + sequences). Use "auto-tty" or "no_color-tty" + to decide based on terminal support only. + Can be used multiple times --compat-options OPTS Options that can help keep compatibility with youtube-dl or youtube-dlc configurations by reverting some of the diff --git a/supportedsites.md b/supportedsites.md index 42543af39..c8b8fbb35 100644 --- a/supportedsites.md +++ b/supportedsites.md @@ -354,7 +354,6 @@ # Supported sites - **DigitallySpeaking** - **Digiteka** - **DiscogsReleasePlaylist** - - **Discovery** - **DiscoveryLife** - **DiscoveryNetworksDe** - **DiscoveryPlus** @@ -363,7 +362,6 @@ # Supported sites - **DiscoveryPlusItaly** - **DiscoveryPlusItalyShow** - **Disney** - - **DIYNetwork** - **dlf** - **dlf:corpus**: DLF Multi-feed Archives - **dlive:stream** @@ -516,7 +514,6 @@ # Supported sites - **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine") - **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine") - **Glide**: Glide mobile video messages (glide.me) - - **GlobalCyclingNetworkPlus** - **GlobalPlayerAudio** - **GlobalPlayerAudioEpisode** - **GlobalPlayerLive** @@ -820,8 +817,6 @@ # Supported sites - **MotherlessGroup** - **MotherlessUploader** - **Motorsport**: motorsport.com (**Currently broken**) - - **MotorTrend** - - **MotorTrendOnDemand** - **MovieFap** - **Moviepilot** - **MoviewPlay** diff --git a/yt_dlp/version.py b/yt_dlp/version.py index 31de564c5..db5b342d1 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.07.09' +__version__ = '2024.07.16' -RELEASE_GIT_HEAD = '7ead7332af69422cee931aec3faa277288e9e212' +RELEASE_GIT_HEAD = '89a161e8c62569a662deda1c948664152efcb6b4' VARIANT = None @@ -12,4 +12,4 @@ ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.07.09' +_pkg_version = '2024.07.16' From e046db8a116b1c320d4785daadd48ea0b22a3987 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 18 Jul 2024 15:33:28 -0500 Subject: [PATCH 14/69] [build] Pin `setuptools` version (#10493) https://github.com/pypa/setuptools/issues/4480#issuecomment-2236507819 https://github.com/pypa/setuptools/issues/4482 Authored by: bashonly --- pyproject.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index e4c06d271..d5480e1c6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -66,7 +66,7 @@ build = [ "build", "hatchling", "pip", - "setuptools", + "setuptools>=71.0.2", # 71.0.0 broke pyinstaller "wheel", ] dev = [ From a3bab4752a2b3d56e5a59b4e0411bb8f695c010b Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 18 Jul 2024 15:43:31 -0500 Subject: [PATCH 15/69] [ie/abematv] Adapt key retrieval to request handler framework (#10491) Fixes a regression caused by a dependence on buggy behavior that was corrected in 150ecc45d9cacc919550c13b04fd998ac5103a6b Closes #10489 Authored by: bashonly --- yt_dlp/extractor/abematv.py | 67 ++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 38 deletions(-) diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py index 9471df1da..2611c6fdd 100644 --- a/yt_dlp/extractor/abematv.py +++ b/yt_dlp/extractor/abematv.py @@ -9,12 +9,12 @@ import struct import time import urllib.parse -import urllib.request -import urllib.response import uuid from .common import InfoExtractor from ..aes import aes_ecb_decrypt +from ..networking import RequestHandler, Response +from ..networking.exceptions import TransportError from ..utils import ( ExtractorError, OnDemandPagedList, @@ -26,37 +26,36 @@ traverse_obj, update_url_query, ) -from ..utils.networking import clean_proxies -def add_opener(ydl, handler): # FIXME: Create proper API in .networking - """Add a handler for opening URLs, like _download_webpage""" - # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426 - # https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605 - rh = ydl._request_director.handlers['Urllib'] - if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES: - return - headers = ydl.params['http_headers'].copy() - proxies = ydl.proxies.copy() - clean_proxies(proxies, headers) - opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies) - assert isinstance(opener, urllib.request.OpenerDirector) - opener.add_handler(handler) - rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license') +class AbemaLicenseRH(RequestHandler): + _SUPPORTED_URL_SCHEMES = ('abematv-license',) + _SUPPORTED_PROXY_SCHEMES = None + _SUPPORTED_FEATURES = None + RH_NAME = 'abematv_license' + _STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz' + _HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E' -class AbemaLicenseHandler(urllib.request.BaseHandler): - handler_order = 499 - STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz' - HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E' - - def __init__(self, ie: 'AbemaTVIE'): - # the protocol that this should really handle is 'abematv-license://' - # abematv_license_open is just a placeholder for development purposes - # ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510 - setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None)) + def __init__(self, *, ie: 'AbemaTVIE', **kwargs): + super().__init__(**kwargs) self.ie = ie + def _send(self, request): + url = request.url + ticket = urllib.parse.urlparse(url).netloc + + try: + response_data = self._get_videokey_from_ticket(ticket) + except ExtractorError as e: + raise TransportError(cause=e.cause) from e + except (IndexError, KeyError, TypeError) as e: + raise TransportError(cause=repr(e)) from e + + return Response( + io.BytesIO(response_data), url, + headers={'Content-Length': str(len(response_data))}) + def _get_videokey_from_ticket(self, ticket): to_show = self.ie.get_param('verbose', False) media_token = self.ie._get_media_token(to_show=to_show) @@ -72,25 +71,17 @@ def _get_videokey_from_ticket(self, ticket): 'Content-Type': 'application/json', }) - res = decode_base_n(license_response['k'], table=self.STRTABLE) + res = decode_base_n(license_response['k'], table=self._STRTABLE) encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff)) h = hmac.new( - binascii.unhexlify(self.HKEY), + binascii.unhexlify(self._HKEY), (license_response['cid'] + self.ie._DEVICE_ID).encode(), digestmod=hashlib.sha256) enckey = bytes_to_intlist(h.digest()) return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey)) - def abematv_license_open(self, url): - url = url.get_full_url() if isinstance(url, urllib.request.Request) else url - ticket = urllib.parse.urlparse(url).netloc - response_data = self._get_videokey_from_ticket(ticket) - return urllib.response.addinfourl(io.BytesIO(response_data), headers={ - 'Content-Length': str(len(response_data)), - }, url=url, code=200) - class AbemaTVBaseIE(InfoExtractor): _NETRC_MACHINE = 'abematv' @@ -139,7 +130,7 @@ def _get_device_token(self): if self._USERTOKEN: return self._USERTOKEN - add_opener(self._downloader, AbemaLicenseHandler(self)) + self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None)) username, _ = self._get_login_info() auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19') From 713b4cd18f00556771af8cfdd9cea6cc1a09e948 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 23 Jul 2024 16:25:49 -0500 Subject: [PATCH 16/69] [ie/youtube] Fix `n` function name extraction for player `3400486c` (#10542) Authored by: bashonly --- test/test_youtube_signature.py | 4 ++++ yt_dlp/extractor/youtube.py | 9 ++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index a14bef511..ae167d16d 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -171,6 +171,10 @@ 'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js', 'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A', ), + ( + 'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js', + 'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl', + ), ] diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 53aca3816..7364e8a2e 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3131,7 +3131,14 @@ def _decrypt_nsig(self, s, video_id, player_url): def _extract_n_function_name(self, jscode): funcname, idx = self._search_regex( - r'''(?x)(?:\.get\("n"\)\)&&\(b=|b=String\.fromCharCode\(110\),c=a\.get\(b\)\)&&\(c=) + r'''(?x) + (?: + \.get\("n"\)\)&&\(b=| + (?: + b=String\.fromCharCode\(110\)| + ([a-zA-Z0-9$.]+)&&\(b="nn"\[\+\1\] + ),c=a\.get\(b\)\)&&\(c= + ) (?P[a-zA-Z0-9$]+)(?:\[(?P\d+)\])?\([a-zA-Z0-9]\)''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) if not idx: From 2f97779f335ac069ecccd9c7bf81abf4a83cfe7a Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 23 Jul 2024 16:49:31 -0500 Subject: [PATCH 17/69] [ie/tiktok] Fix and deprioritize JSON subtitles (#10516) Fixes regression caused by 5ce582448ececb8d9c30c8c31f58330090ced03a Closes #10514 Authored by: bashonly --- yt_dlp/extractor/tiktok.py | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py index aa1dcecf6..9d823a315 100644 --- a/yt_dlp/extractor/tiktok.py +++ b/yt_dlp/extractor/tiktok.py @@ -23,7 +23,6 @@ mimetype2ext, parse_qs, qualities, - remove_start, srt_subtitles_timecode, str_or_none, traverse_obj, @@ -254,7 +253,16 @@ def _extract_web_data_and_status(self, url, video_id, fatal=True): def _get_subtitles(self, aweme_detail, aweme_id, user_name): # TODO: Extract text positioning info + + EXT_MAP = { # From lowest to highest preference + 'creator_caption': 'json', + 'srt': 'srt', + 'webvtt': 'vtt', + } + preference = qualities(tuple(EXT_MAP.values())) + subtitles = {} + # aweme/detail endpoint subs captions_info = traverse_obj( aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict) @@ -278,8 +286,8 @@ def _get_subtitles(self, aweme_detail, aweme_id, user_name): if not caption.get('url'): continue subtitles.setdefault(caption.get('lang') or 'en', []).append({ - 'ext': remove_start(caption.get('caption_format'), 'web'), 'url': caption['url'], + 'ext': EXT_MAP.get(caption.get('Format')), }) # webpage subs if not subtitles: @@ -288,9 +296,14 @@ def _get_subtitles(self, aweme_detail, aweme_id, user_name): self._create_url(user_name, aweme_id), aweme_id, fatal=False) for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])): subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({ - 'ext': remove_start(caption.get('Format'), 'web'), 'url': caption['Url'], + 'ext': EXT_MAP.get(caption.get('Format')), }) + + # Deprioritize creator_caption json since it can't be embedded or used by media players + for lang, subs_list in subtitles.items(): + subtitles[lang] = sorted(subs_list, key=lambda x: preference(x['ext'])) + return subtitles def _parse_url_key(self, url_key): From a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 23 Jul 2024 17:00:57 -0500 Subject: [PATCH 18/69] [ie/vimeo] Fix chapters extraction (#10544) Closes #5308 Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 51 ++++++++++++++++++++++++++++++--------- 1 file changed, 39 insertions(+), 12 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 18eb08444..d10689cd8 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -212,16 +212,6 @@ def _parse_config(self, config, video_id): owner = video_data.get('owner') or {} video_uploader_url = owner.get('url') - duration = int_or_none(video_data.get('duration')) - chapter_data = try_get(config, lambda x: x['embed']['chapters']) or [] - chapters = [{ - 'title': current_chapter.get('title'), - 'start_time': current_chapter.get('timecode'), - 'end_time': next_chapter.get('timecode'), - } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])] - if chapters and chapters[0]['start_time']: # Chapters may not start from 0 - chapters[:0] = [{'title': '', 'start_time': 0, 'end_time': chapters[0]['start_time']}] - return { 'id': str_or_none(video_data.get('id')) or video_id, 'title': video_title, @@ -229,8 +219,12 @@ def _parse_config(self, config, video_id): 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, 'uploader_url': video_uploader_url, 'thumbnails': thumbnails, - 'duration': duration, - 'chapters': chapters or None, + 'duration': int_or_none(video_data.get('duration')), + 'chapters': sorted(traverse_obj(config, ( + 'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, { + 'title': ('title', {str}), + 'start_time': ('timecode', {int_or_none}), + })), key=lambda c: c['start_time']) or None, 'formats': formats, 'subtitles': subtitles, 'live_status': live_status, @@ -708,6 +702,39 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip_download': True, }, }, + { + # chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308 + 'url': 'https://player.vimeo.com/video/756714419', + 'info_dict': { + 'id': '756714419', + 'ext': 'mp4', + 'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep', + 'uploader': 'Alex Howard', + 'uploader_id': 'user54729178', + 'uploader_url': 'https://vimeo.com/user54729178', + 'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280', + 'duration': 2636, + 'chapters': [ + {'start_time': 0, 'end_time': 10, 'title': ''}, + {'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'}, + {'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'}, + {'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'}, + {'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'}, + {'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"}, + {'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'}, + {'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'}, + {'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'}, + {'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'}, + {'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'}, + {'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'}, + ], + }, + 'params': { + 'http_headers': {'Referer': 'https://sleepsuperconference.com'}, + 'skip_download': 'm3u8', + }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + }, { # user playlist alias -> https://vimeo.com/258705797 'url': 'https://vimeo.com/user26785108/newspiritualguide', From 1a34a802f44a1dab8f642c79c3cc810e21541d3b Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 23 Jul 2024 18:08:24 -0500 Subject: [PATCH 19/69] [ie/facebook] Fix extraction (#10531) Closes #10532 Authored by: bashonly --- yt_dlp/extractor/facebook.py | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index a3ca291fc..6aba477a6 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -571,16 +571,21 @@ def process_formats(info): # Formats larger than ~500MB will return error 403 unless chunk size is regulated f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20 - def extract_relay_data(_filter): - return self._parse_json(self._search_regex( - rf'data-sjs>({{.*?{_filter}.*?}})', - webpage, 'replay data', default='{}'), video_id, fatal=False) or {} + def yield_all_relay_data(_filter): + for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})', webpage): + yield self._parse_json(relay_data, video_id, fatal=False) or {} - def extract_relay_prefetched_data(_filter): - return traverse_obj(extract_relay_data(_filter), ( - 'require', (None, (..., ..., ..., '__bbox', 'require')), + def extract_relay_data(_filter): + return next(filter(None, yield_all_relay_data(_filter)), {}) + + def extract_relay_prefetched_data(_filter, target_keys=None): + path = 'data' + if target_keys is not None: + path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys)) + return traverse_obj(yield_all_relay_data(_filter), ( + ..., 'require', (None, (..., ..., ..., '__bbox', 'require')), lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v), - ..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {} + ..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {} if not video_data: server_js_data = self._parse_json(self._search_regex([ @@ -591,7 +596,8 @@ def extract_relay_prefetched_data(_filter): if not video_data: data = extract_relay_prefetched_data( - r'"(?:dash_manifest|playable_url(?:_quality_hd)?)') + r'"(?:dash_manifest|playable_url(?:_quality_hd)?)', + target_keys=('video', 'event', 'nodes', 'node', 'mediaset')) if data: entries = [] From f0993391e6052ec8f7aacc286609564f226943b9 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 24 Jul 2024 16:22:55 -0500 Subject: [PATCH 20/69] [ie/mlbtv] Fix extractor (#10515) Closes #10510 Authored by: bashonly --- yt_dlp/extractor/mlb.py | 223 ++++++++++++++++++++++++++++++++-------- 1 file changed, 180 insertions(+), 43 deletions(-) diff --git a/yt_dlp/extractor/mlb.py b/yt_dlp/extractor/mlb.py index 6f67602a6..230c218e7 100644 --- a/yt_dlp/extractor/mlb.py +++ b/yt_dlp/extractor/mlb.py @@ -1,16 +1,21 @@ +import json import re -import urllib.parse +import time import uuid from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( + ExtractorError, determine_ext, int_or_none, join_nonempty, + jwt_decode_hs256, parse_duration, parse_iso8601, try_get, url_or_none, + urlencode_postdata, ) from ..utils.traversal import traverse_obj @@ -276,81 +281,213 @@ def _download_video_data(self, display_id): class MLBTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P\d{6})' _NETRC_MACHINE = 'mlb' - _TESTS = [{ 'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638', 'info_dict': { 'id': '661581', 'ext': 'mp4', 'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies', + 'release_date': '20220702', + 'release_timestamp': 1656792300, }, 'params': { 'skip_download': True, }, }] + _GRAPHQL_INIT_QUERY = '''\ +mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) { + initSession(device: $device, clientType: $clientType, experience: $experience) { + deviceId + sessionId + entitlements { + code + } + location { + countryCode + regionName + zipCode + latitude + longitude + } + clientExperience + features + } + }''' + _GRAPHQL_PLAYBACK_QUERY = '''\ +mutation initPlaybackSession( + $adCapabilities: [AdExperienceType] + $mediaId: String! + $deviceId: String! + $sessionId: String! + $quality: PlaybackQuality + ) { + initPlaybackSession( + adCapabilities: $adCapabilities + mediaId: $mediaId + deviceId: $deviceId + sessionId: $sessionId + quality: $quality + ) { + playbackSessionId + playback { + url + token + expiration + cdn + } + } + }''' + _APP_VERSION = '7.8.2' + _device_id = None + _session_id = None _access_token = None + _token_expiry = 0 + + @property + def _api_headers(self): + if (self._token_expiry - 120) <= time.time(): + self.write_debug('Access token has expired; re-logging in') + self._perform_login(*self._get_login_info()) + return {'Authorization': f'Bearer {self._access_token}'} def _real_initialize(self): if not self._access_token: self.raise_login_required( 'All videos are only available to registered users', method='password') + def _set_device_id(self, username): + if not self._device_id: + self._device_id = self.cache.load( + self._NETRC_MACHINE, 'device_ids', default={}).get(username) + if self._device_id: + return + self._device_id = str(uuid.uuid4()) + self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id}) + def _perform_login(self, username, password): - data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356' - access_token = self._download_json( - 'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None, - headers={ - 'User-Agent': 'okhttp/3.12.1', - 'Content-Type': 'application/x-www-form-urlencoded', - }, data=data.encode())['access_token'] + try: + self._access_token = self._download_json( + 'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None, + 'Logging in', 'Unable to log in', headers={ + 'User-Agent': 'okhttp/3.12.1', + 'Content-Type': 'application/x-www-form-urlencoded', + }, data=urlencode_postdata({ + 'grant_type': 'password', + 'username': username, + 'password': password, + 'scope': 'openid offline_access', + 'client_id': '0oa3e1nutA1HLzAKG356', + }))['access_token'] + except ExtractorError as error: + if isinstance(error.cause, HTTPError) and error.cause.status == 400: + raise ExtractorError('Invalid username or password', expected=True) + raise - entitlement = self._download_webpage( - f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None, - headers={ - 'User-Agent': 'okhttp/3.12.1', - 'Authorization': f'Bearer {access_token}', - }) + self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0 + self._set_device_id(username) - data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv' - self._access_token = self._download_json( - 'https://us.edge.bamgrid.com/token', None, + self._session_id = self._call_api({ + 'operationName': 'initSession', + 'query': self._GRAPHQL_INIT_QUERY, + 'variables': { + 'device': { + 'appVersion': self._APP_VERSION, + 'deviceFamily': 'desktop', + 'knownDeviceId': self._device_id, + 'languagePreference': 'ENGLISH', + 'manufacturer': '', + 'model': '', + 'os': '', + 'osVersion': '', + }, + 'clientType': 'WEB', + }, + }, None, 'session ID')['data']['initSession']['sessionId'] + + def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True): + return self._download_json( + 'https://media-gateway.mlb.com/graphql', video_id, + f'Downloading {description}', f'Unable to download {description}', fatal=fatal, headers={ + **self._api_headers, 'Accept': 'application/json', - 'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk', - 'Content-Type': 'application/x-www-form-urlencoded', - }, data=data.encode())['access_token'] + 'Content-Type': 'application/json', + 'x-client-name': 'WEB', + 'x-client-version': self._APP_VERSION, + }, data=json.dumps(data, separators=(',', ':')).encode()) + + def _extract_formats_and_subtitles(self, broadcast, video_id): + feed = traverse_obj(broadcast, ('homeAway', {str.title})) + medium = traverse_obj(broadcast, ('type', {str})) + language = traverse_obj(broadcast, ('language', {str.lower})) + format_id = join_nonempty(feed, medium, language) + + response = self._call_api({ + 'operationName': 'initPlaybackSession', + 'query': self._GRAPHQL_PLAYBACK_QUERY, + 'variables': { + 'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'], + 'deviceId': self._device_id, + 'mediaId': broadcast['mediaId'], + 'quality': 'PLACEHOLDER', + 'sessionId': self._session_id, + }, + }, video_id, f'{format_id} broadcast JSON', fatal=False) + + playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict})) + m3u8_url = traverse_obj(playback, ('url', {url_or_none})) + token = traverse_obj(playback, ('token', {str})) + + if not (m3u8_url and token): + errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str}))) + if 'not entitled' in errors: + raise ExtractorError(errors, expected=True) + elif errors: # Only warn when 'blacked out' since radio formats are available + self.report_warning(f'API returned errors for {format_id}: {errors}') + else: + self.report_warning(f'No formats available for {format_id} broadcast; skipping') + return [], {} + + cdn_headers = {'x-cdn-token': token} + fmts, subs = self._extract_m3u8_formats_and_subtitles( + m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4', + m3u8_id=format_id, fatal=False, headers=cdn_headers) + for fmt in fmts: + fmt['http_headers'] = cdn_headers + fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' ')) + fmt.setdefault('language', language) + if fmt.get('vcodec') == 'none' and fmt['language'] == 'en': + fmt['source_preference'] = 10 + + return fmts, subs def _real_extract(self, url): video_id = self._match_id(url) - airings = self._download_json( - f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D', - video_id)['data']['Airings'] + metadata = traverse_obj(self._download_json( + 'https://statsapi.mlb.com/api/v1/schedule', video_id, query={ + 'gamePk': video_id, + 'hydrate': 'broadcasts(all),statusFlags', + }), ('dates', ..., 'games', lambda _, v: str(v['gamePk']) == video_id and v['broadcasts'], any)) + + broadcasts = traverse_obj(metadata, ( + 'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF')) formats, subtitles = [], {} - for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']): - format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing) - m3u8_url = traverse_obj(self._download_json( - airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id, - note=f'Downloading {format_id} stream info JSON', - errnote=f'Failed to download {format_id} stream info, skipping', - fatal=False, headers={ - 'Authorization': self._access_token, - 'Accept': 'application/vnd.media-service+json; version=2', - }), ('stream', 'complete', {url_or_none})) - if not m3u8_url: - continue - f, s = self._extract_m3u8_formats_and_subtitles( - m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False) - formats.extend(f) - self._merge_subtitles(s, target=subtitles) + for broadcast in broadcasts: + fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id) + formats.extend(fmts) + self._merge_subtitles(subs, target=subtitles) return { 'id': video_id, - 'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False), - 'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE', + 'title': join_nonempty( + traverse_obj(metadata, ('officialDate', {str})), + traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})), + delim=' - '), + 'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON', + 'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})), 'formats': formats, 'subtitles': subtitles, - 'http_headers': {'Authorization': f'Bearer {self._access_token}'}, } From 6b1e430d8e4af56cd4fcb8bdc00fca9b79356464 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Thu, 25 Jul 2024 03:29:27 +0000 Subject: [PATCH 21/69] Release 2024.07.25 Created by: bashonly :ci skip all :ci run dl --- Changelog.md | 13 +++++++++++++ yt_dlp/version.py | 6 +++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/Changelog.md b/Changelog.md index 194d75e8a..b2cad7dc4 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,19 @@ # Changelog # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.07.25 + +#### Extractor changes +- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly) +- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly) +- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly) +- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly) +- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly) +- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly) + +#### Misc. changes +- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly) + ### 2024.07.16 #### Core changes diff --git a/yt_dlp/version.py b/yt_dlp/version.py index db5b342d1..e641bf5ae 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.07.16' +__version__ = '2024.07.25' -RELEASE_GIT_HEAD = '89a161e8c62569a662deda1c948664152efcb6b4' +RELEASE_GIT_HEAD = 'f0993391e6052ec8f7aacc286609564f226943b9' VARIANT = None @@ -12,4 +12,4 @@ ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.07.16' +_pkg_version = '2024.07.25' From 0b7728618417e1aa382722a4d29b916b594d4459 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 25 Jul 2024 17:00:58 -0500 Subject: [PATCH 22/69] [ie/DiscoveryPlus] Support olympics URLs (#10566) Closes #10564 Authored by: bashonly --- yt_dlp/extractor/dplay.