From 360aed810ad85db950df586282d256516c98cd2d Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Mon, 2 Dec 2024 03:16:50 +1300 Subject: [PATCH 01/21] [ie/instagram] Support `share` URLs (#11677) Closes #11630 Authored by: grqz --- yt_dlp/extractor/instagram.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/instagram.py b/yt_dlp/extractor/instagram.py index dee8cb85d..55086d0b2 100644 --- a/yt_dlp/extractor/instagram.py +++ b/yt_dlp/extractor/instagram.py @@ -254,7 +254,7 @@ class InstagramIOSIE(InfoExtractor): class InstagramIE(InstagramBaseIE): - _VALID_URL = r'(?Phttps?://(?:www\.)?instagram\.com(?:/[^/]+)?/(?:p|tv|reels?(?!/audio/))/(?P[^/?#&]+))' + _VALID_URL = r'(?Phttps?://(?:www\.)?instagram\.com(?:/(?!share/)[^/?#]+)?/(?:p|tv|reels?(?!/audio/))/(?P[^/?#&]+))' _EMBED_REGEX = [r']+src=(["\'])(?P(?:https?:)?//(?:www\.)?instagram\.com/p/[^/]+/embed.*?)\1'] _TESTS = [{ 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', From cd0f934604587ed793e9177f6a127e5dcf99a7dd Mon Sep 17 00:00:00 2001 From: DarkZeros Date: Sun, 1 Dec 2024 14:21:57 +0000 Subject: [PATCH 02/21] [ie/mitele] Fix extractor (#11683) Closes #11690 Authored by: DarkZeros --- yt_dlp/extractor/mitele.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/mitele.py b/yt_dlp/extractor/mitele.py index 3573a2a3f..76fef337a 100644 --- a/yt_dlp/extractor/mitele.py +++ b/yt_dlp/extractor/mitele.py @@ -80,9 +80,9 @@ class MiTeleIE(TelecincoBaseIE): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - pre_player = self._parse_json(self._search_regex( - r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})', - webpage, 'Pre Player'), display_id)['prePlayer'] + pre_player = self._search_json( + r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=', + webpage, 'Pre Player', display_id)['prePlayer'] title = pre_player['title'] video_info = self._parse_content(pre_player['video'], url) content = pre_player.get('content') or {} From 0d146c1e36f467af30e87b7af651bdee67b73500 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Sun, 1 Dec 2024 15:25:09 +0000 Subject: [PATCH 03/21] [ie/youtube] Adjust player clients for site changes (#11663) Closes #11640 Authored by: bashonly --- README.md | 4 ++-- yt_dlp/extractor/youtube.py | 46 +++++++++++++++++++++++-------------- 2 files changed, 31 insertions(+), 19 deletions(-) diff --git a/README.md b/README.md index 0a62d8e74..772395d24 100644 --- a/README.md +++ b/README.md @@ -1761,7 +1761,7 @@ $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-" # EXTRACTOR ARGUMENTS -Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"` +Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=tv,mweb;formats=incomplete" --extractor-args "funimation:version=uncut"` Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"` @@ -1770,7 +1770,7 @@ 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`, `mediaconnect`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,mweb` is used, and `web_creator` is added as needed for age-gated videos when account age verification is required. Similarly, 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. 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,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_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 7a9133466..a67f09e62 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -83,6 +83,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, 'REQUIRE_PO_TOKEN': True, + 'SUPPORTS_COOKIES': True, }, # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats 'web_safari': { @@ -95,6 +96,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, 'REQUIRE_PO_TOKEN': True, + 'SUPPORTS_COOKIES': True, }, 'web_embedded': { 'INNERTUBE_CONTEXT': { @@ -104,6 +106,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 56, + 'SUPPORTS_COOKIES': True, }, 'web_music': { 'INNERTUBE_HOST': 'music.youtube.com', @@ -114,6 +117,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, + 'SUPPORTS_COOKIES': True, }, # This client now requires sign-in for every video 'web_creator': { @@ -125,6 +129,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, }, 'android': { 'INNERTUBE_CONTEXT': { @@ -157,6 +162,7 @@ INNERTUBE_CLIENTS = { 'REQUIRE_JS_PLAYER': False, 'REQUIRE_PO_TOKEN': True, 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, }, # This client now requires sign-in for every video 'android_creator': { @@ -191,6 +197,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 28, 'REQUIRE_JS_PLAYER': False, + 'SUPPORTS_COOKIES': True, }, # iOS clients have HLS live streams. Setting device model to get 60fps formats. # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 @@ -225,6 +232,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, 'REQUIRE_JS_PLAYER': False, 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, }, # This client now requires sign-in for every video 'ios_creator': { @@ -253,6 +261,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 2, + 'SUPPORTS_COOKIES': True, }, 'tv': { 'INNERTUBE_CONTEXT': { @@ -262,6 +271,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 7, + 'SUPPORTS_COOKIES': True, }, # This client now requires sign-in for every video # It was previously an age-gate workaround for videos that were `playable_in_embed` @@ -275,19 +285,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 85, 'REQUIRE_AUTH': True, - }, - # This client now requires sign-in for every video - # It may be able to receive pre-merged video+audio 720p/1080p streams - 'mediaconnect': { - 'INNERTUBE_CONTEXT': { - 'client': { - 'clientName': 'MEDIA_CONNECT_FRONTEND', - 'clientVersion': '0.1', - }, - }, - 'INNERTUBE_CONTEXT_CLIENT_NAME': 95, - 'REQUIRE_JS_PLAYER': False, - 'REQUIRE_AUTH': True, + 'SUPPORTS_COOKIES': True, }, } @@ -317,6 +315,7 @@ def build_innertube_clients(): ytcfg.setdefault('REQUIRE_JS_PLAYER', True) ytcfg.setdefault('REQUIRE_PO_TOKEN', False) ytcfg.setdefault('REQUIRE_AUTH', False) + ytcfg.setdefault('SUPPORTS_COOKIES', False) ytcfg.setdefault('PLAYER_PARAMS', None) ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') @@ -1357,6 +1356,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') _DEFAULT_CLIENTS = ('ios', 'mweb') + _DEFAULT_AUTHED_CLIENTS = ('web_creator', 'mweb') _GEO_BYPASS = False @@ -3823,12 +3823,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _get_requested_clients(self, url, smuggled_data): requested_clients = [] excluded_clients = [] + default_clients = self._DEFAULT_AUTHED_CLIENTS if self.is_authenticated else self._DEFAULT_CLIENTS allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) for client in self._configuration_arg('player_client'): if client == 'default': - requested_clients.extend(self._DEFAULT_CLIENTS) + requested_clients.extend(default_clients) elif client == 'all': requested_clients.extend(allowed_clients) elif client.startswith('-'): @@ -3838,7 +3839,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: requested_clients.append(client) if not requested_clients: - requested_clients.extend(self._DEFAULT_CLIENTS) + requested_clients.extend(default_clients) for excluded_client in excluded_clients: if excluded_client in requested_clients: requested_clients.remove(excluded_client) @@ -3850,9 +3851,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): _, base_client, variant = _split_innertube_client(requested_client) music_client = f'{base_client}_music' if base_client != 'mweb' else 'web_music' if variant != 'music' and music_client in INNERTUBE_CLIENTS: - if not INNERTUBE_CLIENTS[music_client]['REQUIRE_AUTH'] or self.is_authenticated: + client_info = INNERTUBE_CLIENTS[music_client] + if not client_info['REQUIRE_AUTH'] or (self.is_authenticated and client_info['SUPPORTS_COOKIES']): requested_clients.append(music_client) + if self.is_authenticated: + unsupported_clients = [ + client for client in requested_clients if not INNERTUBE_CLIENTS[client]['SUPPORTS_COOKIES'] + ] + for client in unsupported_clients: + self.report_warning(f'Skipping client "{client}" since it does not support cookies', only_once=True) + requested_clients.remove(client) + return orderedSet(requested_clients) def _invalid_player_response(self, pr, video_id): @@ -3958,6 +3968,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: prs.append(pr) + ''' This code is pointless while web_creator is in _DEFAULT_AUTHED_CLIENTS # EU countries require age-verification for accounts to access age-restricted videos # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients if self.is_authenticated and self._is_agegated(pr): @@ -3965,9 +3976,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f'{video_id}: This video is age-restricted and YouTube is requiring ' 'account age-verification; some formats may be missing', only_once=True) # web_creator can work around the age-verification requirement - # android_vr and mediaconnect may also be able to work around age-verification + # android_vr may also be able to work around age-verification # tv_embedded may(?) still work around age-verification if the video is embeddable append_client('web_creator') + ''' prs.extend(deprioritized_prs) From 239f5f36fe04603bec59c8b975f6a792f10246db Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Mon, 2 Dec 2024 10:55:18 +1300 Subject: [PATCH 04/21] [ie/bilibili] Fix extractor (#11667) Closes #11665 Authored by: grqz --- yt_dlp/extractor/bilibili.py | 43 ++++++++++++++++++------------------ 1 file changed, 21 insertions(+), 22 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 02ea67707..f01befcc0 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -18,7 +18,6 @@ from ..utils import ( InAdvancePagedList, OnDemandPagedList, bool_or_none, - clean_html, determine_ext, filter_dict, float_or_none, @@ -639,31 +638,27 @@ class BiliBiliIE(BilibiliBaseIE): headers['Referer'] = url initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id) + + if traverse_obj(initial_state, ('error', 'trueCode')) == -403: + self.raise_login_required() + if traverse_obj(initial_state, ('error', 'trueCode')) == -404: + raise ExtractorError( + 'This video may be deleted or geo-restricted. ' + 'You might want to try a VPN or a proxy server (with --proxy)', expected=True) + is_festival = 'videoData' not in initial_state if is_festival: video_data = initial_state['videoInfo'] else: - play_info_obj = self._search_json( - r'window\.