From f4f9f6d00edcac6d4eb2b3fb78bf81326235d492 Mon Sep 17 00:00:00 2001 From: sepro <4618135+seproDev@users.noreply.github.com> Date: Fri, 8 Mar 2024 23:36:41 +0100 Subject: [PATCH] [cleanup] Fix infodict returned fields (#8906) Authored by: seproDev --- README.md | 10 +++- yt_dlp/extractor/abc.py | 3 -- yt_dlp/extractor/abematv.py | 2 +- yt_dlp/extractor/acfun.py | 7 +-- yt_dlp/extractor/archiveorg.py | 13 ++--- yt_dlp/extractor/axs.py | 8 ++-- yt_dlp/extractor/beeg.py | 7 +-- yt_dlp/extractor/bellmedia.py | 2 +- yt_dlp/extractor/bfmtv.py | 1 - yt_dlp/extractor/bitchute.py | 1 - yt_dlp/extractor/bleacherreport.py | 7 +-- yt_dlp/extractor/ceskatelevize.py | 2 +- yt_dlp/extractor/cgtn.py | 18 ++++--- yt_dlp/extractor/chingari.py | 8 ---- yt_dlp/extractor/cnbc.py | 10 ++-- yt_dlp/extractor/common.py | 2 +- yt_dlp/extractor/cpac.py | 2 +- yt_dlp/extractor/crunchyroll.py | 12 ++--- yt_dlp/extractor/cybrary.py | 4 +- yt_dlp/extractor/damtomo.py | 1 - yt_dlp/extractor/daum.py | 10 ++-- yt_dlp/extractor/duoplay.py | 6 +-- yt_dlp/extractor/eplus.py | 1 - yt_dlp/extractor/funimation.py | 6 +-- yt_dlp/extractor/gab.py | 1 - yt_dlp/extractor/gamejolt.py | 11 ++--- yt_dlp/extractor/gaskrank.py | 1 - yt_dlp/extractor/hotstar.py | 16 +++---- yt_dlp/extractor/hungama.py | 1 - yt_dlp/extractor/hypergryph.py | 4 +- yt_dlp/extractor/lbry.py | 1 - yt_dlp/extractor/likee.py | 10 ---- yt_dlp/extractor/megaphone.py | 8 ++-- yt_dlp/extractor/musicdex.py | 20 ++++---- yt_dlp/extractor/nekohacker.py | 4 -- yt_dlp/extractor/niconico.py | 2 - yt_dlp/extractor/ninecninemedia.py | 6 +-- yt_dlp/extractor/novaplay.py | 2 - yt_dlp/extractor/ondemandkorea.py | 7 +-- yt_dlp/extractor/orf.py | 1 - yt_dlp/extractor/peekvids.py | 2 - yt_dlp/extractor/pladform.py | 1 - yt_dlp/extractor/planetmarathi.py | 1 - yt_dlp/extractor/podchaser.py | 4 +- yt_dlp/extractor/pr0gramm.py | 23 +++++---- yt_dlp/extractor/prankcast.py | 6 +-- yt_dlp/extractor/radiocomercial.py | 14 ++++-- yt_dlp/extractor/radlive.py | 4 -- yt_dlp/extractor/rcti.py | 8 ++-- yt_dlp/extractor/rokfin.py | 13 +++-- yt_dlp/extractor/rumble.py | 1 - yt_dlp/extractor/rutube.py | 8 ++-- yt_dlp/extractor/sbs.py | 2 - yt_dlp/extractor/skeb.py | 10 ++-- yt_dlp/extractor/stageplus.py | 16 +++---- yt_dlp/extractor/steam.py | 18 +++---- yt_dlp/extractor/tenplay.py | 5 +- yt_dlp/extractor/tiktok.py | 77 +++++++++++++++++------------- yt_dlp/extractor/tnaflix.py | 1 - yt_dlp/extractor/truth.py | 1 - yt_dlp/extractor/tv2hu.py | 3 -- yt_dlp/extractor/tver.py | 2 - yt_dlp/extractor/videofyme.py | 4 +- yt_dlp/extractor/viewlift.py | 2 - yt_dlp/extractor/vimeo.py | 1 - yt_dlp/extractor/vk.py | 2 +- yt_dlp/extractor/vvvvid.py | 2 - yt_dlp/extractor/wdr.py | 1 - yt_dlp/extractor/ximalaya.py | 8 ++-- yt_dlp/extractor/xinpianchang.py | 13 ++--- yt_dlp/extractor/yle_areena.py | 4 -- yt_dlp/extractor/youku.py | 2 +- yt_dlp/extractor/younow.py | 5 +- yt_dlp/extractor/zingmp3.py | 2 - 74 files changed, 230 insertions(+), 274 deletions(-) diff --git a/README.md b/README.md index 3f92a8136..99235220a 100644 --- a/README.md +++ b/README.md @@ -1310,6 +1310,8 @@ # OUTPUT TEMPLATE - `description` (string): The description of the video - `display_id` (string): An alternative identifier for the video - `uploader` (string): Full name of the video uploader + - `uploader_id` (string): Nickname or id of the video uploader + - `uploader_url` (string): URL to the video uploader's profile - `license` (string): License name the video is licensed under - `creators` (list): The creators of the video - `creator` (string): The creators of the video; comma-separated @@ -1320,9 +1322,9 @@ # OUTPUT TEMPLATE - `release_year` (numeric): Year (YYYY) when the video or album was released - `modified_timestamp` (numeric): UNIX timestamp of the moment the video was last modified - `modified_date` (string): The date (YYYYMMDD) when the video was last modified in UTC - - `uploader_id` (string): Nickname or id of the video uploader - `channel` (string): Full name of the channel the video is uploaded on - `channel_id` (string): Id of the channel + - `channel_url` (string): URL of the channel - `channel_follower_count` (numeric): Number of followers of the channel - `channel_is_verified` (boolean): Whether the channel is verified on the platform - `location` (string): Physical location where the video was filmed @@ -1362,7 +1364,10 @@ # OUTPUT TEMPLATE - `webpage_url_basename` (string): The basename of the webpage URL - `webpage_url_domain` (string): The domain of the webpage URL - `original_url` (string): The URL given by the user (or same as `webpage_url` for playlist entries) - + - `categories` (list): List of categories the video belongs to + - `tags` (list): List of tags assigned to the video + - `cast` (list): List of cast members + All the fields in [Filtering Formats](#filtering-formats) can also be used Available for the video that belongs to some logical chapter or section: @@ -1374,6 +1379,7 @@ # OUTPUT TEMPLATE Available for the video that is an episode of some series or programme: - `series` (string): Title of the series or programme the video episode belongs to + - `series_id` (string): Id of the series or programme the video episode belongs to - `season` (string): Title of the season the video episode belongs to - `season_number` (numeric): Number of the season the video episode belongs to - `season_id` (string): Id of the season the video episode belongs to diff --git a/yt_dlp/extractor/abc.py b/yt_dlp/extractor/abc.py index a7b614ca1..b21742281 100644 --- a/yt_dlp/extractor/abc.py +++ b/yt_dlp/extractor/abc.py @@ -245,7 +245,6 @@ class ABCIViewIE(InfoExtractor): 'episode_id': 'NC2203H039S00', 'season_number': 2022, 'season': 'Season 2022', - 'episode_number': None, 'episode': 'Locking Up Kids', 'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/nc/NC2203H039S00_636d8a0944a22_1920.jpg', 'timestamp': 1668460497, @@ -271,8 +270,6 @@ class ABCIViewIE(InfoExtractor): 'episode_id': 'RF2004Q043S00', 'season_number': 2021, 'season': 'Season 2021', - 'episode_number': None, - 'episode': None, 'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/rf/RF2004Q043S00_61a950639dbc0_1920.jpg', 'timestamp': 1638710705, diff --git a/yt_dlp/extractor/abematv.py b/yt_dlp/extractor/abematv.py index 6453dde97..6742f75d5 100644 --- a/yt_dlp/extractor/abematv.py +++ b/yt_dlp/extractor/abematv.py @@ -259,7 +259,7 @@ class AbemaTVIE(AbemaTVBaseIE): 'title': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】', 'series': 'ゆるキャン△ SEASON２', 'episode': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】', - 'series_number': 2, + 'season_number': 2, 'episode_number': 1, 'description': 'md5:9c5a3172ae763278f9303922f0ea5b17', }, diff --git a/yt_dlp/extractor/acfun.py b/yt_dlp/extractor/acfun.py index dc5792944..c3b4f432e 100644 --- a/yt_dlp/extractor/acfun.py +++ b/yt_dlp/extractor/acfun.py @@ -3,6 +3,7 @@ float_or_none, format_field, int_or_none, + str_or_none, traverse_obj, parse_codecs, parse_qs, @@ -129,7 +130,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE): 'title': '红孩儿之趴趴蛙寻石记 第5话 ', 'duration': 760.0, 'season': '红孩儿之趴趴蛙寻石记', - 'season_id': 5023171, + 'season_id': '5023171', 'season_number': 1, # series has only 1 season 'episode': 'Episode 5', 'episode_number': 5, @@ -146,7 +147,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE): 'title': '叽歪老表（第二季） 第5话 坚不可摧', 'season': '叽歪老表（第二季）', 'season_number': 2, - 'season_id': 6065485, + 'season_id': '6065485', 'episode': '坚不可摧', 'episode_number': 5, 'upload_date': '20220324', @@ -191,7 +192,7 @@ def _real_extract(self, url): 'title': json_bangumi_data.get('showTitle'), 'thumbnail': json_bangumi_data.get('image'), 'season': json_bangumi_data.get('bangumiTitle'), - 'season_id': season_id, + 'season_id': str_or_none(season_id), 'season_number': season_number, 'episode': json_bangumi_data.get('title'), 'episode_number': episode_number, diff --git a/yt_dlp/extractor/archiveorg.py b/yt_dlp/extractor/archiveorg.py index c1bc1ba92..41f3a4ff2 100644 --- a/yt_dlp/extractor/archiveorg.py +++ b/yt_dlp/extractor/archiveorg.py @@ -31,6 +31,7 @@ unified_timestamp, url_or_none, urlhandle_detect_ext, + variadic, ) @@ -49,7 +50,7 @@ class ArchiveOrgIE(InfoExtractor): 'release_date': '19681210', 'timestamp': 1268695290, 'upload_date': '20100315', - 'creator': 'SRI International', + 'creators': ['SRI International'], 'uploader': 'laura@archive.org', 'thumbnail': r're:https://archive\.org/download/.*\.jpg', 'display_id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.cdr', @@ -109,7 +110,7 @@ class ArchiveOrgIE(InfoExtractor): 'title': 'Turning', 'ext': 'flac', 'track': 'Turning', - 'creator': 'Grateful Dead', + 'creators': ['Grateful Dead'], 'display_id': 'gd1977-05-08d01t01.flac', 'track_number': 1, 'album': '1977-05-08 - Barton Hall - Cornell University', @@ -129,7 +130,7 @@ class ArchiveOrgIE(InfoExtractor): 'location': 'Barton Hall - Cornell University', 'duration': 438.68, 'track': 'Deal', - 'creator': 'Grateful Dead', + 'creators': ['Grateful Dead'], 'album': '1977-05-08 - Barton Hall - Cornell University', 'release_date': '19770508', 'display_id': 'gd1977-05-08d01t07.flac', @@ -167,7 +168,7 @@ class ArchiveOrgIE(InfoExtractor): 'upload_date': '20160610', 'description': 'md5:f70956a156645a658a0dc9513d9e78b7', 'uploader': 'dimitrios@archive.org', - 'creator': ['British Broadcasting Corporation', 'Time-Life Films'], + 'creators': ['British Broadcasting Corporation', 'Time-Life Films'], 'timestamp': 1465594947, }, 'playlist': [ @@ -257,7 +258,7 @@ def _real_extract(self, url): 'title': m['title'], 'description': clean_html(m.get('description')), 'uploader': dict_get(m, ['uploader', 'adder']), - 'creator': m.get('creator'), + 'creators': traverse_obj(m, ('creator', {variadic}, {lambda x: x[0] and list(x)})), 'license': m.get('licenseurl'), 'release_date': unified_strdate(m.get('date')), 'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])), @@ -272,7 +273,7 @@ def _real_extract(self, url): 'title': f.get('title') or f['name'], 'display_id': f['name'], 'description': clean_html(f.get('description')), - 'creator': f.get('creator'), + 'creators': traverse_obj(f, ('creator', {variadic}, {lambda x: x[0] and list(x)})), 'duration': parse_duration(f.get('length')), 'track_number': int_or_none(f.get('track')), 'album': f.get('album'), diff --git a/yt_dlp/extractor/axs.py b/yt_dlp/extractor/axs.py index 4b263725f..7e9166771 100644 --- a/yt_dlp/extractor/axs.py +++ b/yt_dlp/extractor/axs.py @@ -24,7 +24,8 @@ class AxsIE(InfoExtractor): 'timestamp': 1685729564, 'duration': 1284.216, 'series': 'Rock & Roll Road Trip with Sammy Hagar', - 'season': 2, + 