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index e9f9357ad..cdf84c52d 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -934,7 +934,7 @@ class TLCIE(DiscoveryPlusBaseIE): class DiscoveryPlusIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P[a-z]{2})/)?video(?:/sport)?' + DPlayBaseIE._PATH_REGEX + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P[a-z]{2})/)?video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family', 'info_dict': { @@ -958,6 +958,9 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE): }, { 'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review', 'only_matching': True, + }, { + 'url': 'https://www.discoveryplus.com/gb/video/olympics/dplus-sport-dplus-sport-sport/rugby-sevens-australia-samoa', + 'only_matching': True, }] _PRODUCT = None From 28d485714fef88937c82635438afba5db81f9089 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 25 Jul 2024 17:30:00 -0500 Subject: [PATCH 23/69] [ie/tva] Fix extractor (#10567) Closes #10555 Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 5 +-- yt_dlp/extractor/tva.py | 72 +++++++++++++-------------------- yt_dlp/extractor/unsupported.py | 4 ++ 3 files changed, 32 insertions(+), 49 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index d2140bc52..dcce7ffa7 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -2169,10 +2169,7 @@ TV5UnisVideoIE, ) from .tv24ua import TV24UAVideoIE -from .tva import ( - TVAIE, - QubIE, -) +from .tva import TVAIE from .tvanouvelles import ( TVANouvellesArticleIE, TVANouvellesIE, diff --git a/yt_dlp/extractor/tva.py b/yt_dlp/extractor/tva.py index e3e10557c..d702640f3 100644 --- a/yt_dlp/extractor/tva.py +++ b/yt_dlp/extractor/tva.py @@ -1,60 +1,29 @@ import functools import re +from .brightcove import BrightcoveNewIE from .common import InfoExtractor from ..utils import float_or_none, int_or_none, smuggle_url, strip_or_none from ..utils.traversal import traverse_obj class TVAIE(InfoExtractor): - _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P\d+)' + IE_NAME = 'tvaplus' + IE_DESC = 'TVA+' + _VALID_URL = r'https?://(?:www\.)?tvaplus\.ca/(?:[^/?#]+/)*[\w-]+-(?P\d+)(?:$|[#?])' _TESTS = [{ - 'url': 'https://videos.tva.ca/details/_5596811470001', - 'info_dict': { - 'id': '5596811470001', - 'ext': 'mp4', - 'title': 'Un extrait de l\'épisode du dimanche 8 octobre 2017 !', - 'uploader_id': '5481942443001', - 'upload_date': '20171003', - 'timestamp': 1507064617, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'skip': 'HTTP Error 404: Not Found', - }, { - 'url': 'https://video.tva.ca/details/_5596811470001', - 'only_matching': True, - }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - video_id = self._match_id(url) - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['CA']}), - 'ie_key': 'BrightcoveNew', - } - - -class QubIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?qub\.ca/(?:[^/]+/)*[0-9a-z-]+-(?P\d+)' - _TESTS = [{ - 'url': 'https://www.qub.ca/tvaplus/tva/alerte-amber/saison-1/episode-01-1000036619', + 'url': 'https://www.tvaplus.ca/tva/alerte-amber/saison-1/episode-01-1000036619', 'md5': '949490fd0e7aee11d0543777611fbd53', 'info_dict': { 'id': '6084352463001', 'ext': 'mp4', - 'title': 'Ép 01. Mon dernier jour', + 'title': 'Mon dernier jour', 'uploader_id': '5481942443001', 'upload_date': '20190907', 'timestamp': 1567899756, 'description': 'md5:9c0d7fbb90939420c651fd977df90145', 'thumbnail': r're:https://.+\.jpg', - 'episode': 'Ép 01. Mon dernier jour', + 'episode': 'Mon dernier jour', 'episode_number': 1, 'tags': ['alerte amber', 'alerte amber saison 1', 'surdemande'], 'duration': 2625.963, @@ -64,23 +33,36 @@ class QubIE(InfoExtractor): 'channel': 'TVA', }, }, { - 'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943', - 'only_matching': True, + 'url': 'https://www.tvaplus.ca/tva/le-baiser-du-barbu/le-baiser-du-barbu-886644190', + 'info_dict': { + 'id': '6354448043112', + 'ext': 'mp4', + 'title': 'Le Baiser du barbu', + 'uploader_id': '5481942443001', + 'upload_date': '20240606', + 'timestamp': 1717694023, + 'description': 'md5:025b1219086c1cbf4bc27e4e034e8b57', + 'thumbnail': r're:https://.+\.jpg', + 'episode': 'Le Baiser du barbu', + 'tags': ['fullepisode', 'films'], + 'duration': 6053.504, + 'series': 'Le Baiser du barbu', + 'channel': 'TVA', + }, }] - # reference_id also works with old account_id(5481942443001) - # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5813221784001/default_default/index.html?videoId=ref:%s' + _BC_URL_TMPL = 'https://players.brightcove.net/5481942443001/default_default/index.html?videoId={}' def _real_extract(self, url): entity_id = self._match_id(url) webpage = self._download_webpage(url, entity_id) - entity = self._search_nextjs_data(webpage, entity_id)['props']['initialProps']['pageProps']['fallbackData'] + entity = self._search_nextjs_data(webpage, entity_id)['props']['pageProps']['staticEntity'] video_id = entity['videoId'] episode = strip_or_none(entity.get('name')) return { '_type': 'url_transparent', - 'url': f'https://videos.tva.ca/details/_{video_id}', - 'ie_key': TVAIE.ie_key(), + 'url': smuggle_url(self._BC_URL_TMPL.format(video_id), {'geo_countries': ['CA']}), + 'ie_key': BrightcoveNewIE.ie_key(), 'id': video_id, 'title': episode, 'episode': episode, diff --git a/yt_dlp/extractor/unsupported.py b/yt_dlp/extractor/unsupported.py index 1e2d118aa..8b7ec1dd9 100644 --- a/yt_dlp/extractor/unsupported.py +++ b/yt_dlp/extractor/unsupported.py @@ -49,6 +49,7 @@ class KnownDRMIE(UnsupportedInfoExtractor): r'amazon\.(?:\w{2}\.)?\w+/gp/video', r'music\.amazon\.(?:\w{2}\.)?\w+', r'(?:watch|front)\.njpwworld\.com', + r'qub\.ca/vrai', ) _TESTS = [{ @@ -149,6 +150,9 @@ class KnownDRMIE(UnsupportedInfoExtractor): }, { 'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs', 'only_matching': True, + }, { + 'url': 'https://www.qub.ca/vrai/l-effet-bocuse-d-or/saison-1/l-effet-bocuse-d-or-saison-1-bande-annonce-1098225063', + 'only_matching': True, }] def _real_extract(self, url): From 6daf2c27c0464fba98337be30de0b66d520d0db1 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 29 Jul 2024 00:35:46 -0500 Subject: [PATCH 24/69] [utils] `unified_timestamp`: Recognize Sunday (#10589) Authored by: bashonly --- test/test_utils.py | 2 ++ yt_dlp/utils/_utils.py | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/test/test_utils.py b/test/test_utils.py index e82f551bc..a2b459352 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -444,6 +444,8 @@ def test_unified_timestamps(self): self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540) self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140) self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363) + self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600) + self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200) self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1) self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86) diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 3e3b285a4..0d3e707c5 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -1217,7 +1217,7 @@ def unified_timestamp(date_str, day_first=True): return None date_str = re.sub(r'\s+', ' ', re.sub( - r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?)(day)?', '', date_str)) + r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?|sun)(day)?', '', date_str)) pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0 timezone, date_str = extract_timezone(date_str) From ef36d517f9b05785d61abca7691d9ab7d63cc75c Mon Sep 17 00:00:00 2001 From: middlingphys <38708390+middlingphys@users.noreply.github.com> Date: Mon, 29 Jul 2024 14:54:59 +0900 Subject: [PATCH 25/69] [ie/abematv] Fix availability extraction (#10569) Authored by: middlingphys --- yt_dlp/extractor/abematv.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py index 2611c6fdd..66ab083fe 100644 --- a/yt_dlp/extractor/abematv.py +++ b/yt_dlp/extractor/abematv.py @@ -377,8 +377,7 @@ def _real_extract(self, url): f'https://api.abema.io/v1/video/programs/{video_id}', video_id, note='Checking playability', headers=headers) - ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType')) - if 3 not in ondemand_types: + if not traverse_obj(api_response, ('label', 'free', {bool})): # cannot acquire decryption key for these streams self.report_warning('This is a premium-only stream') availability = 'premium_only' From 2b6df93a243bdfb9d6bb5c1e18020625cd02d465 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 29 Jul 2024 16:55:06 -0500 Subject: [PATCH 26/69] [ie/vimeo:review] Fix password-protected video extraction (#10598) Closes #10255 Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index d10689cd8..a20cf4b17 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -1267,7 +1267,7 @@ class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE class VimeoReviewIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'(?Phttps://vimeo\.com/[^/]+/review/(?P[^/]+)/[0-9a-f]{10})' + _VALID_URL = r'https?://vimeo\.com/(?P[^/?#]+)/review/(?P\d+)/(?P[\da-f]{10})' _TESTS = [{ 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'md5': 'c507a72f780cacc12b2248bb4006d253', @@ -1313,26 +1313,22 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): }] def _real_extract(self, url): - page_url, video_id = self._match_valid_url(url).groups() - data = self._download_json( - page_url.replace('/review/', '/review/data/'), video_id) + user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash') + data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}' + data = self._download_json(data_url, video_id) if data.get('isLocked') is True: video_password = self._get_video_password() viewer = self._download_json( 'https://vimeo.com/_rv/viewer', video_id) - webpage = self._verify_video_password(video_id, video_password, viewer['xsrft']) - clip_page_config = self._parse_json(self._search_regex( - r'window\.vimeo\.clip_page_config\s*=\s*({.+?});', - webpage, 'clip page config'), video_id) - config_url = clip_page_config['player']['config_url'] - clip_data = clip_page_config.get('clip') or {} - else: - clip_data = data['clipData'] - config_url = clip_data['configUrl'] + self._verify_video_password(video_id, video_password, viewer['xsrft']) + data = self._download_json(data_url, video_id) + clip_data = data['clipData'] + config_url = clip_data['configUrl'] config = self._download_json(config_url, video_id) info_dict = self._parse_config(config, video_id) source_format = self._extract_original_format( - page_url + '/action', video_id) + f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', video_id, + unlisted_hash=traverse_obj(config_url, ({parse_qs}, 'h', -1))) if source_format: info_dict['formats'].append(source_format) info_dict['description'] = clean_html(clip_data.get('description')) From 94a1c5e642e468cebeb51f74c6c220434cb47d96 Mon Sep 17 00:00:00 2001 From: trainman261 Date: Mon, 29 Jul 2024 23:58:26 +0200 Subject: [PATCH 27/69] [ie/cbc.ca:player] Fix extractor (#10302) Closes #10170 Authored by: trainman261, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/cbc.py | 269 ++++++++++++++++++++++++++++++++-------- 1 file changed, 214 insertions(+), 55 deletions(-) diff --git a/yt_dlp/extractor/cbc.py b/yt_dlp/extractor/cbc.py index 1522b08e2..373c9d2c9 100644 --- a/yt_dlp/extractor/cbc.py +++ b/yt_dlp/extractor/cbc.py @@ -1,4 +1,5 @@ import base64 +import functools import json import re import time @@ -6,17 +7,24 @@ import xml.etree.ElementTree from .common import InfoExtractor +from ..networking import HEADRequest from ..utils import ( ExtractorError, + float_or_none, int_or_none, join_nonempty, js_to_json, + mimetype2ext, orderedSet, parse_iso8601, + replace_extension, smuggle_url, strip_or_none, traverse_obj, try_get, + update_url, + url_basename, + url_or_none, ) @@ -149,6 +157,7 @@ def _real_extract(self, url): class CBCPlayerIE(InfoExtractor): IE_NAME = 'cbc.ca:player' _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P(?:\d\.)?\d+)' + _GEO_COUNTRIES = ['CA'] _TESTS = [{ 'url': 'http://www.cbc.ca/player/play/2683190193', 'md5': '64d25f841ddf4ddb28a235338af32e2c', @@ -172,21 +181,20 @@ class CBCPlayerIE(InfoExtractor): 'description': 'md5:dd3b692f0a139b0369943150bd1c46a9', 'timestamp': 1425704400, 'upload_date': '20150307', - 'uploader': 'CBCC-NEW', - 'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg', + 'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg', 'chapters': [], 'duration': 494.811, - 'categories': ['AudioMobile/All in a Weekend Montreal'], - 'tags': 'count:8', + 'categories': ['All in a Weekend Montreal'], + 'tags': 'count:11', 'location': 'Quebec', 'series': 'All in a Weekend Montreal', 'season': 'Season 2015', 'season_number': 2015, 'media_type': 'Excerpt', + 'genres': ['Other'], }, }, { 'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062', - 'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6', 'info_dict': { 'id': '2164402062', 'ext': 'mp4', @@ -194,107 +202,168 @@ class CBCPlayerIE(InfoExtractor): 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.', 'timestamp': 1320410746, 'upload_date': '20111104', - 'uploader': 'CBCC-NEW', - 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg', + 'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg', 'chapters': [], 'duration': 186.867, 'series': 'CBC News: Windsor at 6:00', - 'categories': ['News/Canada/Windsor'], + 'categories': ['Windsor'], 'location': 'Windsor', - 'tags': ['cancer'], - 'creators': ['Allison Johnson'], + 'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'], 'media_type': 'Excerpt', + 'genres': ['News'], }, + 'params': {'skip_download': 'm3u8'}, }, { # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/ 'url': 'https://www.cbc.ca/player/play/1.2985700', 'md5': 'e5e708c34ae6fca156aafe17c43e8b75', 'info_dict': { - 'id': '2657631896', + 'id': '1.2985700', 'ext': 'mp3', 'title': 'CBC Montreal is organizing its first ever community hackathon!', 'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.', 'timestamp': 1425704400, 'upload_date': '20150307', - 'uploader': 'CBCC-NEW', - 'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg', + 'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg', 'chapters': [], 'duration': 494.811, - 'categories': ['AudioMobile/All in a Weekend Montreal'], - 'tags': 'count:8', + 'categories': ['All in a Weekend Montreal'], + 'tags': 'count:11', 'location': 'Quebec', 'series': 'All in a Weekend Montreal', 'season': 'Season 2015', 'season_number': 2015, 'media_type': 'Excerpt', + 'genres': ['Other'], }, }, { 'url': 'https://www.cbc.ca/player/play/1.1711287', - 'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6', 'info_dict': { - 'id': '2164402062', + 'id': '1.1711287', 'ext': 'mp4', 'title': 'Cancer survivor four times over', 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.', 'timestamp': 1320410746, 'upload_date': '20111104', - 'uploader': 'CBCC-NEW', - 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg', + 'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg', 'chapters': [], 'duration': 186.867, 'series': 'CBC News: Windsor at 6:00', - 'categories': ['News/Canada/Windsor'], + 'categories': ['Windsor'], 'location': 'Windsor', - 'tags': ['cancer'], - 'creators': ['Allison Johnson'], + 'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'], 'media_type': 'Excerpt', + 'genres': ['News'], }, + 'params': {'skip_download': 'm3u8'}, }, { # Has subtitles # These broadcasts expire after ~1 month, can find new test URL here: # https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast - 'url': 'https://www.cbc.ca/player/play/1.7159484', - 'md5': '6ed6cd0fc2ef568d2297ba68a763d455', + 'url': 'https://www.cbc.ca/player/play/video/9.6424403', + 'md5': '8025909eaffcf0adf59922904def9a5e', 'info_dict': { - 'id': '2324213316001', + 'id': '9.6424403', 'ext': 'mp4', - 'title': 'The National | School boards sue social media giants', - 'description': 'md5:4b4db69322fa32186c3ce426da07402c', - 'timestamp': 1711681200, - 'duration': 2743.400, - 'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]}, - 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg', - 'uploader': 'CBCC-NEW', + 'title': 'The National | N.W.T. wildfire emergency', + 'description': 'md5:ada33d36d1df69347ed575905bfd496c', + 'timestamp': 1718589600, + 'duration': 2692.833, + 'subtitles': { + 'en-US': [{ + 'name': 'English Captions', + 'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt', + }], + }, + 'thumbnail': 'https://i.cbc.ca/ais/6272b5c6-5e78-4c05-915d-0e36672e33d1,1714756287822/full/max/0/default.jpg', 'chapters': 'count:5', - 'upload_date': '20240329', - 'categories': 'count:4', + 'upload_date': '20240617', + 'categories': ['News', 'The National', 'The National Latest Broadcasts'], 'series': 'The National - Full Show', - 'tags': 'count:1', - 'creators': ['News'], + 'tags': ['The National'], 'location': 'Canada', 'media_type': 'Full Program', + 'genres': ['News'], }, }, { 'url': 'https://www.cbc.ca/player/play/video/1.7194274', 'md5': '188b96cf6bdcb2540e178a6caa957128', 'info_dict': { - 'id': '2334524995812', + 'id': '1.7194274', 'ext': 'mp4', 'title': '#TheMoment a rare white spirit moose was spotted in Alberta', 'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3', 'timestamp': 1714788791, 'duration': 77.678, 'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]}, - 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg', - 'uploader': 'CBCC-NEW', - 'chapters': 'count:0', - 'upload_date': '20240504', + 'thumbnail': 'https://i.cbc.ca/ais/1.7194274,1717224990425/full/max/0/default.jpg', + 'chapters': [], 'categories': 'count:3', 'series': 'The National', - 'tags': 'count:15', - 'creators': ['encoder'], + 'tags': 'count:17', 'location': 'Canada', 'media_type': 'Excerpt', + 'upload_date': '20240504', + 'genres': ['News'], + }, + }, { + 'url': 'https://www.cbc.ca/player/play/video/9.6427282', + 'info_dict': { + 'id': '9.6427282', + 'ext': 'mp4', + 'title': 'Men\'s Soccer - Argentina vs Morocco', + 'description': 'Argentina faces Morocco on the football pitch at Saint Etienne Stadium.', + 'series': 'CBC Sports', + 'media_type': 'Event Coverage', + 'thumbnail': 'https://i.cbc.ca/ais/a4c5c0c2-99fa-4bd3-8061-5a63879c1b33,1718828053500/full/max/0/default.jpg', + 'timestamp': 1721825400.0, + 'upload_date': '20240724', + 'duration': 10568.0, + 'chapters': [], + 'genres': [], + 'tags': ['2024 Paris Olympic Games'], + 'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'], + 'location': 'Canada', + }, + 'params': {'skip_download': 'm3u8'}, + }, { + 'url': 'https://www.cbc.ca/player/play/video/9.6459530', + 'md5': '6c1bb76693ab321a2e99c347a1d5ecbc', + 'info_dict': { + 'id': '9.6459530', + 'ext': 'mp4', + 'title': 'Parts of Jasper incinerated as wildfire rages', + 'description': 'md5:6f1caa8d128ad3f629257ef5fecf0962', + 'series': 'The National', + 'media_type': 'Excerpt', + 'thumbnail': 'https://i.cbc.ca/ais/507c0086-31a2-494d-96e4-bffb1048d045,1721953984375/full/max/0/default.jpg', + 'timestamp': 1721964091.012, + 'upload_date': '20240726', + 'duration': 952.285, + 'chapters': [], + 'genres': [], + 'tags': 'count:23', + 'categories': ['News (FAST)', 'News', 'The National', 'TV News Shows', 'The National '], + }, + }, { + 'url': 'https://www.cbc.ca/player/play/video/9.6420651', + 'md5': '71a850c2c6ee5e912de169f5311bb533', + 'info_dict': { + 'id': '9.6420651', + 'ext': 'mp4', + 'title': 'Is it a breath of fresh air? Measuring air quality in Edmonton', + 'description': 'md5:3922b92cc8b69212d739bd9dd095b1c3', + 'series': 'CBC News Edmonton', + 'media_type': 'Excerpt', + 'thumbnail': 'https://i.cbc.ca/ais/73c4ab9c-7ad4-46ee-bb9b-020fdc01c745,1718214547576/full/max/0/default.jpg', + 'timestamp': 1718220065.768, + 'upload_date': '20240612', + 'duration': 286.086, + 'chapters': [], + 'genres': ['News'], + 'categories': ['News', 'Edmonton'], + 'tags': 'count:7', + 'location': 'Edmonton', }, }, { 'url': 'cbcplayer:1.7159484', @@ -307,23 +376,113 @@ class CBCPlayerIE(InfoExtractor): 'only_matching': True, }] + def _parse_param(self, asset_data, name): + return traverse_obj(asset_data, ('params', lambda _, v: v['name'] == name, 'value', {str}, any)) + def _real_extract(self, url): video_id = self._match_id(url) - if '.' in video_id: - webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id) - video_id = self._search_json( - r'window\.__INITIAL_STATE__\s*=', webpage, - 'initial state', video_id)['video']['currentClip']['mediaId'] + webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id) + data = self._search_json( + r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip'] + assets = traverse_obj( + data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type'])) + + if not assets and (media_id := traverse_obj(data, ('mediaId', {str}))): + # XXX: Deprecated; CBC is migrating off of ThePlatform + return { + '_type': 'url_transparent', + 'ie_key': 'ThePlatform', + 'url': smuggle_url( + f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{media_id}?mbr=true&formats=MPEG4,FLV,MP3', { + 'force_smil_url': True, + }), + 'id': media_id, + '_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS + } + + is_live = traverse_obj(data, ('media', 'streamType', {str})) == 'Live' + formats, subtitles = [], {} + + for sub in traverse_obj(data, ('media', 'textTracks', lambda _, v: url_or_none(v['src']))): + subtitles.setdefault(sub.get('language') or 'und', []).append({ + 'url': sub['src'], + 'name': sub.get('label'), + }) + + for asset in assets: + asset_key = asset['key'] + asset_type = asset['type'] + if asset_type != 'medianet': + self.report_warning(f'Skipping unsupported asset type "{asset_type}": {asset_key}') + continue + asset_data = self._download_json(asset_key, video_id, f'Downloading {asset_type} JSON') + ext = mimetype2ext(self._parse_param(asset_data, 'contentType')) + if ext == 'm3u8': + fmts, subs = self._extract_m3u8_formats_and_subtitles( + asset_data['url'], video_id, 'mp4', m3u8_id='hls', live=is_live) + formats.extend(fmts) + # Avoid slow/error-prone webvtt-over-m3u8 if direct https vtt is available + if not subtitles: + self._merge_subtitles(subs, target=subtitles) + if is_live or not fmts: + continue + # Check for direct https mp4 format + best_video_fmt = traverse_obj(fmts, ( + lambda _, v: v.get('vcodec') != 'none' and v['tbr'], all, + {functools.partial(sorted, key=lambda x: x['tbr'])}, -1, {dict})) or {} + base_url = self._search_regex( + r'(https?://[^?