__playinfo__\s*=', webpage, 'play info', video_id, fatal=False) - if not play_info_obj: - if traverse_obj(initial_state, ('error', 'trueCode')) == -403: - self.raise_login_required() - if traverse_obj(initial_state, ('error', 'trueCode')) == -404: - raise ExtractorError( - 'This video may be deleted or geo-restricted. ' - 'You might want to try a VPN or a proxy server (with --proxy)', expected=True) - play_info = traverse_obj(play_info_obj, ('data', {dict})) - if not play_info: - if traverse_obj(play_info_obj, 'code') == 87007: - toast = get_element_by_class('tips-toast', webpage) or '' - msg = clean_html( - f'{get_element_by_class("belongs-to", toast) or ""}，' - + (get_element_by_class('level', toast) or '')) - raise ExtractorError( - f'This is a supporter-only video: {msg}. {self._login_hint()}', expected=True) - raise ExtractorError('Failed to extract play info') video_data = initial_state['videoData'] + if video_data.get('is_upower_exclusive'): + high_level = traverse_obj(initial_state, ('elecFullInfo', 'show_info', 'high_level', {dict})) or {} + raise ExtractorError( + 'This is a supporter-only video: ' + f'{join_nonempty("title", "sub_title", from_dict=high_level, delim="，")}. ' + f'{self._login_hint()}', expected=True) + video_id, title = video_data['bvid'], video_data.get('title') # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. @@ -689,10 +684,14 @@ class BiliBiliIE(BilibiliBaseIE): old_video_id = format_field(aid, None, f'%s_part{part_id or 1}') cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid') + play_info = ( + traverse_obj( + self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None), + ('data', {dict})) + or self._download_playinfo(video_id, cid, headers=headers)) + festival_info = {} if is_festival: - play_info = self._download_playinfo(video_id, cid, headers=headers) - festival_info = traverse_obj(initial_state, { 'uploader': ('videoInfo', 'upName'), 'uploader_id': ('videoInfo', 'upMid', {str_or_none}), From 62cba8a1bedbfc0ddde7267ae57b72bf5f7ea7b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= Date: Mon, 2 Dec 2024 00:33:11 +0200 Subject: [PATCH 05/21] [ie/duoplay] Fix extractor (#11588) Authored by: glensc, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/duoplay.py | 60 +++++++++++++++++++++++++++++-------- 1 file changed, 47 insertions(+), 13 deletions(-) diff --git a/yt_dlp/extractor/duoplay.py b/yt_dlp/extractor/duoplay.py index 18642fea3..75650c3a6 100644 --- a/yt_dlp/extractor/duoplay.py +++ b/yt_dlp/extractor/duoplay.py @@ -5,15 +5,16 @@ from ..utils import ( get_element_text_and_html_by_tag, int_or_none, join_nonempty, + parse_qs, str_or_none, try_call, unified_timestamp, ) -from ..utils.traversal import traverse_obj +from ..utils.traversal import traverse_obj, value class DuoplayIE(InfoExtractor): - _VALID_URL = r'https?://duoplay\.ee/(?P\d+)/[\w-]+/?(?:\?(?:[^#]+&)?ep=(?P\d+))?' + _VALID_URL = r'https?://duoplay\.ee/(?P\d+)(?:[/?#]|$)' _TESTS = [{ 'note': 'Siberi võmm S02E12', 'url': 'https://duoplay.ee/4312/siberi-vomm?ep=24', @@ -34,15 +35,16 @@ class DuoplayIE(InfoExtractor): 'episode_number': 12, 'episode_id': '24', }, + 'skip': 'No video found', }, { 'note': 'Empty title', 'url': 'https://duoplay.ee/17/uhikarotid?ep=14', - 'md5': '6aca68be71112314738dd17cced7f8bf', + 'md5': 'cba9f5dabf2582b224d80ac44fb80e47', 'info_dict': { 'id': '17_14', 'ext': 'mp4', - 'title': 'Ühikarotid', - 'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$', + 'title': 'Episode 14', + 'thumbnail': r're:https?://.+\.jpg', 'description': 'md5:4719b418e058c209def41d48b601276e', 'upload_date': '20100916', 'timestamp': 1284661800, @@ -52,6 +54,8 @@ class DuoplayIE(InfoExtractor): 'season_number': 2, 'episode_id': '14', 'release_year': 2010, + 'episode': 'Episode 14', + 'episode_number': 14, }, }, { 'note': 'Movie without expiry', @@ -68,10 +72,32 @@ class DuoplayIE(InfoExtractor): 'timestamp': 1671054000, 'release_year': 2018, }, + 'skip': 'No video found', + }, { + 'note': 'Episode url without show name', + 'url': 'https://duoplay.ee/9644?ep=185', + 'md5': '63f324b4fe2dbd8194dca16a6d52184a', + 'info_dict': { + 'id': '9644_185', + 'ext': 'mp4', + 'title': 'Episode 185', + 'thumbnail': r're:https?://.+\.jpg', + 'description': 'md5:ed25ba4e9e5d54bc291a4a0cdd241467', + 'upload_date': '20241120', + 'timestamp': 1732077000, + 'episode': 'Episode 63', + 'episode_id': '185', + 'episode_number': 63, + 'season': 'Season 2', + 'season_number': 2, + 'series': 'Telehommik', + 'series_id': '9644', + }, }] def _real_extract(self, url): - telecast_id, episode = self._match_valid_url(url).group('id', 'ep') + telecast_id = self._match_id(url) + episode = traverse_obj(parse_qs(url), ('ep', 0, {int_or_none}, {str_or_none})) video_id = join_nonempty(telecast_id, episode, delim='_') webpage = self._download_webpage(url, video_id) video_player = try_call(lambda: extract_attributes( @@ -79,25 +105,33 @@ class DuoplayIE(InfoExtractor): if not video_player or not video_player.get('manifest-url'): raise ExtractorError('No video found', expected=True) + manifest_url = video_player['manifest-url'] + session_token = self._download_json( + 'https://sts.postimees.ee/session/register', video_id, 'Registering session', + 'Unable to register session', headers={ + 'Accept': 'application/json', + 'X-Original-URI': manifest_url, + })['session'] + episode_attr = self._parse_json(video_player.get(':episode') or '', video_id, fatal=False) or {} return { 'id': video_id, - 'formats': self._extract_m3u8_formats(video_player['manifest-url'], video_id, 'mp4'), + 'formats': self._extract_m3u8_formats(manifest_url, video_id, 'mp4', query={'s': session_token}), **traverse_obj(episode_attr, { - 'title': 'title', - 'description': 'synopsis', + 'title': ('title', {str}), + 'description': ('synopsis', {str}), 'thumbnail': ('images', 'original'), 'timestamp': ('airtime', {lambda x: unified_timestamp(x + ' +0200')}), - 'cast': ('cast', {lambda x: x.split(', ')}), + 'cast': ('cast', filter, {lambda x: x.split(', ')}), 'release_year': ('year', {int_or_none}), }), **(traverse_obj(episode_attr, { - 'title': (None, ('subtitle', ('episode_nr', {lambda x: f'Episode {x}' if x else None}))), - 'series': 'title', + 'title': (None, (('subtitle', {str}, filter), {value(f'Episode {episode}' if episode else None)})), + 'series': ('title', {str}), 'series_id': ('telecast_id', {str_or_none}), 'season_number': ('season_id', {int_or_none}), - 'episode': 'subtitle', + 'episode': ('subtitle', {str}, filter), 'episode_number': ('episode_nr', {int_or_none}), 'episode_id': ('episode_id', {str_or_none}), }, get_all=False) if episode_attr.get('category') != 'movies' else {}), From 2bea7936323ca4b6f3b9b1fdd892566223e30efa Mon Sep 17 00:00:00 2001 From: sepro Date: Mon, 2 Dec 2024 16:22:16 +0100 Subject: [PATCH 06/21] [ie/MicrosoftEmbed] Make format extraction non fatal (#11654) Authored by: seproDev --- yt_dlp/extractor/microsoftembed.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/microsoftembed.py b/yt_dlp/extractor/microsoftembed.py index d0135f5a9..2575d6c5e 100644 --- a/yt_dlp/extractor/microsoftembed.py +++ b/yt_dlp/extractor/microsoftembed.py @@ -26,6 +26,7 @@ class MicrosoftEmbedIE(InfoExtractor): 'timestamp': 1631658316, 'upload_date': '20210914', }, + 'expected_warnings': ['Failed to parse XML: syntax error: line 1, column 0'], }] _API_URL = 'https://prod-video-cms-rt-microsoft-com.akamaized.net/vhs/api/videos/' @@ -36,11 +37,11 @@ class MicrosoftEmbedIE(InfoExtractor): formats = [] for source_type, source in metadata['streams'].items(): if source_type == 'smooth_Streaming': - formats.extend(self._extract_ism_formats(source['url'], video_id, 'mss')) + formats.extend(self._extract_ism_formats(source['url'], video_id, 'mss', fatal=False)) elif source_type == 'apple_HTTP_Live_Streaming': - formats.extend(self._extract_m3u8_formats(source['url'], video_id, 'mp4')) + formats.extend(self._extract_m3u8_formats(source['url'], video_id, 'mp4', fatal=False)) elif source_type == 'mPEG_DASH': - formats.extend(self._extract_mpd_formats(source['url'], video_id)) + formats.extend(self._extract_mpd_formats(source['url'], video_id, fatal=False)) else: formats.append({ 'format_id': source_type, From d8fb3490863653182864d2a53522f350d67a9ff8 Mon Sep 17 00:00:00 2001 From: sepro Date: Mon, 2 Dec 2024 16:29:30 +0100 Subject: [PATCH 07/21] [cleanup] Bump ruff to 0.8.x (#11608) Authored by: seproDev --- pyproject.toml | 6 ++---- yt_dlp/YoutubeDL.py | 10 +++++----- yt_dlp/__init__.py | 6 +++--- yt_dlp/aes.py | 14 ++++++-------- yt_dlp/cookies.py | 4 ++-- yt_dlp/downloader/hls.py | 8 ++++---- yt_dlp/downloader/youtube_live_chat.py | 4 ++-- yt_dlp/extractor/bilibili.py | 4 ++-- yt_dlp/extractor/common.py | 2 +- yt_dlp/extractor/funimation.py | 6 +++--- yt_dlp/extractor/youtube.py | 14 +++++++------- yt_dlp/plugins.py | 2 +- yt_dlp/postprocessor/__init__.py | 2 +- yt_dlp/postprocessor/ffmpeg.py | 2 +- yt_dlp/utils/_utils.py | 4 ++-- 15 files changed, 42 insertions(+), 46 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 97ea4375f..96e2d669a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -76,7 +76,7 @@ dev = [ ] static-analysis = [ "autopep8~=2.0", - "ruff~=0.7.0", + "ruff~=0.8.0", ] test = [ "pytest~=8.1", @@ -186,6 +186,7 @@ ignore = [ "E501", # line-too-long "E731", # lambda-assignment "E741", # ambiguous-variable-name + "UP031", # printf-string-formatting "UP036", # outdated-version-block "B006", # mutable-argument-default "B008", # function-call-in-default-argument @@ -258,9 +259,6 @@ select = [ "A002", # builtin-argument-shadowing "C408", # unnecessary-collection-call ] -"yt_dlp/jsinterp.py" = [ - "UP031", # printf-string-formatting -] [tool.ruff.lint.isort] known-first-party = [ diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index a9a8e4133..65b72e026 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -1116,7 +1116,7 @@ class YoutubeDL: def raise_no_formats(self, info, forced=False, *, msg=None): has_drm = info.get('_has_drm') ignored, expected = self.params.get('ignore_no_formats_error'), bool(msg) - msg = msg or has_drm and 'This video is DRM protected' or 'No video formats found!' + msg = msg or (has_drm and 'This video is DRM protected') or 'No video formats found!' if forced or not ignored: raise ExtractorError(msg, video_id=info['id'], ie=info['extractor'], expected=has_drm