[ie/joqrag] merge "master"

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>

README.md

@@ -1268,7 +1268,7 @@ The field names themselves (the part inside the parenthesis) can also have some
 
 1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a dot `.` separator; e.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`. You can do Python slicing with colon `:`; E.g. `%(id.3:7:-1)s`, `%(formats.:.format_id)s`. Curly braces `{}` can be used to build dictionaries with only specific keys; e.g. `%(formats.:.{format_id,height})#j`. An empty field name `%()s` refers to the entire infodict; e.g. `%(.{id,title})s`. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields
 
-1. **Addition**: Addition and subtraction of numeric fields can be done using `+` and `-` respectively. E.g. `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
+1. **Arithmetic**: Simple arithmetic can be done on numeric fields using `+`, `-` and `*`. E.g. `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
 
 1. **Date/time Formatting**: Date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it separated from the field name using a `>`. E.g. `%(duration>%H-%M-%S)s`, `%(upload_date>%Y-%m-%d)s`, `%(epoch-3600>%H-%M-%S)s`
 
@@ -1333,6 +1333,7 @@ The available fields are:
  - `was_live` (boolean): Whether this video was originally a live stream
  - `playable_in_embed` (string): Whether this video is allowed to play in embedded players on other sites
  - `availability` (string): Whether the video is "private", "premium_only", "subscriber_only", "needs_auth", "unlisted" or "public"
+ - `media_type` (string): The type of media as classified by the site, e.g. "episode", "clip", "trailer"
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
  - `extractor` (string): Name of the extractor

test/test_YoutubeDL.py

@@ -797,6 +797,7 @@ class TestYoutubeDL(unittest.TestCase):
         test('%(title|%)s %(title|%%)s', '% %%')
         test('%(id+1-height+3)05d', '00158')
         test('%(width+100)05d', 'NA')
+        test('%(filesize*8)d', '8192')
         test('%(formats.0) 15s', ('% 15s' % FORMATS[0], None))
         test('%(formats.0)r', (repr(FORMATS[0]), None))
         test('%(height.0)03d', '001')

test/test_utils.py

@@ -2317,23 +2317,6 @@ Line 1
         self.assertEqual(traverse_obj({}, (0, slice(1)), traverse_string=True), [],
                          msg='branching should result in list if `traverse_string`')
 
-        # Test is_user_input behavior
-        _IS_USER_INPUT_DATA = {'range8': list(range(8))}
-        self.assertEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3'),
-                                      is_user_input=True), 3,
-                         msg='allow for string indexing if `is_user_input`')
-        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', '3:'),
-                                           is_user_input=True), tuple(range(8))[3:],
-                              msg='allow for string slice if `is_user_input`')
-        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':4:2'),
-                                           is_user_input=True), tuple(range(8))[:4:2],
-                              msg='allow step in string slice if `is_user_input`')
-        self.assertCountEqual(traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':'),
-                                           is_user_input=True), range(8),
-                              msg='`:` should be treated as `...` if `is_user_input`')
-        with self.assertRaises(TypeError, msg='too many params should result in error'):
-            traverse_obj(_IS_USER_INPUT_DATA, ('range8', ':::'), is_user_input=True)
-
         # Test re.Match as input obj
         mobj = re.fullmatch(r'0(12)(?P<group>3)(4)?', '0123')
         self.assertEqual(traverse_obj(mobj, ...), [x for x in mobj.groups() if x is not None],

yt_dlp/YoutubeDL.py

@@ -1179,6 +1179,7 @@ class YoutubeDL:
         MATH_FUNCTIONS = {
             '+': float.__add__,
             '-': float.__sub__,
+            '*': float.__mul__,
         }
         # Field is of the form key1.key2...
         # where keys (except first) can be string, int, slice or "{field, ...}"
@@ -1200,6 +1201,15 @@ class YoutubeDL:
                 (?:\|(?P<default>.*?))?
             )$''')
 
+        def _from_user_input(field):
+            if field == ':':
+                return ...
+            elif ':' in field:
+                return slice(*map(int_or_none, field.split(':')))
+            elif int_or_none(field) is not None:
+                return int(field)
+            return field
+
         def _traverse_infodict(fields):
             fields = [f for x in re.split(r'\.({.+?})\.?', fields)
                       for f in ([x] if x.startswith('{') else x.split('.'))]
@@ -1209,11 +1219,12 @@ class YoutubeDL:
 
             for i, f in enumerate(fields):
                 if not f.startswith('{'):
+                    fields[i] = _from_user_input(f)
                     continue
                 assert f.endswith('}'), f'No closing brace for {f} in {fields}'
-                fields[i] = {k: k.split('.') for k in f[1:-1].split(',')}
+                fields[i] = {k: list(map(_from_user_input, k.split('.'))) for k in f[1:-1].split(',')}
 