#]+?/)hdntl=', best_video_fmt.get('url'), 'base url', default=None) + if not base_url or '/live/' in base_url: + continue + mp4_url = base_url + replace_extension(url_basename(best_video_fmt['url']), 'mp4') + if self._request_webpage( + HEADRequest(mp4_url), video_id, 'Checking for https format', + errnote=False, fatal=False): + formats.append({ + **best_video_fmt, + 'url': mp4_url, + 'format_id': 'https-mp4', + 'protocol': 'https', + 'manifest_url': None, + 'acodec': None, + }) + else: + formats.append({ + 'url': asset_data['url'], + 'ext': ext, + 'vcodec': 'none' if self._parse_param(asset_data, 'mediaType') == 'audio' else None, + }) + + chapters = traverse_obj(data, ( + 'media', 'chapters', lambda _, v: float(v['startTime']) is not None, { + 'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}), + 'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}), + 'title': ('name', {str}), + })) + # Filter out pointless single chapters with start_time==0 and no end_time + if len(chapters) == 1 and not (chapters[0].get('start_time') or chapters[0].get('end_time')): + chapters = [] return { - '_type': 'url_transparent', - 'ie_key': 'ThePlatform', - 'url': smuggle_url( - f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{video_id}?mbr=true&formats=MPEG4,FLV,MP3', { - 'force_smil_url': True, - }), + **traverse_obj(data, { + 'title': ('title', {str}), + 'description': ('description', {str.strip}), + 'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}), + 'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}), + 'media_type': ('media', 'clipType', {str}), + 'series': ('showName', {str}), + 'season_number': ('media', 'season', {int_or_none}), + 'duration': ('media', 'duration', {float_or_none}, {lambda x: None if is_live else x}), + 'location': ('media', 'region', {str}), + 'tags': ('tags', ..., 'name', {str}), + 'genres': ('media', 'genre', all), + 'categories': ('categories', ..., 'name', {str}), + }), 'id': video_id, - '_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS + 'formats': formats, + 'subtitles': subtitles, + 'chapters': chapters, + 'is_live': is_live, } From fe15d3178e242803ae7a934b90137f13598eba2e Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 30 Jul 2024 04:09:55 -0500 Subject: [PATCH 28/69] [ie/learningonscreen] Add extractor (#10590) Authored by: bashonly, Grub4K Co-authored-by: Simon Sawicki --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/common.py | 8 +-- yt_dlp/extractor/learningonscreen.py | 78 ++++++++++++++++++++++++++++ 3 files changed, 84 insertions(+), 3 deletions(-) create mode 100644 yt_dlp/extractor/learningonscreen.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index dcce7ffa7..f4bd76158 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -986,6 +986,7 @@ LcpIE, LcpPlayIE, ) +from .learningonscreen import LearningOnScreenIE from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioCourseIE, diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index f63bd7825..187f73e7b 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -3150,7 +3150,7 @@ def _parse_ism_formats_and_subtitles(self, ism_doc, ism_url, ism_id=None): }) return formats, subtitles - def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None): + def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None, _headers=None): def absolute_url(item_url): return urljoin(base_url, item_url) @@ -3174,11 +3174,11 @@ def _media_formats(src, cur_media_type, type_info=None): formats = self._extract_m3u8_formats( full_url, video_id, ext='mp4', entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id, - preference=preference, quality=quality, fatal=False) + preference=preference, quality=quality, fatal=False, headers=_headers) elif ext == 'mpd': is_plain_url = False formats = self._extract_mpd_formats( - full_url, video_id, mpd_id=mpd_id, fatal=False) + full_url, video_id, mpd_id=mpd_id, fatal=False, headers=_headers) else: is_plain_url = True formats = [{ @@ -3272,6 +3272,8 @@ def _media_formats(src, cur_media_type, type_info=None): }) for f in media_info['formats']: f.setdefault('http_headers', {})['Referer'] = base_url + if _headers: + f['http_headers'].update(_headers) if media_info['formats'] or media_info['subtitles']: entries.append(media_info) return entries diff --git a/yt_dlp/extractor/learningonscreen.py b/yt_dlp/extractor/learningonscreen.py new file mode 100644 index 000000000..dcf83144c --- /dev/null +++ b/yt_dlp/extractor/learningonscreen.py @@ -0,0 +1,78 @@ +import functools +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + clean_html, + extract_attributes, + get_element_by_class, + get_element_html_by_id, + join_nonempty, + parse_duration, + unified_timestamp, +) +from ..utils.traversal import traverse_obj + + +class LearningOnScreenIE(InfoExtractor): + _VALID_URL = r'https?://learningonscreen\.ac\.uk/ondemand/index\.php/prog/(?P\w+)' + _TESTS = [{ + 'url': 'https://learningonscreen.ac.uk/ondemand/index.php/prog/005D81B2?bcast=22757013', + 'info_dict': { + 'id': '005D81B2', + 'ext': 'mp4', + 'title': 'Planet Earth', + 'duration': 3600.0, + 'timestamp': 1164567600.0, + 'upload_date': '20061126', + 'thumbnail': 'https://stream.learningonscreen.ac.uk/trilt-cover-images/005D81B2-Planet-Earth-2006-11-26T190000Z-BBC4.jpg', + }, + }] + + def _real_initialize(self): + if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'): + self.raise_login_required( + 'Use --cookies for authentication. See ' + ' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp ' + 'for how to manually pass cookies', method=None) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + details = traverse_obj(webpage, ( + {functools.partial(get_element_html_by_id, 'programme-details')}, { + 'title': ({functools.partial(re.search, r'

([^<]+)

')}, 1, {clean_html}), + 'timestamp': ( + {functools.partial(get_element_by_class, 'broadcast-date')}, + {functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}), + 'duration': ( + {functools.partial(get_element_by_class, 'prog-running-time')}, + {clean_html}, {parse_duration}), + })) + + title = details.pop('title', None) or traverse_obj(webpage, ( + {functools.partial(get_element_html_by_id, 'add-to-existing-playlist')}, + {extract_attributes}, 'data-record-title', {clean_html})) + + entries = self._parse_html5_media_entries( + 'https://stream.learningonscreen.ac.uk', webpage, video_id, m3u8_id='hls', mpd_id='dash', + _headers={'Origin': 'https://learningonscreen.ac.uk', 'Referer': 'https://learningonscreen.ac.uk/'}) + if not entries: + raise ExtractorError('No video found') + + if len(entries) > 1: + duration = details.pop('duration', None) + for idx, entry in enumerate(entries, start=1): + entry.update(details) + entry['id'] = join_nonempty(video_id, idx) + entry['title'] = join_nonempty(title, idx) + return self.playlist_result(entries, video_id, title, duration=duration) + + return { + **entries[0], + **details, + 'id': video_id, + 'title': title, + } From 0e539617a41913c7da1edd74fb6543c10ad727b3 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 30 Jul 2024 16:27:06 -0500 Subject: [PATCH 29/69] [ie/youtube] Player client maintenance (#10573) - Add clients: android_producer, android_testsuite, android_vr, tv, web_safari - Remove obsolete clients: android_embedded, ios_embedded, *_embedscreen Authored by: bashonly --- README.md | 6 +- yt_dlp/extractor/youtube.py | 231 ++++++++++++++++++++++-------------- 2 files changed, 142 insertions(+), 95 deletions(-) diff --git a/README.md b/README.md index 3ed8717f0..a35efffc4 100644 --- a/README.md +++ b/README.md @@ -1758,7 +1758,7 @@ # Replace all spaces and "_" in title and uploader with a `-` # EXTRACTOR ARGUMENTS -Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"` +Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"` Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"` @@ -1767,7 +1767,7 @@ # EXTRACTOR ARGUMENTS #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `web_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web` is used, but `tv_embedded` and `_creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) @@ -1775,7 +1775,7 @@ #### youtube * E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total * `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8) * `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others -* `innertube_key`: Innertube API key to use for all API requests +* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used * `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning #### youtubetab (YouTube playlists, channels, feeds, etc.) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 7364e8a2e..1a3e286c6 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -72,133 +72,169 @@ # any clients starting with _ cannot be explicitly requested by the user INNERTUBE_CLIENTS = { 'web': { - 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB', - 'clientVersion': '2.20220801.00.00', + 'clientVersion': '2.20240726.00.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, + }, + # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats + 'web_safari': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'WEB', + 'clientVersion': '2.20240726.00.00', + 'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, }, 'web_embedded': { - 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_EMBEDDED_PLAYER', - 'clientVersion': '1.20220731.00.00', + 'clientVersion': '1.20240723.01.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 56, }, 'web_music': { - 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', 'INNERTUBE_HOST': 'music.youtube.com', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_REMIX', - 'clientVersion': '1.20220727.01.00', + 'clientVersion': '1.20240724.00.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, }, 'web_creator': { - 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_CREATOR', - 'clientVersion': '1.20220726.00.00', + 'clientVersion': '1.20240723.03.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, }, 'android': { - 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'ANDROID', - 'clientVersion': '19.09.37', + 'clientVersion': '19.29.37', 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip', + 'userAgent': 'com.google.android.youtube/19.29.37 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, 'REQUIRE_JS_PLAYER': False, }, - 'android_embedded': { - 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw', - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'ANDROID_EMBEDDED_PLAYER', - 'clientVersion': '19.09.37', - 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, - 'REQUIRE_JS_PLAYER': False, - }, 'android_music': { - 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'ANDROID_MUSIC', - 'clientVersion': '6.42.52', + 'clientVersion': '7.11.50', 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.apps.youtube.music/6.42.52 (Linux; U; Android 11) gzip', + 'userAgent': 'com.google.android.apps.youtube.music/7.11.50 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, 'REQUIRE_JS_PLAYER': False, }, 'android_creator': { - 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'ANDROID_CREATOR', - 'clientVersion': '22.30.100', + 'clientVersion': '24.30.100', 'androidSdkVersion': 30, - 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip', + 'userAgent': 'com.google.android.apps.youtube.creator/24.30.100 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, 'REQUIRE_JS_PLAYER': False, }, + # YouTube Kids videos aren't returned on this client for some reason + 'android_vr': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_VR', + 'clientVersion': '1.57.29', + 'deviceMake': 'Oculus', + 'deviceModel': 'Quest 3', + 'androidSdkVersion': 32, + 'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.57.29 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip', + 'osName': 'Android', + 'osVersion': '12L', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 28, + 'REQUIRE_JS_PLAYER': False, + }, + 'android_testsuite': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_TESTSUITE', + 'clientVersion': '1.9', + 'androidSdkVersion': 30, + 'userAgent': 'com.google.android.youtube/1.9 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 30, + 'REQUIRE_JS_PLAYER': False, + 'PLAYER_PARAMS': '2AMB', + }, + # This client only has legacy formats and storyboards + 'android_producer': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'ANDROID_PRODUCER', + 'clientVersion': '0.111.1', + 'androidSdkVersion': 30, + 'userAgent': 'com.google.android.apps.youtube.producer/0.111.1 (Linux; U; Android 11) gzip', + 'osName': 'Android', + 'osVersion': '11', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 91, + 'REQUIRE_JS_PLAYER': False, + }, # iOS clients have HLS live streams. Setting device model to get 60fps formats. # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 'ios': { - 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'IOS', - 'clientVersion': '19.09.3', - 'deviceModel': 'iPhone14,3', - 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)', + 'clientVersion': '19.29.1', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.youtube/19.29.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '17.5.1.21F90', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, 'REQUIRE_JS_PLAYER': False, }, - 'ios_embedded': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'IOS_MESSAGES_EXTENSION', - 'clientVersion': '19.09.3', - 'deviceModel': 'iPhone14,3', - 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, - 'REQUIRE_JS_PLAYER': False, - }, 'ios_music': { - 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'IOS_MUSIC', - 'clientVersion': '6.33.3', - 'deviceModel': 'iPhone14,3', - 'userAgent': 'com.google.ios.youtubemusic/6.33.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)', + 'clientVersion': '7.08.2', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.youtubemusic/7.08.2 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '17.5.1.21F90', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, @@ -208,9 +244,12 @@ 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'IOS_CREATOR', - 'clientVersion': '22.33.101', - 'deviceModel': 'iPhone14,3', - 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)', + 'clientVersion': '24.30.100', + 'deviceMake': 'Apple', + 'deviceModel': 'iPhone16,2', + 'userAgent': 'com.google.ios.ytcreator/24.30.100 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)', + 'osName': 'iPhone', + 'osVersion': '17.5.1.21F90', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, @@ -219,19 +258,26 @@ # mweb has 'ultralow' formats # See: https://github.com/yt-dlp/yt-dlp/pull/557 'mweb': { - 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'MWEB', - 'clientVersion': '2.20220801.00.00', + 'clientVersion': '2.20240726.01.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 2, }, + 'tv': { + 'INNERTUBE_CONTEXT': { + 'client': { + 'clientName': 'TVHTML5', + 'clientVersion': '7.20240724.13.00', + }, + }, + 'INNERTUBE_CONTEXT_CLIENT_NAME': 7, + }, # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option) # See: https://github.com/zerodytrash/YouTube-Internal-Clients 'tv_embedded': { - 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', @@ -249,6 +295,7 @@ }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 95, + 'REQUIRE_JS_PLAYER': False, }, } @@ -262,7 +309,7 @@ def _split_innertube_client(client_name): def short_client_name(client_name): - main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_') + main, *parts = _split_innertube_client(client_name)[0].split('_') return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper() @@ -274,23 +321,18 @@ def build_innertube_clients(): priority = qualities(BASE_CLIENTS[::-1]) for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): - ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') ytcfg.setdefault('REQUIRE_JS_PLAYER', True) + ytcfg.setdefault('PLAYER_PARAMS', None) ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') _, base_client, variant = _split_innertube_client(client) ytcfg['priority'] = 10 * priority(base_client) - if not variant: - INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg) - embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' - embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY - embedscreen['priority'] -= 3 - elif variant == 'embedded': + if variant == 'embedded': ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY ytcfg['priority'] -= 2 - else: + elif variant: ytcfg['priority'] -= 3 @@ -566,9 +608,6 @@ def _select_api_hostname(self, req_api_hostname, default_client=None): return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0] or req_api_hostname or self._get_innertube_host(default_client or 'web')) - def _extract_api_key(self, ytcfg=None, default_client='web'): - return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client) - def _extract_context(self, ytcfg=None, default_client='web'): context = get_first( (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) @@ -614,13 +653,15 @@ def _call_api(self, ep, query, video_id, fatal=True, headers=None, real_headers.update({'content-type': 'application/json'}) if headers: real_headers.update(headers) - api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0] - or api_key or self._extract_api_key(default_client=default_client)) return self._download_json( f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}', video_id=video_id, fatal=fatal, note=note, errnote=errnote, data=json.dumps(data).encode('utf8'), headers=real_headers, - query={'key': api_key, 'prettyPrint': 'false'}) + query=filter_dict({ + 'key': self._configuration_arg( + 'innertube_key', [api_key], ie_key=YoutubeIE.ie_key(), casesense=True)[0], + 'prettyPrint': 'false', + }, cndn=lambda _, v: v)) def extract_yt_initial_data(self, item_id, webpage, fatal=True): return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal) @@ -972,7 +1013,6 @@ def _extract_response(self, item_id, query, note='Downloading API JSON', headers ep=ep, fatal=True, headers=headers, video_id=item_id, query=query, note=note, context=self._extract_context(ytcfg, default_client), - api_key=self._extract_api_key(ytcfg, default_client), api_hostname=api_hostname, default_client=default_client) except ExtractorError as e: if not isinstance(e.cause, network_exceptions): @@ -1295,6 +1335,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') _POTOKEN_EXPERIMENTS = ('51217476', '51217102') + _BROKEN_CLIENTS = { + short_client_name(client): client + for client in ('android', 'android_creator', 'android_music') + } _GEO_BYPASS = False @@ -3661,9 +3705,10 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, 'videoId': video_id, } - pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0] - if pp_arg: - yt_query['params'] = pp_arg + default_pp = traverse_obj( + INNERTUBE_CLIENTS, (_split_innertube_client(client)[0], 'PLAYER_PARAMS', {str})) + if player_params := self._configuration_arg('player_params', [default_pp], casesense=True)[0]: + yt_query['params'] = player_params yt_query.update(self._generate_player_context(sts)) return self._extract_response( @@ -3675,7 +3720,7 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, def _get_requested_clients(self, url, smuggled_data): requested_clients = [] - android_clients = [] + broken_clients = [] default = ['ios', 'web'] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), @@ -3687,18 +3732,21 @@ def _get_requested_clients(self, url, smuggled_data): requested_clients.extend(allowed_clients) elif client not in allowed_clients: self.report_warning(f'Skipping unsupported client {client}') - elif client.startswith('android'): - android_clients.append(client) + elif client in self._BROKEN_CLIENTS.values(): + broken_clients.append(client) else: requested_clients.append(client) - # Force deprioritization of broken Android clients for format de-duplication - requested_clients.extend(android_clients) + # Force deprioritization of _BROKEN_CLIENTS for format de-duplication + requested_clients.extend(broken_clients) if not requested_clients: requested_clients = default if smuggled_data.get('is_music_url') or self.is_music_url(url): - requested_clients.extend( - f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) + for requested_client in requested_clients: + _, base_client, variant = _split_innertube_client(requested_client) + music_client = f'{base_client}_music' + if variant != 'music' and music_client in INNERTUBE_CLIENTS: + requested_clients.append(music_client) return orderedSet(requested_clients) @@ -3793,13 +3841,12 @@ def append_client(*client_names): prs.append(pr) # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in - if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated: + if variant == 'tv_embedded' and self._is_unplayable(pr) and self.is_authenticated: append_client(f'{base_client}_creator') - elif self._is_agegated(pr): - if variant == 'tv_embedded': - append_client(f'{base_client}_embedded') - elif not variant: - append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded') + elif variant != 'tv_embedded' and self._is_agegated(pr): + if self.is_authenticated: + append_client(f'{base_client}_creator') + append_client(f'tv_embedded.{base_client}') if skipped_clients: self.report_warning( @@ -3935,13 +3982,13 @@ def build_fragments(f): f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) client_name = fmt.get(STREAMING_DATA_CLIENT_NAME) - # Android client formats are broken due to integrity check enforcement + # _BROKEN_CLIENTS return videoplayback URLs that expire after 30 seconds # Ref: https://github.com/yt-dlp/yt-dlp/issues/9554 - is_broken = client_name and client_name.startswith(short_client_name('android')) + is_broken = client_name in self._BROKEN_CLIENTS if is_broken: self.report_warning( - f'{video_id}: Android client formats are broken and may yield HTTP Error 403. ' - 'They will be deprioritized', only_once=True) + f'{video_id}: {self._BROKEN_CLIENTS[client_name]} client formats are broken ' + 'and may yield HTTP Error 403. They will be deprioritized', only_once=True) name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or '' fps = int_or_none(fmt.get('fps')) or 0 From 4b69e1b53ea21e631cd5dd68ff531e2f1671ec17 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 30 Jul 2024 18:17:05 -0500 Subject: [PATCH 30/69] [ie/mlbtv] Fix makeup game extraction (#10607) Closes #10606 Authored by: bashonly --- yt_dlp/extractor/mlb.py | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/mlb.py b/yt_dlp/extractor/mlb.py index 230c218e7..935bf8561 100644 --- a/yt_dlp/extractor/mlb.py +++ b/yt_dlp/extractor/mlb.py @@ -290,9 +290,18 @@ class MLBTVIE(InfoExtractor): 'release_date': '20220702', 'release_timestamp': 1656792300, }, - 'params': { - 'skip_download': True, + 'params': {'skip_download': 'm3u8'}, + }, { + # makeup game: has multiple dates, need to avoid games with 'rescheduleDate' + 'url': 'https://www.mlb.com/tv/g747039/vd22541c4-5a29-45f7-822b-635ec041cf5e', + 'info_dict': { + 'id': '747039', + 'ext': 'mp4', + 'title': '2024-07-29 - Toronto Blue Jays @ Baltimore Orioles', + 'release_date': '20240729', + 'release_timestamp': 1722280200, }, + 'params': {'skip_download': 'm3u8'}, }] _GRAPHQL_INIT_QUERY = '''\ mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) { @@ -463,11 +472,14 @@ def _extract_formats_and_subtitles(self, broadcast, video_id): def _real_extract(self, url): video_id = self._match_id(url) - metadata = traverse_obj(self._download_json( + data = self._download_json( 'https://statsapi.mlb.com/api/v1/schedule', video_id, query={ 'gamePk': video_id, 'hydrate': 'broadcasts(all),statusFlags', - }), ('dates', ..., 'games', lambda _, v: str(v['gamePk']) == video_id and v['broadcasts'], any)) + }) + metadata = traverse_obj(data, ( + 'dates', ..., 'games', + lambda _, v: str(v['gamePk']) == video_id and not v.get('rescheduleDate'), any)) broadcasts = traverse_obj(metadata, ( 'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF')) From 2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 30 Jul 2024 20:50:20 -0500 Subject: [PATCH 31/69] [ie/olympics] Fix extractor (#10604) Closes #10592 Authored by: bashonly --- yt_dlp/extractor/olympics.py | 106 ++++++++++++++++++++++++++++++----- 1 file changed, 93 insertions(+), 13 deletions(-) diff --git a/yt_dlp/extractor/olympics.py b/yt_dlp/extractor/olympics.py index becf052f6..a50c510cb 100644 --- a/yt_dlp/extractor/olympics.py +++ b/yt_dlp/extractor/olympics.py @@ -1,9 +1,17 @@ from .common import InfoExtractor -from ..utils import int_or_none, try_get +from ..networking.exceptions import HTTPError +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, + try_get, + url_or_none, +) +from ..utils.traversal import traverse_obj class OlympicsReplayIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P[^/#&?]