diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 4b69642603..0102264180 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -713,3 +713,5 @@ xiaomac wesson09 Crypto90 MutantPiggieGolem1 +Sanceilaks +Strkmn diff --git a/Changelog.md b/Changelog.md index 22a9a6e4bb..cf9806ea11 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,25 @@ # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2025.01.12 + +#### Core changes +- [Fix filename sanitization with `--no-windows-filenames`](https://github.com/yt-dlp/yt-dlp/commit/8346b549150003df988538e54c9d8bc4de568979) ([#11988](https://github.com/yt-dlp/yt-dlp/issues/11988)) by [bashonly](https://github.com/bashonly) +- [Validate retries values are non-negative](https://github.com/yt-dlp/yt-dlp/commit/1f4e1e85a27c5b43e34d7706cfd88ffce1b56a4a) ([#11927](https://github.com/yt-dlp/yt-dlp/issues/11927)) by [Strkmn](https://github.com/Strkmn) + +#### Extractor changes +- **drtalks**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1f489f4a45691cac3f9e787d22a3a8a086229ba6) ([#10831](https://github.com/yt-dlp/yt-dlp/issues/10831)) by [pzhlkj6612](https://github.com/pzhlkj6612), [seproDev](https://github.com/seproDev) +- **plvideo**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3c14e9191f3035b9a729d1d87bc0381f42de57cf) ([#10657](https://github.com/yt-dlp/yt-dlp/issues/10657)) by [Sanceilaks](https://github.com/Sanceilaks), [seproDev](https://github.com/seproDev) +- **vine**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/e2ef4fece6c9742d1733e3bae408c4787765f78c) ([#11700](https://github.com/yt-dlp/yt-dlp/issues/11700)) by [allendema](https://github.com/allendema) +- **xiaohongshu**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/763ed06ee69f13949397897bd42ff2ec3dc3d384) ([#11806](https://github.com/yt-dlp/yt-dlp/issues/11806)) by [HobbyistDev](https://github.com/HobbyistDev) +- **youtube** + - [Fix DASH formats incorrectly skipped in some situations](https://github.com/yt-dlp/yt-dlp/commit/0b6b7742c2e7f2a1fcb0b54ef3dd484bab404b3f) ([#11910](https://github.com/yt-dlp/yt-dlp/issues/11910)) by [coletdjnz](https://github.com/coletdjnz) + - [Refactor cookie auth](https://github.com/yt-dlp/yt-dlp/commit/75079f4e3f7dce49b61ef01da7adcd9876a0ca3b) ([#11989](https://github.com/yt-dlp/yt-dlp/issues/11989)) by [coletdjnz](https://github.com/coletdjnz) + - [Use `tv` instead of `mweb` client by default](https://github.com/yt-dlp/yt-dlp/commit/712d2abb32f59b2d246be2901255f84f1a4c30b3) ([#12059](https://github.com/yt-dlp/yt-dlp/issues/12059)) by [coletdjnz](https://github.com/coletdjnz) + +#### Misc. changes +- **cleanup**: Miscellaneous: [dade5e3](https://github.com/yt-dlp/yt-dlp/commit/dade5e35c89adaad04408bfef766820dbca06ebe) by [grqz](https://github.com/grqz), [Grub4K](https://github.com/Grub4K), [seproDev](https://github.com/seproDev) + ### 2024.12.23 #### Core changes diff --git a/README.md b/README.md index 1c628d0257..2f848bd132 100644 --- a/README.md +++ b/README.md @@ -1769,7 +1769,7 @@ The following extractors use this feature: #### 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 `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,mweb` is used, or `web_creator,mweb` is used when authenticating with cookies. The `_music` variants are added for `music.youtube.com` URLs. Some clients, such as `web` and `android`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, will only work with authentication. Not all clients support authentication via cookies. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web` +* `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 `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, or `web_creator,tv` is used when authenticating with cookies. The `_music` variants are added for `music.youtube.com` URLs. Some clients, such as `web` and `android`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, will only work with authentication. Not all clients support authentication via cookies. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web` * `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/pyproject.toml b/pyproject.toml index 96e2d669a4..5eb9a96447 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -76,7 +76,7 @@ dev = [ ] static-analysis = [ "autopep8~=2.0", - "ruff~=0.8.0", + "ruff~=0.9.0", ] test = [ "pytest~=8.1", @@ -195,6 +195,7 @@ ignore = [ "B023", # function-uses-loop-variable (false positives) "B028", # no-explicit-stacklevel "B904", # raise-without-from-inside-except + "A005", # stdlib-module-shadowing "C401", # unnecessary-generator-set "C402", # unnecessary-generator-dict "PIE790", # unnecessary-placeholder diff --git a/supportedsites.md b/supportedsites.md index 916735e08b..1420742d17 100644 --- a/supportedsites.md +++ b/supportedsites.md @@ -374,6 +374,7 @@ - **Dropbox** - **Dropout**: [*dropout*](## "netrc machine") - **DropoutSeason** + - **DrTalks** - **DrTuber** - **drtv** - **drtv:live** @@ -1086,6 +1087,7 @@ - **pluralsight**: [*pluralsight*](## "netrc machine") - **pluralsight:course** - **PlutoTV**: (**Currently broken**) + - **PlVideo**: Платформа - **PodbayFM** - **PodbayFMChannel** - **Podchaser** @@ -1641,8 +1643,6 @@ - **Vimm:stream** - **ViMP** - **ViMP:Playlist** - - **Vine** - - **vine:user** - **Viously** - **Viqeo**: (**Currently broken**) - **Viu** diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index 764baf3a00..f6155dd2e9 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -283,7 +283,10 @@ class YoutubeDL: lazy_playlist: Process playlist entries as they are received. matchtitle: Download only matching titles. rejecttitle: Reject downloads for matching titles. - logger: Log messages to a logging.Logger instance. + logger: A class having a `debug`, `warning` and `error` function where + each has a single string parameter, the message to be logged. + For compatibility reasons, both debug and info messages are passed to `debug`. + A debug message will have a prefix of `[debug] ` to discern it from info messages. logtostderr: Print everything to stderr instead of stdout. consoletitle: Display progress in the console window's titlebar. writedescription: Write the video description to a .description file @@ -1323,7 +1326,7 @@ class YoutubeDL: elif (sys.platform != 'win32' and not self.params.get('restrictfilenames') and self.params.get('windowsfilenames') is False): def sanitize(key, value): - return value.replace('/', '\u29F8').replace('\0', '') + return str(value).replace('/', '\u29F8').replace('\0', '') else: def sanitize(key, value): return filename_sanitizer(key, value, restricted=self.params.get('restrictfilenames')) diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index 20111175b1..c76fe27483 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -261,9 +261,11 @@ def validate_options(opts): elif value in ('inf', 'infinite'): return float('inf') try: - return int(value) + int_value = int(value) except (TypeError, ValueError): validate(False, f'{name} retry count', value) + validate_positive(f'{name} retry count', int_value) + return int_value opts.retries = parse_retries('download', opts.retries) opts.fragment_retries = parse_retries('fragment', opts.fragment_retries) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index bbd6d21bd7..d42bce21b2 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -555,6 +555,7 @@ from .dropout import ( DropoutIE, DropoutSeasonIE, ) +from .drtalks import DrTalksIE from .drtuber import DrTuberIE from .drtv import ( DRTVIE, @@ -2355,10 +2356,6 @@ from .vimm import ( VimmIE, VimmRecordingIE, ) -from .vine import ( - VineIE, - VineUserIE, -) from .viously import ViouslyIE from .viqeo import ViqeoIE from .viu import ( diff --git a/yt_dlp/extractor/drtalks.py b/yt_dlp/extractor/drtalks.py new file mode 100644 index 0000000000..5ea7f75807 --- /dev/null +++ b/yt_dlp/extractor/drtalks.py @@ -0,0 +1,51 @@ +from .brightcove import BrightcoveNewIE +from .common import InfoExtractor +from ..utils import url_or_none +from ..utils.traversal import traverse_obj + + +class DrTalksIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?drtalks\.com/videos/(?P[\w-]+)' + _TESTS = [{ + 'url': 'https://drtalks.com/videos/six-pillars-of-resilience-tools-for-managing-stress-and-flourishing/', + 'info_dict': { + 'id': '6366193757112', + 'ext': 'mp4', + 'uploader_id': '6314452011001', + 'tags': ['resilience'], + 