or ignored or expected) @@ -2196,7 +2196,7 @@ class YoutubeDL: def _default_format_spec(self, info_dict): prefer_best = ( self.params['outtmpl']['default'] == '-' - or info_dict.get('is_live') and not self.params.get('live_from_start')) + or (info_dict.get('is_live') and not self.params.get('live_from_start'))) def can_merge(): merger = FFmpegMergerPP(self) @@ -2365,7 +2365,7 @@ class YoutubeDL: vexts=[f['ext'] for f in video_fmts], aexts=[f['ext'] for f in audio_fmts], preferences=(try_call(lambda: self.params['merge_output_format'].split('/')) - or self.params.get('prefer_free_formats') and ('webm', 'mkv'))) + or (self.params.get('prefer_free_formats') and ('webm', 'mkv')))) filtered = lambda *keys: filter(None, (traverse_obj(fmt, *keys) for fmt in formats_info)) @@ -3541,8 +3541,8 @@ class YoutubeDL: and info_dict.get('container') == 'm4a_dash', 'writing DASH m4a. Only some players support this container', FFmpegFixupM4aPP) - ffmpeg_fixup(downloader == 'hlsnative' and not self.params.get('hls_use_mpegts') - or info_dict.get('is_live') and self.params.get('hls_use_mpegts') is None, + ffmpeg_fixup((downloader == 'hlsnative' and not self.params.get('hls_use_mpegts')) + or (info_dict.get('is_live') and self.params.get('hls_use_mpegts') is None), 'Possible MPEG-TS in MP4 container or malformed AAC timestamps', FFmpegFixupM3u8PP) ffmpeg_fixup(downloader == 'dashsegments' diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index a1880bf7d..20111175b 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -1062,7 +1062,7 @@ def _real_main(argv=None): # If we only have a single process attached, then the executable was double clicked # When using `pyinstaller` with `--onefile`, two processes get attached is_onefile = hasattr(sys, '_MEIPASS') and os.path.basename(sys._MEIPASS).startswith('_MEI') - if attached_processes == 1 or is_onefile and attached_processes == 2: + if attached_processes == 1 or (is_onefile and attached_processes == 2): print(parser._generate_error_message( 'Do not double-click the executable, instead call it from a command line.\n' 'Please read the README for further information on how to use yt-dlp: ' @@ -1109,9 +1109,9 @@ def main(argv=None): from .extractor import gen_extractors, list_extractors __all__ = [ - 'main', 'YoutubeDL', - 'parse_options', 'gen_extractors', 'list_extractors', + 'main', + 'parse_options', ] diff --git a/yt_dlp/aes.py b/yt_dlp/aes.py index 0930d36df..9908434a5 100644 --- a/yt_dlp/aes.py +++ b/yt_dlp/aes.py @@ -534,19 +534,17 @@ def ghash(subkey, data): __all__ = [ 'aes_cbc_decrypt', 'aes_cbc_decrypt_bytes', - 'aes_ctr_decrypt', - 'aes_decrypt_text', - 'aes_decrypt', - 'aes_ecb_decrypt', - 'aes_gcm_decrypt_and_verify', - 'aes_gcm_decrypt_and_verify_bytes', - 'aes_cbc_encrypt', 'aes_cbc_encrypt_bytes', + 'aes_ctr_decrypt', 'aes_ctr_encrypt', + 'aes_decrypt', + 'aes_decrypt_text', + 'aes_ecb_decrypt', 'aes_ecb_encrypt', 'aes_encrypt', - + 'aes_gcm_decrypt_and_verify', + 'aes_gcm_decrypt_and_verify_bytes', 'key_expansion', 'pad_block', 'pkcs7_padding', diff --git a/yt_dlp/cookies.py b/yt_dlp/cookies.py index d5b0d3991..772433b0f 100644 --- a/yt_dlp/cookies.py +++ b/yt_dlp/cookies.py @@ -1276,8 +1276,8 @@ class YoutubeDLCookieJar(http.cookiejar.MozillaCookieJar): def _really_save(self, f, ignore_discard, ignore_expires): now = time.time() for cookie in self: - if (not ignore_discard and cookie.discard - or not ignore_expires and cookie.is_expired(now)): + if ((not ignore_discard and cookie.discard) + or (not ignore_expires and cookie.is_expired(now))): continue name, value = cookie.name, cookie.value if value is None: diff --git a/yt_dlp/downloader/hls.py b/yt_dlp/downloader/hls.py index 0a00d5dab..da2574da7 100644 --- a/yt_dlp/downloader/hls.py +++ b/yt_dlp/downloader/hls.py @@ -119,12 +119,12 @@ class HlsFD(FragmentFD): self.to_screen(f'[{self.FD_NAME}] Fragment downloads will be delegated to {real_downloader.get_basename()}') def is_ad_fragment_start(s): - return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s - or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) + return ((s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s) + or (s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))) def is_ad_fragment_end(s): - return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s - or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) + return ((s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s) + or (s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))) fragments = [] diff --git a/yt_dlp/downloader/youtube_live_chat.py b/yt_dlp/downloader/youtube_live_chat.py index 961938d44..ddd912ca2 100644 --- a/yt_dlp/downloader/youtube_live_chat.py +++ b/yt_dlp/downloader/youtube_live_chat.py @@ -123,8 +123,8 @@ class YoutubeLiveChatFD(FragmentFD): data, lambda x: x['continuationContents']['liveChatContinuation'], dict) or {} - func = (info_dict['protocol'] == 'youtube_live_chat' and parse_actions_live - or frag_index == 1 and try_refresh_replay_beginning + func = ((info_dict['protocol'] == 'youtube_live_chat' and parse_actions_live) + or (frag_index == 1 and try_refresh_replay_beginning) or parse_actions_replay) return (True, *func(live_chat_continuation)) except HTTPError as err: diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index f01befcc0..72d5f20cf 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -662,12 +662,12 @@ class BiliBiliIE(BilibiliBaseIE): video_id, title = video_data['bvid'], video_data.get('title') # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. - page_list_json = not is_festival and traverse_obj( + page_list_json = (not is_festival and traverse_obj( self._download_json( 'https://api.bilibili.com/x/player/pagelist', video_id, fatal=False, query={'bvid': video_id, 'jsonp': 'jsonp'}, note='Extracting videos in anthology', headers=headers), - 'data', expected_type=list) or [] + 'data', expected_type=list)) or [] is_anthology = len(page_list_json) > 1 part_id = int_or_none(parse_qs(url).get('p', [None])[-1]) diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index ce79e0b62..92ddad2b7 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -3803,7 +3803,7 @@ class InfoExtractor: def mark_watched(self, *args, **kwargs): if not self.get_param('mark_watched', False): return - if self.supports_login() and self._get_login_info()[0] is not None or self._cookies_passed: + if (self.supports_login() and self._get_login_info()[0] is not None) or self._cookies_passed: self._mark_watched(*args, **kwargs) def _mark_watched(self, *args, **kwargs): diff --git a/yt_dlp/extractor/funimation.py b/yt_dlp/extractor/funimation.py index d3e61c84f..01b53bcde 100644 --- a/yt_dlp/extractor/funimation.py +++ b/yt_dlp/extractor/funimation.py @@ -193,9 +193,9 @@ class FunimationIE(FunimationBaseIE): for lang, version, fmt in self._get_experiences(episode): experience_id = str(fmt['experienceId']) - if (only_initial_experience and experience_id != initial_experience_id - or requested_languages and lang.lower() not in requested_languages - or requested_versions and version.lower() not in requested_versions): + if ((only_initial_experience and experience_id != initial_experience_id) + or (requested_languages and lang.lower() not in requested_languages) + or (requested_versions and version.lower() not in requested_versions)): continue thumbnails.append({'url': fmt.get('poster')}) duration = max(duration, fmt.get('duration', 0)) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index a67f09e62..41cd90db9 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -2925,7 +2925,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # Obtain from MPD's maximum seq value old_mpd_url = mpd_url last_error = ctx.pop('last_error', None) - expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403 + expire_fast = immediate or (last_error and isinstance(last_error, HTTPError) and last_error.status == 403) mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) or (mpd_url, stream_number, False)) if not refresh_sequence: @@ -3995,8 +3995,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return prs, player_url def _needs_live_processing(self, live_status, duration): - if (live_status == 'is_live' and self.get_param('live_from_start') - or live_status == 'post_live' and (duration or 0) > 2 * 3600): + if ((live_status == 'is_live' and self.get_param('live_from_start')) + or (live_status == 'post_live' and (duration or 0) > 2 * 3600)): return live_status def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration): @@ -4192,7 +4192,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): skip_manifests = set(self._configuration_arg('skip')) if (not self.get_param('youtube_include_hls_manifest', True) or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway - or needs_live_processing and skip_bad_formats): + or (needs_live_processing and skip_bad_formats)): skip_manifests.add('hls') if not self.get_param('youtube_include_dash_manifest', True): @@ -4390,14 +4390,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): expected_type=dict) translated_title = self._get_text(microformats, (..., 'title')) - video_title = (self._preferred_lang and translated_title + video_title = ((self._preferred_lang and translated_title) or get_first(video_details, 'title') # primary or translated_title or search_meta(['og:title', 'twitter:title', 'title'])) translated_description = self._get_text(microformats, (..., 'description')) original_description = get_first(video_details, 'shortDescription') video_description = ( - self._preferred_lang and translated_description + (self._preferred_lang and translated_description) # If original description is blank, it will be an empty string. # Do not prefer translated description in this case. or original_description if original_description is not None else translated_description) @@ -6837,7 +6837,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor): tab_url = urljoin(base_url, traverse_obj( tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url'))) - tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:] + tab_id = ((tab_url and self._get_url_mobj(tab_url)['tab'][1:]) or traverse_obj(tab, 'tabIdentifier', expected_type=str)) if tab_id: return { diff --git a/yt_dlp/plugins.py b/yt_dlp/plugins.py