+)' + _VALID_URL = r'https?://(?:www\.)?olympics\.com/[a-z]{2}/(?:paris-2024/)?(?:replay|videos?|original-series/episode)/(?P[\w-]+)' _TESTS = [{ 'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays', 'info_dict': { @@ -11,26 +19,98 @@ class OlympicsReplayIE(InfoExtractor): 'ext': 'mp4', 'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020', 'upload_date': '20210801', - 'timestamp': 1627783200, + 'timestamp': 1627797600, 'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3', - 'uploader': 'International Olympic Committee', + 'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2', + 'duration': 7017.0, }, 'params': { 'skip_download': True, }, }, { - 'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp', - 'only_matching': True, + 'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024', + 'info_dict': { + 'id': '32633650-c5ee-4280-8b94-fb6defb6a9b5', + 'ext': 'mp4', + 'title': 'B-girl Nicka - Breaking Life, Road to Paris 2024 | Episode 1', + 'upload_date': '20240517', + 'timestamp': 1715948200, + 'description': 'md5:f63d728a41270ec628f6ac33ce471bb1', + 'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/a3j96l7j6so3vyfijby1', + 'duration': 1321.0, + }, + }, { + 'url': 'https://olympics.com/en/paris-2024/videos/men-s-preliminaries-gbr-esp-ned-rsa-hockey-olympic-games-paris-2024', + 'info_dict': { + 'id': '3d96db23-8eee-4b7c-8ef5-488a0361026c', + 'ext': 'mp4', + 'title': 'Men\'s Preliminaries GBR-ESP & NED-RSA | Hockey | Olympic Games Paris 2024', + 'upload_date': '20240727', + 'timestamp': 1722066600, + }, + 'skip': 'Geo-restricted to RU, BR, BT, NP, TM, BD, TL', + }, { + 'url': 'https://olympics.com/en/paris-2024/videos/dnp-suni-lee-i-have-goals-and-i-have-expectations-for-myself-but-i-also-am-trying-to-give-myself-grace', + 'info_dict': { + 'id': 'a42f37ab-8a74-41d0-a7d9-af27b7b02a90', + 'ext': 'mp4', + 'title': 'md5:c7cfbc9918636a98e66400a812e4d407', + 'upload_date': '20240729', + 'timestamp': 1722288600, + }, }] + _GEO_BYPASS = False + + def _extract_from_nextjs_data(self, webpage, video_id): + data = traverse_obj(self._search_nextjs_data(webpage, video_id, default={}), ( + 'props', 'pageProps', 'page', 'items', + lambda _, v: v['name'] == 'videoPlaylist', 'data', 'currentVideo', {dict}, any)) + if not data: + return None + + geo_countries = traverse_obj(data, ('countries', ..., {str})) + if traverse_obj(data, ('geoRestrictedVideo', {bool})): + self.raise_geo_restricted(countries=geo_countries) + + is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE' + m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl'] + tokenized_url = m3u8_url if is_live else self._tokenize_url(m3u8_url, video_id) + + try: + formats, subtitles = self._extract_m3u8_formats_and_subtitles( + tokenized_url, video_id, 'mp4', m3u8_id='hls') + except ExtractorError as e: + if isinstance(e.cause, HTTPError) and 'georestricted' in e.cause.msg: + self.raise_geo_restricted(countries=geo_countries) + raise + + return { + 'formats': formats, + 'subtitles': subtitles, + 'is_live': is_live, + **traverse_obj(data, { + 'id': ('videoID', {str}), + 'title': ('title', {str}), + 'timestamp': ('contentDate', {parse_iso8601}), + }), + } + + def _tokenize_url(self, url, video_id): + return self._download_json( + 'https://olympics.com/tokenGenerator', video_id, + 'Downloading tokenized m3u8 url', query={'url': url}) def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + + if info := self._extract_from_nextjs_data(webpage, video_id): + return info + title = self._html_search_meta(('title', 'og:title', 'twitter:title'), webpage) - uuid = self._html_search_meta('episode_uid', webpage) + video_uuid = self._html_search_meta('episode_uid', webpage) m3u8_url = self._html_search_meta('video_url', webpage) - json_ld = self._search_json_ld(webpage, uuid) + json_ld = self._search_json_ld(webpage, video_uuid) thumbnails_list = json_ld.get('image') if not thumbnails_list: thumbnails_list = self._html_search_regex( @@ -48,12 +128,12 @@ def _real_extract(self, url): 'width': width, 'height': int_or_none(try_get(width, lambda x: x * height_a / width_a)), }) - m3u8_url = self._download_json( - f'https://olympics.com/tokenGenerator?url={m3u8_url}', uuid, note='Downloading m3u8 url') - formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, 'mp4', m3u8_id='hls') + + formats, subtitles = self._extract_m3u8_formats_and_subtitles( + self._tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls') return { - 'id': uuid, + 'id': video_uuid, 'title': title, 'thumbnails': thumbnails, 'formats': formats, From 5260696b1cba77161828941fdb38f09f14ac6c60 Mon Sep 17 00:00:00 2001 From: vvto33 <54504675+vvto33@users.noreply.github.com> Date: Wed, 31 Jul 2024 11:18:43 +0900 Subject: [PATCH 32/69] [ie/tver] Support olympic URLs (#10600) Closes #10583 Authored by: vvto33 --- yt_dlp/extractor/tver.py | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/tver.py b/yt_dlp/extractor/tver.py index 8105db41c..c13832c6f 100644 --- a/yt_dlp/extractor/tver.py +++ b/yt_dlp/extractor/tver.py @@ -10,7 +10,7 @@ class TVerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?Plp|corner|series|episodes?|feature|tokyo2020/video)/)+(?P[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?Plp|corner|series|episodes?|feature|tokyo2020/video|olympic/paris2024/video)/)+(?P[a-zA-Z0-9]+)' _TESTS = [{ 'skip': 'videos are only available for 7 days', 'url': 'https://tver.jp/episodes/ep83nf3w4p', @@ -23,6 +23,20 @@ class TVerIE(InfoExtractor): 'channel': 'テレビ朝日', }, 'add_ie': ['BrightcoveNew'], + }, { + 'url': 'https://tver.jp/olympic/paris2024/video/6359578055112/', + 'info_dict': { + 'id': '6359578055112', + 'ext': 'mp4', + 'title': '堀米雄斗 金メダルで五輪連覇！「みんなの応援が最後に乗れたカギ」', + 'timestamp': 1722279928, + 'upload_date': '20240729', + 'tags': ['20240729', 'japanese', 'japanmedal', 'paris'], + 'uploader_id': '4774017240001', + 'thumbnail': r're:https?://[^/?#]+boltdns\.net/[^?#]+/1920x1080/match/image\.jpg', + 'duration': 670.571, + }, + 'params': {'skip_download': 'm3u8'}, }, { 'url': 'https://tver.jp/corner/f0103888', 'only_matching': True, @@ -47,7 +61,15 @@ def _real_initialize(self): def _real_extract(self, url): video_id, video_type = self._match_valid_url(url).group('id', 'type') - if video_type not in {'series', 'episodes'}: + + if video_type == 'olympic/paris2024/video': + # Player ID is taken from .content.brightcove.E200.pro.pc.account_id: + # https://tver.jp/olympic/paris2024/req/api/hook?q=https%3A%2F%2Folympic-assets.tver.jp%2Fweb-static%2Fjson%2Fconfig.json&d= + return self.url_result(smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % ('4774017240001', video_id), + {'geo_countries': ['JP']}), 'BrightcoveNew') + + elif video_type not in {'series', 'episodes'}: webpage = self._download_webpage(url, video_id, note='Resolving to new URL') video_id = self._match_id(self._search_regex( (r'canonical"\s*href="(https?://tver\.jp/[^"]+)"', r'&link=(https?://tver\.jp/[^?&]+)[?&]'), From 7e3e4779ad13e4511c9ba3869879e53f0267bd7a Mon Sep 17 00:00:00 2001 From: szantnerb <2652078+szantnerb@users.noreply.github.com> Date: Wed, 31 Jul 2024 04:22:44 +0200 Subject: [PATCH 33/69] [ie/mediaklikk] Fix extractor (#10605) Closes #10588 Authored by: szantnerb --- yt_dlp/extractor/mediaklikk.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/mediaklikk.py b/yt_dlp/extractor/mediaklikk.py index bd1a27fcc..f51342060 100644 --- a/yt_dlp/extractor/mediaklikk.py +++ b/yt_dlp/extractor/mediaklikk.py @@ -133,7 +133,9 @@ def _real_extract(self, url): r']+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None)) player_data['video'] = player_data.pop('token') - player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data) + player_page = self._download_webpage( + 'https://player.mediaklikk.hu/playernew/player.php', video_id, + query=player_data, headers={'Referer': url}) player_json = self._search_json( r'\bpl\.setup\s*\(', player_page, 'player json', video_id, end_pattern=r'\);') playlist_url = traverse_obj( From 011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 31 Jul 2024 16:19:30 -0500 Subject: [PATCH 34/69] [ie/youtube] Fix `n` function name extraction for player `20dfca59` (#10611) Closes #10608 Authored by: bashonly --- test/test_youtube_signature.py | 4 ++++ yt_dlp/extractor/youtube.py | 26 ++++++++++++++++++++------ 2 files changed, 24 insertions(+), 6 deletions(-) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index ae167d16d..d37df7a2e 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -175,6 +175,10 @@ 'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js', 'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl', ), + ( + 'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js', + '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw', + ), ] diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 1a3e286c6..4993ce397 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3174,18 +3174,32 @@ def _decrypt_nsig(self, s, video_id, player_url): return ret def _extract_n_function_name(self, jscode): + # Examples (with placeholders nfunc, narray, idx): + # * .get("n"))&&(b=nfunc(b) + # * .get("n"))&&(b=narray[idx](b) + # * b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c) + # * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("") + # * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("") funcname, idx = self._search_regex( r'''(?x) (?: \.get\("n"\)\)&&\(b=| (?: b=String\.fromCharCode\(110\)| - ([a-zA-Z0-9$.]+)&&\(b="nn"\[\+\1\] - ),c=a\.get\(b\)\)&&\(c= - ) - (?P[a-zA-Z0-9$]+)(?:\[(?P\d+)\])?\([a-zA-Z0-9]\)''', - jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) - if not idx: + (?P[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\] + ),c=a\.get\(b\)\)&&\(c=| + \b(?P[a-zA-Z0-9_$]+)= + )(?P[a-zA-Z0-9_$]+)(?:\[(?P\d+)\])?\([a-zA-Z]\) + (?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''', + jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None)) + if not funcname: + self.report_warning('Falling back to generic n function search') + return self._search_regex( + r'''(?xs) + ;\s*(?P[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\) + \s*\{(?:(?!};).)+?["']enhanced_except_''', + jscode, 'Initial JS player n function name', group='name') + elif not idx: return funcname return json.loads(js_to_json(self._search_regex( From d19fcb934269465fd707e68a87f735ec6983e93d Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 31 Jul 2024 16:39:36 -0500 Subject: [PATCH 35/69] [ie/youtube] Fix age-verification workaround (#10610) Authored by: bashonly, Grub4K Co-authored-by: Simon Sawicki --- README.md | 2 +- yt_dlp/extractor/youtube.py | 26 ++++++++++++++++++++------ 2 files changed, 21 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index a35efffc4..ea3fad1c1 100644 --- a/README.md +++ b/README.md @@ -1767,7 +1767,7 @@ # EXTRACTOR ARGUMENTS #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `web_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web` is used, but `tv_embedded` and `_creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 4993ce397..b20dfda41 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3854,14 +3854,28 @@ def append_client(*client_names): f[STREAMING_DATA_CLIENT_NAME] = name prs.append(pr) - # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in - if variant == 'tv_embedded' and self._is_unplayable(pr) and self.is_authenticated: - append_client(f'{base_client}_creator') - elif variant != 'tv_embedded' and self._is_agegated(pr): - if self.is_authenticated: - append_client(f'{base_client}_creator') + # tv_embedded can work around age-gate and age-verification IF the video is embeddable + if self._is_agegated(pr) and variant != 'tv_embedded': append_client(f'tv_embedded.{base_client}') + # Unauthenticated users will only get tv_embedded client formats if age-gated + if self._is_agegated(pr) and not self.is_authenticated: + self.to_screen( + f'{video_id}: This video is age-restricted; some formats may be missing ' + f'without authentication. {self._login_hint()}', only_once=True) + + # EU countries require age-verification for accounts to access age-restricted videos + # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients + # If embedding is disabled for the video, _is_unplayable() will be truthy for tv_embedded + embedding_is_disabled = variant == 'tv_embedded' and self._is_unplayable(pr) + if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled): + self.to_screen( + f'{video_id}: This video is age-restricted and YouTube is requiring ' + 'account age-verification; some formats may be missing', only_once=True) + # web_creator and mediaconnect can work around the age-verification requirement + # _producer, _testsuite, & _vr variants can also work around age-verification + append_client('web_creator', 'mediaconnect') + if skipped_clients: self.report_warning( f'Skipping player responses from {"/".join(skipped_clients)} clients ' From bb3936ae2b3ce96d0b53f9e17cad1082058f032b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?O=C4=9Fulcan=20Tokar?= <42005993+luvyana@users.noreply.github.com> Date: Thu, 1 Aug 2024 03:00:52 +0300 Subject: [PATCH 36/69] [ie/kick:clips] Add extractor (#10572) Closes #8115 Authored by: luvyana --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/kick.py | 205 +++++++++++++++++++++++--------- 2 files changed, 150 insertions(+), 56 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index f4bd76158..9b73fcd75 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -939,6 +939,7 @@ KhanAcademyUnitIE, ) from .kick import ( + KickClipIE, KickIE, KickVODIE, ) diff --git a/yt_dlp/extractor/kick.py b/yt_dlp/extractor/kick.py index 889548f52..1c1b2a177 100644 --- a/yt_dlp/extractor/kick.py +++ b/yt_dlp/extractor/kick.py @@ -1,9 +1,14 @@ +import functools + from .common import InfoExtractor from ..networking import HEADRequest from ..utils import ( UserNotLive, + determine_ext, float_or_none, + int_or_none, merge_dicts, + parse_iso8601, str_or_none, traverse_obj, unified_timestamp, @@ -25,104 +30,192 @@ def _real_initialize(self): def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs): return self._download_json( - f'https://kick.com/api/v1/{path}', display_id, note=note, + f'https://kick.com/api/{path}', display_id, note=note, headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs) class KickIE(KickBaseIE): + IE_NAME = 'kick:live' _VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P[\w-]+)' _TESTS = [{ - 'url': 'https://kick.com/yuppy', + 'url': 'https://kick.com/buddha', 'info_dict': { - 'id': '6cde1-kickrp-joe-flemmingskick-info-heremust-knowmust-see21', + 'id': '92722911-nopixel-40', 'ext': 'mp4', 'title': str, 'description': str, - 'channel': 'yuppy', - 'channel_id': '33538', - 'uploader': 'Yuppy', - 'uploader_id': '33793', - 'upload_date': str, - 'live_status': 'is_live', 'timestamp': int, - 'thumbnail': r're:^https?://.*\.jpg', + 'thumbnail': r're:https?://.+\.jpg', 'categories': list, + 'upload_date': str, + 'channel': 'buddha', + 'channel_id': '32807', + 'uploader': 'Buddha', + 'uploader_id': '33057', + 'live_status': 'is_live', + 'concurrent_view_count': int, + 'release_timestamp': int, + 'age_limit': 18, + 'release_date': str, }, - 'skip': 'livestream', + 'params': {'skip_download': 'livestream'}, + # 'skip': 'livestream', }, { - 'url': 'https://kick.com/kmack710', + 'url': 'https://kick.com/xqc', 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if KickClipIE.suitable(url) else super().suitable(url) + def _real_extract(self, url): channel = self._match_id(url) - response = self._call_api(f'channels/{channel}', channel) + response = self._call_api(f'v2/channels/{channel}', channel) if not traverse_obj(response, 'livestream', expected_type=dict): raise UserNotLive(video_id=channel) return { - 'id': str(traverse_obj( - response, ('livestream', ('slug', 'id')), get_all=False, default=channel)), - 'formats': self._extract_m3u8_formats( - response['playback_url'], channel, 'mp4', live=True), - 'title': traverse_obj( - response, ('livestream', ('session_title', 'slug')), get_all=False, default=''), - 'description': traverse_obj(response, ('user', 'bio')), 'channel': channel, - 'channel_id': str_or_none(traverse_obj(response, 'id', ('livestream', 'channel_id'))), - 'uploader': traverse_obj(response, 'name', ('user', 'username')), - 'uploader_id': str_or_none(traverse_obj(response, 'user_id', ('user', 'id'))), 'is_live': True, - 'timestamp': unified_timestamp(traverse_obj(response, ('livestream', 'created_at'))), - 'thumbnail': traverse_obj( - response, ('livestream', 'thumbnail', 'url'), expected_type=url_or_none), - 'categories': traverse_obj(response, ('recent_categories', ..., 'name')), + 'formats': self._extract_m3u8_formats(response['playback_url'], channel, 'mp4', live=True), + **traverse_obj(response, { + 'id': ('livestream', 'slug', {str}), + 'title': ('livestream', 'session_title', {str}), + 'description': ('user', 'bio', {str}), + 'channel_id': (('id', ('livestream', 'channel_id')), {int}, {str_or_none}, any), + 'uploader': (('name', ('user', 'username')), {str}, any), + 'uploader_id': (('user_id', ('user', 'id')), {int}, {str_or_none}, any), + 'timestamp': ('livestream', 'created_at', {unified_timestamp}), + 'release_timestamp': ('livestream', 'start_time', {unified_timestamp}), + 'thumbnail': ('livestream', 'thumbnail', 'url', {url_or_none}), + 'categories': ('recent_categories', ..., 'name', {str}), + 'concurrent_view_count': ('livestream', 'viewer_count', {int_or_none}), + 'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}), + }), } class KickVODIE(KickBaseIE): + IE_NAME = 'kick:vod' _VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' _TESTS = [{ - 'url': 'https://kick.com/video/58bac65b-e641-4476-a7ba-3707a35e60e3', + 'url': 'https://kick.com/video/e74614f4-5270-4319-90ad-32179f19a45c', 'md5': '3870f94153e40e7121a6e46c068b70cb', 'info_dict': { - 'id': '58bac65b-e641-4476-a7ba-3707a35e60e3', + 'id': 'e74614f4-5270-4319-90ad-32179f19a45c', 'ext': 'mp4', - 'title': '🤠REBIRTH IS BACK!!!!🤠!stake CODE JAREDFPS 🤠', - 'description': 'md5:02b0c46f9b4197fb545ab09dddb85b1d', - 'channel': 'jaredfps', - 'channel_id': '26608', - 'uploader': 'JaredFPS', - 'uploader_id': '26799', - 'upload_date': '20240402', - 'timestamp': 1712097108, - 'duration': 33859.0, + 'title': r're:❎ MEGA DRAMA ❎ LIVE ❎ CLICK ❎ ULTIMATE SKILLS .+', + 'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.', + 'channel': 'xqc', + 'channel_id': '668', + 'uploader': 'xQc', + 'uploader_id': '676', + 'upload_date': '20240724', + 'timestamp': 1721796562, + 'duration': 18566.0, 'thumbnail': r're:^https?://.*\.jpg', - 'categories': ['Call of Duty: Warzone'], + 'view_count': int, + 'categories': ['VALORANT'], + 'age_limit': 0, }, - 'params': { - 'skip_download': 'm3u8', - }, - 'expected_warnings': [r'impersonation'], + 'params': {'skip_download': 'm3u8'}, }] def _real_extract(self, url): video_id = self._match_id(url) - response = self._call_api(f'video/{video_id}', video_id) + response = self._call_api(f'v1/video/{video_id}', video_id) return { 'id': video_id, 'formats': self._extract_m3u8_formats(response['source'], video_id, 'mp4'), - 'title': traverse_obj( - response, ('livestream', ('session_title', 'slug')), get_all=False, default=''), - 'description': traverse_obj(response, ('livestream', 'channel', 'user', 'bio')), - 'channel': traverse_obj(response, ('livestream', 'channel', 'slug')), - 'channel_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'id'))), - 'uploader': traverse_obj(response, ('livestream', 'channel', 'user', 'username')), - 'uploader_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'user_id'))), - 'timestamp': unified_timestamp(response.get('created_at')), - 'duration': float_or_none(traverse_obj(response, ('livestream', 'duration')), scale=1000), - 'thumbnail': traverse_obj( - response, ('livestream', 'thumbnail'), expected_type=url_or_none), - 'categories': traverse_obj(response, ('livestream', 'categories', ..., 'name')), + **traverse_obj(response, { + 'title': ('livestream', ('session_title', 'slug'), {str}, any), + 'description': ('livestream', 'channel', 'user', 'bio', {str}), + 'channel': ('livestream', 'channel', 'slug', {str}), + 'channel_id': ('livestream', 'channel', 'id', {int}, {str_or_none}), + 'uploader': ('livestream', 'channel', 'user', 'username', {str}), + 'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}), + 'timestamp': ('created_at', {parse_iso8601}), + 'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}), + 'thumbnail': ('livestream', 'thumbnail', {url_or_none}), + 'categories': ('livestream', 'categories', ..., 'name', {str}), + 'view_count': ('views', {int_or_none}), + 'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}), + }), + } + + +class KickClipIE(KickBaseIE): + IE_NAME = 'kick:clips' + _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/?\?(?:[^#]+&)?clip=(?Pclip_[\w-]+)' + _TESTS = [{ + 'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X', + 'info_dict': { + 'id': 'clip_01GYXVB5Y8PWAPWCWMSBCFB05X', + 'ext': 'mp4', + 'title': 'Maddy detains Abd D:', + 'channel': 'mxddy', + 'channel_id': '133789', + 'uploader': 'AbdCreates', + 'uploader_id': '3309077', + 'thumbnail': r're:^https?://.*\.jpeg', + 'duration': 35, + 'timestamp': 1682481453, + 'upload_date': '20230426', + 'view_count': int, + 'like_count': int, + 'categories': ['VALORANT'], + 'age_limit': 18, + }, + 'params': {'skip_download': 'm3u8'}, + }, { + 'url': 'https://kick.com/destiny?clip=clip_01H9SKET879NE7N9RJRRDS98J3', + 'info_dict': { + 'id': 'clip_01H9SKET879NE7N9RJRRDS98J3', + 'title': 'W jews', + 'ext': 'mp4', + 'channel': 'destiny', + 'channel_id': '1772249', + 'uploader': 'punished_furry', + 'uploader_id': '2027722', + 'duration': 49.0, + 'upload_date': '20230908', + 'timestamp': 1694150180, + 'thumbnail': 'https://clips.kick.com/clips/j3/clip_01H9SKET879NE7N9RJRRDS98J3/thumbnail.png', + 'view_count': int, + 'like_count': int, + 'categories': ['Just Chatting'], + 'age_limit': 0, + }, + 'params': {'skip_download': 'm3u8'}, + }] + + def _real_extract(self, url): + clip_id = self._match_id(url) + clip = self._call_api(f'v2/clips/{clip_id}/play', clip_id)['clip'] + clip_url = clip['clip_url'] + + if determine_ext(clip_url) == 'm3u8': + formats = self._extract_m3u8_formats(clip_url, clip_id, 'mp4') + else: + formats = [{'url': clip_url}] + + return { + 'id': clip_id, + 'formats': formats, + **traverse_obj(clip, { + 'title': ('title', {str}), + 'channel': ('channel', 'slug', {str}), + 'channel_id': ('channel', 'id', {int}, {str_or_none}), + 'uploader': ('creator', 'username', {str}), + 'uploader_id': ('creator', 'id', {int}, {str_or_none}), + 'thumbnail': ('thumbnail_url', {url_or_none}), + 'duration': ('duration', {float_or_none}), + 'categories': ('category', 'name', {str}, all), + 'timestamp': ('created_at', {parse_iso8601}), + 'view_count': ('views', {int_or_none}), + 'like_count': ('likes', {int_or_none}), + 'age_limit': ('is_mature', {bool}, {lambda x: 18 if x else 0}), + }), } From efb42763dec23ccf6a2e3bac3afbfefce8efd012 Mon Sep 17 00:00:00 2001 From: sepro Date: Thu, 1 Aug 2024 16:03:03 +0200 Subject: [PATCH 37/69] [ie/youtube] Change default player clients to `ios,tv` (#10457) Closes #10046 Authored by: seproDev --- README.md | 2 +- yt_dlp/extractor/youtube.