'description': 'md5:9c6805aee237ee6de8052461855b9dda', + 'timestamp': 1734546659, + 'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/12/Episode-82-Eva-Selhub-DrTalks-Thumbs.jpg', + 'title': 'Six Pillars of Resilience: Tools for Managing Stress and Flourishing', + 'duration': 2800.682, + 'upload_date': '20241218', + }, + }, { + 'url': 'https://drtalks.com/videos/the-pcos-puzzle-mastering-metabolic-health-with-marcelle-pick/', + 'info_dict': { + 'id': '6364699891112', + 'ext': 'mp4', + 'title': 'The PCOS Puzzle: Mastering Metabolic Health with Marcelle Pick', + 'description': 'md5:e87cbe00ca50135d5702787fc4043aaa', + 'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/11/Episode-34-Marcelle-Pick-OBGYN-NP-DrTalks.jpg', + 'duration': 3515.2, + 'tags': ['pcos'], + 'upload_date': '20241114', + 'timestamp': 1731592119, + 'uploader_id': '6314452011001', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + next_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']['video'] + + return self.url_result( + next_data['videos']['brightcoveVideoLink'], BrightcoveNewIE, video_id, + url_transparent=True, + **traverse_obj(next_data, { + 'title': ('title', {str}), + 'description': ('videos', 'summury', {str}), + 'thumbnail': ('featuredImage', 'node', 'sourceUrl', {url_or_none}), + })) diff --git a/yt_dlp/extractor/tumblr.py b/yt_dlp/extractor/tumblr.py index d6d4368839..1f2c9b19ca 100644 --- a/yt_dlp/extractor/tumblr.py +++ b/yt_dlp/extractor/tumblr.py @@ -189,26 +189,6 @@ class TumblrIE(InfoExtractor): 'release_date': '20140227', }, 'add_ie': ['Vimeo'], - }, { - 'url': 'http://sutiblr.tumblr.com/post/139638707273', - 'md5': '2dd184b3669e049ba40563a7d423f95c', - 'info_dict': { - 'id': 'ir7qBEIKqvq', - 'ext': 'mp4', - 'title': 'Vine by sutiblr', - 'alt_title': 'Vine by sutiblr', - 'uploader': 'sutiblr', - 'uploader_id': '1198993975374495744', - 'upload_date': '20160220', - 'like_count': int, - 'comment_count': int, - 'repost_count': int, - 'thumbnail': r're:^https?://.*\.jpg', - 'timestamp': 1455940159, - 'view_count': int, - }, - 'add_ie': ['Vine'], - 'skip': 'Vine is unavailable', }, { 'url': 'https://silami.tumblr.com/post/84250043974/my-bad-river-flows-in-you-impression-on-maschine', 'md5': '3c92d7c3d867f14ccbeefa2119022277', @@ -366,7 +346,6 @@ class TumblrIE(InfoExtractor): _providers = { 'instagram': 'Instagram', 'vimeo': 'Vimeo', - 'vine': 'Vine', 'youtube': 'Youtube', 'dailymotion': 'Dailymotion', 'tiktok': 'TikTok', diff --git a/yt_dlp/extractor/twitter.py b/yt_dlp/extractor/twitter.py index 8196ce6c32..c05b5bf9cb 100644 --- a/yt_dlp/extractor/twitter.py +++ b/yt_dlp/extractor/twitter.py @@ -409,26 +409,6 @@ class TwitterCardIE(InfoExtractor): }, 'add_ie': ['Youtube'], }, - { - 'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568', - 'info_dict': { - 'id': 'iBb2x00UVlv', - 'ext': 'mp4', - 'upload_date': '20151113', - 'uploader_id': '1189339351084113920', - 'uploader': 'ArsenalTerje', - 'title': 'Vine by ArsenalTerje', - 'timestamp': 1447451307, - 'alt_title': 'Vine by ArsenalTerje', - 'comment_count': int, - 'like_count': int, - 'thumbnail': r're:^https?://[^?#]+\.jpg', - 'view_count': int, - 'repost_count': int, - }, - 'add_ie': ['Vine'], - 'params': {'skip_download': 'm3u8'}, - }, { 'url': 'https://twitter.com/i/videos/tweet/705235433198714880', 'md5': '884812a2adc8aaf6fe52b15ccbfa3b88', @@ -567,25 +547,6 @@ class TwitterIE(TwitterBaseIE): 'age_limit': 0, '_old_archive_ids': ['twitter 700207533655363584'], }, - }, { - 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609', - 'md5': '89a15ed345d13b86e9a5a5e051fa308a', - 'info_dict': { - 'id': 'MIOxnrUteUd', - 'ext': 'mp4', - 'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン', - 'uploader': 'TAKUMA', - 'uploader_id': '1004126642786242560', - 'timestamp': 1402826626, - 'upload_date': '20140615', - 'thumbnail': r're:^https?://.