-            return traverse_obj(info_dict, fields, is_user_input=True, traverse_string=True)
+            return traverse_obj(info_dict, fields, traverse_string=True)
 
         def get_value(mdict):
             # Object traversal

yt_dlp/__init__.py

@@ -73,14 +73,16 @@ def _exit(status=0, *args):
 
 
 def get_urls(urls, batchfile, verbose):
-    # Batch file verification
+    """
+    @param verbose      -1: quiet, 0: normal, 1: verbose
+    """
     batch_urls = []
     if batchfile is not None:
         try:
             batch_urls = read_batch_urls(
-                read_stdin('URLs') if batchfile == '-'
+                read_stdin(None if verbose == -1 else 'URLs') if batchfile == '-'
                 else open(expand_path(batchfile), encoding='utf-8', errors='ignore'))
-            if verbose:
+            if verbose == 1:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
         except OSError:
             _exit(f'ERROR: batch file {batchfile} could not be read')
@@ -721,7 +723,7 @@ ParsedOptions = collections.namedtuple('ParsedOptions', ('parser', 'options', 'u
 def parse_options(argv=None):
     """@returns ParsedOptions(parser, opts, urls, ydl_opts)"""
     parser, opts, urls = parseOpts(argv)
-    urls = get_urls(urls, opts.batchfile, opts.verbose)
+    urls = get_urls(urls, opts.batchfile, -1 if opts.quiet and not opts.verbose else opts.verbose)
 
     set_compat_opts(opts)
     try:

yt_dlp/extractor/aenetworks.py

@@ -121,11 +121,21 @@ class AENetworksIE(AENetworksBaseIE):
         'info_dict': {
             'id': '22253814',
             'ext': 'mp4',
-            'title': 'Winter is Coming',
-            'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
+            'title': 'Winter Is Coming',
+            'description': 'md5:a40e370925074260b1c8a633c632c63a',
             'timestamp': 1338306241,
             'upload_date': '20120529',
             'uploader': 'AENE-NEW',
+            'duration': 2592.0,
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:5',
+            'tags': 'count:14',
+            'categories': ['Mountain Men'],
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'season': 'Season 1',
+            'season_number': 1,
+            'series': 'Mountain Men',
         },
         'params': {
             # m3u8 download
@@ -143,6 +153,15 @@ class AENetworksIE(AENetworksBaseIE):
             'timestamp': 1452634428,
             'upload_date': '20160112',
             'uploader': 'AENE-NEW',
+            'duration': 1277.695,
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:4',
+            'tags': 'count:23',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'season': 'Season 9',
+            'season_number': 9,
+            'series': 'Duck Dynasty',
         },
         'params': {
             # m3u8 download

yt_dlp/extractor/bitchute.py

@@ -7,8 +7,10 @@ from ..utils import (
     ExtractorError,
     OnDemandPagedList,
     clean_html,
+    extract_attributes,
     get_element_by_class,
     get_element_by_id,
+    get_element_html_by_class,
     get_elements_html_by_class,
     int_or_none,
     orderedSet,
@@ -17,6 +19,7 @@ from ..utils import (
     traverse_obj,
     unified_strdate,
     urlencode_postdata,
+    urljoin,
 )
 
 
@@ -34,6 +37,25 @@ class BitChuteIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20170103',
+            'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+            'channel': 'BitChute',
+            'channel_url': 'https://www.bitchute.com/channel/bitchute/'
+        },
+    }, {
+        # test case: video with different channel and uploader
+        'url': 'https://www.bitchute.com/video/Yti_j9A-UZ4/',
+        'md5': 'f10e6a8e787766235946d0868703f1d0',
+        'info_dict': {
+            'id': 'Yti_j9A-UZ4',
+            'ext': 'mp4',
+            'title': 'Israel at War | Full Measure',
+            'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'sharylattkisson',
+            'upload_date': '20231106',
+            'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
+            'channel': 'Full Measure with Sharyl Attkisson',
+            'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/'
         },
     }, {
         # video not downloadable in browser, but we can recover it
@@ -48,6 +70,9 @@ class BitChuteIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20181113',
+            'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+            'channel': 'BitChute',
+            'channel_url': 'https://www.bitchute.com/channel/bitchute/'
         },
         'params': {'check_formats': None},
     }, {
@@ -99,6 +124,11 @@ class BitChuteIE(InfoExtractor):
             reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
             self.raise_geo_restricted(reason)
 