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index ea3fad1c1..dd78012a8 100644 --- a/README.md +++ b/README.md @@ -1767,7 +1767,7 @@ # EXTRACTOR ARGUMENTS #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index b20dfda41..c56358288 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3735,7 +3735,7 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, def _get_requested_clients(self, url, smuggled_data): requested_clients = [] broken_clients = [] - default = ['ios', 'web'] + default = ['ios', 'tv'] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) From ffd7781d6588926f820b44a34b9e6e3068fb9f97 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 1 Aug 2024 10:03:49 -0500 Subject: [PATCH 38/69] [cleanup] Misc (#10623) Authored by: bashonly --- yt_dlp/extractor/youtube.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index c56358288..88e1a28ae 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3173,7 +3173,7 @@ def _decrypt_nsig(self, s, video_id, player_url): self.write_debug(f'Decrypted nsig {s} => {ret}') return ret - def _extract_n_function_name(self, jscode): + def _extract_n_function_name(self, jscode, player_url=None): # Examples (with placeholders nfunc, narray, idx): # * .get("n"))&&(b=nfunc(b) # * .get("n"))&&(b=narray[idx](b) @@ -3193,7 +3193,9 @@ def _extract_n_function_name(self, jscode): (?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''', jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None)) if not funcname: - self.report_warning('Falling back to generic n function search') + self.report_warning(join_nonempty( + 'Falling back to generic n function search', + player_url and f' player = {player_url}', delim='\n')) return self._search_regex( r'''(?xs) ;\s*(?P[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\) @@ -3215,7 +3217,7 @@ def _extract_n_function_code(self, video_id, player_url): if func_code: return jsi, player_id, func_code - func_name = self._extract_n_function_name(jscode) + func_name = self._extract_n_function_name(jscode, player_url=player_url) func_code = jsi.extract_function_code(func_name) From abe10131fc235b7cc7af39f833e417f4264c1fdb Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Thu, 1 Aug 2024 15:11:19 +0000 Subject: [PATCH 39/69] Release 2024.08.01 Created by: bashonly :ci skip all :ci run dl --- CONTRIBUTORS | 2 ++ Changelog.md | 26 ++++++++++++++++++++++++++ supportedsites.md | 9 +++++---- yt_dlp/version.py | 6 +++--- 4 files changed, 36 insertions(+), 7 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 01c07aab9..2180ecfe2 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -653,3 +653,5 @@ LeSuisse DunnesH iancmy mokrueger +luvyana +szantnerb diff --git a/Changelog.md b/Changelog.md index b2cad7dc4..73bf828a6 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,32 @@ # Changelog # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.08.01 + +#### Core changes +- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly) + +#### Extractor changes +- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys) +- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261) +- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly) +- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana) +- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K) +- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb) +- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly) +- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly) +- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly) +- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33) +- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly) +- **youtube** + - [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev) + - [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly) + - [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K) + - [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly) + +#### Misc. changes +- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly) + ### 2024.07.25 #### Extractor changes diff --git a/supportedsites.md b/supportedsites.md index c8b8fbb35..e3bbe03ec 100644 --- a/supportedsites.md +++ b/supportedsites.md @@ -655,10 +655,11 @@ # Supported sites - **Ketnet** - **khanacademy** - **khanacademy:unit** - - **Kick** + - **kick:clips** + - **kick:live** + - **kick:vod** - **Kicker** - **KickStarter** - - **KickVOD** - **kinja:embed** - **KinoPoisk** - **Kommunetv** @@ -690,6 +691,7 @@ # Supported sites - **Lcp** - **LcpPlay** - **Le**: 乐视网 + - **LearningOnScreen** - **Lecture2Go**: (**Currently broken**) - **Lecturio**: [*lecturio*](## "netrc machine") - **LecturioCourse**: [*lecturio*](## "netrc machine") @@ -1140,7 +1142,6 @@ # Supported sites - **QuantumTV**: [*quantumtv*](## "netrc machine") - **QuantumTVLive**: [*quantumtv*](## "netrc machine") - **QuantumTVRecordings**: [*quantumtv*](## "netrc machine") - - **Qub** - **R7**: (**Currently broken**) - **R7Article**: (**Currently broken**) - **Radiko** @@ -1517,9 +1518,9 @@ # Supported sites - **tv5unis** - **tv5unis:video** - **tv8.it** - - **TVA** - **TVANouvelles** - **TVANouvellesArticle** + - **tvaplus**: TVA+ - **TVC** - **TVCArticle** - **TVer** diff --git a/yt_dlp/version.py b/yt_dlp/version.py index e641bf5ae..81d1c2c96 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.07.25' +__version__ = '2024.08.01' -RELEASE_GIT_HEAD = 'f0993391e6052ec8f7aacc286609564f226943b9' +RELEASE_GIT_HEAD = 'ffd7781d6588926f820b44a34b9e6e3068fb9f97' VARIANT = None @@ -12,4 +12,4 @@ ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.07.25' +_pkg_version = '2024.08.01' From 0088c6de23d832b117061a33e984dc452d992e9c Mon Sep 17 00:00:00 2001 From: hugepower Date: Fri, 2 Aug 2024 00:40:46 +0800 Subject: [PATCH 40/69] [ie/youku] Fix extractor (#10626) Closes #10549 Authored by: hugepower --- yt_dlp/extractor/youku.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/youku.py b/yt_dlp/extractor/youku.py index fa6b0539b..3bdfa6c93 100644 --- a/yt_dlp/extractor/youku.py +++ b/yt_dlp/extractor/youku.py @@ -136,7 +136,7 @@ def _real_extract(self, url): # request basic data basic_data_params = { 'vid': video_id, - 'ccode': '0524', + 'ccode': '0564', 'client_ip': '192.168.1.1', 'utid': cna, 'client_ts': time.time() / 1000, From 919540a9644e55deb78cdd6751757ec8fdaf76f4 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 1 Aug 2024 15:25:46 -0500 Subject: [PATCH 41/69] [ie/olympics] Fix extraction (#10625) Bugfix for 2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94 Closes #10592 Authored by: bashonly --- yt_dlp/extractor/olympics.py | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/yt_dlp/extractor/olympics.py b/yt_dlp/extractor/olympics.py index a50c510cb..bbf83e531 100644 --- a/yt_dlp/extractor/olympics.py +++ b/yt_dlp/extractor/olympics.py @@ -4,7 +4,9 @@ ExtractorError, int_or_none, parse_iso8601, + parse_qs, try_get, + update_url, url_or_none, ) from ..utils.traversal import traverse_obj @@ -24,9 +26,6 @@ class OlympicsReplayIE(InfoExtractor): 'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2', 'duration': 7017.0, }, - 'params': { - 'skip_download': True, - }, }, { 'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024', 'info_dict': { @@ -74,7 +73,7 @@ def _extract_from_nextjs_data(self, webpage, video_id): is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE' m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl'] - tokenized_url = m3u8_url if is_live else self._tokenize_url(m3u8_url, video_id) + tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id) try: formats, subtitles = self._extract_m3u8_formats_and_subtitles( @@ -95,10 +94,20 @@ def _extract_from_nextjs_data(self, webpage, video_id): }), } - def _tokenize_url(self, url, video_id): + def _tokenize_url(self, url, token, is_live, video_id): + return self._download_json( + 'https://metering.olympics.com/tokengenerator', video_id, + 'Downloading tokenized m3u8 url', query={ + **parse_qs(url), + 'url': update_url(url, query=None), + 'service-id': 'live' if is_live else 'vod', + 'user-auth': token, + })['data']['url'] + + def _legacy_tokenize_url(self, url, video_id): return self._download_json( 'https://olympics.com/tokenGenerator', video_id, - 'Downloading tokenized m3u8 url', query={'url': url}) + 'Downloading legacy tokenized m3u8 url', query={'url': url}) def _real_extract(self, url): video_id = self._match_id(url) @@ -130,7 +139,7 @@ def _real_extract(self, url): }) formats, subtitles = self._extract_m3u8_formats_and_subtitles( - self._tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls') + self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls') return { 'id': video_uuid, From e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sun, 4 Aug 2024 10:20:45 -0500 Subject: [PATCH 42/69] [ie/DiscoveryPlusItaly] Support sport and olympics URLs (#10655) Closes #10654 Authored by: bashonly --- yt_dlp/extractor/dplay.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index cdf84c52d..8d7707271 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -1147,13 +1147,19 @@ def _real_extract(self, url): class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE): - _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX + _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX _TESTS = [{ 'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi', 'only_matching': True, }, { 'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer', 'only_matching': True, + }, { + 'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy', + 'only_matching': True, + }, { + 'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno', + 'only_matching': True, }] _PRODUCT = 'dplus_it' From bb8bf1db993f59752d20b73b861bd55e40cf0e31 Mon Sep 17 00:00:00 2001 From: sepro Date: Mon, 5 Aug 2024 22:28:24 +0200 Subject: [PATCH 43/69] [jsinterp] Improve `slice` implementation (#10664) Authored by: seproDev --- test/test_jsinterp.py | 28 ++++++++++++++++++++++++++++ yt_dlp/jsinterp.py | 6 +++--- 2 files changed, 31 insertions(+), 3 deletions(-) diff --git a/test/test_jsinterp.py b/test/test_jsinterp.py index df92c8315..06840ed85 100644 --- a/test/test_jsinterp.py +++ b/test/test_jsinterp.py @@ -403,6 +403,34 @@ def test_split(self): self._test(jsi, [''], args=['', '-']) self._test(jsi, [], args=['', '']) + def test_slice(self): + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', []) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', []) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', []) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7]) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', []) + self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7]) + self._test('function f(){return "012345678".slice()}', '012345678') + self._test('function f(){return "012345678".slice(0)}', '012345678') + self._test('function f(){return "012345678".slice(5)}', '5678') + self._test('function f(){return "012345678".slice(99)}', '') + self._test('function f(){return "012345678".slice(-2)}', '78') + self._test('function f(){return "012345678".slice(-99)}', '012345678') + self._test('function f(){return "012345678".slice(0, 0)}', '') + self._test('function f(){return "012345678".slice(1, 0)}', '') + self._test('function f(){return "012345678".slice(0, 1)}', '0') + self._test('function f(){return "012345678".slice(3, 6)}', '345') + self._test('function f(){return "012345678".slice(1, -1)}', '1234567') + self._test('function f(){return "012345678".slice(-1, 1)}', '') + self._test('function f(){return "012345678".slice(-3, -1)}', '67') + if __name__ == '__main__': unittest.main() diff --git a/yt_dlp/jsinterp.py b/yt_dlp/jsinterp.py index 851d4dc7b..ba059babb 100644 --- a/yt_dlp/jsinterp.py +++ b/yt_dlp/jsinterp.py @@ -709,9 +709,9 @@ def eval_method(): obj.reverse() return obj elif member == 'slice': - assertion(isinstance(obj, list), 'must be applied on a list') - assertion(len(argvals) == 1, 'takes exactly one argument') - return obj[argvals[0]:] + assertion(isinstance(obj, (list, str)), 'must be applied on a list or string') + assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments') + return obj[slice(*argvals, None)] elif member == 'splice': assertion(isinstance(obj, list), 'must be applied on a list') assertion(argvals, 'takes one or more arguments') From c86891eb9434b4d7eec426d38c0c625b5e13cb2f Mon Sep 17 00:00:00 2001 From: sepro Date: Mon, 5 Aug 2024 22:36:11 +0200 Subject: [PATCH 44/69] [ie/youtube] Fix `n` function name extraction for player `b12cc44b` (#10668) Authored by: seproDev --- test/test_youtube_signature.py | 4 ++++ yt_dlp/extractor/youtube.py | 9 ++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index d37df7a2e..0f7ae34f4 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -179,6 +179,10 @@ 'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js', '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw', ), + ( + 'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js', + 'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw', + ), ] diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 88e1a28ae..46822cfde 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3180,6 +3180,7 @@ def _extract_n_function_name(self, jscode, player_url=None): # * b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c) # * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("") # * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("") + # * a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("") funcname, idx = self._search_regex( r'''(?x) (?: @@ -3187,7 +3188,13 @@ def _extract_n_function_name(self, jscode, player_url=None): (?: b=String\.fromCharCode\(110\)| (?P[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\] - ),c=a\.get\(b\)\)&&\(c=| + ) + (?: + ,[a-zA-Z0-9_$]+\(a\))?,c=a\. + (?: + get\(b\)| + [a-zA-Z0-9_$]+\[b\]\|\|null + )\)&&\(c=| \b(?P[a-zA-Z0-9_$]+)= )(?P[a-zA-Z0-9_$]+)(?:\[(?P\d+)\])?\([a-zA-Z]\) (?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''', From 406f4c2e47502fffc1b0c210b4ee6487c89a44cb Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 5 Aug 2024 18:26:50 -0500 Subject: [PATCH 45/69] [ie/youtube] Change default player clients to `ios,web_creator` (#10674) Closes #10660 Authored by: bashonly --- README.md | 2 +- yt_dlp/extractor/youtube.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index dd78012a8..ca32e09bf 100644 --- a/README.md +++ b/README.md @@ -1767,7 +1767,7 @@ # EXTRACTOR ARGUMENTS #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 46822cfde..224c9b988 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3744,7 +3744,7 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, def _get_requested_clients(self, url, smuggled_data): requested_clients = [] broken_clients = [] - default = ['ios', 'tv'] + default = ['ios', 'web_creator'] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) From fc5eecfa31c9571b6031cc3968aaa0394be55d7a Mon Sep 17 00:00:00 2001 From: scribblemaniac Date: Mon, 5 Aug 2024 19:02:21 -0600 Subject: [PATCH 46/69] [ie/gem.cbc.ca:live] Fix extractor (#10565) Authored by: scribblemaniac, bashonly --- yt_dlp/extractor/cbc.py | 87 +++++++++++++++++++++++++++++------------ 1 file changed, 61 insertions(+), 26 deletions(-) diff --git a/yt_dlp/extractor/cbc.py b/yt_dlp/extractor/cbc.py index 373c9d2c9..40224f63f 100644 --- a/yt_dlp/extractor/cbc.py +++ b/yt_dlp/extractor/cbc.py @@ -806,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor): 'title': 'Ottawa', 'description': 'The live TV channel and local programming from Ottawa', 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg', - 'is_live': True, + 'live_status': 'is_live', 'id': 'AyqZwxRqh8EH', 'ext': 'mp4', - 'timestamp': 1492106160, - 'upload_date': '20170413', + 'release_timestamp': 1492106160, + 'release_date': '20170413', 'uploader': 'CBCC-NEW', }, 'skip': 'Live might have ended', @@ -839,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor): 'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.', 'live_status': 'is_live', 'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*', - 'timestamp': 1679706000, - 'upload_date': '20230325', + 'release_timestamp': 1679706000, + 'release_date': '20230325', }, 'params': {'skip_download': True}, 'skip': 'Live might have ended', }, + { # event replay (medianetlive) + 'url': 'https://gem.cbc.ca/live-event/42314', + 'md5': '297a9600f554f2258aed01514226a697', + 'info_dict': { + 'id': '42314', + 'ext': 'mp4', + 'live_status': 'was_live', + 'title': 'Women\'s Soccer - Canada vs New Zealand', + 'description': 'md5:36200e5f1a70982277b5a6ecea86155d', + 'thumbnail': r're:https://.+default\.jpg', + 'release_timestamp': 1721917200, + 'release_date': '20240725', + }, + 'params': {'skip_download': True}, + 'skip': 'Replay might no longer be available', + }, + { # event replay (medianetlive) + 'url': 'https://gem.cbc.ca/live-event/43273', + 'only_matching': True, + }, ] + _GEO_COUNTRIES = ['CA'] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data'] - # Two types of metadata JSON + # Three types of video_info JSON: info in root, freeTv stream/item, event replay if not video_info.get('formattedIdMedia'): - video_info = traverse_obj( - video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}), - get_all=False, default={}) + if traverse_obj(video_info, ('event', 'key')) == video_id: + video_info = video_info['event'] + else: + video_info = traverse_obj(video_info, ( + ('freeTv', ('streams', ...)), 'items', + lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {} video_stream_id = video_info.get('formattedIdMedia') if not video_stream_id: - raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True) + raise ExtractorError( + 'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True) - stream_data = self._download_json( - 'https://services.radio-canada.ca/media/validation/v2/', video_id, query={ - 'appCode': 'mpx', - 'connectionType': 'hd', - 'deviceType': 'ipad', - 'idMedia': video_stream_id, - 'multibitrate': 'true', - 'output': 'json', - 'tech': 'hls', - 'manifestType': 'desktop', - }) + live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live' + release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601})) + + if live_status == 'is_live' and release_timestamp and release_timestamp > time.time(): + formats = [] + live_status = 'is_upcoming' + self.raise_no_formats('This livestream has not yet started', expected=True) + else: + stream_data = self._download_json( + 'https://services.radio-canada.ca/media/validation/v2/', video_id, query={ + 'appCode': 'medianetlive', + 'connectionType': 'hd', + 'deviceType': 'ipad', + 'idMedia': video_stream_id, + 'multibitrate': 'true', + 'output': 'json', + 'tech': 'hls', + 'manifestType': 'desktop', + }) + formats = self._extract_m3u8_formats( + stream_data['url'], video_id, 'mp4', live=live_status == 'is_live') return { 'id': video_id, - 'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True), - 'is_live': True, + 'formats': formats, + 'live_status': live_status, + 'release_timestamp': release_timestamp, **traverse_obj(video_info, { - 'title': 'title', - 'description': 'description', + 'title': ('title', {str}), + 'description': ('description', {str}), 'thumbnail': ('images', 'card', 'url'), - 'timestamp': ('airDate', {parse_iso8601}), }), } From 4d9231208332d4c32364b8cd814bff8b20232cae Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 5 Aug 2024 21:50:06 -0500 Subject: [PATCH 47/69] [ie/niconico] Fix extractor (#10677) Closes #10662 Authored by: bashonly --- yt_dlp/extractor/niconico.py | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/yt_dlp/extractor/niconico.py b/yt_dlp/extractor/niconico.py index 9d7b010c5..179e7a9b1 100644 --- a/yt_dlp/extractor/niconico.py +++ b/yt_dlp/extractor/niconico.py @@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.nicovideo.jp/watch/sm22312215', - 'md5': 'd1a75c0823e2f629128c43e1212760f9', 'info_dict': { 'id': 'sm22312215', 'ext': 'mp4', @@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor): 'comment_count': int, 'genres': ['未設定'], 'tags': [], - 'expected_protocol': str, }, + 'params': {'skip_download': 'm3u8'}, }, { # File downloaded with and without credentials are different, so omit # the md5 field @@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor): 'view_count': int, 'genres': ['音楽・サウンド'], 'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'], - 'expected_protocol': str, }, + 'params': {'skip_download': 'm3u8'}, }, { # 'video exists but is marked as "deleted" # md5 is unstable @@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor): }, { # video not available via `getflv`; "old" HTML5 video 'url': 'http://www.nicovideo.jp/watch/sm1151009', - 'md5': 'f95a3d259172667b293530cc2e41ebda', 'info_dict': { 'id': 'sm1151009', 'ext': 'mp4', @@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor): 'comment_count': int, 'genres': ['ゲーム'], 'tags': [], - 'expected_protocol': str, }, + 'params': {'skip_download': 'm3u8'}, }, { # "New" HTML5 video - # md5 is unstable 'url': 'http://www.nicovideo.jp/watch/sm31464864', 'info_dict': { 'id': 'sm31464864', @@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor): 'comment_count': int, 'genres': ['アニメ'], 'tags': [], - 'expected_protocol': str, }, + 'params': {'skip_download': 'm3u8'}, }, { # Video without owner 'url': 'http://www.nicovideo.jp/watch/sm18238488', - 'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e', 'info_dict': { 'id': 'sm18238488', 'ext': 'mp4', @@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor): 'comment_count': int, 'genres': ['エンターテイメント'], 'tags': [], - 'expected_protocol': str, }, + 'params': {'skip_download': 'm3u8'}, }, { 'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg', 'only_matching': True, @@ -458,9 +454,11 @@ def _real_extract(self, url): if video_id.startswith('so'): video_id = self._match_id(handle.url) - api_data = self._parse_json(self._html_search_regex( - 'data-api-data="([^"]+)"', webpage, - 'API data', default='{}'), video_id) + api_data = traverse_obj( + self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id), + ('data', 'response', {dict})) + if not api_data: + raise ExtractorError('Server response data not found') except ExtractorError as e: try: api_data = self._download_json( From a065086640e888e8d58c615d52ed2f4f4e4c9d18 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Tue, 6 Aug 2024 03:03:12 +0000 Subject: [PATCH 48/69] Release 2024.08.06 Created by: bashonly :ci skip all :ci run dl --- CONTRIBUTORS | 2 ++ Changelog.md | 15 +++++++++++++++ yt_dlp/version.py | 6 +++--- 3 files changed, 20 insertions(+), 3 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 2180ecfe2..489ab7da8 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -655,3 +655,5 @@ iancmy mokrueger luvyana szantnerb +hugepower +scribblemaniac diff --git a/Changelog.md b/Changelog.md index 73bf828a6..0b96ab29c 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,21 @@ # Changelog # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.08.06 + +#### Core changes +- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev) + +#### Extractor changes +- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly) +- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac) +- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly) +- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly) +- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower) +- **youtube** + - [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly) + - [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev) + ### 2024.08.01 #### Core changes diff --git a/yt_dlp/version.py b/yt_dlp/version.py index 81d1c2c96..6633a11b9 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.08.01' +__version__ = '2024.08.06' -RELEASE_GIT_HEAD = 'ffd7781d6588926f820b44a34b9e6e3068fb9f97' +RELEASE_GIT_HEAD = '4d9231208332d4c32364b8cd814bff8b20232cae' VARIANT = None @@ -12,4 +12,4 @@ ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.08.01' +_pkg_version = '2024.08.06' From 49f3741a820ed142f6866317c2e7d247b130960e Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 12 Aug 2024 04:12:46 -0500 Subject: [PATCH 49/69] [ie/youtube] Support excluding `player_client`s in extractor-arg (#10710) Closes #10699 Authored by: bashonly --- yt_dlp/extractor/youtube.py | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 224c9b988..2501398ba 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -1339,6 +1339,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): short_client_name(client): client for client in ('android', 'android_creator', 'android_music') } + _DEFAULT_CLIENTS = ('ios', 'web_creator') _GEO_BYPASS = False @@ -3744,17 +3745,19 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, def _get_requested_clients(self, url, smuggled_data): requested_clients = [] broken_clients = [] - default = ['ios', 'web_creator'] + excluded_clients = [] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) for client in self._configuration_arg('player_client'): if client == 'default': - requested_clients.extend(default) + requested_clients.extend(self._DEFAULT_CLIENTS) elif client == 'all': requested_clients.extend(allowed_clients) + elif client.startswith('-'): + excluded_clients.append(client[1:]) elif client not in allowed_clients: - self.report_warning(f'Skipping unsupported client {client}') + self.report_warning(f'Skipping unsupported client "{client}"') elif client in self._BROKEN_CLIENTS.values(): broken_clients.append(client) else: @@ -3762,7 +3765,12 @@ def _get_requested_clients(self, url, smuggled_data): # Force deprioritization of _BROKEN_CLIENTS for format de-duplication requested_clients.extend(broken_clients) if not requested_clients: - requested_clients = default + requested_clients.extend(self._DEFAULT_CLIENTS) + for excluded_client in excluded_clients: + if excluded_client in requested_clients: + requested_clients.remove(excluded_client) + if not requested_clients: + raise ExtractorError('No player clients have been requested', expected=True) if smuggled_data.get('is_music_url') or self.is_music_url(url): for requested_client in requested_clients: From 232e6db30c474d1b387e405342f34173ceeaf832 Mon Sep 17 00:00:00 2001 From: Hank Brown Date: Tue, 13 Aug 2024 18:26:55 -0500 Subject: [PATCH 50/69] [ie/PatreonCampaign] Support API URLs (#10734) Closes #10733 Authored by: hibes, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/patreon.py | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/patreon.py b/yt_dlp/extractor/patreon.py index 7d6e8439c..4489d533a 100644 --- a/yt_dlp/extractor/patreon.py +++ b/yt_dlp/extractor/patreon.py @@ -420,7 +420,7 @@ def _get_comments(self, post_id): class PatreonCampaignIE(PatreonBaseIE): - _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P\d+))|(?P[-\w]+))' + _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m|api/campaigns)/(?P\d+)|(?P[-\w]+))' _TESTS = [{ 'url': 'https://www.patreon.com/dissonancepod/', 'info_dict': { @@ -442,25 +442,44 @@ class PatreonCampaignIE(PatreonBaseIE): 'url': 'https://www.patreon.com/m/4767637/posts', 'info_dict': { 'title': 'Not Just Bikes', - 'channel_follower_count': int, 'id': '4767637', 'channel_id': '4767637', 'channel_url': 'https://www.patreon.com/notjustbikes', - 'description': 'md5:595c6e7dca76ae615b1d38c298a287a1', + 'description': 'md5:9f4b70051216c4d5c58afe580ffc8d0f', 'age_limit': 0, 'channel': 'Not Just Bikes', 'uploader_url': 'https://www.patreon.com/notjustbikes', - 'uploader': 'Not Just Bikes', + 'uploader': 'Jason', 'uploader_id': '37306634', 'thumbnail': r're:^https?://.