'season': 'Season 2', + 'season_number': 2, 'episode': '3', 'thumbnail': 'https://images.dotstudiopro.com/5f4e9d330a0c3b295a7e8394', }, @@ -41,7 +42,8 @@ class AxsIE(InfoExtractor): 'timestamp': 1676403615, 'duration': 2570.668, 'series': 'The Big Interview with Dan Rather', - 'season': 3, + 'season': 'Season 3', + 'season_number': 3, 'episode': '5', 'thumbnail': 'https://images.dotstudiopro.com/5f4d1901f340b50d937cec32', }, @@ -77,7 +79,7 @@ def _real_extract(self, url): 'title': ('title', {str}), 'description': ('description', {str}), 'series': ('seriestitle', {str}), - 'season': ('season', {int}), + 'season_number': ('season', {int}), 'episode': ('episode', {str}), 'duration': ('duration', {float_or_none}), 'timestamp': ('updated_at', {parse_iso8601}), diff --git a/yt_dlp/extractor/beeg.py b/yt_dlp/extractor/beeg.py index 52ee68eca..042b3220b 100644 --- a/yt_dlp/extractor/beeg.py +++ b/yt_dlp/extractor/beeg.py @@ -2,6 +2,7 @@ from ..utils import ( int_or_none, + str_or_none, traverse_obj, try_get, unified_timestamp, @@ -22,7 +23,7 @@ class BeegIE(InfoExtractor): 'age_limit': 18, 'upload_date': '20220131', 'timestamp': 1643656455, - 'display_id': 2540839, + 'display_id': '2540839', } }, { 'url': 'https://beeg.com/-0599050563103750?t=4-861', @@ -36,7 +37,7 @@ class BeegIE(InfoExtractor): 'age_limit': 18, 'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9', 'timestamp': 1643623200, - 'display_id': 2569965, + 'display_id': '2569965', 'upload_date': '20220131', } }, { @@ -78,7 +79,7 @@ def _real_extract(self, url): return { 'id': video_id, - 'display_id': first_fact.get('id'), + 'display_id': str_or_none(first_fact.get('id')), 'title': traverse_obj(video, ('file', 'stuff', 'sf_name')), 'description': traverse_obj(video, ('file', 'stuff', 'sf_story')), 'timestamp': unified_timestamp(first_fact.get('fc_created')), diff --git a/yt_dlp/extractor/bellmedia.py b/yt_dlp/extractor/bellmedia.py index 5ae4b917a..677680b42 100644 --- a/yt_dlp/extractor/bellmedia.py +++ b/yt_dlp/extractor/bellmedia.py @@ -32,7 +32,7 @@ class BellMediaIE(InfoExtractor): 'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3', 'upload_date': '20180525', 'timestamp': 1527288600, - 'season_id': 73997, + 'season_id': '73997', 'season': '2018', 'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg', 'tags': [], diff --git a/yt_dlp/extractor/bfmtv.py b/yt_dlp/extractor/bfmtv.py index 5d0c73ff3..c4621ca82 100644 --- a/yt_dlp/extractor/bfmtv.py +++ b/yt_dlp/extractor/bfmtv.py @@ -93,7 +93,6 @@ class BFMTVArticleIE(BFMTVBaseIE): 'id': '6318445464112', 'ext': 'mp4', 'title': 'Le plein de bioéthanol fait de plus en plus mal à la pompe', - 'description': None, 'uploader_id': '876630703001', 'upload_date': '20230110', 'timestamp': 1673341692, diff --git a/yt_dlp/extractor/bitchute.py b/yt_dlp/extractor/bitchute.py index 41367c5b9..194bf1f46 100644 --- a/yt_dlp/extractor/bitchute.py +++ b/yt_dlp/extractor/bitchute.py @@ -185,7 +185,6 @@ class BitChuteChannelIE(InfoExtractor): 'info_dict': { 'id': 'UGlrF9o9b-Q', 'ext': 'mp4', - 'filesize': None, 'title': 'This is the first video on #BitChute !', 'description': 'md5:a0337e7b1fe39e32336974af8173a034', 'thumbnail': r're:^https?://.*\.jpg$', diff --git a/yt_dlp/extractor/bleacherreport.py b/yt_dlp/extractor/bleacherreport.py index 5e5155af2..12630fb86 100644 --- a/yt_dlp/extractor/bleacherreport.py +++ b/yt_dlp/extractor/bleacherreport.py @@ -4,6 +4,7 @@ ExtractorError, int_or_none, parse_iso8601, + str_or_none, ) @@ -16,7 +17,7 @@ class BleacherReportIE(InfoExtractor): 'id': '2496438', 'ext': 'mp4', 'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?', - 'uploader_id': 3992341, + 'uploader_id': '3992341', 'description': 'CFB, ACC, Florida State', 'timestamp': 1434380212, 'upload_date': '20150615', @@ -33,7 +34,7 @@ class BleacherReportIE(InfoExtractor): 'timestamp': 1446839961, 'uploader': 'Sean Fay', 'description': 'md5:b1601e2314c4d8eec23b6eafe086a757', - 'uploader_id': 6466954, + 'uploader_id': '6466954', 'upload_date': '20151011', }, 'add_ie': ['Youtube'], @@ -58,7 +59,7 @@ def _real_extract(self, url): 'id': article_id, 'title': article_data['title'], 'uploader': article_data.get('author', {}).get('name'), - 'uploader_id': article_data.get('authorId'), + 'uploader_id': str_or_none(article_data.get('authorId')), 'timestamp': parse_iso8601(article_data.get('createdAt')), 'thumbnails': thumbnails, 'comment_count': int_or_none(article_data.get('commentsCount')), diff --git a/yt_dlp/extractor/ceskatelevize.py b/yt_dlp/extractor/ceskatelevize.py index 8390160a0..156b6a324 100644 --- a/yt_dlp/extractor/ceskatelevize.py +++ b/yt_dlp/extractor/ceskatelevize.py @@ -51,7 +51,7 @@ class CeskaTelevizeIE(InfoExtractor): 'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/', 'only_matching': True, 'info_dict': { - 'id': 402, + 'id': '402', 'ext': 'mp4', 'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$', 'is_live': True, diff --git a/yt_dlp/extractor/cgtn.py b/yt_dlp/extractor/cgtn.py index aaafa02d1..5d9d9bcde 100644 --- a/yt_dlp/extractor/cgtn.py +++ b/yt_dlp/extractor/cgtn.py @@ -17,6 +17,7 @@ class CGTNIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1615295940, 'upload_date': '20210309', + 'categories': ['Video'], }, 'params': { 'skip_download': True @@ -29,8 +30,8 @@ class CGTNIE(InfoExtractor): 'title': 'China, Indonesia vow to further deepen maritime cooperation', 'thumbnail': r're:^https?://.*\.png$', 'description': 'China and Indonesia vowed to upgrade their cooperation into the maritime sector and also for political security, economy, and cultural and people-to-people exchanges.', - 'author': 'CGTN', - 'category': 'China', + 'creators': ['CGTN'], + 'categories': ['China'], 'timestamp': 1622950200, 'upload_date': '20210606', }, @@ -45,7 +46,12 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) download_url = self._html_search_regex(r'data-video ="(?P.+m3u8)"', webpage, 'download_url') - datetime_str = self._html_search_regex(r'\s*(.+?)\s*', webpage, 'datetime_str', fatal=False) + datetime_str = self._html_search_regex( + r'\s*(.+?)\s*', webpage, 'datetime_str', fatal=False) + category = self._html_search_regex( + r'\s*(.+?)\s*', webpage, 'category', fatal=False) + author = self._search_regex( + r'
\s*(.+?)\s*
', webpage, 'author', default=None) return { 'id': video_id, @@ -53,9 +59,7 @@ def _real_extract(self, url): 'description': self._og_search_description(webpage, default=None), 'thumbnail': self._og_search_thumbnail(webpage), 'formats': self._extract_m3u8_formats(download_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'), - 'category': self._html_search_regex(r'\s*(.+?)\s*', - webpage, 'category', fatal=False), - 'author': self._html_search_regex(r'
\s*(.+?)\s*
', - webpage, 'author', default=None, fatal=False), + 'categories': [category] if category else None, + 'creators': [author] if author else None, 'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600), } diff --git a/yt_dlp/extractor/chingari.py b/yt_dlp/extractor/chingari.py index 48091dd65..fd194482e 100644 --- a/yt_dlp/extractor/chingari.py +++ b/yt_dlp/extractor/chingari.py @@ -84,8 +84,6 @@ class ChingariIE(ChingariBaseIE): 'uploader_id': '5f0403982c8bd344f4813f8c', 'uploader': 'ISKCON,Inc.', 'uploader_url': 'https://chingari.io/iskcon,inc', - 'track': None, - 'artist': None, }, 'params': {'skip_download': True} }] @@ -125,8 +123,6 @@ class ChingariUserIE(ChingariBaseIE): 'uploader_id': '5efc4b12cca35c3d1794c2d3', 'uploader': 'dada (girish) dhawale', 'uploader_url': 'https://chingari.io/dada1023', - 'track': None, - 'artist': None }, 'params': {'skip_download': True} }, { @@ -147,8 +143,6 @@ class ChingariUserIE(ChingariBaseIE): 'uploader_id': '5efc4b12cca35c3d1794c2d3', 'uploader': 'dada (girish) dhawale', 'uploader_url': 'https://chingari.io/dada1023', - 'track': None, - 'artist': None }, 'params': {'skip_download': True} }, { @@ -169,8 +163,6 @@ class ChingariUserIE(ChingariBaseIE): 'uploader_id': '5efc4b12cca35c3d1794c2d3', 'uploader': 'dada (girish) dhawale', 'uploader_url': 'https://chingari.io/dada1023', - 'track': None, - 'artist': None }, 'params': {'skip_download': True} }], diff --git a/yt_dlp/extractor/cnbc.py b/yt_dlp/extractor/cnbc.py index b8ce2b49a..cedfd3ef9 100644 --- a/yt_dlp/extractor/cnbc.py +++ b/yt_dlp/extractor/cnbc.py @@ -21,7 +21,7 @@ class CNBCVideoIE(InfoExtractor): 'modified_date': '20231208', 'release_date': '20231207', 'duration': 65, - 'author': 'Sean Conlon', + 'creators': ['Sean Conlon'], 'title': 'Here\'s a first look at McDonald\'s new spinoff brand, CosMc\'s', 'thumbnail': 'https://image.cnbcfm.com/api/v1/image/107344192-1701894812493-CosMcsskyHero_2336x1040_hero-desktop.jpg?v=1701894855', }, @@ -29,7 +29,7 @@ class CNBCVideoIE(InfoExtractor): }, { 'url': 'https://www.cnbc.com/video/2023/12/08/jim-cramer-shares-his-take-on-seattles-tech-scene.html', 'info_dict': { - 'author': 'Jim Cramer', + 'creators': ['Jim Cramer'], 'channel': 'Mad Money with Jim Cramer', 'description': 'md5:72925be21b952e95eba51178dddf4e3e', 'duration': 299.0, @@ -49,7 +49,7 @@ class CNBCVideoIE(InfoExtractor): }, { 'url': 'https://www.cnbc.com/video/2023/12/08/the-epicenter-of-ai-is-in-seattle-says-jim-cramer.html', 'info_dict': { - 'author': 'Jim Cramer', + 'creators': ['Jim Cramer'], 'channel': 'Mad Money with Jim Cramer', 'description': 'md5:72925be21b952e95eba51178dddf4e3e', 'duration': 113.0, @@ -86,12 +86,12 @@ def _real_extract(self, url): 'id': ('id', {str_or_none}), 'title': ('title', {str}), 'description': ('description', {str}), - 'author': ('author', ..., 'name', {str}), + 'creators': ('author', ..., 'name', {str}), 'timestamp': ('datePublished', {parse_iso8601}), 'release_timestamp': ('uploadDate', {parse_iso8601}), 'modified_timestamp': ('dateLastPublished', {parse_iso8601}), 'thumbnail': ('thumbnail', {url_or_none}), 'duration': ('duration', {int_or_none}), 'channel': ('section', 'title', {str}), - }, get_all=False), + }), } diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index a85064636..f57963da2 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -262,7 +262,7 @@ class InfoExtractor: direct: True if a direct video file was given (must only be set by GenericIE) alt_title: A secondary title of the video. - display_id An alternative identifier for the video, not necessarily + display_id: An alternative identifier for the video, not necessarily unique, but available before title. Typically, id is something like "4234987", title "Dancing naked mole rats", and display_id "dancing-naked-mole-rats" diff --git a/yt_dlp/extractor/cpac.py b/yt_dlp/extractor/cpac.py index 0f23f2be2..32bba1e5a 100644 --- a/yt_dlp/extractor/cpac.py +++ b/yt_dlp/extractor/cpac.py @@ -65,7 +65,7 @@ def is_live(v_type): 'title': title, 'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))), 'timestamp': unified_timestamp(content['details'].get('liveDateTime')), - 'category': [category] if category else None, + 'categories': [category] if category else None, 'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))), 'is_live': is_live(content['details'].get('type')), } diff --git a/yt_dlp/extractor/crunchyroll.py b/yt_dlp/extractor/crunchyroll.py index ee34aced5..8d997debf 100644 --- a/yt_dlp/extractor/crunchyroll.py +++ b/yt_dlp/extractor/crunchyroll.py @@ -514,7 +514,7 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE): 'track': 'Egaono Hana', 'artist': 'Goose house', 'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$', - 'genre': ['J-Pop'], + 'genres': ['J-Pop'], }, 'params': {'skip_download': 'm3u8'}, }, { @@ -527,7 +527,7 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE): 'track': 'Crossing Field', 'artist': 'LiSA', 'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$', - 'genre': ['Anime'], + 'genres': ['Anime'], }, 'params': {'skip_download': 'm3u8'}, }, { @@ -541,7 +541,7 @@ class CrunchyrollMusicIE(CrunchyrollBaseIE): 'artist': 'LiSA', 'thumbnail': r're:(?i)^https://www.crunchyroll.com/imgsrv/.