diff --git a/yt_dlp/extractor/asobistage.py b/yt_dlp/extractor/asobistage.py index 8fa8f3edb6..0437908bff 100644 --- a/yt_dlp/extractor/asobistage.py +++ b/yt_dlp/extractor/asobistage.py @@ -101,9 +101,10 @@ class AsobiStageIE(InfoExtractor): 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', { diff --git a/yt_dlp/extractor/eurosport.py b/yt_dlp/extractor/eurosport.py index 0c5e1238d9..682546f8f4 100644 --- a/yt_dlp/extractor/eurosport.py +++ b/yt_dlp/extractor/eurosport.py @@ -3,7 +3,12 @@ from ..utils import traverse_obj 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 @@ class EurosportIE(InfoExtractor): 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/radiko.py b/yt_dlp/extractor/radiko.py index b0b6681c9f..f94d6a3e72 100644 --- a/yt_dlp/extractor/radiko.py +++ b/yt_dlp/extractor/radiko.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, clean_html, + join_nonempty, time_seconds, try_call, unified_timestamp, @@ -167,7 +168,7 @@ class RadikoBaseIE(InfoExtractor): 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 @@ class RadikoIE(RadikoBaseIE): 'ft': radio_begin, 'end_at': radio_end, 'to': radio_end, - 'seek': video_id, + 'seek': timestring, }, ), } diff --git a/yt_dlp/extractor/tvn24.py b/yt_dlp/extractor/tvn24.py index 0dc43a9d47..a0590e4f70 100644 --- a/yt_dlp/extractor/tvn24.py +++ b/yt_dlp/extractor/tvn24.py @@ -8,7 +8,7 @@ from ..utils import ( 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', diff --git a/yt_dlp/extractor/twitter.py b/yt_dlp/extractor/twitter.py index d056797f3c..aca94df2dd 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 @@ class TwitterSpacesIE(TwitterBaseIE): 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'