*$', }, 'playlist_mincount': 71, + }, { + 'url': 'https://www.patreon.com/api/campaigns/4243769/posts', + 'info_dict': { + 'title': 'Second Thought', + 'channel_follower_count': int, + 'id': '4243769', + 'channel_id': '4243769', + 'channel_url': 'https://www.patreon.com/secondthought', + 'description': 'md5:69c89a3aba43efdb76e85eb023e8de8b', + 'age_limit': 0, + 'channel': 'Second Thought', + 'uploader_url': 'https://www.patreon.com/secondthought', + 'uploader': 'JT Chapman', + 'uploader_id': '32718287', + 'thumbnail': r're:^https?://.*$', + }, + 'playlist_mincount': 201, }, { 'url': 'https://www.patreon.com/dissonancepod/posts', 'only_matching': True, }, { 'url': 'https://www.patreon.com/m/5932659', 'only_matching': True, + }, { + 'url': 'https://www.patreon.com/api/campaigns/4243769', + 'only_matching': True, }] @classmethod From b43bd864851f2862e26caa85461c5d825d49d463 Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Fri, 16 Aug 2024 07:33:41 +1200 Subject: [PATCH 51/69] [ie/bilibili] Fix festival URL support (#10740) Closes #10739 Authored by: grqz, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/bilibili.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index a84b7a6f7..3163df8ab 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -298,7 +298,7 @@ def _get_interactive_entries(self, video_id, cid, metainfo, headers=None): class BiliBiliIE(BilibiliBaseIE): - _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/\w+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?bilibili\.com/(?:video/|festival/[^/?#]+\?(?:[^#]*&)?bvid=)[aAbB][vV](?P[^/?#&]+)' _TESTS = [{ 'url': 'https://www.bilibili.com/video/BV13x41117TL', @@ -622,6 +622,10 @@ class BiliBiliIE(BilibiliBaseIE): 'ext': 'mp4', }, 'skip': 'geo-restricted', + }, { + 'note': 'has - in the last path segment of the url', + 'url': 'https://www.bilibili.com/festival/bh3-7th?bvid=BV1tr4y1f7p2&', + 'only_matching': True, }] def _real_extract(self, url): From cc88a54bb1ef285154775f8a6a413335ce4c71ce Mon Sep 17 00:00:00 2001 From: Christopher Schreiner Date: Thu, 15 Aug 2024 21:50:08 +0200 Subject: [PATCH 52/69] [ie/adn] Fix extractors (#10749) Closes #10748 Authored by: infanf --- yt_dlp/extractor/adn.py | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/yt_dlp/extractor/adn.py b/yt_dlp/extractor/adn.py index 337071794..c8a261375 100644 --- a/yt_dlp/extractor/adn.py +++ b/yt_dlp/extractor/adn.py @@ -49,9 +49,9 @@ class ADNBaseIE(InfoExtractor): class ADNIE(ADNBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?Pde)/)?video/[^/?#]+/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?Pde)/)?video/[^/?#]+/(?P\d+)' _TESTS = [{ - 'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir', + 'url': 'https://animationdigitalnetwork.com/video/558-fruits-basket/9841-episode-1-a-ce-soir', 'md5': '1c9ef066ceb302c86f80c2b371615261', 'info_dict': { 'id': '9841', @@ -71,10 +71,7 @@ class ADNIE(ADNBaseIE): }, 'skip': 'Only available in French and German speaking Europe', }, { - 'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites', - 'only_matching': True, - }, { - 'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1', + 'url': 'https://animationdigitalnetwork.com/de/video/973-the-eminence-in-shadow/23550-folge-1', 'md5': '5c5651bf5791fa6fcd7906012b9d94e8', 'info_dict': { 'id': '23550', @@ -167,7 +164,7 @@ def _perform_login(self, username, password): 'username': username, })) or {}).get('accessToken') if access_token: - self._HEADERS = {'authorization': 'Bearer ' + access_token} + self._HEADERS['Authorization'] = f'Bearer {access_token}' except ExtractorError as e: message = None if isinstance(e.cause, HTTPError) and e.cause.status == 401: @@ -178,6 +175,7 @@ def _perform_login(self, username, password): def _real_extract(self, url): lang, video_id = self._match_valid_url(url).group('lang', 'id') + self._HEADERS['X-Target-Distribution'] = lang or 'fr' video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/' player = self._download_json( video_base_url + 'configuration', video_id, @@ -218,7 +216,6 @@ def _real_extract(self, url): links_data = self._download_json( links_url, video_id, 'Downloading links JSON metadata', headers={ 'X-Player-Token': authorization, - 'X-Target-Distribution': lang or 'fr', **self._HEADERS, }, query={ 'freeWithAds': 'true', @@ -257,6 +254,7 @@ def _real_extract(self, url): load_balancer_data = self._download_json( load_balancer_url, video_id, f'Downloading {format_id} {quality} JSON metadata', + headers=self._HEADERS, fatal=False) or {} m3u8_url = load_balancer_data.get('location') if not m3u8_url: @@ -277,7 +275,7 @@ def _real_extract(self, url): video = (self._download_json( self._API_BASE_URL + f'video/{video_id}', video_id, - 'Downloading additional video metadata', fatal=False) or {}).get('video') or {} + 'Downloading additional video metadata', fatal=False, headers=self._HEADERS) or {}).get('video') or {} show = video.get('show') or {} return { @@ -299,9 +297,9 @@ def _real_extract(self, url): class ADNSeasonIE(ADNBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?Pde)/)?video/(?P[^/?#]+)/?(?:$|[#?])' + _VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?Pde)/)?video/(?P\d+)[^/?#]*/?(?:$|[#?])' _TESTS = [{ - 'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new', + 'url': 'https://animationdigitalnetwork.com/video/911-tokyo-mew-mew-new', 'playlist_count': 12, 'info_dict': { 'id': '911', @@ -312,16 +310,14 @@ class ADNSeasonIE(ADNBaseIE): def _real_extract(self, url): lang, video_show_slug = self._match_valid_url(url).group('lang', 'id') + self._HEADERS['X-Target-Distribution'] = lang or 'fr' show = self._download_json( f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug, 'Downloading show JSON metadata', headers=self._HEADERS)['show'] show_id = str(show['id']) episodes = self._download_json( f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug, - 'Downloading episode list', headers={ - 'X-Target-Distribution': lang or 'fr', - **self._HEADERS, - }, query={ + 'Downloading episode list', headers=self._HEADERS, query={ 'order': 'asc', 'limit': '-1', }) From d62fef7e07d454c0d2ba2d69fb96d691dba1ded0 Mon Sep 17 00:00:00 2001 From: kclauhk <78251477+kclauhk@users.noreply.github.com> Date: Fri, 16 Aug 2024 03:53:37 +0800 Subject: [PATCH 53/69] [ie/facebook:ads] Fix extractor (#10704) Closes #10701 Authored by: kclauhk --- yt_dlp/extractor/facebook.py | 43 ++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 9 deletions(-) diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index 6aba477a6..a43ffe95e 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -963,6 +963,7 @@ class FacebookAdsIE(InfoExtractor): 'id': '899206155126718', 'ext': 'mp4', 'title': 'video by Kandao', + 'description': 'md5:0822724069e3aca97cbed5dabbab282e', 'uploader': 'Kandao', 'uploader_id': '774114102743284', 'uploader_url': r're:^https?://.*', @@ -971,6 +972,22 @@ class FacebookAdsIE(InfoExtractor): 'upload_date': '20231214', 'like_count': int, }, + }, { + # key 'watermarked_video_sd_url' missing + 'url': 'https://www.facebook.com/ads/library/?id=501152689226254', + 'info_dict': { + 'id': '501152689226254', + 'ext': 'mp4', + 'title': 'video by mat.nawrocki', + 'description': 'md5:02a446ace7ff8c3c37a2892922492490', + 'uploader': 'mat.nawrocki', + 'uploader_id': '148586968341456', + 'uploader_url': r're:^https?://.*', + 'timestamp': 1723452305, + 'thumbnail': r're:^https?://.*', + 'upload_date': '20240812', + 'like_count': int, + }, }, { 'url': 'https://www.facebook.com/ads/library/?id=893637265423481', 'info_dict': { @@ -1017,34 +1034,42 @@ def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - post_data = [self._parse_json(j, video_id, fatal=False) - for j in re.findall(r's\.handle\(({.*})\);requireLazy\(', webpage)] - data = traverse_obj(post_data, ( - ..., 'require', ..., ..., ..., 'props', 'deeplinkAdCard', 'snapshot', {dict}), get_all=False) + post_data = traverse_obj( + re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})', webpage), (..., {json.loads})) + data = get_first(post_data, ( + 'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., + 'entryPointRoot', 'otherProps', 'deeplinkAdCard', 'snapshot', {dict})) if not data: raise ExtractorError('Unable to extract ad data') title = data.get('title') if not title or title == '{{product.name}}': title = join_nonempty('display_format', 'page_name', delim=' by ', from_dict=data) + markup_id = traverse_obj(data, ('body', '__m', {str})) + markup = traverse_obj(post_data, ( + ..., 'require', ..., ..., ..., '__bbox', 'markup', lambda _, v: v[0].startswith(markup_id), + ..., '__html', {clean_html}, {lambda x: not x.startswith('{{product.') and x}, any)) - info_dict = traverse_obj(data, { - 'description': ('link_description', {str}, {lambda x: x if x != '{{product.description}}' else None}), + info_dict = merge_dicts({ + 'title': title, + 'description': markup or None, + }, traverse_obj(data, { + 'description': ('link_description', {lambda x: x if not x.startswith('{{product.') else None}), 'uploader': ('page_name', {str}), 'uploader_id': ('page_id', {str_or_none}), 'uploader_url': ('page_profile_uri', {url_or_none}), 'timestamp': ('creation_time', {int_or_none}), 'like_count': ('page_like_count', {int_or_none}), - }) + })) entries = [] for idx, entry in enumerate(traverse_obj( - data, (('videos', 'cards'), lambda _, v: any(url_or_none(v[f]) for f in self._FORMATS_MAP))), 1, + data, (('videos', 'cards'), lambda _, v: any(url_or_none(v.get(f)) for f in self._FORMATS_MAP))), 1, ): entries.append({ 'id': f'{video_id}_{idx}', 'title': entry.get('title') or title, - 'description': entry.get('link_description') or info_dict.get('description'), + 'description': traverse_obj(entry, 'body', 'link_description') or info_dict.get('description'), 'thumbnail': url_or_none(entry.get('video_preview_image_url')), 'formats': self._extract_formats(entry), }) From a7d3235c84dac57a127cbe0ff38f7f7c2fdd8fa0 Mon Sep 17 00:00:00 2001 From: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Date: Mon, 19 Aug 2024 00:50:06 +0800 Subject: [PATCH 54/69] [ie/asobistage] Support redirected URLs (#10768) Authored by: pzhlkj6612 --- yt_dlp/extractor/asobistage.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/asobistage.py b/yt_dlp/extractor/asobistage.py index 8fa8f3edb..0437908bf 100644 --- a/yt_dlp/extractor/asobistage.py +++ b/yt_dlp/extractor/asobistage.py @@ -101,9 +101,10 @@ def _real_initialize(self): self._HEADERS['Authorization'] = f'Bearer {token}' def _real_extract(self, url): - video_id, event, type_, slug = self._match_valid_url(url).group('id', 'event', 'type', 'slug') + webpage, urlh = self._download_webpage_handle(url, self._match_id(url)) + video_id, event, type_, slug = self._match_valid_url(urlh.url).group('id', 'event', 'type', 'slug') video_type = {'archive': 'archives', 'player': 'broadcasts'}[type_] - webpage = self._download_webpage(url, video_id) + event_data = traverse_obj( self._search_nextjs_data(webpage, video_id, default={}), ('props', 'pageProps', 'eventCMSData', { From c8d096c5ce111411fbdbe2abb8fed54f317a6182 Mon Sep 17 00:00:00 2001 From: garret1317 Date: Mon, 19 Aug 2024 16:22:19 +0100 Subject: [PATCH 55/69] [ie/radiko] Extract unique `id` values (#10726) Authored by: garret1317 --- yt_dlp/extractor/radiko.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/radiko.py b/yt_dlp/extractor/radiko.py index b0b6681c9..f94d6a3e7 100644 --- a/yt_dlp/extractor/radiko.py +++ b/yt_dlp/extractor/radiko.py @@ -7,6 +7,7 @@ from ..utils import ( ExtractorError, clean_html, + join_nonempty, time_seconds, try_call, unified_timestamp, @@ -167,7 +168,7 @@ def _extract_performers(self, prog): class RadikoIE(RadikoBaseIE): - _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P[A-Z0-9-]+)/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P[A-Z0-9-]+)/(?P\d+)' _TESTS = [{ # QRR (文化放送) station provides @@ -183,8 +184,9 @@ class RadikoIE(RadikoBaseIE): }] def _real_extract(self, url): - station, video_id = self._match_valid_url(url).groups() - vid_int = unified_timestamp(video_id, False) + station, timestring = self._match_valid_url(url).group('station', 'timestring') + video_id = join_nonempty(station, timestring) + vid_int = unified_timestamp(timestring, False) prog, station_program, ft, radio_begin, radio_end = self._find_program(video_id, station, vid_int) auth_token, area_id = self._auth_client() @@ -207,7 +209,7 @@ def _real_extract(self, url): 'ft': radio_begin, 'end_at': radio_end, 'to': radio_end, - 'seek': video_id, + 'seek': timestring, }, ), } From bef1d4d6fc9493fda7f75e2289c07c507d10092f Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 19 Aug 2024 10:38:19 -0500 Subject: [PATCH 56/69] [ie/twitter:spaces] Support video spaces (#10789) Authored by: bashonly --- yt_dlp/extractor/twitter.py | 44 +++++++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 9 deletions(-) diff --git a/yt_dlp/extractor/twitter.py b/yt_dlp/extractor/twitter.py index d056797f3..aca94df2d 100644 --- a/yt_dlp/extractor/twitter.py +++ b/yt_dlp/extractor/twitter.py @@ -1764,7 +1764,7 @@ class TwitterSpacesIE(TwitterBaseIE): 'release_timestamp': 1659904215, 'release_date': '20220807', }, - 'params': {'skip_download': 'm3u8'}, + 'skip': 'No longer available', }, { # post_live/TimedOut but downloadable 'url': 'https://twitter.com/i/spaces/1vAxRAVQWONJl', @@ -1780,6 +1780,8 @@ class TwitterSpacesIE(TwitterBaseIE): 'upload_date': '20230413', 'release_timestamp': 1681839000, 'release_date': '20230418', + 'protocol': 'm3u8', # ffmpeg is forced + 'container': 'm4a_dash', # audio-only format fixup is applied }, 'params': {'skip_download': 'm3u8'}, }, { @@ -1790,11 +1792,31 @@ class TwitterSpacesIE(TwitterBaseIE): 'ext': 'm4a', 'title': 'あ', 'description': 'Twitter Space participated by nobody yet', - 'uploader': '息根とめる🔪Twitchで復活', + 'uploader': '息根とめる', 'uploader_id': 'tomeru_ikinone', 'live_status': 'was_live', 'timestamp': 1685617198, 'upload_date': '20230601', + 'protocol': 'm3u8', # ffmpeg is forced + 'container': 'm4a_dash', # audio-only format fixup is applied + }, + 'params': {'skip_download': 'm3u8'}, + }, { + # Video Space + 'url': 'https://x.com/i/spaces/1DXGydznBYWKM', + 'info_dict': { + 'id': '1DXGydznBYWKM', + 'ext': 'mp4', + 'title': 'America and Israel’s “special relationship”', + 'description': 'Twitter Space participated by nobody yet', + 'uploader': 'Candace Owens', + 'uploader_id': 'RealCandaceO', + 'live_status': 'was_live', + 'timestamp': 1723931351, + 'upload_date': '20240817', + 'release_timestamp': 1723932000, + 'release_date': '20240817', + 'protocol': 'm3u8_native', # not ffmpeg, detected as video space }, 'params': {'skip_download': 'm3u8'}, }] @@ -1854,13 +1876,17 @@ def _real_extract(self, url): source = traverse_obj( self._call_api(f'live_video_stream/status/{metadata["media_key"]}', metadata['media_key']), ('source', ('noRedirectPlaybackUrl', 'location'), {url_or_none}), get_all=False) - formats = self._extract_m3u8_formats( # XXX: Some Spaces need ffmpeg as downloader - source, metadata['media_key'], 'm4a', entry_protocol='m3u8', live=is_live, - headers=headers, fatal=False) if source else [] - for fmt in formats: - fmt.update({'vcodec': 'none', 'acodec': 'aac'}) - if not is_live: - fmt['container'] = 'm4a_dash' + is_audio_space = source and 'audio-space' in source + formats = self._extract_m3u8_formats( + source, metadata['media_key'], 'm4a' if is_audio_space else 'mp4', + # XXX: Some audio-only Spaces need ffmpeg as downloader + entry_protocol='m3u8' if is_audio_space else 'm3u8_native', + live=is_live, headers=headers, fatal=False) if source else [] + if is_audio_space: + for fmt in formats: + fmt.update({'vcodec': 'none', 'acodec': 'aac'}) + if not is_live: + fmt['container'] = 'm4a_dash' participants = ', '.join(traverse_obj( space_data, ('participants', 'speakers', ..., 'display_name'))) or 'nobody yet' From f0bb28504c8c2b75ee3e5796aed50de2a7f90a1b Mon Sep 17 00:00:00 2001 From: sepro Date: Tue, 20 Aug 2024 00:12:42 +0200 Subject: [PATCH 57/69] [ie/Eurosport] Support local URL variants (#10785) Authored by: seproDev --- yt_dlp/extractor/eurosport.py | 50 ++++++++++++++++++++++++++++++++--- yt_dlp/extractor/tvn24.py | 2 +- 2 files changed, 47 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/eurosport.py b/yt_dlp/extractor/eurosport.py index 0c5e1238d..682546f8f 100644 --- a/yt_dlp/extractor/eurosport.py +++ b/yt_dlp/extractor/eurosport.py @@ -3,7 +3,12 @@ class EurosportIE(InfoExtractor): - _VALID_URL = r'https?://www\.eurosport\.com/\w+/(?:[\w-]+/[\d-]+/)?[\w-]+_(?Pvid\d+)' + _VALID_URL = r'''(?x) + https?://(?: + (?:(?:www|espanol)\.)?eurosport\.(?:com(?:\.tr)?|de|dk|es|fr|hu|it|nl|no|ro)| + eurosport\.tvn24\.pl + )/[\w-]+/(?:[\w-]+/[\d-]+/)?[\w.-]+_(?Pvid\d+) + ''' _TESTS = [{ 'url': 'https://www.eurosport.com/tennis/roland-garros/2022/highlights-rafael-nadal-brushes-aside-caper-ruud-to-win-record-extending-14th-french-open-title_vid1694147/video.shtml', 'info_dict': { @@ -70,6 +75,42 @@ class EurosportIE(InfoExtractor): 'duration': 105.0, 'upload_date': '20230518', }, + }, { + 'url': 'https://www.eurosport.de/radsport/vuelta-a-espana/2024/vuelta-a-espana-2024-wout-van-aert-und-co.-verzweifeln-an-mcnulty-zeitfahr-krimi-in-lissabon_vid2219478/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.dk/speedway/mikkel-michelsen-misser-finalen-i-cardiff-se-danskeren-i-semifinalen-her_vid2219363/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.nl/mixed-martial-arts/ufc/2022/ufc-305-respect-tussen-adesanya-en-du-plessis_vid2219650/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.es/ciclismo/la-vuelta-2024-carlos-rodriguez-olvida-la-crono-y-ya-espera-que-llegue-la-montana-no-me-encontre-nada-comodo_vid2219682/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.fr/football/supercoupe-d-europe/2024-2025/kylian-mbappe-vinicius-junior-eduardo-camavinga-touche.-extraits-de-l-entrainement-du-real-madrid-en-video_vid2216993/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.it/calcio/serie-a/2024-2025/samardzic-a-bergamo-per-le-visite-mediche-con-l-atalanta_vid2219680/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.hu/kerekpar/vuelta-a-espana/2024/dramai-harc-a-masodpercekert-meglepetesgyoztes-a-vuelta-nyitoszakaszan_vid2219481/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid30000618/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.no/golf/fedex-st-jude-championship/2024/ligger-pa-andreplass-sa-skjer-dette-drama_vid2219531/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.ro/tenis/western-southern-open-2/2024/rezumatul-partidei-dintre-zverev-si-shelton-de-la-cincinnati_vid2219657/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://www.eurosport.com.tr/hentbol/olympic-games-paris-2024/2024/paris-2024-denmark-ile-germany-olimpiyatlarin-onemli-anlari_vid2215836/video.shtml', + 'only_matching': True, + }, { + 'url': 'https://eurosport.tvn24.pl/kolarstwo/tour-de-france-kobiet/2024/kasia-niewiadoma-przed-ostatnim-8.-etapem-tour-de-france-kobiet_vid2219765/video.shtml', + 'only_matching': True, }] _TOKEN = None @@ -77,6 +118,7 @@ class EurosportIE(InfoExtractor): # actually defined in https://netsport.eurosport.io/?variables={"databaseId":,"playoutType":"VDP"}&extensions={"persistedQuery":{"version":1 .. # but this method require to get sha256 hash _GEO_COUNTRIES = ['DE', 'NL', 'EU', 'IT', 'FR'] # Not complete list but it should work + _GEO_BYPASS = False def _real_initialize(self): if EurosportIE._TOKEN is None: @@ -98,13 +140,13 @@ def _real_extract(self, url): for stream_type in json_data['attributes']['streaming']: if stream_type == 'hls': fmts, subs = self._extract_m3u8_formats_and_subtitles( - traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4') + traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4', fatal=False) elif stream_type == 'dash': fmts, subs = self._extract_mpd_formats_and_subtitles( - traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id) + traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False) elif stream_type == 'mss': fmts, subs = self._extract_ism_formats_and_subtitles( - traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id) + traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, fatal=False) formats.extend(fmts) self._merge_subtitles(subs, target=subtitles) diff --git a/yt_dlp/extractor/tvn24.py b/yt_dlp/extractor/tvn24.py index 0dc43a9d4..a0590e4f7 100644 --- a/yt_dlp/extractor/tvn24.py +++ b/yt_dlp/extractor/tvn24.py @@ -8,7 +8,7 @@ class TVN24IE(InfoExtractor): _WORKING = False - _VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P[^/]+)' + _VALID_URL = r'https?://(?:(?!eurosport)[^/]+\.)?tvn24(?:bis)?\.pl/(?:[^/?#]+/)*(?P[^/?