*\.jpeg?$', 'description': 'md5:747444e7e6300907b7a43f0a0503072e', - 'genre': ['J-Pop'], + 'genres': ['J-Pop'], }, 'params': {'skip_download': 'm3u8'}, }, { @@ -594,7 +594,7 @@ def _transform_music_response(data): 'width': ('width', {int_or_none}), 'height': ('height', {int_or_none}), }), - 'genre': ('genres', ..., 'displayValue'), + 'genres': ('genres', ..., 'displayValue'), 'age_limit': ('maturity_ratings', -1, {parse_age_limit}), }), } @@ -611,7 +611,7 @@ class CrunchyrollArtistIE(CrunchyrollBaseIE): 'info_dict': { 'id': 'MA179CB50D', 'title': 'LiSA', - 'genre': ['J-Pop', 'Anime', 'Rock'], + 'genres': ['J-Pop', 'Anime', 'Rock'], 'description': 'md5:16d87de61a55c3f7d6c454b73285938e', }, 'playlist_mincount': 83, @@ -645,6 +645,6 @@ def _transform_artist_response(data): 'width': ('width', {int_or_none}), 'height': ('height', {int_or_none}), }), - 'genre': ('genres', ..., 'displayValue'), + 'genres': ('genres', ..., 'displayValue'), }), } diff --git a/yt_dlp/extractor/cybrary.py b/yt_dlp/extractor/cybrary.py index c4c78ee1b..614d0cd9e 100644 --- a/yt_dlp/extractor/cybrary.py +++ b/yt_dlp/extractor/cybrary.py @@ -114,7 +114,7 @@ class CybraryCourseIE(CybraryBaseIE): _TESTS = [{ 'url': 'https://app.cybrary.it/browse/course/az-500-microsoft-azure-security-technologies', 'info_dict': { - 'id': 898, + 'id': '898', 'title': 'AZ-500: Microsoft Azure Security Technologies', 'description': 'md5:69549d379c0fc1dec92926d4e8b6fbd4' }, @@ -122,7 +122,7 @@ class CybraryCourseIE(CybraryBaseIE): }, { 'url': 'https://app.cybrary.it/browse/course/cybrary-orientation', 'info_dict': { - 'id': 1245, + 'id': '1245', 'title': 'Cybrary Orientation', 'description': 'md5:9e69ff66b32fe78744e0ad4babe2e88e' }, diff --git a/yt_dlp/extractor/damtomo.py b/yt_dlp/extractor/damtomo.py index 0e08e4f65..5e14d6aff 100644 --- a/yt_dlp/extractor/damtomo.py +++ b/yt_dlp/extractor/damtomo.py @@ -83,7 +83,6 @@ class DamtomoRecordIE(DamtomoBaseIE): 'info_dict': { 'id': '27376862', 'title': 'イカSUMMER [良音]', - 'description': None, 'uploader': 'ＮＡＮＡ', 'uploader_id': 'MzAyMDExNTY', 'upload_date': '20210721', diff --git a/yt_dlp/extractor/daum.py b/yt_dlp/extractor/daum.py index 3ef514065..24c520855 100644 --- a/yt_dlp/extractor/daum.py +++ b/yt_dlp/extractor/daum.py @@ -27,7 +27,7 @@ class DaumIE(DaumBaseIE): 'duration': 2117, 'view_count': int, 'comment_count': int, - 'uploader_id': 186139, + 'uploader_id': '186139', 'uploader': '콘간지', 'timestamp': 1387310323, }, @@ -44,7 +44,7 @@ class DaumIE(DaumBaseIE): 'view_count': int, 'comment_count': int, 'uploader': 'MBC 예능', - 'uploader_id': 132251, + 'uploader_id': '132251', 'timestamp': 1421604228, }, }, { @@ -63,7 +63,7 @@ class DaumIE(DaumBaseIE): 'view_count': int, 'comment_count': int, 'uploader': '까칠한 墮落始祖 황비홍님의', - 'uploader_id': 560824, + 'uploader_id': '560824', 'timestamp': 1203770745, }, }, { @@ -77,7 +77,7 @@ class DaumIE(DaumBaseIE): 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', 'upload_date': '20170129', 'uploader': '쇼! 음악중심', - 'uploader_id': 2653210, + 'uploader_id': '2653210', 'timestamp': 1485684628, }, }] @@ -107,7 +107,7 @@ class DaumClipIE(DaumBaseIE): 'duration': 3868, 'view_count': int, 'uploader': 'GOMeXP', - 'uploader_id': 6667, + 'uploader_id': '6667', 'timestamp': 1377911092, }, }, { diff --git a/yt_dlp/extractor/duoplay.py b/yt_dlp/extractor/duoplay.py index 7d3f39942..ebce0b5f2 100644 --- a/yt_dlp/extractor/duoplay.py +++ b/yt_dlp/extractor/duoplay.py @@ -32,7 +32,7 @@ class DuoplayIE(InfoExtractor): 'season_number': 2, 'episode': 'Operatsioon "Öö"', 'episode_number': 12, - 'episode_id': 24, + 'episode_id': '24', }, }, { 'note': 'Empty title', @@ -50,7 +50,7 @@ class DuoplayIE(InfoExtractor): 'series_id': '17', 'season': 'Season 2', 'season_number': 2, - 'episode_id': 14, + 'episode_id': '14', 'release_year': 2010, }, }, { @@ -99,6 +99,6 @@ def _real_extract(self, url): 'season_number': ('season_id', {int_or_none}), 'episode': 'subtitle', 'episode_number': ('episode_nr', {int_or_none}), - 'episode_id': ('episode_id', {int_or_none}), + 'episode_id': ('episode_id', {str_or_none}), }, get_all=False) if episode_attr.get('category') != 'movies' else {}), } diff --git a/yt_dlp/extractor/eplus.py b/yt_dlp/extractor/eplus.py index 6383691a1..88a8d5a94 100644 --- a/yt_dlp/extractor/eplus.py +++ b/yt_dlp/extractor/eplus.py @@ -42,7 +42,6 @@ class EplusIbIE(InfoExtractor): 'live_status': 'was_live', 'release_date': '20210719', 'release_timestamp': 1626703200, - 'description': None, }, 'params': { 'skip_download': True, diff --git a/yt_dlp/extractor/funimation.py b/yt_dlp/extractor/funimation.py index 41de85cc6..c32f005ba 100644 --- a/yt_dlp/extractor/funimation.py +++ b/yt_dlp/extractor/funimation.py @@ -301,7 +301,7 @@ class FunimationShowIE(FunimationBaseIE): _TESTS = [{ 'url': 'https://www.funimation.com/en/shows/sk8-the-infinity', 'info_dict': { - 'id': 1315000, + 'id': '1315000', 'title': 'SK8 the Infinity' }, 'playlist_count': 13, @@ -312,7 +312,7 @@ class FunimationShowIE(FunimationBaseIE): # without lang code 'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/', 'info_dict': { - 'id': 39643, + 'id': '39643', 'title': 'Ouran High School Host Club' }, 'playlist_count': 26, @@ -339,7 +339,7 @@ def _real_extract(self, url): return { '_type': 'playlist', - 'id': show_info['id'], + 'id': str_or_none(show_info['id']), 'title': show_info['name'], 'entries': orderedSet( self.url_result( diff --git a/yt_dlp/extractor/gab.py b/yt_dlp/extractor/gab.py index 5016e2ff9..f9d22fd33 100644 --- a/yt_dlp/extractor/gab.py +++ b/yt_dlp/extractor/gab.py @@ -19,7 +19,6 @@ class GabTVIE(InfoExtractor): 'id': '61217eacea5665de450d0488', 'ext': 'mp4', 'title': 'WHY WAS AMERICA IN AFGHANISTAN - AMERICA FIRST AGAINST AMERICAN OLIGARCHY', - 'description': None, 'uploader': 'Wurzelroot', 'uploader_id': '608fb0a85738fd1974984f7d', 'thumbnail': 'https://tv.gab.com/image/61217eacea5665de450d0488', diff --git a/yt_dlp/extractor/gamejolt.py b/yt_dlp/extractor/gamejolt.py index 8ec046bb3..4d57391ac 100644 --- a/yt_dlp/extractor/gamejolt.py +++ b/yt_dlp/extractor/gamejolt.py @@ -267,9 +267,9 @@ class GameJoltIE(GameJoltBaseIE): 'id': 'dszyjnwi', 'ext': 'webm', 'title': 'gif-presentacion-mejorado-dszyjnwi', - 'n_entries': 1, } - }] + }], + 'playlist_count': 1, }, { # Multiple GIFs 'url': 'https://gamejolt.com/p/gif-yhsqkumq', @@ -374,7 +374,6 @@ class GameJoltGameSoundtrackIE(GameJoltBaseIE): 'info_dict': { 'id': '657899', 'title': 'Friday Night Funkin\': Vs Oswald', - 'n_entries': None, }, 'playlist': [{ 'info_dict': { @@ -384,7 +383,6 @@ class GameJoltGameSoundtrackIE(GameJoltBaseIE): 'url': r're:^https://.+vs-oswald-menu-music\.mp3$', 'release_timestamp': 1635190816, 'release_date': '20211025', - 'n_entries': 3, } }, { 'info_dict': { @@ -394,7 +392,6 @@ class GameJoltGameSoundtrackIE(GameJoltBaseIE): 'url': r're:^https://.+rabbit-s-luck--full-version-\.mp3$', 'release_timestamp': 1635190841, 'release_date': '20211025', - 'n_entries': 3, } }, { 'info_dict': { @@ -404,9 +401,9 @@ class GameJoltGameSoundtrackIE(GameJoltBaseIE): 'url': r're:^https://.+last-straw\.mp3$', 'release_timestamp': 1635881104, 'release_date': '20211102', - 'n_entries': 3, } - }] + }], + 'playlist_count': 3, }] def _real_extract(self, url): diff --git a/yt_dlp/extractor/gaskrank.py b/yt_dlp/extractor/gaskrank.py index e0bbdae0a..bc56b03e3 100644 --- a/yt_dlp/extractor/gaskrank.py +++ b/yt_dlp/extractor/gaskrank.py @@ -21,7 +21,6 @@ class GaskrankIE(InfoExtractor): 'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden', 'uploader_id': 'Bikefun', 'upload_date': '20170110', - 'uploader_url': None, } }, { 'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm', diff --git a/yt_dlp/extractor/hotstar.py b/yt_dlp/extractor/hotstar.py index 541792b90..a3a3c20c9 100644 --- a/yt_dlp/extractor/hotstar.py +++ b/yt_dlp/extractor/hotstar.py @@ -115,11 +115,11 @@ class HotStarIE(HotStarBaseIE): 'upload_date': '20190501', 'duration': 1219, 'channel': 'StarPlus', - 'channel_id': 3, + 'channel_id': '3', 'series': 'Ek Bhram - Sarvagun Sampanna', 'season': 'Chapter 1', 'season_number': 1, - 'season_id': 6771, + 'season_id': '6771', 'episode': 'Janhvi Targets Suman', 'episode_number': 8, } @@ -135,12 +135,12 @@ class HotStarIE(HotStarBaseIE): 'channel': 'StarPlus', 'series': 'Anupama', 'season_number': 1, - 'season_id': 7399, + 'season_id': '7399', 'upload_date': '20230307', 'episode': 'Anupama, Anuj Share a Moment', 'episode_number': 853, 'duration': 1272, - 'channel_id': 3, + 'channel_id': '3', }, 'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes }, { @@ -155,12 +155,12 @@ class HotStarIE(HotStarBaseIE): 'channel': 'Hotstar Specials', 'series': 'Kana Kaanum Kaalangal', 'season_number': 1, - 'season_id': 9441, + 'season_id': '9441', 'upload_date': '20220421', 'episode': 'Back To School', 'episode_number': 1, 'duration': 1810, - 'channel_id': 54, + 'channel_id': '54', }, }, { 'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286', @@ -325,11 +325,11 @@ def _real_extract(self, url): 'formats': formats, 'subtitles': subs, 'channel': video_data.get('channelName'), - 'channel_id': video_data.get('channelId'), + 'channel_id': str_or_none(video_data.get('channelId')), 'series': video_data.get('showName'), 'season': video_data.get('seasonName'), 'season_number': int_or_none(video_data.get('seasonNo')), - 