*\.jpg', - 'alt_title': 'Vine by TAKUMA', - 'comment_count': int, - 'repost_count': int, - 'like_count': int, - 'view_count': int, - }, - 'add_ie': ['Vine'], }, { 'url': 'https://twitter.com/captainamerica/status/719944021058060289', 'info_dict': { diff --git a/yt_dlp/extractor/vine.py b/yt_dlp/extractor/vine.py deleted file mode 100644 index eed4bfeeb9..0000000000 --- a/yt_dlp/extractor/vine.py +++ /dev/null @@ -1,150 +0,0 @@ -from .common import InfoExtractor -from ..utils import ( - determine_ext, - format_field, - int_or_none, - unified_timestamp, -) - - -class VineIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P\w+)' - _EMBED_REGEX = [r']+src=[\'"](?P(?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))'] - _TESTS = [{ - 'url': 'https://vine.co/v/b9KOOWX7HUx', - 'md5': '2f36fed6235b16da96ce9b4dc890940d', - 'info_dict': { - 'id': 'b9KOOWX7HUx', - 'ext': 'mp4', - 'title': 'Chicken.', - 'alt_title': 'Vine by Jack', - 'timestamp': 1368997951, - 'upload_date': '20130519', - 'uploader': 'Jack', - 'uploader_id': '76', - 'view_count': int, - 'like_count': int, - 'comment_count': int, - 'repost_count': int, - }, - }, { - 'url': 'https://vine.co/v/e192BnZnZ9V', - 'info_dict': { - 'id': 'e192BnZnZ9V', - 'ext': 'mp4', - 'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2', - 'alt_title': 'Vine by Pimry_zaa', - 'timestamp': 1436057405, - 'upload_date': '20150705', - 'uploader': 'Pimry_zaa', - 'uploader_id': '1135760698325307392', - 'view_count': int, - 'like_count': int, - 'comment_count': int, - 'repost_count': int, - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'https://vine.co/v/MYxVapFvz2z', - 'only_matching': True, - }, { - 'url': 'https://vine.co/v/bxVjBbZlPUH', - 'only_matching': True, - }, { - 'url': 'https://vine.co/oembed/MYxVapFvz2z.json', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - data = self._download_json( - f'https://archive.vine.co/posts/{video_id}.json', video_id) - - def video_url(kind): - for url_suffix in ('Url', 'URL'): - format_url = data.get(f'video{kind}{url_suffix}') - if format_url: - return format_url - - formats = [] - for quality, format_id in enumerate(('low', '', 'dash')): - format_url = video_url(format_id.capitalize()) - if not format_url: - continue - # DASH link returns plain mp4 - if format_id == 'dash' and determine_ext(format_url) == 'mpd': - formats.extend(self._extract_mpd_formats( - format_url, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'url': format_url, - 'format_id': format_id or 'standard', - 'quality': quality, - }) - self._check_formats(formats, video_id) - - username = data.get('username') - - alt_title = format_field(username, None, 'Vine by %s') - - return { - 'id': video_id, - 'title': data.get('description') or alt_title or 'Vine video', - 'alt_title': alt_title, - 'thumbnail': data.get('thumbnailUrl'), - 'timestamp': unified_timestamp(data.get('created')), - 'uploader': username, - 'uploader_id': data.get('userIdStr'), - 'view_count': int_or_none(data.get('loops')), - 'like_count': int_or_none(data.get('likes')), - 'comment_count': int_or_none(data.get('comments')), - 'repost_count': int_or_none(data.get('reposts')), - 'formats': formats, - } - - -class VineUserIE(InfoExtractor): - IE_NAME = 'vine:user' - _VALID_URL = r'https?://vine\.co/(?Pu/)?(?P[^/]+)' - _VINE_BASE_URL = 'https://vine.co/' - _TESTS = [{ - 'url': 'https://vine.co/itsruthb', - 'info_dict': { - 'id': 'itsruthb', - 'title': 'Ruth B', - 'description': '| Instagram/Twitter: itsruthb | still a lost boy from neverland', - }, - 'playlist_mincount': 611, - }, { - 'url': 'https://vine.co/u/942914934646415360', - 'only_matching': True, - }] - - @classmethod - def suitable(cls, url): - return False if VineIE.suitable(url) else super().suitable(url) - - def _real_extract(self, url): - mobj = self._match_valid_url(url) - user = mobj.group('user') - u = mobj.group('u') - - profile_url = '{}api/users/profiles/{}{}'.format( - self._VINE_BASE_URL, 'vanity/' if not u else '', user) - profile_data = self._download_json( - profile_url, user, note='Downloading user profile data') - - data = profile_data['data'] - user_id = data.get('userId') or data['userIdStr'] - profile = self._download_json( - f'https://archive.vine.co/profiles/{user_id}.json', user_id) - entries = [ - self.url_result( - f'https://vine.co/v/{post_id}', ie='Vine', video_id=post_id) - for post_id in profile['posts'] - if post_id and isinstance(post_id, str)] - return