index 2bf55df71..94335a9a3 100644 --- a/yt_dlp/plugins.py +++ b/yt_dlp/plugins.py @@ -183,4 +183,4 @@ def load_plugins(name, suffix): sys.meta_path.insert(0, PluginFinder(f'{PACKAGE_NAME}.extractor', f'{PACKAGE_NAME}.postprocessor')) -__all__ = ['directories', 'load_plugins', 'PACKAGE_NAME', 'COMPAT_PACKAGE_NAME'] +__all__ = ['COMPAT_PACKAGE_NAME', 'PACKAGE_NAME', 'directories', 'load_plugins'] diff --git a/yt_dlp/postprocessor/__init__.py b/yt_dlp/postprocessor/__init__.py index 164540b5d..7b1620544 100644 --- a/yt_dlp/postprocessor/__init__.py +++ b/yt_dlp/postprocessor/__init__.py @@ -44,4 +44,4 @@ def get_postprocessor(key): globals().update(_PLUGIN_CLASSES) __all__ = [name for name in globals() if name.endswith('PP')] -__all__.extend(('PostProcessor', 'FFmpegPostProcessor')) +__all__.extend(('FFmpegPostProcessor', 'PostProcessor')) diff --git a/yt_dlp/postprocessor/ffmpeg.py b/yt_dlp/postprocessor/ffmpeg.py index d994754fd..8965806ae 100644 --- a/yt_dlp/postprocessor/ffmpeg.py +++ b/yt_dlp/postprocessor/ffmpeg.py @@ -626,7 +626,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): sub_ext = sub_info['ext'] if sub_ext == 'json': self.report_warning('JSON subtitles cannot be embedded') - elif ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': + elif ext != 'webm' or (ext == 'webm' and sub_ext == 'vtt'): sub_langs.append(lang) sub_names.append(sub_info.get('name')) sub_filenames.append(sub_info['filepath']) diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 8517b762e..699bf1e7f 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -2683,8 +2683,8 @@ def merge_dicts(*dicts): merged = {} for a_dict in dicts: for k, v in a_dict.items(): - if (v is not None and k not in merged - or isinstance(v, str) and merged[k] == ''): + if ((v is not None and k not in merged) + or (isinstance(v, str) and merged[k] == '')): merged[k] = v return merged From f05a1cd1492fc98dc8d80d2081d632a1879913d2 Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Tue, 3 Dec 2024 14:19:22 +1300 Subject: [PATCH 08/21] [ie/bilibili] Fix supporter-only video extraction (#11711) Fix bug in 239f5f36fe04603bec59c8b975f6a792f10246db Closes #11702 Authored by: grqz, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/bilibili.py | 129 ++++++++++++++++++----------------- 1 file changed, 66 insertions(+), 63 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 72d5f20cf..e538e5308 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -652,13 +652,6 @@ class BiliBiliIE(BilibiliBaseIE): else: video_data = initial_state['videoData'] - if video_data.get('is_upower_exclusive'): - high_level = traverse_obj(initial_state, ('elecFullInfo', 'show_info', 'high_level', {dict})) or {} - raise ExtractorError( - 'This is a supporter-only video: ' - f'{join_nonempty("title", "sub_title", from_dict=high_level, delim="，")}. ' - f'{self._login_hint()}', expected=True) - video_id, title = video_data['bvid'], video_data.get('title') # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself. @@ -726,62 +719,72 @@ class BiliBiliIE(BilibiliBaseIE): self._get_interactive_entries(video_id, cid, metainfo, headers=headers), **metainfo, duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})), __post_extractor=self.extract_comments(aid)) - else: - formats = self.extract_formats(play_info) - - if not traverse_obj(play_info, ('dash')): - # we only have legacy formats and need additional work - has_qn = lambda x: x in traverse_obj(formats, (..., 'quality')) - for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})): - formats.extend(traverse_obj( - self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, qn=qn)), - lambda _, v: not has_qn(v['quality']))) - self._check_missing_formats(play_info, formats) - flv_formats = traverse_obj(formats, lambda _, v: v['fragments']) - if flv_formats and len(flv_formats) < len(formats): - # Flv and mp4 are incompatible due to `multi_video` workaround, so drop one - if not self._configuration_arg('prefer_multi_flv'): - dropped_fmts = ', '.join( - f'{f.get("format_note")} ({f.get("format_id")})' for f in flv_formats) - formats = traverse_obj(formats, lambda _, v: not v.get('fragments')) - if dropped_fmts: - self.to_screen( - f'Dropping incompatible flv format(s) {dropped_fmts} since mp4 is available. ' - 'To extract flv, pass --extractor-args "bilibili:prefer_multi_flv"') - else: - formats = traverse_obj( - # XXX: Filtering by extractor-arg is for testing purposes - formats, lambda _, v: v['quality'] == int(self._configuration_arg('prefer_multi_flv')[0]), - ) or [max(flv_formats, key=lambda x: x['quality'])] - - if traverse_obj(formats, (0, 'fragments')): - # We have flv formats, which are individual short videos with their own timestamps and metainfo - # Binary concatenation corrupts their timestamps, so we need a `multi_video` workaround - return { - **metainfo, - '_type': 'multi_video', - 'entries': [{ - 'id': f'{metainfo["id"]}_{idx}', - 'title': metainfo['title'], - 'http_headers': metainfo['http_headers'], - 'formats': [{ - **fragment, - 'format_id': formats[0].get('format_id'), - }], - 'subtitles': self.extract_subtitles(video_id, cid) if idx == 0 else None, - '__post_extractor': self.extract_comments(aid) if idx == 0 else None, - } for idx, fragment in enumerate(formats[0]['fragments'])], - 'duration': float_or_none(play_info.get('timelength'), scale=1000), - } - else: - return { - **metainfo, - 'formats': formats, - 'duration': float_or_none(play_info.get('timelength'), scale=1000), - 'chapters': self._get_chapters(aid, cid), - 'subtitles': self.extract_subtitles(video_id, cid), - '__post_extractor': self.extract_comments(aid), - } + + formats = self.extract_formats(play_info) + + if video_data.get('is_upower_exclusive'): + high_level = traverse_obj(initial_state, ('elecFullInfo', 'show_info', 'high_level', {dict})) or {} + msg = f'{join_nonempty("title", "sub_title", from_dict=high_level, delim="，")}. {self._login_hint()}' + if not formats: + raise ExtractorError(f'This is a supporter-only video: {msg}', expected=True) + if '试看' in traverse_obj(play_info, ('accept_description', ..., {str})): + self.report_warning( + f'This is a supporter-only video, only the preview will be extracted: {msg}', + video_id=video_id) + + if not traverse_obj(play_info, 'dash'): + # we only have legacy formats and need additional work + has_qn = lambda x: x in traverse_obj(formats, (..., 'quality')) + for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})): + formats.extend(traverse_obj( + self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, qn=qn)), + lambda _, v: not has_qn(v['quality']))) + self._check_missing_formats(play_info, formats) + flv_formats = traverse_obj(formats, lambda _, v: v['fragments']) + if flv_formats and len(flv_formats) < len(formats): + # Flv and mp4 are incompatible due to `multi_video` workaround, so drop one + if not self._configuration_arg('prefer_multi_flv'): + dropped_fmts = ', '.join( + f'{f.get("format_note")} ({f.get("format_id")})' for f in flv_formats) + formats = traverse_obj(formats, lambda _, v: not v.get('fragments')) + if dropped_fmts: + self.to_screen( + f'Dropping incompatible flv format(s) {dropped_fmts} since mp4 is available. ' + 'To extract flv, pass --extractor-args "bilibili:prefer_multi_flv"') + else: + formats = traverse_obj( + # XXX: Filtering by extractor-arg is for testing purposes + formats, lambda _, v: v['quality'] == int(self._configuration_arg('prefer_multi_flv')[0]), + ) or [max(flv_formats, key=lambda x: x['quality'])] + + if traverse_obj(formats, (0, 'fragments')): + # We have flv formats, which are individual short videos with their own timestamps and metainfo + # Binary concatenation corrupts their timestamps, so we need a `multi_video` workaround + return { + **metainfo, + '_type': 'multi_video', + 'entries': [{ + 'id': f'{metainfo["id"]}_{idx}', + 'title': metainfo['title'], + 'http_headers': metainfo['http_headers'], + 'formats': [{ + **fragment, + 'format_id': formats[0].get('format_id'), + }], + 'subtitles': self.extract_subtitles(video_id, cid) if idx == 0 else None, + '__post_extractor': self.extract_comments(aid) if idx == 0 else None, + } for idx, fragment in enumerate(formats[0]['fragments'])], + 'duration': float_or_none(play_info.get('timelength'), scale=1000), + } + + return { + **metainfo, + 'formats': formats, + 'duration': float_or_none(play_info.get('timelength'), scale=1000), + 'chapters': self._get_chapters(aid, cid), + 'subtitles': self.extract_subtitles(video_id, cid), + '__post_extractor': self.extract_comments(aid), + } class BiliBiliBangumiIE(BilibiliBaseIE): From dc1687648077c5bf64863b307ecc5ab7e029bd8d Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Tue, 3 Dec 2024 16:44:03 +1300 Subject: [PATCH 09/21] [ie/bilibili] Always try to extract HD formats (#10559) Closes #10554 Authored by: grqz --- yt_dlp/extractor/bilibili.py | 38 +++++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 14 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index e538e5308..23c8255ee 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -62,7 +62,7 @@ class BilibiliBaseIE(InfoExtractor): 'support_formats', lambda _, v: v['quality'] not in parsed_qualities))], delim=', ') if missing_formats: self.to_screen( - f'Format(s) {missing_formats} are missing; you have to login or ' + f'Format(s) {missing_formats} are missing; you have to ' f'become a premium member to download them. {self._login_hint()}') def extract_formats(self, play_info): @@ -164,14 +164,18 @@ class BilibiliBaseIE(InfoExtractor): params['w_rid'] = hashlib.md5(f'{query}{self._get_wbi_key(video_id)}'.encode()).hexdigest() return params - def _download_playinfo(self, bvid, cid, headers=None, qn=None): - params = {'bvid': bvid, 'cid': cid, 'fnval': 4048} - if qn: - params['qn'] = qn + def _download_playinfo(self, bvid, cid, headers=None, query=None): + params = {'bvid': bvid, 'cid': cid, 'fnval': 4048, **(query or {})} + if self.is_logged_in: + params.pop('try_look', None) + if qn := params.get('qn'): + note = f'Downloading video format {qn} for cid {cid}' + else: + note = f'Downloading video formats for cid {cid}' + return self._download_json( 'https://api.bilibili.com/x/player/wbi/playurl', bvid, - query=self._sign_wbi(params, bvid), headers=headers, - note=f'Downloading video