#]+)' _TESTS = [{ 'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html', 'md5': 'fbdec753d7bc29d96036808275f2130c', From 6f9e6537434562d513d0c9b68ced8a61ade94a64 Mon Sep 17 00:00:00 2001 From: coletdjnz Date: Wed, 21 Aug 2024 19:17:26 +1200 Subject: [PATCH 58/69] [rh:websockets] Upgrade websockets to 13.0 (#10815) Fixes CI hanging Authored by: coletdjnz --- .github/workflows/core.yml | 1 + .github/workflows/quick-test.yml | 1 + pyproject.toml | 2 +- test/test_websockets.py | 8 ++++---- yt_dlp/networking/_websockets.py | 5 +---- 5 files changed, 8 insertions(+), 9 deletions(-) diff --git a/.github/workflows/core.yml b/.github/workflows/core.yml index fdfdebc65..21a64efa9 100644 --- a/.github/workflows/core.yml +++ b/.github/workflows/core.yml @@ -55,6 +55,7 @@ jobs: - name: Install test requirements run: python3 ./devscripts/install_deps.py --include test --include curl-cffi - name: Run tests + timeout-minutes: 15 continue-on-error: False run: | python3 -m yt_dlp -v || true # Print debug head diff --git a/.github/workflows/quick-test.yml b/.github/workflows/quick-test.yml index 3afb51a30..fe2a7e923 100644 --- a/.github/workflows/quick-test.yml +++ b/.github/workflows/quick-test.yml @@ -17,6 +17,7 @@ jobs: - name: Install test requirements run: python3 ./devscripts/install_deps.py --include test - name: Run tests + timeout-minutes: 15 run: | python3 -m yt_dlp -v || true python3 ./devscripts/run_tests.py core diff --git a/pyproject.toml b/pyproject.toml index d5480e1c6..fe6894a42 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -49,7 +49,7 @@ dependencies = [ "pycryptodomex", "requests>=2.32.2,<3", "urllib3>=1.26.17,<3", - "websockets>=12.0", + "websockets>=13.0", ] [project.optional-dependencies] diff --git a/test/test_websockets.py b/test/test_websockets.py index 43f20ac65..06112cc0b 100644 --- a/test/test_websockets.py +++ b/test/test_websockets.py @@ -88,7 +88,7 @@ def create_wss_websocket_server(): certfn = os.path.join(TEST_DIR, 'testcert.pem') sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER) sslctx.load_cert_chain(certfn, None) - return create_websocket_server(ssl_context=sslctx) + return create_websocket_server(ssl=sslctx) MTLS_CERT_DIR = os.path.join(TEST_DIR, 'testdata', 'certificate') @@ -103,7 +103,7 @@ def create_mtls_wss_websocket_server(): sslctx.load_verify_locations(cafile=cacertfn) sslctx.load_cert_chain(certfn, None) - return create_websocket_server(ssl_context=sslctx) + return create_websocket_server(ssl=sslctx) def create_legacy_wss_websocket_server(): @@ -112,7 +112,7 @@ def create_legacy_wss_websocket_server(): sslctx.maximum_version = ssl.TLSVersion.TLSv1_2 sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL') sslctx.load_cert_chain(certfn, None) - return create_websocket_server(ssl_context=sslctx) + return create_websocket_server(ssl=sslctx) def ws_validate_and_send(rh, req): @@ -139,7 +139,7 @@ def setup_class(cls): cls.wss_thread, cls.wss_port = create_wss_websocket_server() cls.wss_base_url = f'wss://127.0.0.1:{cls.wss_port}' - cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl_context=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)) + cls.bad_wss_thread, cls.bad_wss_port = create_websocket_server(ssl=ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)) cls.bad_wss_host = f'wss://127.0.0.1:{cls.bad_wss_port}' cls.mtls_wss_thread, cls.mtls_wss_port = create_mtls_wss_websocket_server() diff --git a/yt_dlp/networking/_websockets.py b/yt_dlp/networking/_websockets.py index 492af1154..21b765b91 100644 --- a/yt_dlp/networking/_websockets.py +++ b/yt_dlp/networking/_websockets.py @@ -47,10 +47,7 @@ # 2: "AttributeError: 'ClientConnection' object has no attribute 'recv_events_exc'. Did you mean: 'recv_events'?" import websockets.sync.connection # isort: split with contextlib.suppress(Exception): - # > 12.0 websockets.sync.connection.Connection.recv_exc = None - # 12.0 - websockets.sync.connection.Connection.recv_events_exc = None class WebsocketsResponseAdapter(WebSocketResponse): @@ -162,7 +159,7 @@ def _send(self, request): additional_headers=headers, open_timeout=timeout, user_agent_header=None, - ssl_context=ssl_ctx if wsuri.secure else None, + ssl=ssl_ctx if wsuri.secure else None, close_timeout=0, # not ideal, but prevents yt-dlp hanging ) return WebsocketsResponseAdapter(conn, url=request.url) From e978c312d6550a6ae4c9df18001afb1b420cb72f Mon Sep 17 00:00:00 2001 From: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Date: Tue, 27 Aug 2024 04:56:36 +0800 Subject: [PATCH 59/69] [ie/Vidflex] Add extractor (#10002) Closes #1377 Authored by: pzhlkj6612 --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/vidflex.py | 148 ++++++++++++++++++++++++++++++++ 2 files changed, 149 insertions(+) create mode 100644 yt_dlp/extractor/vidflex.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 9b73fcd75..a3610dc97 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -2311,6 +2311,7 @@ VideomoreVideoIE, ) from .videopress import VideoPressIE +from .vidflex import VidflexIE from .vidio import ( VidioIE, VidioLiveIE, diff --git a/yt_dlp/extractor/vidflex.py b/yt_dlp/extractor/vidflex.py new file mode 100644 index 000000000..ce0880b47 --- /dev/null +++ b/yt_dlp/extractor/vidflex.py @@ -0,0 +1,148 @@ +import base64 +import json + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + join_nonempty, + mimetype2ext, + url_or_none, +) +from ..utils.traversal import traverse_obj + + +class VidflexIE(InfoExtractor): + _DOMAINS_RE = [ + r'[^.]+\.vidflex\.tv', + r'(?:www\.)?acactv\.ca', + r'(?:www\.)?albertalacrossetv\.com', + r'(?:www\.)?cjfltv\.com', + r'(?:www\.)?figureitoutbaseball\.com', + r'(?:www\.)?ocaalive\.com', + r'(?:www\.)?pegasussports\.tv', + r'(?:www\.)?praxisseries\.ca', + r'(?:www\.)?silenticetv\.com', + r'(?:www\.)?tuffhedemantv\.com', + r'(?:www\.)?watchfuntv\.com', + r'live\.ofsaa\.on\.ca', + r'tv\.procoro\.ca', + r'tv\.realcastmedia\.net', + r'tv\.fringetheatre\.ca', + r'video\.haisla\.ca', + r'video\.hockeycanada\.ca', + r'video\.huuayaht\.org', + r'video\.turningpointensemble\.ca', + r'videos\.livingworks\.net', + r'videos\.telusworldofscienceedmonton\.ca', + r'watch\.binghamtonbulldogs\.com', + r'watch\.rekindle\.tv', + r'watch\.wpca\.com', + ] + _VALID_URL = rf'https?://(?:{"|".join(_DOMAINS_RE)})/[a-z]{{2}}(?:-[a-z]{{2}})?/c/[\w-]+\.(?P\d+)' + _TESTS = [{ + 'url': 'https://video.hockeycanada.ca/en/c/nwt-micd-up-with-jamie-lee-rattray.107486', + 'only_matching': True, + }, { + # m3u8 + https + 'url': 'https://video.hockeycanada.ca/en-us/c/nwt-micd-up-with-jamie-lee-rattray.107486', + 'info_dict': { + 'id': '107486', + 'title': 'NWT: Mic’d up with Jamie Lee Rattray', + 'ext': 'mp4', + 'duration': 115, + 'timestamp': 1634310409, + 'upload_date': '20211015', + 'tags': ['English', '2021', "National Women's Team"], + 'description': 'md5:efb1cf6165b48cc3f5555c4262dd5b23', + 'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+', + }, + 'params': {'skip_download': True}, + }, { + 'url': 'https://video.hockeycanada.ca/en/c/mwc-remembering-the-wild-ride-in-riga.112307', + 'info_dict': { + 'id': '112307', + 'title': 'MWC: Remembering the wild ride in Riga', + 'ext': 'mp4', + 'duration': 322, + 'timestamp': 1716235607, + 'upload_date': '20240520', + 'tags': ['English', '2024', "National Men's Team", 'IIHF World Championship', 'Fan'], + 'description': r're:.+Canada’s National Men’s Team.+', + 'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+', + }, + 'params': {'skip_download': True}, + }, { + # the same video in French + 'url': 'https://video.hockeycanada.ca/fr/c/cmm-retour-sur-un-parcours-endiable-a-riga.112304', + 'info_dict': { + 'id': '112304', + 'title': 'CMM : Retour sur un parcours endiablé à Riga', + 'ext': 'mp4', + 'duration': 322, + 'timestamp': 1716235545, + 'upload_date': '20240520', + 'tags': ['French', '2024', "National Men's Team", 'IIHF World Championship', 'Fan'], + 'description': 'md5:cf825222882a3dab1cd62cffcf3b4d1f', + 'thumbnail': r're:^https?://wpmedia01-a\.akamaihd\.net/en/asset/public/image/.+', + }, + 'params': {'skip_download': True}, + }, { + 'url': 'https://myfbcgreenville.vidflex.tv/en/c/may-12th-2024.658', + 'only_matching': True, + }, { + 'url': 'https://www.figureitoutbaseball.com/en/c/fiob-podcast-14-dan-bertolini-ncaa-d1-head-coach-recorded-11-29-2018.1367', + 'only_matching': True, + }, { + 'url': 'https://videos.telusworldofscienceedmonton.ca/en/c/the-aurora-project-timelapse-4.577', + 'only_matching': True, + }, { + 'url': 'https://www.tuffhedemantv.com/en/c/2022-tuff-hedeman-tour-hobbs-nm-january-22.227', + 'only_matching': True, + }, { + 'url': 'https://www.albertalacrossetv.com/en/c/up-floor-ground-balls-one-more.3449', + 'only_matching': True, + }, { + 'url': 'https://www.silenticetv.com/en/c/jp-unlocked-day-in-the-life-of-langley-ha-15u.5197', + 'only_matching': True, + }, { + 'url': 'https://jphl.vidflex.tv/en/c/jp-unlocked-day-in-the-life-of-langley-ha-15u.5197', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + data_url = self._html_search_regex( + r'content_api:\s*(["\'])(?Phttps?://(?:(?!\1).)+)\1', webpage, 'content api url', group='url') + media_config = traverse_obj( + self._download_json(data_url, video_id), + ('config', {base64.b64decode}, {bytes.decode}, {json.loads}, {dict})) + + return { + 'id': video_id, + 'formats': list(self._yield_formats(media_config, video_id)), + **self._search_json_ld( + webpage.replace('/**/', ''), video_id), + } + + def _yield_formats(self, media_config, video_id): + for media_source in traverse_obj(media_config, ('media', 'source', lambda _, v: url_or_none(v['src']))): + media_url = media_source['src'] + media_type = mimetype2ext(media_source.get('type')) + + if media_type == 'm3u8': + yield from self._extract_m3u8_formats(media_url, video_id, fatal=False, m3u8_id='hls') + elif media_type == 'mp4': + bitrate = self._search_regex(r'_(\d+)k\.mp4', media_url, 'bitrate', default=None) + yield { + 'format_id': join_nonempty('http', bitrate), + 'url': media_url, + 'ext': 'mp4', + 'tbr': int_or_none(bitrate), + } + else: + yield { + 'url': media_url, + 'ext': media_type, + } From 41be32e78c3845000dbac188ffb90ea3ea7c4dfa Mon Sep 17 00:00:00 2001 From: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Date: Tue, 27 Aug 2024 05:17:25 +0800 Subject: [PATCH 60/69] [ie/Rutube] Support livestreams (#10844) Closes #4418, Closes #4594 Authored by: pzhlkj6612 --- yt_dlp/extractor/rutube.py | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/rutube.py b/yt_dlp/extractor/rutube.py index d389b3209..2c416811a 100644 --- a/yt_dlp/extractor/rutube.py +++ b/yt_dlp/extractor/rutube.py @@ -6,6 +6,7 @@ determine_ext, int_or_none, parse_qs, + traverse_obj, try_get, unified_timestamp, url_or_none, @@ -80,6 +81,8 @@ def _extract_formats(self, options, video_id): 'url': format_url, 'format_id': format_id, }) + for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})): + formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False)) return formats def _download_and_extract_formats(self, video_id, query=None): @@ -90,7 +93,7 @@ def _download_and_extract_formats(self, video_id, query=None): class RutubeIE(RutubeBaseIE): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' - _VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?|(?:play/)?embed)/(?P[\da-z]{32})' + _VALID_URL = r'https?://rutube\.ru/(?:(?:live/)?video(?:/private)?|(?:play/)?embed)/(?P[\da-z]{32})' _EMBED_REGEX = [r']+?src=(["\'])(?P(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1'] _TESTS = [{ @@ -164,6 +167,29 @@ class RutubeIE(RutubeBaseIE): 'uploader': 'Стас Быков', }, 'expected_warnings': ['Unable to download f4m'], + }, { + 'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/', + 'info_dict': { + 'id': 'c58f502c7bb34a8fcdd976b221fca292', + 'ext': 'mp4', + 'categories': ['Телепередачи'], + 'description': '', + 'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg', + 'live_status': 'is_live', + 'age_limit': 0, + 'uploader_id': '23460655', + 'timestamp': 1652972968, + 'view_count': int, + 'upload_date': '20220519', + 'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', + 'uploader': 'Первый канал', + }, + }, { + 'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/', + 'only_matching': True, + }, { + 'url': 'https://rutube.ru/live/video/private/c58f502c7bb34a8fcdd976b221fca292/', + 'only_matching': True, }] @classmethod From ad9a8115aa29a1a95c961b16fcf129a228d98f50 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 28 Aug 2024 03:01:51 -0500 Subject: [PATCH 61/69] [ci] Add issue tracker anti-spam protection (#10861) Authored by: bashonly --- .github/ISSUE_TEMPLATE/1_broken_site.yml | 5 +++++ .../ISSUE_TEMPLATE/2_site_support_request.yml | 5 +++++ .../ISSUE_TEMPLATE/3_site_feature_request.yml | 5 +++++ .github/ISSUE_TEMPLATE/4_bug_report.yml | 5 +++++ .github/ISSUE_TEMPLATE/5_feature_request.yml | 5 +++++ .github/ISSUE_TEMPLATE/6_question.yml | 5 +++++ .github/workflows/antispam.yaml | 20 +++++++++++++++++++ devscripts/make_issue_template.py | 5 +++++ 8 files changed, 55 insertions(+) create mode 100644 .github/workflows/antispam.yaml diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.yml b/.github/ISSUE_TEMPLATE/1_broken_site.yml index 5df13ad9b..4a1442186 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.yml +++ b/.github/ISSUE_TEMPLATE/1_broken_site.yml @@ -77,3 +77,8 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.yml b/.github/ISSUE_TEMPLATE/2_site_support_request.yml index 644c87a7e..748885e85 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.yml +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.yml @@ -89,3 +89,8 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.yml b/.github/ISSUE_TEMPLATE/3_site_feature_request.yml index 59d0474c2..ac68a08c6 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.yml @@ -85,3 +85,8 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.yml b/.github/ISSUE_TEMPLATE/4_bug_report.yml index e20739673..6ae107ec1 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.yml +++ b/.github/ISSUE_TEMPLATE/4_bug_report.yml @@ -70,3 +70,8 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.yml b/.github/ISSUE_TEMPLATE/5_feature_request.yml index e06db9ccf..a2263bec5 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/5_feature_request.yml @@ -64,3 +64,8 @@ body: [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc render: shell + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/ISSUE_TEMPLATE/6_question.yml b/.github/ISSUE_TEMPLATE/6_question.yml index 571223a9c..27eb98bc8 100644 --- a/.github/ISSUE_TEMPLATE/6_question.yml +++ b/.github/ISSUE_TEMPLATE/6_question.yml @@ -70,3 +70,8 @@ body: [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc render: shell + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! diff --git a/.github/workflows/antispam.yaml b/.github/workflows/antispam.yaml new file mode 100644 index 000000000..0fd867072 --- /dev/null +++ b/.github/workflows/antispam.yaml @@ -0,0 +1,20 @@ +name: Anti-Spam +on: + issues: + types: [opened] + +permissions: + issues: write + +jobs: + lockdown: + name: Issue Lockdown + runs-on: ubuntu-latest + steps: + - name: "Lock new issue" + env: + GH_TOKEN: ${{ github.token }} + ISSUE_NUMBER: ${{ github.event.issue.number }} + REPOSITORY: ${{ github.repository }} + run: | + gh issue lock "${ISSUE_NUMBER}" -r too_heated -R "${REPOSITORY}" diff --git a/devscripts/make_issue_template.py b/devscripts/make_issue_template.py index a5d59f3c0..4f782d8c6 100644 --- a/devscripts/make_issue_template.py +++ b/devscripts/make_issue_template.py @@ -46,6 +46,11 @@ render: shell validations: required: true + - type: markdown + attributes: + value: | + ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. + ### If you receive any replies asking you download a file, do NOT follow the download links! '''.strip() NO_SKIP = ''' From 4115c24d157c5b5f63089d75c4e0f51d1f8b4489 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sun, 1 Sep 2024 18:25:36 -0500 Subject: [PATCH 62/69] [ie/vimeo] Always try to extract original format (#10721) Closes #9163 Authored by: bashonly --- yt_dlp/extractor/vimeo.py | 208 ++++++++++++++++++++++++++++---------- 1 file changed, 155 insertions(+), 53 deletions(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index a20cf4b17..2aaac1972 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -234,13 +234,30 @@ def _parse_config(self, config, video_id): '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'), } - def _extract_original_format(self, url, video_id, unlisted_hash=None): + def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None, **kwargs): + return self._download_json( + join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'), + video_id, 'Downloading API JSON', headers={ + 'Authorization': f'jwt {jwt_token}', + 'Accept': 'application/json', + }, query={ + 'fields': ','.join(( + 'config_url', 'created_time', 'description', 'download', 'license', + 'metadata.connections.comments.total', 'metadata.connections.likes.total', + 'release_time', 'stats.plays')), + }, **kwargs) + + def _extract_original_format(self, url, video_id, unlisted_hash=None, jwt=None, api_data=None): + # Original/source formats are only available when logged in + if not self._get_cookies('https://vimeo.com/').get('is_logged_in'): + return + query = {'action': 'load_download_config'} if unlisted_hash: query['unlisted_hash'] = unlisted_hash download_data = self._download_json( - url, video_id, fatal=False, query=query, - headers={'X-Requested-With': 'XMLHttpRequest'}, + url, video_id, 'Loading download config JSON', fatal=False, + query=query, headers={'X-Requested-With': 'XMLHttpRequest'}, expected_status=(403, 404)) or {} source_file = download_data.get('source_file') download_url = try_get(source_file, lambda x: x['download_url']) @@ -261,15 +278,13 @@ def _extract_original_format(self, url, video_id, unlisted_hash=None): 'quality': 1, } - jwt_response = self._download_json( - 'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {} - if not jwt_response.get('jwt'): + jwt = jwt or traverse_obj(self._download_json( + 'https://vimeo.com/_rv/viewer', video_id, 'Downloading jwt token', fatal=False), ('jwt', {str})) + if not jwt: return - headers = {'Authorization': 'jwt {}'.format(jwt_response['jwt']), 'Accept': 'application/json'} - original_response = self._download_json( - f'https://api.vimeo.com/videos/{video_id}', video_id, - headers=headers, fatal=False, expected_status=(403, 404)) or {} - for download_data in original_response.get('download') or []: + original_response = api_data or self._call_videos_api( + video_id, jwt, unlisted_hash, fatal=False, expected_status=(403, 404)) + for download_data in traverse_obj(original_response, ('download', ..., {dict})): download_url = download_data.get('link') if not download_url or download_data.get('quality') != 'source': continue @@ -354,7 +369,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip': 'No longer available', }, { - 'url': 'http://player.vimeo.com/video/54469442', + 'url': 'https://player.vimeo.com/video/54469442', 'md5': '619b811a4417aa4abe78dc653becf511', 'note': 'Videos that embed the url in the player page', 'info_dict': { @@ -370,6 +385,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'params': { 'format': 'best[protocol=https]', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'http://vimeo.com/68375962', @@ -379,22 +395,23 @@ class VimeoIE(VimeoBaseInfoExtractor): 'id': '68375962', 'ext': 'mp4', 'title': 'youtube-dl password protected test video', - 'timestamp': 1371200155, + 'timestamp': 1371214555, 'upload_date': '20130614', + 'release_timestamp': 1371214555, + 'release_date': '20130614', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, - 'description': 'md5:6173f270cd0c0119f22817204b3eb86c', - 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280', - 'view_count': int, 'comment_count': int, 'like_count': int, + 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280', }, 'params': { 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'http://vimeo.com/channels/keypeele/75629013', @@ -418,29 +435,38 @@ class VimeoIE(VimeoBaseInfoExtractor): 'like_count': int, }, 'params': {'format': 'http-1080p'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'http://vimeo.com/76979871', 'note': 'Video with subtitles', 'info_dict': { 'id': '76979871', - 'ext': 'mov', + 'ext': 'mp4', 'title': 'The New Vimeo Player (You Know, For Videos)', - 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', - 'timestamp': 1381846109, + 'description': str, # FIXME: Dynamic SEO spam description + 'timestamp': 1381860509, 'upload_date': '20131015', + 'release_timestamp': 1381860509, + 'release_date': '20131015', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff', 'uploader_id': 'staff', - 'uploader': 'Vimeo Staff', + 'uploader': 'Vimeo', 'duration': 62, + 'comment_count': int, + 'like_count': int, + 'thumbnail': 'https://i.vimeocdn.com/video/452001751-8216e0571c251a09d7a8387550942d89f7f86f6398f8ed886e639b0dd50d3c90-d_1280', 'subtitles': { - 'de': [{'ext': 'vtt'}], - 'en': [{'ext': 'vtt'}], - 'es': [{'ext': 'vtt'}], - 'fr': [{'ext': 'vtt'}], + 'de': 'count:3', + 'en': 'count:3', + 'es': 'count:3', + 'fr': 'count:3', }, }, - 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'], + 'expected_warnings': [ + 'Ignoring subtitle tracks found in the HLS manifest', + 'Failed to parse XML: not well-formed', + ], }, { # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ @@ -456,11 +482,12 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 118, 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { - # contains original format + # contains Original format 'url': 'https://vimeo.com/33951933', - 'md5': '53c688fa95a55bf4b7293d37a89c5c53', + # 'md5': '53c688fa95a55bf4b7293d37a89c5c53', 'info_dict': { 'id': '33951933', 'ext': 'mp4', @@ -476,15 +503,19 @@ class VimeoIE(VimeoBaseInfoExtractor): 'view_count': int, 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280', 'like_count': int, + 'tags': 'count:11', }, + # 'params': {'format': 'Original'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { - 'note': 'Contains original format not accessible in webpage', + 'note': 'Contains source format not accessible in webpage', 'url': 'https://vimeo.com/393756517', - 'md5': 'c464af248b592190a5ffbb5d33f382b0', + # 'md5': 'c464af248b592190a5ffbb5d33f382b0', 'info_dict': { 'id': '393756517', - 'ext': 'mov', + # 'ext': 'mov', + 'ext': 'mp4', 'timestamp': 1582642091, 'uploader_id': 'frameworkla', 'title': 'Straight To Hell - Sabrina: Netflix', @@ -495,6 +526,8 @@ class VimeoIE(VimeoBaseInfoExtractor): 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280', 'uploader_url': 'https://vimeo.com/frameworkla', }, + # 'params': {'format': 'source'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { # only available via https://vimeo.com/channels/tributes/6213729 and @@ -511,16 +544,18 @@ class VimeoIE(VimeoBaseInfoExtractor): 'channel_id': 'tributes', 'timestamp': 1250886430, 'upload_date': '20090821', - 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', + 'description': str, # FIXME: Dynamic SEO spam description 'duration': 321, 'comment_count': int, 'view_count': int, 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280', 'like_count': int, + 'tags': ['[the shining', 'vimeohq', 'cv', 'vimeo tribute]'], }, 'params': { 'skip_download': True, }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { # redirects to ondemand extractor and should be passed through it @@ -543,28 +578,23 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip': 'this page is no longer available.', }, { - 'url': 'http://player.vimeo.com/video/68375962', + 'url': 'https://player.vimeo.com/video/68375962', 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', 'info_dict': { 'id': '68375962', 'ext': 'mp4', 'title': 'youtube-dl password protected test video', - 'timestamp': 1371200155, - 'upload_date': '20130614', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, - 'description': 'md5:6173f270cd0c0119f22817204b3eb86c', 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280', - 'view_count': int, - 'comment_count': int, - 'like_count': int, }, 'params': { 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', @@ -592,7 +622,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc", 'uploader': 'Philipp Hagemeister', 'uploader_id': 'user20132939', - 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b', + 'description': str, # FIXME: Dynamic SEO spam description 'upload_date': '20150209', 'timestamp': 1423518307, 'thumbnail': 'https://i.vimeocdn.com/video/default_1280', @@ -606,6 +636,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { # source file returns 403: Forbidden @@ -633,11 +664,13 @@ class VimeoIE(VimeoBaseInfoExtractor): 'release_date': '20160329', }, 'params': {'skip_download': True}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'https://vimeo.com/138909882', 'info_dict': { 'id': '138909882', + # 'ext': 'm4v', 'ext': 'mp4', 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!', 'description': 'md5:5967e090768a831488f6e74b7821b3c1', @@ -645,11 +678,19 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader': 'Firework Champions', 'upload_date': '20150910', 'timestamp': 1441901895, + 'thumbnail': 'https://i.vimeocdn.com/video/534715882-6ff8e4660cbf2fea68282876d8d44f318825dfe572cc4016e73b3266eac8ae3a-d_1280', + 'uploader_url': 'https://vimeo.com/fireworkchampions', + 'tags': 'count:6', + 'duration': 229, + 'view_count': int, + 'like_count': int, + 'comment_count': int, }, 'params': { 'skip_download': True, - 'format': 'Original', + # 'format': 'source', }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { 'url': 'https://vimeo.com/channels/staffpicks/143603739', @@ -670,8 +711,10 @@ class VimeoIE(VimeoBaseInfoExtractor): 'like_count': int, 'uploader_url': 'https://vimeo.com/karimhd', 'channel_url': 'https://vimeo.com/channels/staffpicks', + 'tags': 'count:6', }, 'params': {'skip_download': 'm3u8'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { # requires passing unlisted_hash(a52724358e) to load_download_config request @@ -701,6 +744,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], }, { # chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308 @@ -735,6 +779,48 @@ class VimeoIE(VimeoBaseInfoExtractor): }, 'expected_warnings': ['Failed to parse XML: not well-formed'], }, + { + # vimeo.com URL with unlisted hash and Original format + 'url': 'https://vimeo.com/144579403/ec02229140', + # 'md5': '6b662c2884e0373183fbde2a0d15cb78', + 'info_dict': { + 'id': '144579403', + 'ext': 'mp4', + 'title': 'SALESMANSHIP', + 'description': 'md5:4338302f347a1ff8841b4a3aecaa09f0', + 'uploader': 'Off the Picture Pictures', + 'uploader_id': 'offthepicturepictures', + 'uploader_url': 'https://vimeo.com/offthepicturepictures', + 'duration': 669, + 'upload_date': '20151104', + 'timestamp': 1446607180, + 'release_date': '20151104', + 'release_timestamp': 1446607180, + 'like_count': int, + 'view_count': int, + 'comment_count': int, + 'thumbnail': r're:https://i\.vimeocdn\.com/video/1018638656-[\da-f]+-d_1280', + }, + # 'params': {'format': 'Original'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + }, + { + # player.vimeo.com URL with source format + 'url': 'https://player.vimeo.com/video/859028877', + # 'md5': '19ca3d2463441dee2d2f0671ac2916a2', + 'info_dict': { + 'id': '859028877', + 'ext': 'mp4', + 'title': 'Ariana Grande - Honeymoon Avenue (Live from London)', + 'uploader': 'Raja Virdi', + 'uploader_id': 'rajavirdi', + 'uploader_url': 'https://vimeo.com/rajavirdi', + 'duration': 309, + 'thumbnail': r're:https://i\.vimeocdn\.com/video/1716727772-[\da-f]+-d_1280', + }, + # 'params': {'format': 'source'}, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + }, { # user playlist alias -> https://vimeo.com/258705797 'url': 'https://vimeo.com/user26785108/newspiritualguide', @@ -768,16 +854,6 @@ def _verify_player_video_password(self, url, video_id, headers): raise ExtractorError('Wrong video password', expected=True) return checked - def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None): - return self._download_json( - join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'), - video_id, 'Downloading API JSON', headers={ - 'Authorization': f'jwt {jwt_token}', - 'Accept': 'application/json', - }, query={ - 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays', - }) - def _extract_from_api(self, video_id, unlisted_hash=None): viewer = self._download_json( 'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info') @@ -798,6 +874,11 @@ def _extract_from_api(self, video_id, unlisted_hash=None): info = self._parse_config(self._download_json( video['config_url'], video_id), video_id) + source_format = self._extract_original_format( + f'https://vimeo.com/{video_id}', video_id, unlisted_hash, jwt=viewer['jwt'], api_data=video) + if source_format: + info['formats'].append(source_format) + get_timestamp = lambda x: parse_iso8601(video.get(x + '_time')) info.update({ 'description': video.get('description'), @@ -899,7 +980,12 @@ def _real_extract(self, url): if config.get('view') == 4: config = self._verify_player_video_password( redirect_url, video_id, headers) - return self._parse_config(config, video_id) + info = self._parse_config(config, video_id) + source_format = self._extract_original_format( + f'https://vimeo.com/{video_id}', video_id, unlisted_hash) + if source_format: + info['formats'].append(source_format) + return info vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None) if vimeo_config: @@ -1269,6 +1355,20 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): IE_DESC = 'Review pages on vimeo' _VALID_URL = r'https?://vimeo\.com/(?P[^/?#]+)/review/(?P\d+)/(?P[\da-f]{10})' _TESTS = [{ + 'url': 'https://vimeo.com/user170863801/review/996447483/a316d6ed8d', + 'info_dict': { + 'id': '996447483', + 'ext': 'mp4', + 'title': 'Rodeo day 1-_2', + 'uploader': 'BROADKAST', + 'uploader_id': 'user170863801', + 'uploader_url': 'https://vimeo.com/user170863801', + 'duration': 30, + 'thumbnail': 'https://i.vimeocdn.com/video/1912612821-09a43bd2e75c203d503aed89de7534f28fc4474a48f59c51999716931a246af5-d_1280', + }, + 'params': {'skip_download': 'm3u8'}, + 'expected_warnings': ['Failed to parse XML'], + }, { 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'md5': 'c507a72f780cacc12b2248bb4006d253', 'info_dict': { @@ -1282,6 +1382,7 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280', 'uploader_url': 'https://vimeo.com/user21297594', }, + 'skip': '404 Not Found', }, { 'note': 'video player needs Referer', 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', @@ -1316,6 +1417,7 @@ def _real_extract(self, url): user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash') data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}' data = self._download_json(data_url, video_id) + viewer = {} if data.get('isLocked') is True: video_password = self._get_video_password() viewer = self._download_json( @@ -1327,8 +1429,8 @@ def _real_extract(self, url): config = self._download_json(config_url, video_id) info_dict = self._parse_config(config, video_id) source_format = self._extract_original_format( - f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', video_id, - unlisted_hash=traverse_obj(config_url, ({parse_qs}, 'h', -1))) + f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', + video_id, unlisted_hash=clip_data.get('unlistedHash'), jwt=viewer.get('jwt')) if source_format: info_dict['formats'].append(source_format) info_dict['description'] = clean_html(clip_data.get('description')) From e6f48ca80821939c1fd11ec2a0cdbf2fba9b258a Mon Sep 17 00:00:00 2001 From: Frank Aurich <1100101@gmail.com> Date: Mon, 2 Sep 2024 01:28:51 +0200 Subject: [PATCH 63/69] [ie/KiKA] Add extractor (#5788) Authored by: 1100101 --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/kika.py | 126 ++++++++++++++++++++++++++++++++ yt_dlp/extractor/mdr.py | 51 +------------ 3 files changed, 130 insertions(+), 48 deletions(-) create mode 100644 yt_dlp/extractor/kika.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index a3610dc97..e7b162512 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -945,6 +945,7 @@ ) from .kicker import KickerIE from .kickstarter import KickStarterIE +from .kika import KikaIE from .kinja import KinjaEmbedIE from .kinopoisk import KinoPoiskIE from .kommunetv import KommunetvIE diff --git a/yt_dlp/extractor/kika.py b/yt_dlp/extractor/kika.py new file mode 100644 index 000000000..852a4de3f --- /dev/null +++ b/yt_dlp/extractor/kika.py @@ -0,0 +1,126 @@ +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + parse_duration, + parse_iso8601, + url_or_none, +) +from ..utils.traversal import traverse_obj + + +class KikaIE(InfoExtractor): + IE_DESC = 'KiKA.de' + _VALID_URL = r'https?://(?:www\.)?kika\.de/[\w/-]+/videos/(?P[a-z-]+\d+)' + _GEO_COUNTRIES = ['DE'] + + _TESTS = [{ + 'url': 'https://www.kika.de/logo/videos/logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100', + 'md5': 'fbfc8da483719ef06f396e5e5b938c69', + 'info_dict': { + 'id': 'logo-vom-samstag-einunddreissig-august-zweitausendvierundzwanzig-100', + 'ext': 'mp4', + 'upload_date': '20240831', + 'timestamp': 1725126600, + 'season_number': 2024, + 'modified_date': '20240831', + 'episode': 'Episode 476', + 'episode_number': 476, + 'season': 'Season 2024', + 'duration': 634, + 'title': 'logo! vom Samstag, 31. August 2024', + 'modified_timestamp': 1725129983, + }, + }, { + 'url': 'https://www.kika.de/kaltstart/videos/video92498', + 'md5': '710ece827e5055094afeb474beacb7aa', + 'info_dict': { + 'id': 'video92498', + 'ext': 'mp4', + 'title': '7. Wo ist Leo?', + 'description': 'md5:fb48396a5b75068bcac1df74f1524920', + 'duration': 436, + 'timestamp': 1702926876, + 'upload_date': '20231218', + 'episode_number': 7, + 'modified_date': '20240319', + 'modified_timestamp': 1710880610, + 'episode': 'Episode 7', + 'season_number': 1, + 'season': 'Season 1', + }, + }, { + 'url': 'https://www.kika.de/bernd-das-brot/astrobrot/videos/video90088', + 'md5': 'ffd1b700d7de0a6616a1d08544c77294', + 'info_dict': { + 'id': 'video90088', + 'ext': 'mp4', + 'upload_date': '20221102', + 'timestamp': 1667390580, + 'duration': 197, + 'modified_timestamp': 1711093771, + 'episode_number': 8, + 'title': 'Es ist nicht leicht, ein Astrobrot zu sein', + 'modified_date': '20240322', + 'description': 'md5:d3641deaf1b5515a160788b2be4159a9', + 'season_number': 1, + 'episode': 'Episode 8', + 'season': 'Season 1', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + doc = self._download_json(f'https://www.kika.de/_next-api/proxy/v1/videos/{video_id}', video_id) + video_assets = self._download_json(doc['assets']['url'], video_id) + + subtitles = {} + if ttml_resource := url_or_none(video_assets.get('videoSubtitle')): + subtitles['de'] = [{ + 'url': ttml_resource, + 'ext': 'ttml', + }] + if webvtt_resource := url_or_none(video_assets.get('webvttUrl')): + subtitles.setdefault('de', []).append({ + 'url': webvtt_resource, + 'ext': 'vtt', + }) + + return { + 'id': video_id, + 'formats': list(self._extract_formats(video_assets, video_id)), + 'subtitles': subtitles, + **traverse_obj(doc, { + 'title': ('title', {str}), + 'description': ('description', {str}), + 'timestamp': ('date', {parse_iso8601}), + 'modified_timestamp': ('modificationDate', {parse_iso8601}), + 'duration': (( + ('durationInSeconds', {int_or_none}), + ('duration', {parse_duration})), any), + 'episode_number': ('episodeNumber', {int_or_none}), + 'season_number': ('season', {int_or_none}), + }), + } + + def _extract_formats(self, media_info, video_id): + for media in traverse_obj(media_info, ('assets', lambda _, v: url_or_none(v['url']))): + stream_url = media['url'] + ext = determine_ext(stream_url) + if ext == 'm3u8': + yield from self._extract_m3u8_formats( + stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + else: + yield { + 'url': stream_url, + 'format_id': ext, + **traverse_obj(media, { + 'width': ('frameWidth', {int_or_none}), + 'height': ('frameHeight', {int_or_none}), + # NB: filesize is 0 if unknown, bitrate is -1 if unknown + 'filesize': ('fileSize', {int_or_none}, {lambda x: x or None}), + 'abr': ('bitrateAudio', {int_or_none}, {lambda x: None if x == -1 else x}), + 'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}), + }), + } diff --git a/yt_dlp/extractor/mdr.py b/yt_dlp/extractor/mdr.py index 46097fa20..dfda3cc53 100644 --- a/yt_dlp/extractor/mdr.py +++ b/yt_dlp/extractor/mdr.py @@ -13,8 +13,8 @@ class MDRIE(InfoExtractor): - IE_DESC = 'MDR.DE and KiKA' - _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P\d+)(?:_.+?)?\.html' + IE_DESC = 'MDR.DE' + _VALID_URL = r'https?://(?:www\.)?mdr\.de/(?:.*)/[a-z-]+-?(?P\d+)(?:_.+?)?\.html' _GEO_COUNTRIES = ['DE'] @@ -34,30 +34,6 @@ class MDRIE(InfoExtractor): 'uploader': 'MITTELDEUTSCHER RUNDFUNK', }, 'skip': '404 not found', - }, { - 'url': 'http://www.kika.de/baumhaus/videos/video19636.html', - 'md5': '4930515e36b06c111213e80d1e4aad0e', - 'info_dict': { - 'id': '19636', - 'ext': 'mp4', - 'title': 'Baumhaus vom 30. Oktober 2015', - 'duration': 134, - 'uploader': 'KIKA', - }, - 'skip': '404 not found', - }, { - 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html', - 'md5': '5fe9c4dd7d71e3b238f04b8fdd588357', - 'info_dict': { - 'id': '8182', - 'ext': 'mp4', - 'title': 'Beutolomäus und der geheime Weihnachtswunsch', - 'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd', - 'timestamp': 1482541200, - 'upload_date': '20161224', - 'duration': 4628, - 'uploader': 'KIKA', - }, }, { # audio with alternative playerURL pattern 'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html', @@ -68,28 +44,7 @@ class MDRIE(InfoExtractor): 'duration': 3239, 'uploader': 'MITTELDEUTSCHER RUNDFUNK', }, - }, { - # empty bitrateVideo and bitrateAudio - 'url': 'https://www.kika.de/filme/sendung128372_zc-572e3f45_zs-1d9fb70e.html', - 'info_dict': { - 'id': '128372', - 'ext': 'mp4', - 'title': 'Der kleine Wichtel kehrt zurück', - 'description': 'md5:f77fafdff90f7aa1e9dca14f662c052a', - 'duration': 4876, - 'timestamp': 1607823300, - 'upload_date': '20201213', - 'uploader': 'ZDF', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html', - 'only_matching': True, - }, { - 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html', - 'only_matching': True, + 'skip': '404 not found', }, { 'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html', 'only_matching': True, From 7e41628ff523b3fe373b0981a5db441358980dab Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sun, 1 Sep 2024 18:56:50 -0500 Subject: [PATCH 64/69] [build] Pin `delocate` version for `macos` (#10901) Authored by: bashonly --- .github/workflows/build.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 12ec5b0d8..4ff1cbc1d 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -266,7 +266,7 @@ jobs: # We need to ignore wheels otherwise we break universal2 builds python3 -m pip install -U --no-binary :all: -r requirements.txt # We need to fuse our own universal2 wheels for curl_cffi - python3 -m pip install -U delocate + python3 -m pip install -U 'delocate==0.11.0' mkdir curl_cffi_whls curl_cffi_universal2 python3 devscripts/install_deps.py --print -o --include curl-cffi > requirements.txt for platform in "macosx_11_0_arm64" "macosx_11_0_x86_64"; do From e8e6a982a1b659eed434d225d7922f632bac6568 Mon Sep 17 00:00:00 2001 From: sepro Date: Mon, 2 Sep 2024 21:20:37 +0200 Subject: [PATCH 65/69] [ie/vimeo] Fix login detection (bugfix for 4115c24d157c5b5f63089d75c4e0f51d1f8b4489) (#10906) Authored by: seproDev --- yt_dlp/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 2aaac1972..9a03948cd 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -249,7 +249,7 @@ def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None, **kwargs): def _extract_original_format(self, url, video_id, unlisted_hash=None, jwt=None, api_data=None): # Original/source formats are only available when logged in - if not self._get_cookies('https://vimeo.com/').get('is_logged_in'): + if not self._get_cookies('https://vimeo.com/').get('vimeo'): return query = {'action': 'load_download_config'} From b6200bdcf3a9415ae36859188f9a57e3e461c696 Mon Sep 17 00:00:00 2001 From: Simon Sawicki Date: Thu, 5 Sep 2024 20:06:15 +0200 Subject: [PATCH 66/69] [ci] Add comment sanitization workflow (#10915) Co-authored-by: bashonly Authored by: bashonly, Grub4K --- .github/ISSUE_TEMPLATE/1_broken_site.yml | 7 +++++-- .../ISSUE_TEMPLATE/2_site_support_request.yml | 7 +++++-- .../ISSUE_TEMPLATE/3_site_feature_request.yml | 7 +++++-- .github/ISSUE_TEMPLATE/4_bug_report.yml | 7 +++++-- .github/ISSUE_TEMPLATE/5_feature_request.yml | 7 +++++-- .github/ISSUE_TEMPLATE/6_question.yml | 7 +++++-- .../{antispam.yaml => issue-lockdown.yml} | 5 +++-- .github/workflows/sanitize-comment.yml | 17 +++++++++++++++++ devscripts/make_issue_template.py | 7 +++++-- 9 files changed, 55 insertions(+), 16 deletions(-) rename .github/workflows/{antispam.yaml => issue-lockdown.yml} (76%) create mode 100644 .github/workflows/sanitize-comment.yml diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.yml b/.github/ISSUE_TEMPLATE/1_broken_site.yml index 4a1442186..3b0ef323d 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.yml +++ b/.github/ISSUE_TEMPLATE/1_broken_site.yml @@ -80,5 +80,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.yml b/.github/ISSUE_TEMPLATE/2_site_support_request.yml index 748885e85..c8702c356 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.yml +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.yml @@ -92,5 +92,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.yml b/.github/ISSUE_TEMPLATE/3_site_feature_request.yml index ac68a08c6..5a6d2b0fb 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.yml @@ -88,5 +88,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.yml b/.github/ISSUE_TEMPLATE/4_bug_report.yml index 6ae107ec1..a17770f61 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.yml +++ b/.github/ISSUE_TEMPLATE/4_bug_report.yml @@ -73,5 +73,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.yml b/.github/ISSUE_TEMPLATE/5_feature_request.yml index a2263bec5..c600a9dcb 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/5_feature_request.yml @@ -67,5 +67,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/ISSUE_TEMPLATE/6_question.yml b/.github/ISSUE_TEMPLATE/6_question.yml index 27eb98bc8..57bc9daf5 100644 --- a/.github/ISSUE_TEMPLATE/6_question.yml +++ b/.github/ISSUE_TEMPLATE/6_question.yml @@ -73,5 +73,8 @@ body: - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. diff --git a/.github/workflows/antispam.yaml b/.github/workflows/issue-lockdown.yml similarity index 76% rename from .github/workflows/antispam.yaml rename to .github/workflows/issue-lockdown.yml index 0fd867072..4b973e2e6 100644 --- a/.github/workflows/antispam.yaml +++ b/.github/workflows/issue-lockdown.yml @@ -1,4 +1,4 @@ -name: Anti-Spam +name: Issue Lockdown on: issues: types: [opened] @@ -9,6 +9,7 @@ permissions: jobs: lockdown: name: Issue Lockdown + if: vars.ISSUE_LOCKDOWN runs-on: ubuntu-latest steps: - name: "Lock new issue" @@ -17,4 +18,4 @@ jobs: ISSUE_NUMBER: ${{ github.event.issue.number }} REPOSITORY: ${{ github.repository }} run: | - gh issue lock "${ISSUE_NUMBER}" -r too_heated -R "${REPOSITORY}" + gh issue lock "${ISSUE_NUMBER}" -R "${REPOSITORY}" diff --git a/.github/workflows/sanitize-comment.yml b/.github/workflows/sanitize-comment.yml new file mode 100644 index 000000000..45c87cdd4 --- /dev/null +++ b/.github/workflows/sanitize-comment.yml @@ -0,0 +1,17 @@ +name: Sanitize comment + +on: + issue_comment: + types: [created, edited] + +permissions: + issues: write + +jobs: + sanitize-comment: + name: Sanitize comment + if: vars.SANITIZE_COMMENT && !github.event.issue.pull_request + runs-on: ubuntu-latest + steps: + - name: Sanitize comment + uses: yt-dlp/sanitize-comment@v1 diff --git a/devscripts/make_issue_template.py b/devscripts/make_issue_template.py index 4f782d8c6..8135689c7 100644 --- a/devscripts/make_issue_template.py +++ b/devscripts/make_issue_template.py @@ -49,8 +49,11 @@ - type: markdown attributes: value: | - ### NOTE: Due to a recent increase in malicious spam activity, this issue will be automatically locked until it is triaged by a maintainer. - ### If you receive any replies asking you download a file, do NOT follow the download links! + > [!CAUTION] + > ### GitHub is experiencing a high volume of malicious spam comments. + > ### If you receive any replies asking you download a file, do NOT follow the download links! + > + > Note that this issue may be temporarily locked as an anti-spam measure after it is opened. '''.strip() NO_SKIP = ''' From 0fba08485b6445b72b5b63ae23ca2a73fa5d967f Mon Sep 17 00:00:00 2001 From: sepro Date: Thu, 5 Sep 2024 20:47:14 +0200 Subject: [PATCH 67/69] [ie/khanacademy] Fix extractor (#10913) Closes #10912 Authored by: seproDev --- yt_dlp/extractor/khanacademy.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/khanacademy.py b/yt_dlp/extractor/khanacademy.py index 3f03f9e4c..42eef3c92 100644 --- a/yt_dlp/extractor/khanacademy.py +++ b/yt_dlp/extractor/khanacademy.py @@ -15,7 +15,7 @@ class KhanAcademyBaseIE(InfoExtractor): _VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P(?:[^/]+/){%s}%s[^?#/&]+)' - _PUBLISHED_CONTENT_VERSION = '171419ab20465d931b356f22d20527f13969bb70' + _PUBLISHED_CONTENT_VERSION = 'dc34750f0572c80f5effe7134082fe351143c1e4' def _parse_video(self, video): return { @@ -39,7 +39,7 @@ def _real_extract(self, url): query={ 'fastly_cacheable': 'persist_until_publish', 'pcv': self._PUBLISHED_CONTENT_VERSION, - 'hash': '1242644265', + 'hash': '3712657851', 'variables': json.dumps({ 'path': display_id, 'countryCode': 'US', From 46f4c80bc363ee8116c33d37f65202e6c3470954 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 7 Sep 2024 17:06:12 +0200 Subject: [PATCH 68/69] [ie/SampleFocus] Fix extractor (#10947) Closes #10945 Authored by: seproDev --- yt_dlp/extractor/samplefocus.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/samplefocus.py b/yt_dlp/extractor/samplefocus.py index 36ceb0254..3db3ce142 100644 --- a/yt_dlp/extractor/samplefocus.py +++ b/yt_dlp/extractor/samplefocus.py @@ -36,7 +36,7 @@ class SampleFocusIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + webpage = self._download_webpage(url, display_id, impersonate=True) sample_id = self._search_regex( r']+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P\d+)', @@ -82,7 +82,15 @@ def extract_count(klass): return { 'id': sample_id, 'title': title, - 'url': mp3_url, + 'formats': [{ + 'url': mp3_url, + 'ext': 'mp3', + 'vcodec': 'none', + 'acodec': 'mp3', + 'http_headers': { + 'Referer': url, + }, + }], 'display_id': display_id, 'thumbnail': thumbnail, 'uploader': uploader, From d1c4d88b2d912e8da5e76db455562ca63b1af690 Mon Sep 17 00:00:00 2001 From: coletdjnz Date: Sun, 8 Sep 2024 19:32:44 +1200 Subject: [PATCH 69/69] [networking] Fix handler not being added to RequestError (#10955) Authored by: coletdjnz --- test/test_networking.py | 18 ++++++++++++++++++ yt_dlp/networking/_helper.py | 4 ++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/test/test_networking.py b/test/test_networking.py index 826f11a56..d96624af1 100644 --- a/test/test_networking.py +++ b/test/test_networking.py @@ -822,6 +822,24 @@ def test_remove_logging_handler(self, handler, logger_name): rh.close() assert len(logging_handlers) == before_count + def test_wrap_request_errors(self): + class TestRequestHandler(RequestHandler): + def _validate(self, request): + if request.headers.get('x-fail'): + raise UnsupportedRequest('test error') + + def _send(self, request: Request): + raise RequestError('test error') + + with TestRequestHandler(logger=FakeLogger()) as rh: + with pytest.raises(UnsupportedRequest, match='test error') as exc_info: + rh.validate(Request('http://example.com', headers={'x-fail': '1'})) + assert exc_info.value.handler is rh + + with pytest.raises(RequestError, match='test error') as exc_info: + rh.send(Request('http://example.com')) + assert exc_info.value.handler is rh + @pytest.mark.parametrize('handler', ['Urllib'], indirect=True) class TestUrllibRequestHandler(TestRequestHandlerBase): diff --git a/yt_dlp/networking/_helper.py b/yt_dlp/networking/_helper.py index fe3354ea2..b86d3606d 100644 --- a/yt_dlp/networking/_helper.py +++ b/yt_dlp/networking/_helper.py @@ -10,7 +10,7 @@ import urllib.parse import urllib.request -from .exceptions import RequestError, UnsupportedRequest +from .exceptions import RequestError from ..dependencies import certifi from ..socks import ProxyType, sockssocket from ..utils import format_field, traverse_obj @@ -206,7 +206,7 @@ def wrap_request_errors(func): def wrapper(self, *args, **kwargs): try: return func(self, *args, **kwargs) - except UnsupportedRequest as e: + except RequestError as e: if e.handler is None: e.handler = self raise