self.playlist_result( - entries, user, profile.get('username'), profile.get('description')) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 1e83e41b8f..e16ec43edd 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -32,7 +32,6 @@ from ..utils import ( classproperty, clean_html, datetime_from_str, - dict_get, filesize_from_tbr, filter_dict, float_or_none, @@ -256,11 +255,12 @@ INNERTUBE_CLIENTS = { 'client': { 'clientName': 'MWEB', 'clientVersion': '2.20241202.07.00', - # mweb does not require PO Token with this UA + # mweb previously did not require PO Token with this UA 'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 2, + 'REQUIRE_PO_TOKEN': True, 'SUPPORTS_COOKIES': True, }, 'tv': { @@ -567,9 +567,15 @@ class YoutubeBaseInfoExtractor(InfoExtractor): pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}) self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref)) + def _initialize_cookie_auth(self): + yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() + if yt_sapisid or yt_1psapisid or yt_3psapisid: + self.write_debug('Found YouTube account cookies') + def _real_initialize(self): self._initialize_pref() self._initialize_consent() + self._initialize_cookie_auth() self._check_login_required() def _perform_login(self, username, password): @@ -627,32 +633,63 @@ class YoutubeBaseInfoExtractor(InfoExtractor): client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) return context - _SAPISID = None + @staticmethod + def _make_sid_authorization(scheme, sid, origin, additional_parts): + timestamp = str(round(time.time())) - def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): - time_now = round(time.time()) - if self._SAPISID is None: - yt_cookies = self._get_cookies('https://www.youtube.com') - # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. - # See: https://github.com/yt-dlp/yt-dlp/issues/393 - sapisid_cookie = dict_get( - yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) - if sapisid_cookie and sapisid_cookie.value: - self._SAPISID = sapisid_cookie.value - self.write_debug('Extracted SAPISID cookie') - # SAPISID cookie is required if not already present - if not yt_cookies.get('SAPISID'): - self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') - self._set_cookie( - '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) - else: - self._SAPISID = False - if not self._SAPISID: + hash_parts = [] + if additional_parts: + hash_parts.append(':'.join(additional_parts.values())) + hash_parts.extend([timestamp, sid, origin]) + sidhash = hashlib.sha1(' '.join(hash_parts).encode()).hexdigest() + + parts = [timestamp, sidhash] + if additional_parts: + parts.append(''.join(additional_parts)) + + return f'{scheme} {"_".join(parts)}' + + def _get_sid_cookies(self): + """ + Get SAPISID, 1PSAPISID, 3PSAPISID cookie values + @returns sapisid, 1psapisid, 3psapisid + """ + yt_cookies = self._get_cookies('https://www.youtube.com') + yt_sapisid = try_call(lambda: yt_cookies['SAPISID'].value) + yt_3papisid = try_call(lambda: yt_cookies['__Secure-3PAPISID'].value) + yt_1papisid = try_call(lambda: yt_cookies['__Secure-1PAPISID'].value) + + # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. + # YouTube also falls back to __Secure-3PAPISID if SAPISID is missing. + # See: https://github.com/yt-dlp/yt-dlp/issues/393 + + return yt_sapisid or yt_3papisid, yt_1papisid, yt_3papisid + + def _get_sid_authorization_header(self, origin='https://www.youtube.com', user_session_id=None): + """ + Generate API Session ID Authorization for Innertube requests. Assumes all requests are secure (https). + @param origin: Origin URL + @param user_session_id: Optional User Session ID + @return: Authorization header value + """ + + authorizations = [] + additional_parts = {} + if user_session_id: + additional_parts['u'] = user_session_id + + yt_sapisid, yt_1psapisid, yt_3psapisid = self._get_sid_cookies() + + for scheme, sid in (('SAPISIDHASH', yt_sapisid), + ('SAPISID1PHASH', yt_1psapisid), + ('SAPISID3PHASH', yt_3psapisid)): + if sid: + authorizations.append(self._make_sid_authorization(scheme, sid, origin, additional_parts)) + + if not authorizations: return None - # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 - sapisidhash = hashlib.sha1( - f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest() - return f'SAPISIDHASH {time_now}_{sapisidhash}' + + return ' '.join(authorizations) def _call_api(self, ep, query, video_id, fatal=True, headers=None, note='Downloading API JSON', errnote='Unable to download API page', @@ -688,26 +725,48 @@ class YoutubeBaseInfoExtractor(InfoExtractor): if session_index is not None: return session_index - def _data_sync_id_to_delegated_session_id(self, data_sync_id): - if not data_sync_id: - return - # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel - # and just "user_syncid||" for primary channel. We only want the channel_syncid - channel_syncid, _, user_syncid = data_sync_id.partition('||') - if user_syncid: - return channel_syncid - - def _extract_account_syncid(self, *args): + @staticmethod + def _parse_data_sync_id(data_sync_id): """ - Extract current session ID required to download private playlists of secondary channels + Parse data_sync_id into delegated_session_id and user_session_id. + + data_sync_id is of the form "delegated_session_id||user_session_id" for secondary channel + and just "user_session_id||" for primary channel. + + @param data_sync_id: data_sync_id string + @return: Tuple of (delegated_session_id, user_session_id) + """ + if not data_sync_id: + return None, None + first, _, second = data_sync_id.partition('||') + if second: + return first, second + return None, first + + def _extract_delegated_session_id(self, *args): + """ + Extract current delegated session ID required to download private playlists of secondary channels @params response and/or ytcfg + @return: delegated session ID """ # ytcfg includes channel_syncid if on secondary channel if delegated_sid := traverse_obj(args, (..., 'DELEGATED_SESSION_ID', {str}, any)): return delegated_sid data_sync_id = self._extract_data_sync_id(*args) - return self._data_sync_id_to_delegated_session_id(data_sync_id) + return self._parse_data_sync_id(data_sync_id)[0] + + def _extract_user_session_id(self, *args): + """ + Extract current user session ID + @params response and/or ytcfg + @return: user session ID + """ + if user_sid := traverse_obj(args, (..., 'USER_SESSION_ID', {str}, any)): + return user_sid + + data_sync_id = self._extract_data_sync_id(*args) + return self._parse_data_sync_id(data_sync_id)[1] def _extract_data_sync_id(self, *args): """ @@ -734,7 +793,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor): @functools.cached_property def is_authenticated(self): - return bool(self._generate_sapisidhash_header()) + return bool(self._get_sid_authorization_header()) def extract_ytcfg(self, video_id, webpage): if not webpage: @@ -744,25 +803,28 @@ class YoutubeBaseInfoExtractor(InfoExtractor): r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', default='{}'), video_id, fatal=False) or {} - def _generate_cookie_auth_headers(self, *, ytcfg=None, account_syncid=None, session_index=None, origin=None, **kwargs): + def _generate_cookie_auth_headers(self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, origin=None, **kwargs): headers = {} - account_syncid = account_syncid or self._extract_account_syncid(ytcfg) - if account_syncid: - headers['X-Goog-PageId'] = account_syncid + delegated_session_id = delegated_session_id or self._extract_delegated_session_id(ytcfg) + if delegated_session_id: + headers['X-Goog-PageId'] = delegated_session_id if session_index is None: session_index = self._extract_session_index(ytcfg) - if account_syncid or session_index is not None: + if delegated_session_id or session_index is not None: headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 - auth = self._generate_sapisidhash_header(origin) + auth = self._get_sid_authorization_header(origin, user_session_id=user_session_id or self._extract_user_session_id(ytcfg)) if auth is not None: headers['Authorization'] = auth headers['X-Origin'] = origin + if traverse_obj(ytcfg, 'LOGGED_IN', expected_type=bool): + headers['X-Youtube-Bootstrap-Logged-In'] = 'true' + return headers def