formats for cid {cid} {qn or ""}')['data'] + query=self._sign_wbi(params, bvid), headers=headers, note=note)['data'] def json2srt(self, json_data): srt_data = '' @@ -285,7 +289,7 @@ class BilibiliBaseIE(InfoExtractor): ('data', 'interaction', 'graph_version', {int_or_none})) cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1) for cid, edges in cid_edges.items(): - play_info = self._download_playinfo(video_id, cid, headers=headers) + play_info = self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1}) yield { **metainfo, 'id': f'{video_id}_{cid}', @@ -681,7 +685,7 @@ class BiliBiliIE(BilibiliBaseIE): traverse_obj( self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None), ('data', {dict})) - or self._download_playinfo(video_id, cid, headers=headers)) + or self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1})) festival_info = {} if is_festival: @@ -737,7 +741,7 @@ class BiliBiliIE(BilibiliBaseIE): has_qn = lambda x: x in traverse_obj(formats, (..., 'quality')) for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})): formats.extend(traverse_obj( - self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, qn=qn)), + self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, query={'qn': qn})), lambda _, v: not has_qn(v['quality']))) self._check_missing_formats(play_info, formats) flv_formats = traverse_obj(formats, lambda _, v: v['fragments']) @@ -862,10 +866,16 @@ class BiliBiliBangumiIE(BilibiliBaseIE): self.raise_login_required('This video is for premium members only') headers['Referer'] = url - play_info = self._download_json( - 'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id, - 'Extracting episode', query={'fnval': '4048', 'ep_id': episode_id}, - headers=headers) + + play_info = ( + self._search_json( + r'playurlSSRData\s*=', webpage, 'embedded page info', episode_id, + end_pattern='\n', default=None) + or self._download_json( + 'https://api.bilibili.com/pgc/player/web/v2/playurl', episode_id, + 'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id}, + headers=headers)) + premium_only = play_info.get('code') == -10403 play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {} From a13a336aa6f906812701abec8101b73b73db8ff7 Mon Sep 17 00:00:00 2001 From: Link Date: Tue, 3 Dec 2024 12:08:46 +0800 Subject: [PATCH 10/21] [ie/bilibili] Fix subtitles and chapters extraction (#11708) Authored by: xiaomac --- yt_dlp/extractor/bilibili.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 23c8255ee..91619d9d5 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -194,7 +194,7 @@ class BilibiliBaseIE(InfoExtractor): } video_info = self._download_json( - 'https://api.bilibili.com/x/player/v2', video_id, + 'https://api.bilibili.com/x/player/wbi/v2', video_id, query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid}, note=f'Extracting subtitle info {cid}', headers=self._HEADERS) if traverse_obj(video_info, ('data', 'need_login_subtitle')): @@ -210,7 +210,7 @@ class BilibiliBaseIE(InfoExtractor): def _get_chapters(self, aid, cid): chapters = aid and cid and self._download_json( - 'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid}, + 'https://api.bilibili.com/x/player/wbi/v2', aid, query={'aid': aid, 'cid': cid}, note='Extracting chapters', fatal=False, headers=self._HEADERS) return traverse_obj(chapters, ('data', 'view_points', ..., { 'title': 'content', From c038a7b187ba24360f14134842a7a2cf897c33b1 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 3 Dec 2024 14:28:43 +0000 Subject: [PATCH 11/21] [ie/vk] Fix extractors (#11715) Closes #5832, Closes #11471, Closes #11646, Closes #11670 Authored by: bashonly --- yt_dlp/extractor/vk.py | 96 ++++++++++++++++++++++++++++-------------- 1 file changed, 64 insertions(+), 32 deletions(-) diff --git a/yt_dlp/extractor/vk.py b/yt_dlp/extractor/vk.py index 6ccc701a2..4b36e41ff 100644 --- a/yt_dlp/extractor/vk.py +++ b/yt_dlp/extractor/vk.py @@ -17,10 +17,10 @@ from ..utils import ( get_element_html_by_id, int_or_none, join_nonempty, + parse_qs, parse_resolution, str_or_none, str_to_int, - traverse_obj, try_call, unescapeHTML, unified_timestamp, @@ -29,6 +29,7 @@ from ..utils import ( urlencode_postdata, urljoin, ) +from ..utils.traversal import require, traverse_obj class VKBaseIE(InfoExtractor): @@ -91,17 +92,17 @@ class VKBaseIE(InfoExtractor): class VKIE(VKBaseIE): IE_NAME = 'vk' IE_DESC = 'VK' - _EMBED_REGEX = [r']+?src=(["\'])(?Phttps?://vk\.com/video_ext\.php.+?)\1'] + _EMBED_REGEX = [r']+?src=(["\'])(?Phttps?://vk(?:(?:video)?\.ru|\.com)/video_ext\.php.+?)\1'] _VALID_URL = r'''(?x) https?:// (?: (?: - (?:(?:m|new)\.)?vk\.com/video_| + (?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/video_| (?:www\.)?daxab\.com/ ) ext\.php\?(?P.*?\boid=(?P-?\d+).*?\bid=(?P\d+).*)| (?: - (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)| + (?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/(?:.+?\?.*?z=)?(?:video|clip)| (?:www\.)?daxab\.com/embed/ ) (?P-?\d+_\d+)(?:.*\blist=(?P([\da-f]+)|(ln-[\da-zA-Z]+)))? @@ -110,7 +111,7 @@ class VKIE(VKBaseIE): _TESTS = [ { - 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', + 'url': 'https://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', 'info_dict': { 'id': '-77521_162222515', 'ext': 'mp4', @@ -127,7 +128,7 @@ class VKIE(VKBaseIE): 'params': {'skip_download': 'm3u8'}, }, { - 'url': 'http://vk.com/video205387401_165548505', + 'url': 'https://vk.com/video205387401_165548505', 'info_dict': { 'id': '205387401_165548505', 'ext': 'mp4', @@ -182,10 +183,10 @@ class VKIE(VKBaseIE): 'ext': 'mp4', 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', - 'duration': 178, + 'duration': 179, 'upload_date': '20130117', 'uploader': "Children's Joy Foundation Inc.", - 'uploader_id': 'thecjf', + 'uploader_id': '@CJFIofficial', 'view_count': int, 'channel_id': 'UCgzCNQ11TmR9V97ECnhi3gw', 'availability': 'public', @@ -193,7 +194,7 @@ class VKIE(VKBaseIE): 'live_status': 'not_live', 'playable_in_embed': True, 'channel': 'Children\'s Joy Foundation Inc.', - 'uploader_url': 'http://www.youtube.com/user/thecjf', + 'uploader_url': 'https://www.youtube.com/@CJFIofficial', 'thumbnail': r're:https?://.+\.jpg$', 'tags': 'count:27', 'start_time': 0.0, @@ -201,6 +202,7 @@ class VKIE(VKBaseIE): 'channel_url': 'https://www.youtube.com/channel/UCgzCNQ11TmR9V97ECnhi3gw', 'channel_follower_count': int, 'age_limit': 0, + 'timestamp': 1358394935, }, }, { @@ -222,6 +224,7 @@ class VKIE(VKBaseIE): 'thumbnail': r're:https?://.+x1080$', 'tags': list, }, + 'skip': 'This video has been deleted and is no longer available.', }, { 'url': 'https://vk.com/clips-74006511?z=clip-74006511_456247211', @@ -235,13 +238,13 @@ class VKIE(VKBaseIE): 'timestamp': 1664995597, 'title': 'Clip by @madempress', 'upload_date': '20221005', - 'uploader': 'Шальная императрица', + 'uploader': 'Шальная Императрица', 'uploader_id': '-74006511', }, }, { # video key is extra_data not url\d+ - 'url': 'http://vk.com/video-110305615_171782105', + 'url': 'https://vk.com/video-110305615_171782105', 'md5': 'e13fcda136f99764872e739d13fac1d1', 'info_dict': { 'id': '-110305615_171782105', @@ -273,6 +276,7 @@ class VKIE(VKBaseIE): 'params': { 'skip_download': True, }, + 'skip': 'No formats found', }, { # live stream, hls and rtmp links, most likely already finished live @@ -312,7 +316,16 @@ class VKIE(VKBaseIE): { 'url': 'https://vk.com/clip30014565_456240946', 'only_matching': True, - }] + }, + { + 'url': 'https://vkvideo.ru/video-127553155_456242961', + 'only_matching': True, + }, + { + 'url': 'https://vk.ru/video-220754053_456242564', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = self._match_valid_url(url) @@ -338,7 +351,7 @@ class VKIE(VKBaseIE): video_id = '{}_{}'.format(mobj.group('oid'), mobj.group('id')) info_page = self._download_webpage( - 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) + 'https://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) error_message = self._html_search_regex( [r'(?s)]+class="video_layer_message"[^>]*>(.+?)', @@ -432,7 +445,7 @@ class VKIE(VKBaseIE): if m_opts_url: opts_url = m_opts_url.group(1) if opts_url.startswith('//'): - opts_url = 'http:' + opts_url + opts_url = 'https:' + opts_url return self.url_result(opts_url) data = player['params'][0] @@ -512,8 +525,11 @@ class VKIE(VKBaseIE): class VKUserVideosIE(VKBaseIE): IE_NAME = 'vk:uservideos' IE_DESC = "VK - User's Videos" - _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P
\w+))?|$)' - _TEMPLATE_URL = 'https://vk.com/videos' + _BASE_URL_RE = r'https?://(?:(?:m|new)\.)?vk(?:video\.ru|\.com/video)' + _VALID_URL = [ + rf'{_BASE_URL_RE}/playlist/(?P-?\d+_\d+)', + rf'{_BASE_URL_RE}/(?P@[^/?#]+)(?:/all)?/?(?!\?.*\bz=video)(?:[?#]|$)', + ] _TESTS = [{ 'url': 'https://vk.com/video/@mobidevices', 'info_dict': { @@ -527,12 +543,20 @@ class VKUserVideosIE(VKBaseIE): }, 'playlist_mincount': 182, }, { - 'url': 'https://vk.com/video/playlist/-174476437_2', + 'url': 'https://vkvideo.ru/playlist/-204353299_426', 'info_dict': { - 'id': '-174476437_playlist_2', - 'title': 'Анонсы', + 'id': '-204353299_playlist_426', }, - 'playlist_mincount': 108, + 'playlist_mincount': 33, + }, { + 'url': 'https://vk.com/video/@gorkyfilmstudio/all', + 'only_matching': True, + }, { + 'url': 'https://vkvideo.ru/@mobidevices', + 'only_matching': True, + }, { + 'url': 'https://vk.com/video/playlist/-174476437_2', + 'only_matching': True, }] _VIDEO = collections.namedtuple('Video', ['owner_id', 'id']) @@ -552,7 +576,7 @@ class VKUserVideosIE(VKBaseIE): v = self._VIDEO._make(video[:2]) video_id = '%d_%d' % (v.owner_id, v.id) yield self.url_result( - 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id) + 'https://vk.com/video' + video_id, VKIE.ie_key(), video_id) if count >= total: break video_list_json = self._download_payload('al_video', page_id, { @@ -561,23 +585,25 @@ class VKUserVideosIE(VKBaseIE): 'oid': page_id, 'section': section, })[0][section] - count += video_list_json['count'] + new_count = video_list_json['count'] + if not new_count: + self.to_screen(f'{page_id}: Skipping {total - count} unavailable videos') + break + count += new_count video_list = video_list_json['list'] def _real_extract(self, url): - u_id, section = self._match_valid_url(url).groups() + u_id = self._match_id(url) webpage = self._download_webpage(url, u_id) if