'season_id': video_data.get('seasonId'), + 'season_id': str_or_none(video_data.get('seasonId')), 'episode': video_data.get('title'), 'episode_number': int_or_none(video_data.get('episodeNo')), } diff --git a/yt_dlp/extractor/hungama.py b/yt_dlp/extractor/hungama.py index cdec36838..7da8aad7a 100644 --- a/yt_dlp/extractor/hungama.py +++ b/yt_dlp/extractor/hungama.py @@ -114,7 +114,6 @@ class HungamaSongIE(InfoExtractor): 'title': 'Lucky Ali - Kitni Haseen Zindagi', 'track': 'Kitni Haseen Zindagi', 'artist': 'Lucky Ali', - 'album': None, 'release_year': 2000, 'thumbnail': 'https://stat2.hungama.ind.in/assets/images/default_images/da-200x200.png', }, diff --git a/yt_dlp/extractor/hypergryph.py b/yt_dlp/extractor/hypergryph.py index 9ca6caebc..96e452a51 100644 --- a/yt_dlp/extractor/hypergryph.py +++ b/yt_dlp/extractor/hypergryph.py @@ -9,7 +9,7 @@ class MonsterSirenHypergryphMusicIE(InfoExtractor): 'info_dict': { 'id': '514562', 'ext': 'wav', - 'artist': ['塞壬唱片-MSR'], + 'artists': ['塞壬唱片-MSR'], 'album': 'Flame Shadow', 'title': 'Flame Shadow', } @@ -27,6 +27,6 @@ def _real_extract(self, url): 'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')), 'ext': 'wav', 'vcodec': 'none', - 'artist': traverse_obj(json_data, ('player', 'songDetail', 'artists')), + 'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)), 'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')) } diff --git a/yt_dlp/extractor/lbry.py b/yt_dlp/extractor/lbry.py index cc37c41e8..dcb44d07f 100644 --- a/yt_dlp/extractor/lbry.py +++ b/yt_dlp/extractor/lbry.py @@ -231,7 +231,6 @@ class LBRYIE(LBRYBaseIE): 'release_timestamp': int, 'release_date': str, 'tags': list, - 'duration': None, 'channel': 'RT', 'channel_id': 'fdd11cb3ab75f95efb7b3bc2d726aa13ac915b66', 'channel_url': 'https://odysee.com/@RT:fdd11cb3ab75f95efb7b3bc2d726aa13ac915b66', diff --git a/yt_dlp/extractor/likee.py b/yt_dlp/extractor/likee.py index 74ee2bea9..324463136 100644 --- a/yt_dlp/extractor/likee.py +++ b/yt_dlp/extractor/likee.py @@ -22,8 +22,6 @@ class LikeeIE(InfoExtractor): 'description': 'md5:9a7ebe816f0e78722ee5ed76f75983b4', 'thumbnail': r're:^https?://.+\.jpg', 'uploader': 'Huỳnh Hồng Quân ', - 'play_count': int, - 'download_count': int, 'artist': 'Huỳnh Hồng Quân ', 'timestamp': 1651571320, 'upload_date': '20220503', @@ -44,11 +42,9 @@ class LikeeIE(InfoExtractor): 'comment_count': int, 'like_count': int, 'uploader': 'Vương Phước Nhi', - 'download_count': int, 'timestamp': 1651506835, 'upload_date': '20220502', 'duration': 60024, - 'play_count': int, 'artist': 'Vương Phước Nhi', 'uploader_id': '649222262', 'view_count': int, @@ -65,9 +61,7 @@ class LikeeIE(InfoExtractor): 'duration': 9684, 'uploader_id': 'fernanda_rivasg', 'view_count': int, - 'play_count': int, 'artist': 'La Cami La✨', - 'download_count': int, 'like_count': int, 'uploader': 'Fernanda Rivas🎶', 'timestamp': 1614034308, @@ -83,13 +77,11 @@ class LikeeIE(InfoExtractor): 'thumbnail': r're:^https?://.+\.jpg', 'comment_count': int, 'duration': 18014, - 'play_count': int, 'view_count': int, 'timestamp': 1611694774, 'like_count': int, 'uploader': 'Fernanda Rivas🎶', 'uploader_id': 'fernanda_rivasg', - 'download_count': int, 'artist': 'ʟᴇʀɪᴋ_ᴜɴɪᴄᴏʀɴ♡︎', 'upload_date': '20210126', }, @@ -128,8 +120,6 @@ def _real_extract(self, url): 'description': info.get('share_desc'), 'view_count': int_or_none(info.get('video_count')), 'like_count': int_or_none(info.get('likeCount')), - 'play_count': int_or_none(info.get('play_count')), - 'download_count': int_or_none(info.get('download_count')), 'comment_count': int_or_none(info.get('comment_count')), 'uploader': str_or_none(info.get('nick_name')), 'uploader_id': str_or_none(info.get('likeeId')), diff --git a/yt_dlp/extractor/megaphone.py b/yt_dlp/extractor/megaphone.py index af80523e3..eb790e691 100644 --- a/yt_dlp/extractor/megaphone.py +++ b/yt_dlp/extractor/megaphone.py @@ -8,15 +8,15 @@ class MegaphoneIE(InfoExtractor): _VALID_URL = r'https://player\.megaphone\.fm/(?P[A-Z0-9]+)' _EMBED_REGEX = [rf']*?\ssrc=["\'](?P{_VALID_URL})'] _TEST = { - 'url': 'https://player.megaphone.fm/GLT9749789991?"', + 'url': 'https://player.megaphone.fm/GLT9749789991', 'md5': '4816a0de523eb3e972dc0dda2c191f96', 'info_dict': { 'id': 'GLT9749789991', 'ext': 'mp3', 'title': '#97 What Kind Of Idiot Gets Phished?', 'thumbnail': r're:^https://.*\.png.*$', - 'duration': 1776.26375, - 'author': 'Reply All', + 'duration': 1998.36, + 'creators': ['Reply All'], }, } @@ -40,7 +40,7 @@ def _real_extract(self, url): 'id': video_id, 'thumbnail': thumbnail, 'title': title, - 'author': author, + 'creators': [author] if author else None, 'duration': episode_data['duration'], 'formats': formats, } diff --git a/yt_dlp/extractor/musicdex.py b/yt_dlp/extractor/musicdex.py index 48f29702c..a86351458 100644 --- a/yt_dlp/extractor/musicdex.py +++ b/yt_dlp/extractor/musicdex.py @@ -17,11 +17,11 @@ def _return_info(self, track_json, album_json, id): 'track_number': track_json.get('number'), 'url': format_field(track_json, 'url', 'https://www.musicdex.org/%s'), 'duration': track_json.get('duration'), - 'genre': [genre.get('name') for genre in track_json.get('genres') or []], + 'genres': [genre.get('name') for genre in track_json.get('genres') or []], 'like_count': track_json.get('likes_count'), 'view_count': track_json.get('plays'), - 'artist': [artist.get('name') for artist in track_json.get('artists') or []], - 'album_artist': [artist.get('name') for artist in album_json.get('artists') or []], + 'artists': [artist.get('name') for artist in track_json.get('artists') or []], + 'album_artists': [artist.get('name') for artist in album_json.get('artists') or []], 'thumbnail': format_field(album_json, 'image', 'https://www.musicdex.org/%s'), 'album': album_json.get('name'), 'release_year': try_get(album_json, lambda x: date_from_str(unified_strdate(x['release_date'])).year), @@ -43,11 +43,11 @@ class MusicdexSongIE(MusicdexBaseIE): 'track': 'dual existence', 'track_number': 1, 'duration': 266000, - 'genre': ['Anime'], + 'genres': ['Anime'], 'like_count': int, 'view_count': int, - 'artist': ['fripSide'], - 'album_artist': ['fripSide'], + 'artists': ['fripSide'], + 'album_artists': ['fripSide'], 'thumbnail': 'https://www.musicdex.org/storage/album/9iDIam1DHTVqUG4UclFIEq1WAFGXfPW4y0TtZa91.png', 'album': 'To Aru Kagaku no Railgun T OP2 Single - dual existence', 'release_year': 2020 @@ -69,9 +69,9 @@ class MusicdexAlbumIE(MusicdexBaseIE): 'playlist_mincount': 28, 'info_dict': { 'id': '56', - 'genre': ['OST'], + 'genres': ['OST'], 'view_count': int, - 'artist': ['TENMON & Eiichiro Yanagi / minori'], + 'artists': ['TENMON & Eiichiro Yanagi / minori'], 'title': 'ef - a tale of memories Original Soundtrack 2 ~fortissimo~', 'release_year': 2008, 'thumbnail': 'https://www.musicdex.org/storage/album/2rSHkyYBYfB7sbvElpEyTMcUn6toY7AohOgJuDlE.jpg', @@ -88,9 +88,9 @@ def _real_extract(self, url): 'id': id, 'title': data_json.get('name'), 'description': data_json.get('description'), - 'genre': [genre.get('name') for genre in data_json.get('genres') or []], + 'genres': [genre.get('name') for genre in data_json.get('genres') or []], 'view_count': data_json.get('plays'), - 'artist': [artist.get('name') for artist in data_json.get('artists') or []], + 'artists': [artist.get('name') for artist in data_json.get('artists') or []], 'thumbnail': format_field(data_json, 'image', 'https://www.musicdex.org/%s'), 'release_year': try_get(data_json, lambda x: date_from_str(unified_strdate(x['release_date'])).year), 'entries': entries, diff --git a/yt_dlp/extractor/nekohacker.py b/yt_dlp/extractor/nekohacker.py index e10ffe925..24b66570e 100644 --- a/yt_dlp/extractor/nekohacker.py +++ b/yt_dlp/extractor/nekohacker.py @@ -118,7 +118,6 @@ class NekoHackerIE(InfoExtractor): 'artist': 'Neko Hacker', 'track': 'md5:1a5fcbc96ca3c3265b1c6f9f79f30fd0', 'track_number': 1, - 'duration': None } }, { @@ -136,7 +135,6 @@ class NekoHackerIE(InfoExtractor): 'artist': 'Neko Hacker', 'track': 'むじな de なじむ feat. 六科なじむ (CV: 日高里菜 )', 'track_number': 2, - 'duration': None } }, { @@ -154,7 +152,6 @@ class NekoHackerIE(InfoExtractor): 'artist': 'Neko Hacker', 'track': '進め！むじなカンパニー (instrumental)', 'track_number': 3, - 'duration': None } }, { @@ -172,7 +169,6 @@ class NekoHackerIE(InfoExtractor): 'artist': 'Neko Hacker', 'track': 'むじな de なじむ (instrumental)', 'track_number': 4, - 'duration': None } } ] diff --git a/yt_dlp/extractor/niconico.py b/yt_dlp/extractor/niconico.py index 5383d71ec..6a4624602 100644 --- a/yt_dlp/extractor/niconico.py +++ b/yt_dlp/extractor/niconico.py @@ -163,8 +163,6 @@ class NiconicoIE(InfoExtractor): 'description': 'md5:15df8988e47a86f9e978af2064bf6d8e', 'timestamp': 1341128008, 'upload_date': '20120701', - 'uploader': None, - 'uploader_id': None, 'thumbnail': r're:https?://.*', 'duration': 5271, 'view_count': int, diff --git a/yt_dlp/extractor/ninecninemedia.py b/yt_dlp/extractor/ninecninemedia.py index 31df42f4f..579370f1b 100644 --- a/yt_dlp/extractor/ninecninemedia.py +++ b/yt_dlp/extractor/ninecninemedia.py @@ -3,6 +3,7 @@ float_or_none, int_or_none, parse_iso8601, + str_or_none, try_get, ) @@ -73,7 +74,7 @@ def _real_extract(self, url): 'episode_number': int_or_none(content.get('Episode')), 'season': season.get('Name'), 'season_number': int_or_none(season.get('Number')), - 'season_id': season.get('Id'), + 'season_id': str_or_none(season.get('Id')), 'series': try_get(content, lambda x: x['Media']['Name']), 'tags': tags, 'categories': categories, @@ -109,10 +110,9 @@ class CPTwentyFourIE(InfoExtractor): 'title': 'WATCH: Truck rips ATM from Mississauga business', 'description': 'md5:cf7498480885f080a754389a2b2f7073', 'timestamp': 1637618377, - 'episode_number': None, 'season': 'Season 0', 'season_number': 0, - 'season_id': 57974, + 'season_id': '57974', 'series': 'CTV News Toronto', 'duration': 26.86, 'thumbnail': 'http://images2.9c9media.com/image_asset/2014_11_5_2eb609a0-475b-0132-fbd6-34b52f6f1279_jpg_2000x1125.jpg', diff --git a/yt_dlp/extractor/novaplay.py b/yt_dlp/extractor/novaplay.py index d8849cd88..77ae03fd0 100644 --- a/yt_dlp/extractor/novaplay.py +++ b/yt_dlp/extractor/novaplay.py @@ -18,7 +18,6 @@ class NovaPlayIE(InfoExtractor): 'upload_date': '20220722', 'thumbnail': 'https://nbg-img.fite.tv/img/606627_460x260.jpg', 'description': '29 сек', - 'view_count': False }, }, { @@ -34,7 +33,6 @@ class NovaPlayIE(InfoExtractor): 'upload_date': '20220722', 'thumbnail': 'https://nbg-img.fite.tv/img/606609_460x260.jpg', 'description': '29 сек', - 'view_count': False }, } ] diff --git a/yt_dlp/extractor/ondemandkorea.py b/yt_dlp/extractor/ondemandkorea.py index 94fcac720..591b4147e 