+    @staticmethod
+    def _make_url(html):
+        path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
+        return urljoin('https://www.bitchute.com', path)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
@@ -121,12 +151,19 @@ class BitChuteIE(InfoExtractor):
                 'Video is unavailable. Please make sure this video is playable in the browser '
                 'before reporting this issue.', expected=True, video_id=video_id)
 
+        details = get_element_by_class('details', webpage) or ''
+        uploader_html = get_element_html_by_class('creator', details) or ''
+        channel_html = get_element_html_by_class('name', details) or ''
+
         return {
             'id': video_id,
             'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
             'description': self._og_search_description(webpage, default=None),
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': clean_html(get_element_by_class('owner', webpage)),
+            'uploader': clean_html(uploader_html),
+            'uploader_url': self._make_url(uploader_html),
+            'channel': clean_html(channel_html),
+            'channel_url': self._make_url(channel_html),
             'upload_date': unified_strdate(self._search_regex(
                 r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
             'formats': formats,
@@ -154,6 +191,9 @@ class BitChuteChannelIE(InfoExtractor):
                     'thumbnail': r're:^https?://.*\.jpg$',
                     'uploader': 'BitChute',
                     'upload_date': '20170103',
+                    'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
+                    'channel': 'BitChute',
+                    'channel_url': 'https://www.bitchute.com/channel/bitchute/',
                     'duration': 16,
                     'view_count': int,
                 },
@@ -169,7 +209,7 @@ class BitChuteChannelIE(InfoExtractor):
         'info_dict': {
             'id': 'wV9Imujxasw9',
             'title': 'Bruce MacDonald and "The Light of Darkness"',
-            'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
+            'description': 'md5:747724ef404eebdfc04277714f81863e',
         }
     }]
 

yt_dlp/extractor/cbc.py

@@ -180,6 +180,13 @@ class CBCPlayerIE(InfoExtractor):
             'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
             'chapters': [],
             'duration': 494.811,
+            'categories': ['AudioMobile/All in a Weekend Montreal'],
+            'tags': 'count:8',
+            'location': 'Quebec',
+            'series': 'All in a Weekend Montreal',
+            'season': 'Season 2015',
+            'season_number': 2015,
+            'media_type': 'Excerpt',
         },
     }, {
         'url': 'http://www.cbc.ca/player/play/2164402062',
@@ -195,25 +202,37 @@ class CBCPlayerIE(InfoExtractor):
             'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
             'chapters': [],
             'duration': 186.867,
+            'series': 'CBC News: Windsor at 6:00',
+            'categories': ['News/Canada/Windsor'],
+            'location': 'Windsor',
+            'tags': ['cancer'],
+            'creator': 'Allison Johnson',
+            'media_type': 'Excerpt',
         },
     }, {
         # Has subtitles
         # These broadcasts expire after ~1 month, can find new test URL here:
         # https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
-        'url': 'http://www.cbc.ca/player/play/2249992771553',
-        'md5': '2f2fb675dd4f0f8a5bb7588d1b13bacd',
+        'url': 'http://www.cbc.ca/player/play/2284799043667',
+        'md5': '9b49f0839e88b6ec0b01d840cf3d42b5',
         'info_dict': {
-            'id': '2249992771553',
+            'id': '2284799043667',
             'ext': 'mp4',
-            'title': 'The National | Women’s soccer pay, Florida seawater, Swift quake',
-            'description': 'md5:adba28011a56cfa47a080ff198dad27a',
-            'timestamp': 1690596000,
-            'duration': 2716.333,
+            'title': 'The National | Hockey coach charged, Green grants, Safer drugs',
+            'description': 'md5:84ef46321c94bcf7d0159bb565d26bfa',
+            'timestamp': 1700272800,
+            'duration': 2718.833,
             'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
-            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/481/326/thumbnail.jpeg',
+            'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/907/171/thumbnail.jpeg',
             'uploader': 'CBCC-NEW',
             'chapters': 'count:5',
-            'upload_date': '20230729',
+            'upload_date': '20231118',
+            'categories': 'count:4',
+            'series': 'The National - Full Show',
+            'tags': 'count:1',
+            'creator': 'News',
+            'location': 'Canada',
+            'media_type': 'Full Program',
         },
     }]
 