u_id.startswith('@'): - page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id') - elif '_' in u_id: - page_id, section = u_id.split('_', 1) - section = f'playlist_{section}' + page_id = traverse_obj( + self._search_json(r'\bvar newCur\s*=', webpage, 'cursor data', u_id), + ('oid', {int}, {str_or_none}, {require('page id')})) + section = traverse_obj(parse_qs(url), ('section', 0)) or 'all' else: - raise ExtractorError('Invalid URL', expected=True) - - if not section: - section = 'all' + page_id, _, section = u_id.partition('_') + section = f'playlist_{section}' playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title', webpage)) return self.playlist_result(self._entries(page_id, section), f'{page_id}_{section}', playlist_title) @@ -717,7 +743,7 @@ class VKWallPostIE(VKBaseIE): class VKPlayBaseIE(InfoExtractor): - _BASE_URL_RE = r'https?://(?:vkplay\.live|live\.vkplay\.ru)/' + _BASE_URL_RE = r'https?://(?:vkplay\.live|live\.vk(?:play|video)\.ru)/' _RESOLUTIONS = { 'tiny': '256x144', 'lowest': '426x240', @@ -797,6 +823,9 @@ class VKPlayIE(VKPlayBaseIE): }, { 'url': 'https://live.vkplay.ru/lebwa/record/33a4e4ce-e3ef-49db-bb14-f006cc6fabc9/records', 'only_matching': True, + }, { + 'url': 'https://live.vkvideo.ru/lebwa/record/33a4e4ce-e3ef-49db-bb14-f006cc6fabc9/records', + 'only_matching': True, }] def _real_extract(self, url): @@ -839,6 +868,9 @@ class VKPlayLiveIE(VKPlayBaseIE): }, { 'url': 'https://live.vkplay.ru/lebwa', 'only_matching': True, + }, { + 'url': 'https://live.vkvideo.ru/panterka', + 'only_matching': True, }] def _real_extract(self, url): From 2b67ac300ac8b44368fb121637d1743cea8c5b6b Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 3 Dec 2024 20:22:21 +0000 Subject: [PATCH 12/21] [cleanup] Misc (#11716) Authored by: bashonly, seproDev Co-authored-by: sepro --- yt_dlp/extractor/adn.py | 2 +- yt_dlp/extractor/cultureunplugged.py | 6 ------ yt_dlp/extractor/pixivsketch.py | 5 +++-- 3 files changed, 4 insertions(+), 9 deletions(-) diff --git a/yt_dlp/extractor/adn.py b/yt_dlp/extractor/adn.py index 919e1d6af..7dff40556 100644 --- a/yt_dlp/extractor/adn.py +++ b/yt_dlp/extractor/adn.py @@ -232,7 +232,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text''' error = self._parse_json(e.cause.response.read(), video_id) message = error.get('message') - if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country': + if e.cause.status == 403 and error.get('code') == 'player-bad-geolocation-country': self.raise_geo_restricted(msg=message) raise ExtractorError(message) else: diff --git a/yt_dlp/extractor/cultureunplugged.py b/yt_dlp/extractor/cultureunplugged.py index 8e6579c35..c7ccd2747 100644 --- a/yt_dlp/extractor/cultureunplugged.py +++ b/yt_dlp/extractor/cultureunplugged.py @@ -1,7 +1,4 @@ -import time - from .common import InfoExtractor -from ..networking import HEADRequest from ..utils import int_or_none @@ -31,9 +28,6 @@ class CultureUnpluggedIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id - # request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request - self._request_webpage(HEADRequest( - 'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id) movie_data = self._download_json( f'http://www.cultureunplugged.com/movie-data/cu-{video_id}.json', display_id) diff --git a/yt_dlp/extractor/pixivsketch.py b/yt_dlp/extractor/pixivsketch.py index 344cdb3d0..50b7af535 100644 --- a/yt_dlp/extractor/pixivsketch.py +++ b/yt_dlp/extractor/pixivsketch.py @@ -1,4 +1,5 @@ from .common import InfoExtractor +from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, traverse_obj, @@ -110,8 +111,8 @@ class PixivSketchUserIE(PixivSketchBaseIE): if not traverse_obj(data, 'is_broadcasting'): try: self._call_api(user_id, 'users/current.json', url, 'Investigating reason for request failure') - except ExtractorError as ex: - if ex.cause and ex.cause.code == 401: + except ExtractorError as e: + if isinstance(e.cause, HTTPError) and e.cause.status == 401: self.raise_login_required(f'Please log in, or use direct link like https://sketch.pixiv.net/@{user_id}/1234567890', method='cookies') raise ExtractorError('This user is offline', expected=True) From cfa76f35d25eaf993437df8b833befbbf9255331 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Tue, 3 Dec 2024 20:30:33 +0000 Subject: [PATCH 13/21] Release 2024.12.03 Created by: bashonly :ci skip all --- CONTRIBUTORS | 3 +++ Changelog.md | 36 ++++++++++++++++++++++++++++++++++++ yt_dlp/version.py | 6 +++--- 3 files changed, 42 insertions(+), 3 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 9b8207b28..8ee7fbffa 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -707,3 +707,6 @@ Sakura286 SamDecrock stratus-ss subrat-lima +gitninja1234 +jkruse +xiaomac diff --git a/Changelog.md b/Changelog.md index 4dc032368..c04e936b5 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,42 @@ # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.12.03 + +#### Core changes +- [Add `playlist_webpage_url` field](https://github.com/yt-dlp/yt-dlp/commit/7d6c259a03bc4707a319e5e8c6eff0278707874b) ([#11613](https://github.com/yt-dlp/yt-dlp/issues/11613)) by [seproDev](https://github.com/seproDev) + +#### Extractor changes +- [Handle fragmented formats in `_remove_duplicate_formats`](https://github.com/yt-dlp/yt-dlp/commit/e0500cbf796323551bbabe5b8ed8c75a511ba47a) ([#11637](https://github.com/yt-dlp/yt-dlp/issues/11637)) by [Grub4K](https://github.com/Grub4K) +- **bilibili** + - [Always try to extract HD formats](https://github.com/yt-dlp/yt-dlp/commit/dc1687648077c5bf64863b307ecc5ab7e029bd8d) ([#10559](https://github.com/yt-dlp/yt-dlp/issues/10559)) by [grqz](https://github.com/grqz) + - [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/239f5f36fe04603bec59c8b975f6a792f10246db) ([#11667](https://github.com/yt-dlp/yt-dlp/issues/11667)) by [grqz](https://github.com/grqz) (With fixes in [f05a1cd](https://github.com/yt-dlp/yt-dlp/commit/f05a1cd1492fc98dc8d80d2081d632a1879913d2) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz)) + - [Fix subtitles and chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a13a336aa6f906812701abec8101b73b73db8ff7) ([#11708](https://github.com/yt-dlp/yt-dlp/issues/11708)) by [xiaomac](https://github.com/xiaomac) +- **chaturbate**: [Fix support for non-public streams](https://github.com/yt-dlp/yt-dlp/commit/4b5eec0aaa7c02627f27a386591b735b90e681a8) ([#11624](https://github.com/yt-dlp/yt-dlp/issues/11624)) by [jkruse](https://github.com/jkruse) +- **dacast**: [Fix HLS AES formats extraction](https://github.com/yt-dlp/yt-dlp/commit/0a0d80800b9350d1a4c4b18d82cfb77ffbc3c507) ([#11644](https://github.com/yt-dlp/yt-dlp/issues/11644)) by [bashonly](https://github.com/bashonly) +- **dropbox**: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/00dcde728635633eee969ad4d498b9f233c4a94e) ([#11636](https://github.com/yt-dlp/yt-dlp/issues/11636)) by [bashonly](https://github.com/bashonly) +- **duoplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/62cba8a1bedbfc0ddde7267ae57b72bf5f7ea7b1) ([#11588](https://github.com/yt-dlp/yt-dlp/issues/11588)) by [bashonly](https://github.com/bashonly), [glensc](https://github.com/glensc) +- **facebook**: [Support more groups URLs](https://github.com/yt-dlp/yt-dlp/commit/e0f1ae813b36e783e2348ba2a1566e12f5cd8f6e) ([#11576](https://github.com/yt-dlp/yt-dlp/issues/11576)) by [grqz](https://github.com/grqz) +- **instagram**: [Support `share` URLs](https://github.com/yt-dlp/yt-dlp/commit/360aed810ad85db950df586282d256516c98cd2d) ([#11677](https://github.com/yt-dlp/yt-dlp/issues/11677)) by [grqz](https://github.com/grqz) +- **microsoftembed**: [Make format extraction non fatal](https://github.com/yt-dlp/yt-dlp/commit/2bea7936323ca4b6f3b9b1fdd892566223e30efa) ([#11654](https://github.com/yt-dlp/yt-dlp/issues/11654)) by [seproDev](https://github.com/seproDev) +- **mitele**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/cd0f934604587ed793e9177f6a127e5dcf99a7dd) ([#11683](https://github.com/yt-dlp/yt-dlp/issues/11683)) by [DarkZeros](https://github.com/DarkZeros) +- **stripchat**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/16336c51d0848a6868a4fa04e749fa03548b4913) ([#11596](https://github.com/yt-dlp/yt-dlp/issues/11596)) by [gitninja1234](https://github.com/gitninja1234) +- **tiktok**: [Deprioritize animated thumbnails](https://github.com/yt-dlp/yt-dlp/commit/910ecc422930bca14e2abe4986f5f92359e3cea8) ([#11645](https://github.com/yt-dlp/yt-dlp/issues/11645)) by [bashonly](https://github.com/bashonly) +- **vk**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/c038a7b187ba24360f14134842a7a2cf897c33b1) ([#11715](https://github.com/yt-dlp/yt-dlp/issues/11715)) by [bashonly](https://github.com/bashonly) +- **youtube** + - [Adjust player clients for site changes](https://github.com/yt-dlp/yt-dlp/commit/0d146c1e36f467af30e87b7af651bdee67b73500) ([#11663](https://github.com/yt-dlp/yt-dlp/issues/11663)) by [bashonly](https://github.com/bashonly) + - tab: [Fix playlists tab extraction](https://github.com/yt-dlp/yt-dlp/commit/fe70f20aedf528fdee332131bc9b6710e54e6f10) ([#11615](https://github.com/yt-dlp/yt-dlp/issues/11615)) by [seproDev](https://github.com/seproDev) + +#### Networking changes +- **Request Handler**: websockets: [Support websockets 14.0+](https://github.com/yt-dlp/yt-dlp/commit/c7316373c0a886f65a07a51e50ee147bb3294c85) ([#11616](https://github.com/yt-dlp/yt-dlp/issues/11616)) by [coletdjnz](https://github.com/coletdjnz) + +#### Misc. changes +- **cleanup** + - [Bump ruff to 0.8.x](https://github.com/yt-dlp/yt-dlp/commit/d8fb3490863653182864d2a53522f350d67a9ff8) ([#11608](https://github.com/yt-dlp/yt-dlp/issues/11608)) by [seproDev](https://github.com/seproDev) + - Miscellaneous + - [ccf0a6b](https://github.com/yt-dlp/yt-dlp/commit/ccf0a6b86b7f68a75463804fe485ec240b8635f0) by [bashonly](https://github.com/bashonly), [pzhlkj6612](https://github.com/pzhlkj6612) + - [2b67ac3](https://github.com/yt-dlp/yt-dlp/commit/2b67ac300ac8b44368fb121637d1743cea8c5b6b) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev) + ### 2024.11.18 #### Important changes diff --git a/yt_dlp/version.py b/yt_dlp/version.py index f4b9400bc..b7d5c57bf 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.11.18' +__version__ = '2024.12.03' -RELEASE_GIT_HEAD = '7ea2787920cccc6b8ea30791993d114fbd564434' +RELEASE_GIT_HEAD = '2b67ac300ac8b44368fb121637d1743cea8c5b6b' VARIANT = None @@ -12,4 +12,4 @@ CHANNEL = 'stable' ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.11.18' +_pkg_version = '2024.12.03' From 354cb4026cf2191e1a130ec2a627b95cabfbc60a Mon Sep 17 00:00:00 2001 From: wesson09 <49007620+wesson09@users.noreply.github.com> Date: Wed, 4 Dec 2024 18:41:58 +0100 Subject: [PATCH 14/21] [cookies] Add `--cookies-from-browser` support for MS Store Firefox (#11731) Authored by: wesson09 --- yt_dlp/cookies.