100644 --- a/yt_dlp/extractor/ondemandkorea.py +++ b/yt_dlp/extractor/ondemandkorea.py @@ -11,6 +11,7 @@ join_nonempty, parse_age_limit, parse_qs, + str_or_none, unified_strdate, url_or_none, ) @@ -32,7 +33,7 @@ class OnDemandKoreaIE(InfoExtractor): 'duration': 5486.955, 'release_date': '20220924', 'series': 'Ask Us Anything', - 'series_id': 11790, + 'series_id': '11790', 'episode_number': 351, 'episode': 'Jung Sung-ho, Park Seul-gi, Kim Bo-min, Yang Seung-won', }, @@ -47,7 +48,7 @@ class OnDemandKoreaIE(InfoExtractor): 'duration': 1586.0, 'release_date': '20231001', 'series': 'Breakup Probation, A Week', - 'series_id': 22912, + 'series_id': '22912', 'episode_number': 8, 'episode': 'E08', }, @@ -117,7 +118,7 @@ def if_series(key=None): 'duration': ('duration', {functools.partial(float_or_none, scale=1000)}), 'age_limit': ('age_rating', 'name', {lambda x: x.replace('R', '')}, {parse_age_limit}), 'series': ('episode', {if_series(key='program')}, 'title'), - 'series_id': ('episode', {if_series(key='program')}, 'id'), + 'series_id': ('episode', {if_series(key='program')}, 'id', {str_or_none}), 'episode': ('episode', {if_series(key='title')}), 'episode_number': ('episode', {if_series(key='number')}, {int_or_none}), }, get_all=False), diff --git a/yt_dlp/extractor/orf.py b/yt_dlp/extractor/orf.py index 1b2a79a62..526e9acaf 100644 --- a/yt_dlp/extractor/orf.py +++ b/yt_dlp/extractor/orf.py @@ -49,7 +49,6 @@ class ORFTVthekIE(InfoExtractor): 'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150', 'info_dict': { 'id': '14121079', - 'playlist_count': 1 }, 'playlist': [{ 'info_dict': { diff --git a/yt_dlp/extractor/peekvids.py b/yt_dlp/extractor/peekvids.py index 41f591b09..939c26dc7 100644 --- a/yt_dlp/extractor/peekvids.py +++ b/yt_dlp/extractor/peekvids.py @@ -157,7 +157,6 @@ class PlayVidsIE(PeekVidsBaseIE): 'display_id': '47iUho33toY', 'ext': 'mp4', 'title': 'KATEE OWEN STRIPTIASE IN SEXY RED LINGERIE', - 'description': None, 'timestamp': 1507052209, 'upload_date': '20171003', 'thumbnail': r're:^https?://.*\.jpg$', @@ -176,7 +175,6 @@ class PlayVidsIE(PeekVidsBaseIE): 'display_id': 'z3_7iwWCmqt', 'ext': 'mp4', 'title': 'SEXY TEEN FILIPINA STRIPTEASE - Beautiful Pinay Bargirl Strips and Dances', - 'description': None, 'timestamp': 1607470323, 'upload_date': '20201208', 'thumbnail': r're:^https?://.*\.jpg$', diff --git a/yt_dlp/extractor/pladform.py b/yt_dlp/extractor/pladform.py index 00500686f..d67f6005c 100644 --- a/yt_dlp/extractor/pladform.py +++ b/yt_dlp/extractor/pladform.py @@ -35,7 +35,6 @@ class PladformIE(InfoExtractor): 'thumbnail': str, 'view_count': int, 'description': str, - 'category': list, 'uploader_id': '12082', 'uploader': 'Comedy Club', 'duration': 367, diff --git a/yt_dlp/extractor/planetmarathi.py b/yt_dlp/extractor/planetmarathi.py index 25753fe7e..a4b612a6e 100644 --- a/yt_dlp/extractor/planetmarathi.py +++ b/yt_dlp/extractor/planetmarathi.py @@ -20,7 +20,6 @@ class PlanetMarathiIE(InfoExtractor): 'title': 'ek unad divas', 'alt_title': 'चित्रपट', 'description': 'md5:41c7ed6b041c2fea9820a3f3125bd881', - 'season_number': None, 'episode_number': 1, 'duration': 5539, 'upload_date': '20210829', diff --git a/yt_dlp/extractor/podchaser.py b/yt_dlp/extractor/podchaser.py index 290c48817..fc2d407b1 100644 --- a/yt_dlp/extractor/podchaser.py +++ b/yt_dlp/extractor/podchaser.py @@ -29,7 +29,7 @@ class PodchaserIE(InfoExtractor): 'duration': 3708, 'timestamp': 1636531259, 'upload_date': '20211110', - 'rating': 4.0 + 'average_rating': 4.0 } }, { 'url': 'https://www.podchaser.com/podcasts/the-bone-zone-28853', @@ -59,7 +59,7 @@ def _parse_episode(episode, podcast): 'thumbnail': episode.get('image_url'), 'duration': str_to_int(episode.get('length')), 'timestamp': unified_timestamp(episode.get('air_date')), - 'rating': float_or_none(episode.get('rating')), + 'average_rating': float_or_none(episode.get('rating')), 'categories': list(set(traverse_obj(podcast, (('summary', None), 'categories', ..., 'text')))), 'tags': traverse_obj(podcast, ('tags', ..., 'text')), 'series': podcast.get('title'), diff --git a/yt_dlp/extractor/pr0gramm.py b/yt_dlp/extractor/pr0gramm.py index 36e415f4a..66f8a5f44 100644 --- a/yt_dlp/extractor/pr0gramm.py +++ b/yt_dlp/extractor/pr0gramm.py @@ -1,5 +1,4 @@ import json -from datetime import date from urllib.parse import unquote from .common import InfoExtractor @@ -10,6 +9,7 @@ int_or_none, make_archive_id, mimetype2ext, + str_or_none, urljoin, ) from ..utils.traversal import traverse_obj @@ -25,8 +25,8 @@ class Pr0grammIE(InfoExtractor): 'title': 'pr0gramm-5466437 by g11st', 'tags': ['Neon Genesis Evangelion', 'Touhou Project', 'Fly me to the Moon', 'Marisad', 'Marisa Kirisame', 'video', 'sound', 'Marisa', 'Anime'], 'uploader': 'g11st', - 'uploader_id': 394718, - 'upload_timestamp': 1671590240, + 'uploader_id': '394718', + 'timestamp': 1671590240, 'upload_date': '20221221', 'like_count': int, 'dislike_count': int, @@ -42,8 +42,8 @@ class Pr0grammIE(InfoExtractor): 'title': 'pr0gramm-3052805 by Hansking1', 'tags': 'count:15', 'uploader': 'Hansking1', - 'uploader_id': 385563, - 'upload_timestamp': 1552930408, + 'uploader_id': '385563', + 'timestamp': 1552930408, 'upload_date': '20190318', 'like_count': int, 'dislike_count': int, @@ -60,8 +60,8 @@ class Pr0grammIE(InfoExtractor): 'title': 'pr0gramm-5848332 by erd0pfel', 'tags': 'count:18', 'uploader': 'erd0pfel', - 'uploader_id': 349094, - 'upload_timestamp': 1694489652, + 'uploader_id': '349094', + 'timestamp': 1694489652, 'upload_date': '20230912', 'like_count': int, 'dislike_count': int, @@ -77,8 +77,8 @@ class Pr0grammIE(InfoExtractor): 'title': 'pr0gramm-5895149 by algoholigSeeManThrower', 'tags': 'count:19', 'uploader': 'algoholigSeeManThrower', - 'uploader_id': 457556, - 'upload_timestamp': 1697580902, + 'uploader_id': '457556', + 'timestamp': 1697580902, 'upload_date': '20231018', 'like_count': int, 'dislike_count': int, @@ -192,11 +192,10 @@ def _real_extract(self, url): '_old_archive_ids': [make_archive_id('Pr0grammStatic', video_id)], **traverse_obj(video_info, { 'uploader': ('user', {str}), - 'uploader_id': ('userId', {int}), + 'uploader_id': ('userId', {str_or_none}), 'like_count': ('up', {int}), 'dislike_count': ('down', {int}), - 'upload_timestamp': ('created', {int}), - 'upload_date': ('created', {int}, {date.fromtimestamp}, {lambda x: x.strftime('%Y%m%d')}), + 'timestamp': ('created', {int}), 'thumbnail': ('thumb', {lambda x: urljoin('https://thumb.pr0gramm.com', x)}) }), } diff --git a/yt_dlp/extractor/prankcast.py b/yt_dlp/extractor/prankcast.py index 562aca0ff..56cd40d8a 100644 --- a/yt_dlp/extractor/prankcast.py +++ b/yt_dlp/extractor/prankcast.py @@ -16,7 +16,7 @@ class PrankCastIE(InfoExtractor): 'display_id': 'Beverly-is-back-like-a-heart-attack-', 'timestamp': 1661391575, 'uploader': 'Devonanustart', - 'channel_id': 4, + 'channel_id': '4', 'duration': 7918, 'cast': ['Devonanustart', 'Phonelosers'], 'description': '', @@ -33,7 +33,7 @@ class PrankCastIE(InfoExtractor): 'display_id': 'NOT-COOL', 'timestamp': 1665028364, 'uploader': 'phonelosers', - 'channel_id': 6, + 'channel_id': '6', 'duration': 4044, 'cast': ['phonelosers'], 'description': '', @@ -60,7 +60,7 @@ def _real_extract(self, url): 'url': f'{json_info["broadcast_url"]}{json_info["recording_hash"]}.mp3', 'timestamp': start_date, 'uploader': uploader, - 'channel_id': json_info.get('user_id'), + 'channel_id': str_or_none(json_info.get('user_id')), 'duration': try_call(lambda: parse_iso8601(json_info['end_date']) - start_date), 'cast': list(filter(None, [uploader] + traverse_obj(guests_json, (..., 'name')))), 'description': json_info.get('broadcast_description'), diff --git a/yt_dlp/extractor/radiocomercial.py b/yt_dlp/extractor/radiocomercial.py index 07891fe41..38f8cf786 100644 --- a/yt_dlp/extractor/radiocomercial.py +++ b/yt_dlp/extractor/radiocomercial.py @@ -30,7 +30,8 @@ class RadioComercialIE(InfoExtractor): 'title': 'Taylor Swift entranhando-se que nem uma espada no ventre dos fãs.', 'release_date': '20231025', 'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg', - 'season': 6 + 'season': 'Season 6', + 'season_number': 6, } }, { 'url': 'https://radiocomercial.pt/podcasts/convenca-me-num-minuto/t3/convenca-me-num-minuto-que-os-lobisomens-existem', @@ -41,7 +42,8 @@ class RadioComercialIE(InfoExtractor): 'title': 'Convença-me num minuto que os lobisomens existem', 'release_date': '20231026', 'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg', - 'season': 3 + 'season': 'Season 3', + 'season_number': 3, } }, { 'url': 'https://radiocomercial.pt/podcasts/inacreditavel-by-ines-castel-branco/t2/o-desastre-de-aviao', @@ -53,7 +55,8 @@ class RadioComercialIE(InfoExtractor): 'description': 'md5:8a82beeb372641614772baab7246245f', 'release_date': '20231101', 'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg', - 'season': 2 + 'season': 'Season 2', + 'season_number': 2, }, 'params': { # inconsistant md5 @@ -68,7 +71,8 @@ class RadioComercialIE(InfoExtractor): 'title': 'T.N.T 29 de outubro', 'release_date': '20231029', 'thumbnail': r're:https://radiocomercial.pt/upload/[^.]