yt_dlp/extractor/common.py

@@ -382,6 +382,7 @@ class InfoExtractor:
                     'private', 'premium_only', 'subscriber_only', 'needs_auth',
                     'unlisted' or 'public'. Use 'InfoExtractor._availability'
                     to set it
+    media_type:     The type of media as classified by the site, e.g. "episode", "clip", "trailer"
     _old_archive_ids: A list of old archive ids needed for backward compatibility
     _format_sort_fields: A list of fields to use for sorting formats
     __post_extractor: A function to be called just before the metadata is

yt_dlp/extractor/cwtv.py

@@ -46,6 +46,10 @@ class CWTVIE(InfoExtractor):
             'timestamp': 1444107300,
             'age_limit': 14,
             'uploader': 'CWTV',
+            'thumbnail': r're:^https?://.*\.jpe?g$',
+            'chapters': 'count:4',
+            'episode': 'Episode 20',
+            'season': 'Season 11',
         },
         'params': {
             # m3u8 download

yt_dlp/extractor/eplus.py

@@ -1,15 +1,20 @@
+import json
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     try_call,
     unified_timestamp,
+    urlencode_postdata,
 )
 
 
 class EplusIbIE(InfoExtractor):
-    IE_NAME = 'eplus:inbound'
-    IE_DESC = 'e+ (イープラス) overseas'
-    _VALID_URL = r'https?://live\.eplus\.jp/ex/player\?ib=(?P<id>(?:\w|%2B|%2F){86}%3D%3D)'
+    _NETRC_MACHINE = 'eplus'
+    IE_NAME = 'eplus'
+    IE_DESC = 'e+ (イープラス)'
+    _VALID_URL = [r'https?://live\.eplus\.jp/ex/player\?ib=(?P<id>(?:\w|%2B|%2F){86}%3D%3D)',
+                  r'https?://live\.eplus\.jp/(?P<id>sample|\d+)']
     _TESTS = [{
         'url': 'https://live.eplus.jp/ex/player?ib=YEFxb3Vyc2Dombnjg7blkrLlrablnJLjgrnjgq%2Fjg7zjg6vjgqLjgqTjg4njg6vlkIzlpb3kvJpgTGllbGxhIQ%3D%3D',
         'info_dict': {
@@ -29,14 +34,97 @@ class EplusIbIE(InfoExtractor):
             'No video formats found!',
             'Requested format is not available',
         ],
+    }, {
+        'url': 'https://live.eplus.jp/sample',
+        'info_dict': {
+            'id': 'stream1ng20210719-test-005',
+            'title': 'Online streaming test for DRM',
+            'live_status': 'was_live',
+            'release_date': '20210719',
+            'release_timestamp': 1626703200,
+            'description': None,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Could not find the playlist URL. This event may not be accessible',
+            'No video formats found!',
+            'Requested format is not available',
+            'This video is DRM protected',
+        ],
+    }, {
+        'url': 'https://live.eplus.jp/2053935',
+        'info_dict': {
+            'id': '331320-0001-001',
+            'title': '丘みどり2020配信LIVE Vol.2 ～秋麗～ 【Streaming+(配信チケット)】',
+            'live_status': 'was_live',
+            'release_date': '20200920',
+            'release_timestamp': 1600596000,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'expected_warnings': [
+            'Could not find the playlist URL. This event may not be accessible',
+            'No video formats found!',
+            'Requested format is not available',
+        ],
     }]
 
