diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.yml b/.github/ISSUE_TEMPLATE/1_broken_site.yml index 5df13ad9b..3b0ef323d 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.yml +++ b/.github/ISSUE_TEMPLATE/1_broken_site.yml @@ -77,3 +77,11 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + > [!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 644c87a7e..c8702c356 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.yml +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.yml @@ -89,3 +89,11 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + > [!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 59d0474c2..5a6d2b0fb 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.yml @@ -85,3 +85,11 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + > [!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 e20739673..a17770f61 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.yml +++ b/.github/ISSUE_TEMPLATE/4_bug_report.yml @@ -70,3 +70,11 @@ body: render: shell validations: required: true + - type: markdown + attributes: + value: | + > [!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 e06db9ccf..c600a9dcb 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.yml +++ b/.github/ISSUE_TEMPLATE/5_feature_request.yml @@ -64,3 +64,11 @@ body: [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc render: shell + - type: markdown + attributes: + value: | + > [!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 571223a9c..57bc9daf5 100644 --- a/.github/ISSUE_TEMPLATE/6_question.yml +++ b/.github/ISSUE_TEMPLATE/6_question.yml @@ -70,3 +70,11 @@ body: [youtube] Extracting URL: https://www.youtube.com/watch?v=BaW_jenozKc render: shell + - type: markdown + attributes: + value: | + > [!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/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 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/issue-lockdown.yml b/.github/workflows/issue-lockdown.yml new file mode 100644 index 000000000..4b973e2e6 --- /dev/null +++ b/.github/workflows/issue-lockdown.yml @@ -0,0 +1,21 @@ +name: Issue Lockdown +on: + issues: + types: [opened] + +permissions: + issues: write + +jobs: + lockdown: + name: Issue Lockdown + if: vars.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 "${REPOSITORY}" 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/.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 a5d59f3c0..8135689c7 100644 --- a/devscripts/make_issue_template.py +++ b/devscripts/make_issue_template.py @@ -46,6 +46,14 @@ VERBOSE_TMPL = ''' render: shell validations: required: true + - type: markdown + attributes: + value: | + > [!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 = ''' 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 @@ class TestWebsSocketRequestHandlerConformance: 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/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 85ea19021..9041f67e6 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -949,6 +949,7 @@ from .kidoodletv import ( KidoodleTVIE, KidoodleTVSeriesIE, ) +from .kika import KikaIE from .kinja import KinjaEmbedIE from .kinopoisk import KinoPoiskIE from .kommunetv import KommunetvIE @@ -2315,6 +2316,7 @@ from .videomore import ( VideomoreVideoIE, ) from .videopress import VideoPressIE +from .vidflex import VidflexIE from .vidio import ( VidioIE, VidioLiveIE, 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 @@ 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/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 @@ from ..utils import ( 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 @@ class KhanAcademyBaseIE(InfoExtractor): query={ 'fastly_cacheable': 'persist_until_publish', 'pcv': self._PUBLISHED_CONTENT_VERSION, - 'hash': '1242644265', + 'hash': '3712657851', 'variables': json.dumps({ 'path': display_id, 'countryCode': 'US', 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 @@ from ..utils import ( 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, 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 .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/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 @@ from ..utils import ( determine_ext, int_or_none, parse_qs, + traverse_obj, try_get, unified_timestamp, url_or_none, @@ -80,6 +81,8 @@ class RutubeBaseIE(InfoExtractor): '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 @@ class RutubeBaseIE(InfoExtractor): 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 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 @@ class SampleFocusIE(InfoExtractor): 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, 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 @@ 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 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 @@ 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' 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, + } diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index a20cf4b17..9a03948cd 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -234,13 +234,30 @@ class VimeoBaseInfoExtractor(InfoExtractor): '_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('vimeo'): + 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 @@ class VimeoBaseInfoExtractor(InfoExtractor): '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 @@ class VimeoIE(VimeoBaseInfoExtractor): 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 @@ class VimeoIE(VimeoBaseInfoExtractor): 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 @@ class VimeoIE(VimeoBaseInfoExtractor): 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 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 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 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 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')) 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 @@ from websockets.uri import parse_uri # 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 @@ class WebsocketsRH(WebSocketRequestHandler): 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)