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/yt_dlp/cookies.py b/yt_dlp/cookies.py index 772433b0f..fad323c90 100644 --- a/yt_dlp/cookies.py +++ b/yt_dlp/cookies.py @@ -195,7 +195,10 @@ def _extract_firefox_cookies(profile, container, logger): def _firefox_browser_dirs(): if sys.platform in ('cygwin', 'win32'): - yield os.path.expandvars(R'%APPDATA%\Mozilla\Firefox\Profiles') + yield from map(os.path.expandvars, ( + R'%APPDATA%\Mozilla\Firefox\Profiles', + R'%LOCALAPPDATA%\Packages\Mozilla.Firefox_n80bbvh6b1yt2\LocalCache\Roaming\Mozilla\Firefox\Profiles', + )) elif sys.platform == 'darwin': yield os.path.expanduser('~/Library/Application Support/Firefox/Profiles') From 2e49c789d3eebc39af8910705d65a98bca0e4c4f Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 4 Dec 2024 22:33:14 +0000 Subject: [PATCH 15/21] [ie/youtube] Player client maintenance (#11724) Closes #11686 Authored by: bashonly --- yt_dlp/extractor/youtube.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 41cd90db9..83dde7d9c 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -78,7 +78,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB', - 'clientVersion': '2.20240726.00.00', + 'clientVersion': '2.20241126.01.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, @@ -90,7 +90,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB', - 'clientVersion': '2.20240726.00.00', + 'clientVersion': '2.20241126.01.00', 'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)', }, }, @@ -102,7 +102,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_EMBEDDED_PLAYER', - 'clientVersion': '1.20240723.01.00', + 'clientVersion': '1.20241201.00.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 56, @@ -113,7 +113,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_REMIX', - 'clientVersion': '1.20240724.00.00', + 'clientVersion': '1.20241127.01.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, @@ -124,7 +124,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'WEB_CREATOR', - 'clientVersion': '1.20240723.03.00', + 'clientVersion': '1.20241203.01.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, @@ -257,7 +257,8 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'MWEB', - 'clientVersion': '2.20240726.01.00', + 'clientVersion': '2.20241202.07.00', + '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, @@ -267,7 +268,7 @@ INNERTUBE_CLIENTS = { 'INNERTUBE_CONTEXT': { 'client': { 'clientName': 'TVHTML5', - 'clientVersion': '7.20240724.13.00', + 'clientVersion': '7.20241201.18.00', }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 7, From fca3eb5f8be08d5fab2e18b45b7281a12e566725 Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Thu, 5 Dec 2024 12:11:55 +1300 Subject: [PATCH 16/21] [ie/bilibili] Fix HD formats extraction (#11734) Fixes dc1687648077c5bf64863b307ecc5ab7e029bd8d Closes #10554 Authored by: grqz --- yt_dlp/extractor/bilibili.py | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 91619d9d5..2db951a60 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -681,12 +681,6 @@ class BiliBiliIE(BilibiliBaseIE): old_video_id = format_field(aid, None, f'%s_part{part_id or 1}') cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid') - play_info = ( - traverse_obj( - self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None), - ('data', {dict})) - or self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1})) - festival_info = {} if is_festival: festival_info = traverse_obj(initial_state, { @@ -724,6 +718,13 @@ class BiliBiliIE(BilibiliBaseIE): duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})), __post_extractor=self.extract_comments(aid)) + play_info = None + if self.is_logged_in: + play_info = traverse_obj( + self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None), + ('data', {dict})) + if not play_info: + play_info = self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1}) formats = self.extract_formats(play_info) if video_data.get('is_upower_exclusive'): From 2feb28028ee48f2185d2d95076e62accb09b9e2e Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 6 Dec 2024 15:02:30 +0000 Subject: [PATCH 17/21] [ie/soundcloud] Fix formats extraction (#11742) Authored by: bashonly --- README.md | 2 +- yt_dlp/extractor/soundcloud.py | 98 +++++++++++++++------------------- 2 files changed, 43 insertions(+), 57 deletions(-) diff --git a/README.md b/README.md index 772395d24..1db4ed2a5 100644 --- a/README.md +++ b/README.md @@ -1860,7 +1860,7 @@ The following extractors use this feature: * `cdn`: One or more CDN IDs to use with the API call for stream URLs, e.g. `gcp_cdn`, `gs_cdn_pc_app`, `gs_cdn_mobile_web`, `gs_cdn_pc_web` #### soundcloud -* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3` +* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{codec}`, e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known codecs include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3` #### orfon (orf:on) * `prefer_segments_playlist`: Prefer a playlist of program segments instead of a single complete video when available. If individual segments are desired, use `--concat-playlist never --extractor-args "orfon:prefer_segments_playlist"` diff --git a/yt_dlp/extractor/soundcloud.py b/yt_dlp/extractor/soundcloud.py index 03089e98e..e0dda8ff8 100644 --- a/yt_dlp/extractor/soundcloud.py +++ b/yt_dlp/extractor/soundcloud.py @@ -7,7 +7,6 @@ from .common import InfoExtractor, SearchInfoExtractor from ..networking import HEADRequest from ..networking.exceptions import HTTPError from ..utils import ( - KNOWN_EXTENSIONS, ExtractorError, float_or_none, int_or_none, @@ -251,50 +250,15 @@ class SoundcloudBaseIE(InfoExtractor): def invalid_url(url): return not url or url in format_urls - def add_format(f, protocol, is_preview=False): - mobj = re.search(r'\.(?P\d+)\.(?P[0-9a-z]{3,4})(?=[/?])', stream_url) - if mobj: - for k, v in mobj.groupdict().items(): - if not f.get(k): - f[k] = v - format_id_list = [] - if protocol: - format_id_list.append(protocol) - ext = f.get('ext') - if ext == 'aac': - f.update({ - 'abr': 256, - 'quality': 5, - 'format_note': 'Premium', - }) - for k in ('ext', 'abr'): - v = str_or_none(f.get(k)) - if v: - format_id_list.append(v) - preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url']) - if preview: - format_id_list.append('preview') - abr = f.get('abr') - if abr: - f['abr'] = int(abr) - if protocol in ('hls', 'hls-aes'): - protocol = 'm3u8' if ext == 'aac' else 'm3u8_native' - else: - protocol = 'http' - f.update({ - 'format_id': '_'.join(format_id_list), - 'protocol': protocol, - 'preference': -10 if preview else None, - }) - formats.append(f) - # New API - for t in traverse_obj(info, ('media', 'transcodings', lambda _, v: url_or_none(v['url']))): + for t in traverse_obj(info, ('media', 'transcodings', lambda _, v: url_or_none(v['url']) and v['preset'])): if extract_flat: break format_url = t['url'] + preset = t['preset'] + preset_base = preset.partition('_')[0] - protocol = traverse_obj(t, ('format', 'protocol', {str})) + protocol = traverse_obj(t, ('format', 'protocol', {str})) or 'http' if protocol == 'progressive': protocol = 'http' if protocol != 'hls' and '/hls' in format_url: @@ -302,32 +266,54 @@ class SoundcloudBaseIE(InfoExtractor): if protocol == 'encrypted-hls' or '/encrypted-hls' in format_url: protocol = 'hls-aes' - ext = None - if preset := traverse_obj(t, ('preset', {str_or_none})): - ext = preset.split('_')[0] - if ext not in KNOWN_EXTENSIONS: - ext = mimetype2ext(traverse_obj(t, ('format', 'mime_type', {str}))) - - identifier = join_nonempty(protocol, ext, delim='_') - if not self._is_requested(identifier): - self.write_debug(f'"{identifier}" is not a requested format, skipping') + short_identifier = f'{protocol}_{preset_base}' + if preset_base == 'abr': + self.write_debug(f'Skipping broken "{short_identifier}" format') + continue + if not self._is_requested(short_identifier): + self.write_debug(f'"{short_identifier}" is not a requested format, skipping') continue # XXX: if not extract_flat, 429 error must be caught where _extract_info_dict is called stream_url = traverse_obj(self._call_api( - format_url, track_id, f'Downloading {identifier} format info JSON', + format_url, track_id, f'Downloading {short_identifier} format info JSON', query=query, headers=self._HEADERS), ('url', {url_or_none})) - if invalid_url(stream_url): continue format_urls.add(stream_url) - add_format({ + + mime_type = traverse_obj(t, ('format', 'mime_type', {str})) + codec = self._search_regex(r'codecs="([^"]+)"', mime_type, 'codec', default=None) + ext = { + 'mp4a': 'm4a', + 'opus': 'opus', + }.get(codec[:4] if codec else None) or mimetype2ext(mime_type, default=None) + if not ext or ext == 'm3u8': + ext = preset_base + + is_premium = t.get('quality') == 'hq' + abr = int_or_none( + self._search_regex(r'(\d+)k$', preset, 'abr', default=None) + or self._search_regex(r'\.(\d+)\.