generate_api_headers( - self, *, ytcfg=None, account_syncid=None, session_index=None, + self, *, ytcfg=None, delegated_session_id=None, user_session_id=None, session_index=None, visitor_data=None, api_hostname=None, default_client='web', **kwargs): origin = 'https://' + (self._select_api_hostname(api_hostname, default_client)) @@ -773,7 +835,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor): 'Origin': origin, 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg), 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client), - **self._generate_cookie_auth_headers(ytcfg=ytcfg, account_syncid=account_syncid, session_index=session_index, origin=origin), + **self._generate_cookie_auth_headers( + ytcfg=ytcfg, + delegated_session_id=delegated_session_id, + user_session_id=user_session_id, + session_index=session_index, + origin=origin), } return filter_dict(headers) @@ -1356,8 +1423,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, } _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') - _DEFAULT_CLIENTS = ('ios', 'mweb') - _DEFAULT_AUTHED_CLIENTS = ('web_creator', 'mweb') + _DEFAULT_CLIENTS = ('ios', 'tv') + _DEFAULT_AUTHED_CLIENTS = ('web_creator', 'tv') _GEO_BYPASS = False @@ -3836,9 +3903,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): default_client=client, visitor_data=visitor_data, session_index=self._extract_session_index(master_ytcfg, player_ytcfg), - account_syncid=( - self._data_sync_id_to_delegated_session_id(data_sync_id) - or self._extract_account_syncid(master_ytcfg, initial_pr, player_ytcfg) + delegated_session_id=( + self._parse_data_sync_id(data_sync_id)[0] + or self._extract_delegated_session_id(master_ytcfg, initial_pr, player_ytcfg) + ), + user_session_id=( + self._parse_data_sync_id(data_sync_id)[1] + or self._extract_user_session_id(master_ytcfg, initial_pr, player_ytcfg) ), ) @@ -5350,7 +5421,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): if not continuation_list[0]: continuation_list[0] = self._extract_continuation(parent_renderer) - def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): + def _entries(self, tab, item_id, ytcfg, delegated_session_id, visitor_data): continuation_list = [None] extract_entries = lambda x: self._extract_entries(x, continuation_list) tab_content = try_get(tab, lambda x: x['content'], dict) @@ -5371,7 +5442,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): break seen_continuations.add(continuation_token) headers = self.generate_api_headers( - ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data) + ytcfg=ytcfg, delegated_session_id=delegated_session_id, visitor_data=visitor_data) response = self._extract_response( item_id=f'{item_id} page {page_num}', query=continuation, headers=headers, ytcfg=ytcfg, @@ -5441,7 +5512,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): return self.playlist_result( self._entries( selected_tab, metadata['id'], ytcfg, - self._extract_account_syncid(ytcfg, data), + self._extract_delegated_session_id(ytcfg, data), self._extract_visitor_data(data, ytcfg)), **metadata) @@ -5593,7 +5664,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): watch_endpoint = try_get( playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) headers = self.generate_api_headers( - ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), + ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), visitor_data=self._extract_visitor_data(response, data, ytcfg)) query = { 'playlistId': playlist_id, @@ -5691,7 +5762,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): if not is_playlist: return headers = self.generate_api_headers( - ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), + ytcfg=ytcfg, delegated_session_id=self._extract_delegated_session_id(ytcfg, data), visitor_data=self._extract_visitor_data(data, ytcfg)) query = { 'params': 'wgYCCAA=', diff --git a/yt_dlp/version.py b/yt_dlp/version.py index 1ff43c611f..97a3b1b26a 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.12.23' +__version__ = '2025.01.12' -RELEASE_GIT_HEAD = '65cf46cddd873fd229dbb0fc0689bca4c201c6b6' +RELEASE_GIT_HEAD = 'dade5e35c89adaad04408bfef766820dbca06ebe' VARIANT = None @@ -12,4 +12,4 @@ CHANNEL = 'stable' ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.12.23' +_pkg_version = '2025.01.12'