+.jpg', - 'season': 2023 + 'season': 'Season 2023', + 'season_number': 2023, } }] @@ -82,7 +86,7 @@ def _real_extract(self, url): 'release_date': unified_strdate(get_element_by_class( 'date', get_element_html_by_class('descriptions', webpage) or '')), 'thumbnail': self._og_search_thumbnail(webpage), - 'season': int_or_none(season), + 'season_number': int_or_none(season), 'url': extract_attributes(get_element_html_by_class('audiofile', webpage) or '').get('href'), } diff --git a/yt_dlp/extractor/radlive.py b/yt_dlp/extractor/radlive.py index 9bcbb11d5..3c00183be 100644 --- a/yt_dlp/extractor/radlive.py +++ b/yt_dlp/extractor/radlive.py @@ -38,10 +38,6 @@ class RadLiveIE(InfoExtractor): 'language': 'en', 'thumbnail': 'https://lsp.littlstar.com/channels/WHISTLE/BAD_JOKES/SEASON_1/BAD_JOKES_101/poster.jpg', 'description': 'Bad Jokes - Champions, Adam Pally, Super Troopers, Team Edge and 2Hype', - 'release_timestamp': None, - 'channel': None, - 'channel_id': None, - 'channel_url': None, 'episode': 'E01: Bad Jokes 1', 'episode_number': 1, 'episode_id': '336', diff --git a/yt_dlp/extractor/rcti.py b/yt_dlp/extractor/rcti.py index 79d9c8e31..2f50efeda 100644 --- a/yt_dlp/extractor/rcti.py +++ b/yt_dlp/extractor/rcti.py @@ -229,7 +229,7 @@ class RCTIPlusSeriesIE(RCTIPlusBaseIE): 'age_limit': 2, 'cast': ['Verrel Bramasta', 'Ranty Maria', 'Riza Syah', 'Ivan Fadilla', 'Nicole Parham', 'Dll', 'Aviv Elham'], 'display_id': 'putri-untuk-pangeran', - 'tag': 'count:18', + 'tags': 'count:18', }, }, { # No episodes 'url': 'https://www.rctiplus.com/programs/615/inews-pagi', @@ -239,7 +239,7 @@ class RCTIPlusSeriesIE(RCTIPlusBaseIE): 'title': 'iNews Pagi', 'description': 'md5:f18ee3d4643cfb41c358e5a9b693ee04', 'age_limit': 2, - 'tag': 'count:11', + 'tags': 'count:11', 'display_id': 'inews-pagi', } }] @@ -327,8 +327,8 @@ def _real_extract(self, url): 'age_limit': try_get(series_meta, lambda x: self._AGE_RATINGS[x['age_restriction'][0]['code']]), 'cast': traverse_obj(series_meta, (('starring', 'creator', 'writer'), ..., 'name'), expected_type=lambda x: strip_or_none(x) or None), - 'tag': traverse_obj(series_meta, ('tag', ..., 'name'), - expected_type=lambda x: strip_or_none(x) or None), + 'tags': traverse_obj(series_meta, ('tag', ..., 'name'), + expected_type=lambda x: strip_or_none(x) or None), } return self.playlist_result( self._series_entries(series_id, display_id, video_type, metadata), series_id, diff --git a/yt_dlp/extractor/rokfin.py b/yt_dlp/extractor/rokfin.py index cad76f0c9..5099f3ae4 100644 --- a/yt_dlp/extractor/rokfin.py +++ b/yt_dlp/extractor/rokfin.py @@ -38,7 +38,7 @@ class RokfinIE(InfoExtractor): 'upload_date': '20211023', 'timestamp': 1634998029, 'channel': 'Jimmy Dore', - 'channel_id': 65429, + 'channel_id': '65429', 'channel_url': 'https://rokfin.com/TheJimmyDoreShow', 'availability': 'public', 'live_status': 'not_live', @@ -56,7 +56,7 @@ class RokfinIE(InfoExtractor): 'upload_date': '20190412', 'timestamp': 1555052644, 'channel': 'Ron Placone', - 'channel_id': 10, + 'channel_id': '10', 'channel_url': 'https://rokfin.com/RonPlacone', 'availability': 'public', 'live_status': 'not_live', @@ -73,7 +73,7 @@ class RokfinIE(InfoExtractor): 'thumbnail': r're:https://img\.production\.rokfin\.com/.+', 'description': 'md5:324ce2d3e3b62e659506409e458b9d8e', 'channel': 'TLAVagabond', - 'channel_id': 53856, + 'channel_id': '53856', 'channel_url': 'https://rokfin.com/TLAVagabond', 'availability': 'public', 'is_live': False, @@ -86,7 +86,6 @@ class RokfinIE(InfoExtractor): 'dislike_count': int, 'like_count': int, 'tags': ['FreeThinkingMedia^'], - 'duration': None, } }, { 'url': 'https://rokfin.com/post/126703/Brave-New-World--Aldous-Huxley-DEEPDIVE--Chpts-13--Quite-Frankly--Jay-Dyer', @@ -96,7 +95,7 @@ class RokfinIE(InfoExtractor): 'title': 'Brave New World - Aldous Huxley DEEPDIVE! (Chpts 1-3) - Quite Frankly & Jay Dyer', 'thumbnail': r're:https://img\.production\.rokfin\.com/.+', 'channel': 'Jay Dyer', - 'channel_id': 186881, + 'channel_id': '186881', 'channel_url': 'https://rokfin.com/jaydyer', 'availability': 'premium_only', 'live_status': 'not_live', @@ -116,7 +115,7 @@ class RokfinIE(InfoExtractor): 'title': 'The Grayzone live on Nordstream blame game', 'thumbnail': r're:https://image\.v\.rokfin\.com/.+', 'channel': 'Max Blumenthal', - 'channel_id': 248902, + 'channel_id': '248902', 'channel_url': 'https://rokfin.com/MaxBlumenthal', 'availability': 'premium_only', 'live_status': 'was_live', @@ -174,7 +173,7 @@ def _real_extract(self, url): 'like_count': int_or_none(metadata.get('likeCount')), 'dislike_count': int_or_none(metadata.get('dislikeCount')), 'channel': str_or_none(traverse_obj(metadata, ('createdBy', 'name'), ('creator', 'name'))), - 'channel_id': traverse_obj(metadata, ('createdBy', 'id'), ('creator', 'id')), + 'channel_id': str_or_none(traverse_obj(metadata, ('createdBy', 'id'), ('creator', 'id'))), 'channel_url': url_or_none(f'https://rokfin.com/{uploader}') if uploader else None, 'timestamp': timestamp, 'release_timestamp': timestamp if live_status != 'not_live' else None, diff --git a/yt_dlp/extractor/rumble.py b/yt_dlp/extractor/rumble.py index 1dc049ac8..837a324e6 100644 --- a/yt_dlp/extractor/rumble.py +++ b/yt_dlp/extractor/rumble.py @@ -90,7 +90,6 @@ class RumbleEmbedIE(InfoExtractor): 'channel_url': 'https://rumble.com/c/LofiGirl', 'channel': 'Lofi Girl', 'thumbnail': r're:https://.+\.jpg', - 'duration': None, 'uploader': 'Lofi Girl', 'live_status': 'is_live', }, diff --git a/yt_dlp/extractor/rutube.py b/yt_dlp/extractor/rutube.py index 08d9b9257..287824d08 100644 --- a/yt_dlp/extractor/rutube.py +++ b/yt_dlp/extractor/rutube.py @@ -46,7 +46,7 @@ def _extract_info(self, video, video_id=None, require_title=True): 'uploader': try_get(video, lambda x: x['author']['name']), 'uploader_id': compat_str(uploader_id) if uploader_id else None, 'timestamp': unified_timestamp(video.get('created_ts')), - 'category': [category] if category else None, + 'categories': [category] if category else None, 'age_limit': age_limit, 'view_count': int_or_none(video.get('hits')), 'comment_count': int_or_none(video.get('comments_count')), @@ -112,7 +112,7 @@ class RutubeIE(RutubeBaseIE): 'age_limit': 0, 'view_count': int, 'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg', - 'category': ['Новости и СМИ'], + 'categories': ['Новости и СМИ'], 'chapters': [], }, 'expected_warnings': ['Unable to download f4m'], @@ -144,7 +144,7 @@ class RutubeIE(RutubeBaseIE): 'age_limit': 0, 'view_count': int, 'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg', - 'category': ['Видеоигры'], + 'categories': ['Видеоигры'], 'chapters': [], }, 'expected_warnings': ['Unable to download f4m'], @@ -154,7 +154,7 @@ class RutubeIE(RutubeBaseIE): 'id': 'c65b465ad0c98c89f3b25cb03dcc87c6', 'ext': 'mp4', 'chapters': 'count:4', - 'category': ['Бизнес и предпринимательство'], + 'categories': ['Бизнес и предпринимательство'], 'description': 'md5:252feac1305257d8c1bab215cedde75d', 'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png', 'duration': 782, diff --git a/yt_dlp/extractor/sbs.py b/yt_dlp/extractor/sbs.py index 7a9115047..8d61e22fc 100644 --- a/yt_dlp/extractor/sbs.py +++ b/yt_dlp/extractor/sbs.py @@ -44,8 +44,6 @@ class SBSIE(InfoExtractor): 'timestamp': 1408613220, 'upload_date': '20140821', 'uploader': 'SBSC', - 'tags': None, - 'categories': None, }, 'expected_warnings': ['Unable to download JSON metadata'], }, { diff --git a/yt_dlp/extractor/skeb.py b/yt_dlp/extractor/skeb.py index e02f8cef0..54dfdc441 100644 --- a/yt_dlp/extractor/skeb.py +++ b/yt_dlp/extractor/skeb.py @@ -10,7 +10,7 @@ class SkebIE(InfoExtractor): 'info_dict': { 'id': '466853', 'title': '内容はおまかせします！ by 姫ノ森りぃる@一周年', - 'descripion': 'md5:1ec50901efc3437cfbfe3790468d532d', + 'description': 'md5:1ec50901efc3437cfbfe3790468d532d', 'uploader': '姫ノ森りぃる@一周年', 'uploader_id': 'riiru_wm', 'age_limit': 0, @@ -34,7 +34,7 @@ class SkebIE(InfoExtractor): 'info_dict': { 'id': '489408', 'title': 'いつもお世話になってお... by 古川ノブ@音楽とVlo...', - 'descripion': 'md5:5adc2e41d06d33b558bf7b1faeb7b9c2', + 'description': 'md5:5adc2e41d06d33b558bf7b1faeb7b9c2', 'uploader': '古川ノブ@音楽とVlogのVtuber', 'uploader_id': 'furukawa_nob', 'age_limit': 0, @@ -61,12 +61,12 @@ class SkebIE(InfoExtractor): 'info_dict': { 'id': '6', 'title': 'ヒロ。\n\n私のキャラク... by 諸々', - 'descripion': 'md5:aa6cbf2ba320b50bce219632de195f07', + 'description': 'md5:aa6cbf2ba320b50bce219632de195f07', '_type': 'playlist', 'entries': [{ 'id': '486430', 'title': 'ヒロ。\n\n私のキャラク... by 諸々', - 'descripion': 'md5:aa6cbf2ba320b50bce219632de195f07', + 'description': 'md5:aa6cbf2ba320b50bce219632de195f07', }, { 'id': '486431', 'title': 'ヒロ。\n\n私のキャラク... by 諸々', @@ -81,7 +81,7 @@ def _real_extract(self, url): parent = { 'id': video_id, 'title': nuxt_data.get('title'), - 'descripion': nuxt_data.get('description'), + 'description': nuxt_data.get('description'), 'uploader': traverse_obj(nuxt_data, ('creator', 'name')), 'uploader_id': traverse_obj(nuxt_data, ('creator', 'screen_name')), 'age_limit': 18 if nuxt_data.get('nsfw') else 0, diff --git a/yt_dlp/extractor/stageplus.py b/yt_dlp/extractor/stageplus.py index 4bed4d646..77e4362fc 100644 --- a/yt_dlp/extractor/stageplus.py +++ b/yt_dlp/extractor/stageplus.py @@ -21,7 +21,7 @@ class StagePlusVODConcertIE(InfoExtractor): 'id': 'vod_concert_APNM8GRFDPHMASJKBSPJACG', 'title': 'Yuja Wang plays Rachmaninoff\'s Piano Concerto No. 2 – from Odeonsplatz', 'description': 'md5:50f78ec180518c9bdb876bac550996fc', - 'artist': ['Yuja Wang', 'Lorenzo Viotti'], + 'artists': ['Yuja Wang', 'Lorenzo Viotti'], 'upload_date': '20230331', 'timestamp': 1680249600, 'release_date': '20210709', @@ -40,10 +40,10 @@ class StagePlusVODConcertIE(InfoExtractor): 'release_timestamp': 1625788800, 'duration': 2207, 'chapters': 'count:5', - 'artist': ['Yuja Wang'], - 'composer': ['Sergei Rachmaninoff'], + 'artists': ['Yuja Wang'], + 'composers': ['Sergei Rachmaninoff'], 'album': 'Yuja Wang plays Rachmaninoff\'s Piano Concerto No. 2 – from Odeonsplatz', - 'album_artist': ['Yuja Wang', 'Lorenzo Viotti'], + 'album_artists': ['Yuja Wang', 'Lorenzo Viotti'], 'track': 'Piano Concerto No. 2 in C Minor, Op. 18', 'track_number': 1, 'genre': 'Instrumental Concerto', @@ -474,7 +474,7 @@ def _real_extract(self, url): metadata = traverse_obj(data, { 'title': 'title', 'description': ('shortDescription', {str}), - 'artist': ('artists', 'edges', ..., 'node', 'name'), + 'artists': ('artists', 'edges', ..., 'node', 'name'), 'timestamp': ('archiveReleaseDate', {unified_timestamp}), 'release_timestamp': ('productionDate', {unified_timestamp}), }) @@ -494,7 +494,7 @@ def _real_extract(self, url): 'formats': formats, 'subtitles': subtitles, 'album': metadata.get('title'), - 'album_artist': metadata.get('artist'), + 'album_artists': metadata.get('artist'), 'track_number': idx, **metadata, **traverse_obj(video, { @@ -506,8 +506,8 @@ def _real_extract(self, url): 'title': 'title', 'start_time': ('mark', {float_or_none}), }), - 'artist': ('artists', 'edges', ..., 'node', 'name'), - 'composer': ('work', 'composers', ..., 'name'), + 'artists': ('artists', 'edges', ..., 'node', 'name'), + 'composers': ('work', 'composers', ..., 'name'), 'genre': ('work', 'genre', 'title'), }), }) diff --git a/yt_dlp/extractor/steam.py b/yt_dlp/extractor/steam.py index 7daee2fe0..63da9662a 100644 --- a/yt_dlp/extractor/steam.py +++ b/yt_dlp/extractor/steam.py @@ -2,9 +2,10 @@ from .common import InfoExtractor from ..utils import ( - extract_attributes, ExtractorError, + extract_attributes, get_element_by_class, + str_or_none, ) @@ -30,7 +31,6 @@ class SteamIE(InfoExtractor): 'ext': 'mp4', 'title': 'Terraria video 256785003', 'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com', - 'n_entries': 2, } }, { @@ -39,9 +39,7 @@ class SteamIE(InfoExtractor): 'id': '2040428', 'ext': 'mp4', 'title': 'Terraria video 2040428', - 'playlist_index': 2, 'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com', - 'n_entries': 2, } } ], @@ -55,12 +53,10 @@ class SteamIE(InfoExtractor): }, { 'url': 'https://store.steampowered.com/app/271590/Grand_Theft_Auto_V/', 'info_dict': { - 'id': '256757115', - 'title': 'Grand Theft Auto V video 256757115', - 'ext': 'mp4', - 'thumbnail': r're:^https://cdn\.