(?:opus|mp3)[/?]', stream_url, 'abr', default=None) + or (256 if (is_premium and 'aac' in preset) else None)) + + is_preview = (t.get('snipped') + or '/preview/' in format_url + or re.search(r'/(?:preview|playlist)/0/30/', stream_url)) + + formats.append({ + 'format_id': join_nonempty(protocol, preset, is_preview and 'preview', delim='_'), 'url': stream_url, 'ext': ext, - }, protocol, t.get('snipped') or '/preview/' in format_url) - - for f in formats: - f['vcodec'] = 'none' + 'acodec': codec, + 'vcodec': 'none', + 'abr': abr, + 'protocol': 'm3u8_native' if protocol in ('hls', 'hls-aes') else 'http', + 'container': 'm4a_dash' if ext == 'm4a' else None, + 'quality': 5 if is_premium else 0 if (abr and abr >= 160) else -1, + 'format_note': 'Premium' if is_premium else None, + 'preference': -10 if is_preview else None, + }) if not formats and info.get('policy') == 'BLOCK': self.raise_geo_restricted(metadata_available=True) From 4c85ccd1366c88cf93982f8350f58eed17355981 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 6 Dec 2024 15:34:13 +0000 Subject: [PATCH 18/21] [ie/youtube] Fix signature function extraction (#11751) Closes #11748 Authored by: bashonly --- test/test_youtube_signature.py | 5 +++++ yt_dlp/extractor/youtube.py | 17 ++++++++++++----- 2 files changed, 17 insertions(+), 5 deletions(-) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index 0f7ae34f4..56db096ca 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -68,6 +68,11 @@ _SIG_TESTS = [ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA', 'AOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL2QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0', ), + ( + 'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js', + '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA', + 'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA', + ), ] _NSIG_TESTS = [ diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 83dde7d9c..c9b831618 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3119,19 +3119,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self.to_screen('Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): + # Examples where `sig` is funcname: + # sig=function(a){a=a.split(""); ... ;return a.join("")}; + # ;c&&(c=sig(decodeURIComponent(c)),a.set(b,encodeURIComponent(c)));return a}; + # {var l=f,m=h.sp,n=sig(decodeURIComponent(h.s));l.set(m,encodeURIComponent(n))} + # sig=function(J){J=J.split(""); ... ;return J.join("")}; + # ;N&&(N=sig(decodeURIComponent(N)),J.set(R,encodeURIComponent(N)));return J}; + # {var H=u,k=f.sp,v=sig(decodeURIComponent(f.s));H.set(k,encodeURIComponent(v))} funcname = self._search_regex( - (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P[a-zA-Z0-9$]+)\(', + (r'\b(?P[a-zA-Z0-9$]+)&&\((?P=var)=(?P[a-zA-Z0-9$]{2,})\(decodeURIComponent\((?P=var)\)\)', + r'(?P[a-zA-Z0-9$]+)\s*=\s*function\(\s*(?P[a-zA-Z0-9$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)', + r'(?:\b|[^a-zA-Z0-9$])(?P[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?', + # Old patterns + r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P[a-zA-Z0-9$]+)\(', r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P[a-zA-Z0-9$]+)\(', r'\bm=(?P[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', - r'\bc&&\(c=(?P[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', - r'(?:\b|[^a-zA-Z0-9$])(?P[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?', - r'(?P[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', # Obsolete patterns r'("|\')signature\1\s*,\s*(?P[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P[a-zA-Z0-9$]+)\(', r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P[a-zA-Z0-9$]+)\(', r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P[a-zA-Z0-9$]+)\(', - r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P[a-zA-Z0-9$]+)\(', r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') From a95ee6d8803fca9157adecf63732ab58bf87fd88 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 6 Dec 2024 15:35:18 +0000 Subject: [PATCH 19/21] [ie/youtube] Fix `n` sig extraction for player `3bb1f723` (#11750) Closes #11744 Authored by: bashonly --- test/test_youtube_signature.py | 11 +++++++++-- yt_dlp/extractor/youtube.py | 15 +++++++++++---- 2 files changed, 20 insertions(+), 6 deletions(-) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index 56db096ca..2a99436a6 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -188,6 +188,10 @@ _NSIG_TESTS = [ 'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js', 'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw', ), + ( + 'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js', + 'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ', + ), ] @@ -259,8 +263,11 @@ def signature(jscode, sig_input): def n_sig(jscode, sig_input): - funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode) - return JSInterpreter(jscode).call_function(funcname, sig_input) + ie = YoutubeIE(FakeYDL()) + funcname = ie._extract_n_function_name(jscode) + jsi = JSInterpreter(jscode) + func = jsi.extract_function_from_code(*ie._fixup_n_function_code(*jsi.extract_function_code(funcname))) + return func([sig_input]) make_sig_test = t_factory( diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index c9b831618..2b026ef05 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3212,6 +3212,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("") # * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("") # * a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("") + # * J.J="";J.url="";J.Z&&(R="nn"[+J.Z],mW(J),N=J.K[R]||null)&&(N=narray[idx](N),J.set(R,N))}}; funcname, idx = self._search_regex( r'''(?x) (?: @@ -3228,7 +3229,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): )\)&&\(c=| \b(?P[a-zA-Z0-9_$]+)= )(?P[a-zA-Z0-9_$]+)(?:\[(?P\d+)\])?\([a-zA-Z]\) - (?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''', + (?(var),[a-zA-Z0-9_$]+\.set\((?:"n+"|[a-zA-Z0-9_$]+)\,(?P=var)\))''', jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None)) if not funcname: self.report_warning(join_nonempty( @@ -3237,7 +3238,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return self._search_regex( r'''(?xs) ;\s*(?P[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\) - \s*\{(?:(?!};).)+?["']enhanced_except_''', + \s*\{(?:(?!};).)+?return\s*(?P["'])[\w-]+_w8_(?P=q)\s*\+\s*[a-zA-Z0-9_$]+''', jscode, 'Initial JS player n function name', group='name') elif not idx: return funcname @@ -3246,6 +3247,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode, f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)] + def _fixup_n_function_code(self, argnames, code): + return argnames, re.sub( + rf';\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(["\'])undefined\1\s*\)\s*return\s+{argnames[0]};', + ';', code) + def _extract_n_function_code(self, video_id, player_url): player_id = self._extract_player_info(player_url) func_code = self.cache.load('youtube-nsig', player_id, min_ver='2024.07.09') @@ -3257,7 +3263,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): func_name = self._extract_n_function_name(jscode, player_url=player_url) - func_code = jsi.extract_function_code(func_name) + # XXX: Workaround for the `typeof` gotcha + func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name)) self.cache.store('youtube-nsig', player_id, func_code) return jsi, player_id, func_code @@ -3273,7 +3280,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): except Exception as e: raise JSInterpreter.Exception(traceback.format_exc(), cause=e) - if ret.startswith('enhanced_except_'): + if ret.startswith('enhanced_except_') or ret.endswith(f'_w8_{s}'): raise JSInterpreter.Exception('Signature function returned an exception') return ret From 4bd2655398aed450456197a6767639114a24eac2 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 6 Dec 2024 15:58:44 +0000 Subject: [PATCH 20/21] [ie/youtube] Raise if `n` function returns input value (#11752) Improve a95ee6d8803fca9157adecf63732ab58bf87fd88 Authored by: bashonly --- yt_dlp/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 2b026ef05..e69373ba2 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3280,7 +3280,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): except Exception as e: raise JSInterpreter.Exception(traceback.format_exc(), cause=e) - if ret.startswith('enhanced_except_') or ret.endswith(f'_w8_{s}'): + if ret.startswith('enhanced_except_') or ret.endswith(s): raise JSInterpreter.Exception('Signature function returned an exception') return ret From 6fef824025b3c2f0ca8af7ac9fa04b10d09a3591 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Fri, 6 Dec 2024 16:07:07 +0000 Subject: [PATCH 21/21] Release 2024.12.06 Created by: bashonly :ci skip all --- CONTRIBUTORS | 1 + Changelog.md | 13 +++++++++++++ yt_dlp/version.py | 6 +++--- 3 files changed, 17 insertions(+), 3 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 8ee7fbffa..240197e8a 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -710,3 +710,4 @@ subrat-lima gitninja1234 jkruse xiaomac +wesson09 diff --git a/Changelog.md b/Changelog.md index c04e936b5..9dc905309 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,19 @@ # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.12.06 + +#### Core changes +- **cookies**: [Add `--cookies-from-browser` support for MS Store Firefox](https://github.com/yt-dlp/yt-dlp/commit/354cb4026cf2191e1a130ec2a627b95cabfbc60a) ([#11731](https://github.com/yt-dlp/yt-dlp/issues/11731)) by [wesson09](https://github.com/wesson09) + +#### Extractor changes +- **bilibili**: [Fix HD formats extraction](https://github.com/yt-dlp/yt-dlp/commit/fca3eb5f8be08d5fab2e18b45b7281a12e566725) ([#11734](https://github.com/yt-dlp/yt-dlp/issues/11734)) by [grqz](https://github.com/grqz) +- **soundcloud**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/2feb28028ee48f2185d2d95076e62accb09b9e2e) ([#11742](https://github.com/yt-dlp/yt-dlp/issues/11742)) by [bashonly](https://github.com/bashonly) +- **youtube** + - [Fix `n` sig extraction for player `3bb1f723`](https://github.com/yt-dlp/yt-dlp/commit/a95ee6d8803fca9157adecf63732ab58bf87fd88) ([#11750](https://github.com/yt-dlp/yt-dlp/issues/11750)) by [bashonly](https://github.com/bashonly) (With fixes in [4bd2655](https://github.com/yt-dlp/yt-dlp/commit/4bd2655398aed450456197a6767639114a24eac2)) + - [Fix signature function extraction](https://github.com/yt-dlp/yt-dlp/commit/4c85ccd1366c88cf93982f8350f58eed17355981) ([#11751](https://github.com/yt-dlp/yt-dlp/issues/11751)) by [bashonly](https://github.com/bashonly) + - [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/2e49c789d3eebc39af8910705d65a98bca0e4c4f) ([#11724](https://github.com/yt-dlp/yt-dlp/issues/11724)) by [bashonly](https://github.com/bashonly) + ### 2024.12.03 #### Core changes diff --git a/yt_dlp/version.py b/yt_dlp/version.py index b7d5c57bf..3dec228d3 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.12.03' +__version__ = '2024.12.06' -RELEASE_GIT_HEAD = '2b67ac300ac8b44368fb121637d1743cea8c5b6b' +RELEASE_GIT_HEAD = '4bd2655398aed450456197a6767639114a24eac2' VARIANT = None @@ -12,4 +12,4 @@ CHANNEL = 'stable' ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.12.03' +_pkg_version = '2024.12.06'