[^\.]+\.steamstatic\.com', - 'n_entries': 20, + 'id': '271590', + 'title': 'Grand Theft Auto V', }, + 'playlist_count': 23, }] def _real_extract(self, url): @@ -136,7 +132,7 @@ class SteamCommunityBroadcastIE(InfoExtractor): 'id': '76561199073851486', 'title': r're:Steam Community :: pepperm!nt :: Broadcast 2022-06-26 \d{2}:\d{2}', 'ext': 'mp4', - 'uploader_id': 1113585758, + 'uploader_id': '1113585758', 'uploader': 'pepperm!nt', 'live_status': 'is_live', }, @@ -169,6 +165,6 @@ def _real_extract(self, url): 'live_status': 'is_live', 'view_count': json_data.get('num_view'), 'uploader': uploader_json.get('persona_name'), - 'uploader_id': uploader_json.get('accountid'), + 'uploader_id': str_or_none(uploader_json.get('accountid')), 'subtitles': subs, } diff --git a/yt_dlp/extractor/tenplay.py b/yt_dlp/extractor/tenplay.py index 7ce7cbf84..a98275d86 100644 --- a/yt_dlp/extractor/tenplay.py +++ b/yt_dlp/extractor/tenplay.py @@ -20,7 +20,8 @@ class TenPlayIE(InfoExtractor): 'alt_title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours', 'description': 'md5:a02d0199c901c2dd4c796f1e7dd0de43', 'duration': 186, - 'season': 39, + 'season': 'Season 39', + 'season_number': 39, 'series': 'Neighbours', 'thumbnail': r're:https://.*\.jpg', 'uploader': 'Channel 10', @@ -108,7 +109,7 @@ def _real_extract(self, url): 'description': data.get('description'), 'age_limit': self._AUS_AGES.get(data.get('classification')), 'series': data.get('tvShow'), - 'season': int_or_none(data.get('season')), + 'season_number': int_or_none(data.get('season')), 'episode_number': int_or_none(data.get('episode')), 'timestamp': data.get('published'), 'thumbnail': data.get('imageUrl'), diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py index aa9daa2e8..aa8356796 100644 --- a/yt_dlp/extractor/tiktok.py +++ b/yt_dlp/extractor/tiktok.py @@ -320,7 +320,7 @@ def extract_addr(addr, add_meta={}): if is_generic_og_trackname: music_track, music_author = contained_music_track or 'original sound', contained_music_author else: - music_track, music_author = music_info.get('title'), music_info.get('author') + music_track, music_author = music_info.get('title'), traverse_obj(music_info, ('author', {str})) return { 'id': aweme_id, @@ -336,15 +336,16 @@ def extract_addr(addr, add_meta={}): 'comment_count': 'comment_count', }, expected_type=int_or_none), **traverse_obj(author_info, { - 'uploader': 'unique_id', - 'uploader_id': 'uid', - 'creator': 'nickname', - 'channel_id': 'sec_uid', - }, expected_type=str_or_none), + 'uploader': ('unique_id', {str}), + 'uploader_id': ('uid', {str_or_none}), + 'creators': ('nickname', {str}, {lambda x: [x] if x else None}), # for compat + 'channel': ('nickname', {str}), + 'channel_id': ('sec_uid', {str}), + }), 'uploader_url': user_url, 'track': music_track, 'album': str_or_none(music_info.get('album')) or None, - 'artist': music_author or None, + 'artists': re.split(r'(?:, | & )', music_author) if music_author else None, 'formats': formats, 'subtitles': self.extract_subtitles(aweme_detail, aweme_id), 'thumbnails': thumbnails, @@ -405,7 +406,8 @@ def _parse_aweme_video_web(self, aweme_detail, webpage_url, video_id): 'timestamp': ('createTime', {int_or_none}), }), **traverse_obj(author_info or aweme_detail, { - 'creator': ('nickname', {str}), + 'creators': ('nickname', {str}, {lambda x: [x] if x else None}), # for compat + 'channel': ('nickname', {str}), 'uploader': (('uniqueId', 'author'), {str}), 'uploader_id': (('authorId', 'uid', 'id'), {str_or_none}), }, get_all=False), @@ -416,10 +418,10 @@ def _parse_aweme_video_web(self, aweme_detail, webpage_url, video_id): 'comment_count': 'commentCount', }, expected_type=int_or_none), **traverse_obj(music_info, { - 'track': 'title', - 'album': ('album', {lambda x: x or None}), - 'artist': 'authorName', - }, expected_type=str), + 'track': ('title', {str}), + 'album': ('album', {str}, {lambda x: x or None}), + 'artists': ('authorName', {str}, {lambda x: [x] if x else None}), + }), 'channel_id': channel_id, 'uploader_url': user_url, 'formats': formats, @@ -476,7 +478,8 @@ class TikTokIE(TikTokBaseIE): 'uploader_id': '18702747', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws', 'channel_id': 'MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws', - 'creator': 'patroX', + 'channel': 'patroX', + 'creators': ['patroX'], 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', 'upload_date': '20190930', 'timestamp': 1569860870, @@ -484,7 +487,7 @@ class TikTokIE(TikTokBaseIE): 'like_count': int, 'repost_count': int, 'comment_count': int, - 'artist': 'Evan Todd, Jessica Keenan Wynn, Alice Lee, Barrett Wilbert Weed & Jon Eidson', + 'artists': ['Evan Todd', 'Jessica Keenan Wynn', 'Alice Lee', 'Barrett Wilbert Weed', 'Jon Eidson'], 'track': 'Big Fun', }, }, { @@ -496,12 +499,13 @@ class TikTokIE(TikTokBaseIE): 'title': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥', 'description': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥', 'uploader': 'barudakhb_', - 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', + 'channel': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', + 'creators': ['md5:29f238c49bc0c176cb3cef1a9cea9fa6'], 'uploader_id': '6974687867511718913', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d', 'channel_id': 'MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d', 'track': 'Boka Dance', - 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', + 'artists': ['md5:29f238c49bc0c176cb3cef1a9cea9fa6'], 'timestamp': 1626121503, 'duration': 18, 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', @@ -520,7 +524,8 @@ class TikTokIE(TikTokBaseIE): 'title': 'Slap and Run!', 'description': 'Slap and Run!', 'uploader': 'user440922249', - 'creator': 'Slap And Run', + 'channel': 'Slap And Run', + 'creators': ['Slap And Run'], 'uploader_id': '7036055384943690754', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_', 'channel_id': 'MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_', @@ -544,7 +549,8 @@ class TikTokIE(TikTokBaseIE): 'title': 'TikTok video #7059698374567611694', 'description': '', 'uploader': 'pokemonlife22', - 'creator': 'Pokemon', + 'channel': 'Pokemon', + 'creators': ['Pokemon'], 'uploader_id': '6820838815978423302', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W', 'channel_id': 'MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W', @@ -553,7 +559,7 @@ class TikTokIE(TikTokBaseIE): 'duration': 6, 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', 'upload_date': '20220201', - 'artist': 'Pokemon', + 'artists': ['Pokemon'], 'view_count': int, 'like_count': int, 'repost_count': int, @@ -590,12 +596,13 @@ class TikTokIE(TikTokBaseIE): 'ext': 'mp3', 'title': 'TikTok video #7139980461132074283', 'description': '', - 'creator': 'Antaura', + 'channel': 'Antaura', + 'creators': ['Antaura'], 'uploader': '_le_cannibale_', 'uploader_id': '6604511138619654149', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP', 'channel_id': 'MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP', - 'artist': 'nathan !', + 'artists': ['nathan !'], 'track': 'grahamscott canon', 'upload_date': '20220905', 'timestamp': 1662406249, @@ -603,18 +610,18 @@ class TikTokIE(TikTokBaseIE): 'like_count': int, 'repost_count': int, 'comment_count': int, - 'thumbnail': r're:^https://.+\.webp', + 'thumbnail': r're:^https://.+\.(?:webp|jpe?g)', }, }, { # only available via web - 'url': 'https://www.tiktok.com/@moxypatch/video/7206382937372134662', + 'url': 'https://www.tiktok.com/@moxypatch/video/7206382937372134662', # FIXME 'md5': '6aba7fad816e8709ff2c149679ace165', 'info_dict': { 'id': '7206382937372134662', 'ext': 'mp4', 'title': 'md5:1d95c0b96560ca0e8a231af4172b2c0a', 'description': 'md5:1d95c0b96560ca0e8a231af4172b2c0a', - 'creator': 'MoxyPatch', + 'channel': 'MoxyPatch', 'creators': ['MoxyPatch'], 'uploader': 'moxypatch', 'uploader_id': '7039142049363379205', @@ -635,7 +642,7 @@ class TikTokIE(TikTokBaseIE): 'expected_warnings': ['Unable to find video in feed'], }, { # 1080p format - 'url': 'https://www.tiktok.com/@tatemcrae/video/7107337212743830830', + 'url': 'https://www.tiktok.com/@tatemcrae/video/7107337212743830830', # FIXME 'md5': '982512017a8a917124d5a08c8ae79621', 'info_dict': { 'id': '7107337212743830830', @@ -646,8 +653,9 @@ class TikTokIE(TikTokBaseIE): 'uploader_id': '86328792343818240', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA-0bQT0CqebTRr6I4IkYvMDMKSRSJHLNPBo5HrSklJwyA2psXLSZG5FP-LMNpHnJd', 'channel_id': 'MS4wLjABAAAA-0bQT0CqebTRr6I4IkYvMDMKSRSJHLNPBo5HrSklJwyA2psXLSZG5FP-LMNpHnJd', - 'creator': 'tate mcrae', - 'artist': 'tate mcrae', + 'channel': 'tate mcrae', + 'creators': ['tate mcrae'], + 'artists': ['tate mcrae'], 'track': 'original sound', 'upload_date': '20220609', 'timestamp': 1654805899, @@ -672,8 +680,9 @@ class TikTokIE(TikTokBaseIE): 'uploader_id': '6582536342634676230', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAIAlDxriiPWLE-p8p1R_0Bx8qWKfi-7zwmGhzU8Mv25W8sNxjfIKrol31qTczzuLB', 'channel_id': 'MS4wLjABAAAAIAlDxriiPWLE-p8p1R_0Bx8qWKfi-7zwmGhzU8Mv25W8sNxjfIKrol31qTczzuLB', - 'creator': 'лампочка', - 'artist': 'Øneheart', + 'channel': 'лампочка', + 'creators': ['лампочка'], + 'artists': ['Øneheart'], 'album': 'watching the stars', 'track': 'watching the stars', 'upload_date': '20230708', @@ -682,7 +691,7 @@ class TikTokIE(TikTokBaseIE): 'like_count': int, 'comment_count': int, 'repost_count': int, - 'thumbnail': r're:^https://.+\.webp', + 'thumbnail': r're:^https://.+\.(?:webp|jpe?g)', }, }, { # Auto-captions available @@ -949,7 +958,7 @@ class DouyinIE(TikTokBaseIE): 'uploader_id': '110403406559', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', - 'creator': '杨超越', + 'channel': '杨超越', 'creators': ['杨超越'], 'duration': 19, 'timestamp': 1620905839, @@ -974,7 +983,7 @@ class DouyinIE(TikTokBaseIE): 'uploader_id': '408654318141572', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA', 'channel_id': 'MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA', - 'creator': '杨超越工作室', + 'channel': '杨超越工作室', 'creators': ['杨超越工作室'], 'duration': 42, 'timestamp': 1625739481, @@ -999,7 +1008,7 @@ class DouyinIE(TikTokBaseIE): 'uploader_id': '110403406559', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', - 'creator': '杨超越', + 'channel': '杨超越', 'creators': ['杨超越'], 'duration': 17, 'timestamp': 1619098692, @@ -1041,7 +1050,7 @@ class DouyinIE(TikTokBaseIE): 'uploader_id': '110403406559', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', - 'creator': '杨超越', + 'channel': '杨超越', 'creators': ['杨超越'], 'duration': 15, 'timestamp': 1621261163, diff --git a/yt_dlp/extractor/tnaflix.py b/yt_dlp/extractor/tnaflix.py index b2baf2e87..535e6c8f0 100644 --- a/yt_dlp/extractor/tnaflix.py +++ b/yt_dlp/extractor/tnaflix.py @@ -277,7 +277,6 @@ class EMPFlixIE(TNAEMPFlixBaseIE): 'thumbnail': r're:https?://.*\.jpg$', 'duration': 83, 'age_limit': 18, - 'uploader': None, 'categories': list, } }, { diff --git a/yt_dlp/extractor/truth.py b/yt_dlp/extractor/truth.py index 1c6409ce2..51d28d159 100644 --- a/yt_dlp/extractor/truth.py +++ b/yt_dlp/extractor/truth.py @@ -19,7 +19,6 @@ class TruthIE(InfoExtractor): 'id': '108779000807761862', 'ext': 'qt', 'title': 'Truth video #108779000807761862', - 'description': None, 'timestamp': 1659835827, 'upload_date': '20220807', 'uploader': 'Donald J. Trump', diff --git a/yt_dlp/extractor/tv2hu.py b/yt_dlp/extractor/tv2hu.py index d4c21c046..9c0a111c0 100644 --- a/yt_dlp/extractor/tv2hu.py +++ b/yt_dlp/extractor/tv2hu.py @@ -20,7 +20,6 @@ class TV2HuIE(InfoExtractor): 'description': 'md5:7350147e75485a59598e806c47967b07', 'thumbnail': r're:^https?://.*\.jpg$', 'release_date': '20210825', - 'season_number': None, 'episode_number': 213, }, 'params': { @@ -38,8 +37,6 @@ class TV2HuIE(InfoExtractor): 'description': 'md5:47762155dc9a50241797ded101b1b08c', 'thumbnail': r're:^https?://.*\.jpg$', 'release_date': '20210118', - 'season_number': None, - 'episode_number': None, }, 'params': { 'skip_download': True, diff --git a/yt_dlp/extractor/tver.py b/yt_dlp/extractor/tver.py index cebd027c8..5f7896837 100644 --- a/yt_dlp/extractor/tver.py +++ b/yt_dlp/extractor/tver.py @@ -21,8 +21,6 @@ class TVerIE(InfoExtractor): 'episode': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！', 'alt_title': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！', 'channel': 'テレビ朝日', - 'onair_label': '5月3日(火)放送分', - 'ext_title': '家事ヤロウ!!! 売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！ テレビ朝日 5月3日(火)放送分', }, 'add_ie': ['BrightcoveNew'], }, { diff --git a/yt_dlp/extractor/videofyme.py b/yt_dlp/extractor/videofyme.py index 1d1c8f7b7..735432688 100644 --- a/yt_dlp/extractor/videofyme.py +++ b/yt_dlp/extractor/videofyme.py @@ -22,7 +22,7 @@ class VideofyMeIE(InfoExtractor): 'uploader': 'VideofyMe', 'uploader_id': 'thisisvideofyme', 'view_count': int, - 'likes': int, + 'like_count': int, 'comment_count': int, }, } @@ -45,6 +45,6 @@ def _real_extract(self, url): 'uploader': blog.get('name'), 'uploader_id': blog.get('identifier'), 'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)), - 'likes': int_or_none(video.get('likes')), + 'like_count': int_or_none(video.get('likes')), 'comment_count': int_or_none(video.get('nrOfComments')), } diff --git a/yt_dlp/extractor/viewlift.py b/yt_dlp/extractor/viewlift.py index c93be5f3d..c5d65cdd6 100644 --- a/yt_dlp/extractor/viewlift.py +++ b/yt_dlp/extractor/viewlift.py @@ -231,7 +231,6 @@ class ViewLiftIE(ViewLiftBaseIE): 'description': 'md5:e28f2fb8680096a69c944d37c1fa5ffc', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20211006', - 'series': None }, 'params': {'skip_download': True}, }, { # Free film @@ -243,7 +242,6 @@ class ViewLiftIE(ViewLiftBaseIE): 'description': 'md5:605cba408e51a79dafcb824bdeded51e', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20210827', - 'series': None }, 'params': {'skip_download': True}, }, { # Free episode diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index f03c4bef3..91b976403 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -375,7 +375,6 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware', 'uploader_id': 'businessofsoftware', 'duration': 3610, - 'description': None, 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280', }, 'params': { diff --git a/yt_dlp/extractor/vk.py b/yt_dlp/extractor/vk.py index c12e87362..e4a78c297 100644 --- a/yt_dlp/extractor/vk.py +++ b/yt_dlp/extractor/vk.py @@ -810,7 +810,7 @@ class VKPlayLiveIE(VKPlayBaseIE): 'ext': 'mp4', 'title': r're:эскапизм крута .*', 'uploader': 'Bayda', - 'uploader_id': 12279401, + 'uploader_id': '12279401', 'release_timestamp': 1687209962, 'release_date': '20230619', 'thumbnail': r're:https://images.vkplay.live/public_video_stream/12279401/preview\?change_time=\d+', diff --git a/yt_dlp/extractor/vvvvid.py b/yt_dlp/extractor/vvvvid.py index b42ba8537..b96112360 100644 --- a/yt_dlp/extractor/vvvvid.py +++ b/yt_dlp/extractor/vvvvid.py @@ -24,7 +24,6 @@ class VVVVIDIE(InfoExtractor): 'series': 'The Power of Computing', 'season_id': '518', 'episode': 'Playstation VR cambierà il nostro modo di giocare', - 'episode_number': None, 'episode_id': '4747', 'view_count': int, 'like_count': int, @@ -58,7 +57,6 @@ class VVVVIDIE(InfoExtractor): 'description': 'md5:a5e802558d35247fee285875328c0b80', 'uploader_id': '@EMOTIONLabelChannel', 'uploader': 'EMOTION Label Channel', - 'episode_number': None, 'episode_id': '3115', 'view_count': int, 'like_count': int, diff --git a/yt_dlp/extractor/wdr.py b/yt_dlp/extractor/wdr.py index 6767f2654..f80f140ed 100644 --- a/yt_dlp/extractor/wdr.py +++ b/yt_dlp/extractor/wdr.py @@ -324,7 +324,6 @@ class WDRElefantIE(InfoExtractor): 'title': 'Wippe', 'id': 'mdb-1198320', 'ext': 'mp4', - 'age_limit': None, 'upload_date': '20071003' }, } diff --git a/yt_dlp/extractor/ximalaya.py b/yt_dlp/extractor/ximalaya.py index 3d5e6cf90..c98c8a4fc 100644 --- a/yt_dlp/extractor/ximalaya.py +++ b/yt_dlp/extractor/ximalaya.py @@ -1,7 +1,7 @@ import math from .common import InfoExtractor -from ..utils import traverse_obj, try_call, InAdvancePagedList +from ..utils import InAdvancePagedList, str_or_none, traverse_obj, try_call class XimalayaBaseIE(InfoExtractor): @@ -19,7 +19,7 @@ class XimalayaIE(XimalayaBaseIE): 'id': '47740352', 'ext': 'm4a', 'uploader': '小彬彬爱听书', - 'uploader_id': 61425525, + 'uploader_id': '61425525', 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", @@ -48,7 +48,7 @@ class XimalayaIE(XimalayaBaseIE): 'id': '47740352', 'ext': 'm4a', 'uploader': '小彬彬爱听书', - 'uploader_id': 61425525, + 'uploader_id': '61425525', 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", @@ -107,7 +107,7 @@ def _real_extract(self, url): return { 'id': audio_id, 'uploader': audio_info.get('nickname'), - 'uploader_id': audio_uploader_id, + 'uploader_id': str_or_none(audio_uploader_id), 'uploader_url': f'{scheme}://www.ximalaya.com/zhubo/{audio_uploader_id}/' if audio_uploader_id else None, 'title': audio_info['title'], 'thumbnails': thumbnails, diff --git a/yt_dlp/extractor/xinpianchang.py b/yt_dlp/extractor/xinpianchang.py index ddc1d0b5a..9b878de85 100644 --- a/yt_dlp/extractor/xinpianchang.py +++ b/yt_dlp/extractor/xinpianchang.py @@ -1,6 +1,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, + str_or_none, try_get, update_url_query, url_or_none, @@ -21,9 +22,9 @@ class XinpianchangIE(InfoExtractor): 'duration': 151, 'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/', 'uploader': '正时文创', - 'uploader_id': 10357277, + 'uploader_id': '10357277', 'categories': ['宣传片', '国家城市', '广告', '其他'], - 'keywords': ['北京冬奥会', '冰墩墩', '再见', '告别', '冰墩墩哭了', '感动', '闭幕式', '熄火'] + 'tags': ['北京冬奥会', '冰墩墩', '再见', '告别', '冰墩墩哭了', '感动', '闭幕式', '熄火'] }, }, { 'url': 'https://www.xinpianchang.com/a11762904', @@ -35,9 +36,9 @@ class XinpianchangIE(InfoExtractor): 'duration': 136, 'thumbnail': r're:^https?://oss-xpc0\.xpccdn\.com.+/assets/', 'uploader': '精品动画', - 'uploader_id': 10858927, + 'uploader_id': '10858927', 'categories': ['动画', '三维CG'], - 'keywords': ['France Télévisions', '法国3台', '蠢萌', '冬奥会'] + 'tags': ['France Télévisions', '法国3台', '蠢萌', '冬奥会'] }, }, { 'url': 'https://www.xinpianchang.com/a11779743?from=IndexPick&part=%E7%BC%96%E8%BE%91%E7%B2%BE%E9%80%89&index=2', @@ -78,10 +79,10 @@ def _real_extract(self, url): 'description': data.get('description'), 'duration': int_or_none(data.get('duration')), 'categories': data.get('categories'), - 'keywords': data.get('keywords'), + 'tags': data.get('keywords'), 'thumbnail': data.get('cover'), 'uploader': try_get(data, lambda x: x['owner']['username']), - 'uploader_id': try_get(data, lambda x: x['owner']['id']), + 'uploader_id': str_or_none(try_get(data, lambda x: x['owner']['id'])), 'formats': formats, 'subtitles': subtitles, } diff --git a/yt_dlp/extractor/yle_areena.py b/yt_dlp/extractor/yle_areena.py index c5b45f0cb..dd0e59901 100644 --- a/yt_dlp/extractor/yle_areena.py +++ b/yt_dlp/extractor/yle_areena.py @@ -46,10 +46,6 @@ class YleAreenaIE(InfoExtractor): 'title': 'Albi haluaa vessan', 'description': 'md5:15236d810c837bed861fae0e88663c33', 'series': 'Albi Lumiukko', - 'season': None, - 'season_number': None, - 'episode': None, - 'episode_number': None, 'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/1_l38iz9ur/version/100021', 'uploader_id': 'ovp@yle.fi', 'duration': 319, diff --git a/yt_dlp/extractor/youku.py b/yt_dlp/extractor/youku.py index e35176586..1f3f98a86 100644 --- a/yt_dlp/extractor/youku.py +++ b/yt_dlp/extractor/youku.py @@ -42,11 +42,11 @@ class YoukuIE(InfoExtractor): 'uploader_id': '322014285', 'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==', 'tags': list, - 'skip': '404', }, 'params': { 'videopassword': '100600', }, + 'skip': '404', }, { # /play/get.json contains streams with "channel_type":"tail" 'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html', diff --git a/yt_dlp/extractor/younow.py b/yt_dlp/extractor/younow.py index 18112ba35..b67cb2e17 100644 --- a/yt_dlp/extractor/younow.py +++ b/yt_dlp/extractor/younow.py @@ -6,6 +6,7 @@ ExtractorError, format_field, int_or_none, + str_or_none, try_get, ) @@ -102,7 +103,7 @@ def _extract_moment(item, fatal=True): 'timestamp': int_or_none(item.get('created')), 'creator': uploader, 'uploader': uploader, - 'uploader_id': uploader_id, + 'uploader_id': str_or_none(uploader_id), 'uploader_url': uploader_url, 'formats': [{ 'url': 'https://hls.younow.com/momentsplaylists/live/%s/%s.m3u8' @@ -184,7 +185,7 @@ class YouNowMomentIE(InfoExtractor): 'timestamp': 1490432040, 'upload_date': '20170325', 'uploader': 'GABO...', - 'uploader_id': 35917228, + 'uploader_id': '35917228', }, } diff --git a/yt_dlp/extractor/zingmp3.py b/yt_dlp/extractor/zingmp3.py index f664d88d8..ff5eac89a 100644 --- a/yt_dlp/extractor/zingmp3.py +++ b/yt_dlp/extractor/zingmp3.py @@ -513,7 +513,6 @@ class ZingMp3LiveRadioIE(ZingMp3BaseIE): 'id': 'IWZ979UB', 'title': r're:^V\-POP', 'description': 'md5:aa857f8a91dc9ce69e862a809e4bdc10', - 'protocol': 'm3u8_native', 'ext': 'mp4', 'view_count': int, 'thumbnail': r're:^https?://.*\.jpg', @@ -529,7 +528,6 @@ class ZingMp3LiveRadioIE(ZingMp3BaseIE): 'id': 'IWZ97CWB', 'title': r're:^Live\s247', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', - 'protocol': 'm3u8_native', 'ext': 'm4a', 'view_count': int, 'thumbnail': r're:^https?://.*\.jpg',