+    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0'
+
+    def _login(self, username, password, urlh):
+        if not self._get_cookies('https://live.eplus.jp/').get('ci_session'):
+            raise ExtractorError('Unable to get ci_session cookie')
+
+        cltft_token = urlh.headers.get('X-CLTFT-Token')
+        if not cltft_token:
+            raise ExtractorError('Unable to get X-CLTFT-Token')
+        self._set_cookie('live.eplus.jp', 'X-CLTFT-Token', cltft_token)
+
+        login_json = self._download_json(
+            'https://live.eplus.jp/member/api/v1/FTAuth/idpw', None,
+            note='Sending pre-login info', errnote='Unable to send pre-login info', headers={
+                'Content-Type': 'application/json; charset=UTF-8',
+                'Referer': urlh.url,
+                'X-Cltft-Token': cltft_token,
+                'Accept': '*/*',
+            }, data=json.dumps({
+                'loginId': username,
+                'loginPassword': password,
+            }).encode())
+        if not login_json.get('isSuccess'):
+            raise ExtractorError('Login failed: Invalid id or password', expected=True)
+
+        self._request_webpage(
+            urlh.url, None, note='Logging in', errnote='Unable to log in',
+            data=urlencode_postdata({
+                'loginId': username,
+                'loginPassword': password,
+                'Token.Default': cltft_token,
+                'op': 'nextPage',
+            }), headers={'Referer': urlh.url})
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage, urlh = self._download_webpage_handle(
+            url, video_id, headers={'User-Agent': self._USER_AGENT})
+        if urlh.url.startswith('https://live.eplus.jp/member/auth'):
+            username, password = self._get_login_info()
+            if not username:
+                self.raise_login_required()
+            self._login(username, password, urlh)
+            webpage = self._download_webpage(
+                url, video_id, headers={'User-Agent': self._USER_AGENT})
 
         data_json = self._search_json(r'<script>\s*var app\s*=', webpage, 'data json', video_id)
 
+        if data_json.get('drm_mode') == 'ON':
+            self.report_drm(video_id)
+
         delivery_status = data_json.get('delivery_status')
         archive_mode = data_json.get('archive_mode')
         release_timestamp = try_call(lambda: unified_timestamp(data_json['event_datetime']) - 32400)
@@ -64,7 +152,7 @@ class EplusIbIE(InfoExtractor):
         formats = []
 
         m3u8_playlist_urls = self._search_json(
-            r'var listChannels\s*=', webpage, 'hls URLs', video_id, contains_pattern=r'\[.+\]', default=[])
+            r'var\s+listChannels\s*=', webpage, 'hls URLs', video_id, contains_pattern=r'\[.+\]', default=[])
         if not m3u8_playlist_urls:
             if live_status == 'is_upcoming':
                 self.raise_no_formats(

yt_dlp/extractor/francetv.py

@@ -1,12 +1,14 @@
 from .common import InfoExtractor
+from .dailymotion import DailymotionIE
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     format_field,
+    int_or_none,
+    join_nonempty,
     parse_iso8601,
     parse_qs,
 )
-from .dailymotion import DailymotionIE
 
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
@@ -82,6 +84,8 @@ class FranceTVIE(InfoExtractor):
         videos = []
         title = None
         subtitle = None
+        episode_number = None
+        season_number = None
         image = None
         duration = None
         timestamp = None
@@ -112,7 +116,9 @@ class FranceTVIE(InfoExtractor):
             if meta:
                 if title is None:
                     title = meta.get('title')
-                # XXX: what is meta['pre_title']?
+                # meta['pre_title'] contains season and episode number for series in format "S<ID> E<ID>"
+                season_number, episode_number = self._search_regex(
+                    r'S(\d+)\s*E(\d+)', meta.get('pre_title'), 'episode info', group=(1, 2), default=(None, None))
                 if subtitle is None:
                     subtitle = meta.get('additional_title')
                 if image is None:
@@ -191,19 +197,19 @@ class FranceTVIE(InfoExtractor):
                 } for sheet in spritesheets]
             })
 
-        if subtitle:
-            title += ' - %s' % subtitle
-        title = title.strip()
-
         return {
             'id': video_id,
-            'title': title,
+            'title': join_nonempty(title, subtitle, delim=' - ').strip(),
             'thumbnail': image,
             'duration': duration,
             'timestamp': timestamp,
             'is_live': is_live,
             'formats': formats,
             'subtitles': subtitles,
+            'episode': subtitle if episode_number else None,
+            'series': title if episode_number else None,
+            'episode_number': int_or_none(episode_number),
+            'season_number': int_or_none(season_number),
         }
 
     def _real_extract(self, url):
@@ -230,14 +236,31 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
             'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
             'ext': 'mp4',
             'title': '13h15, le dimanche... - Les mystères de Jésus',
-            'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
             'timestamp': 1502623500,
+            'duration': 2580,
+            'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20170813',
         },
         'params': {
             'skip_download': True,
         },
         'add_ie': [FranceTVIE.ie_key()],
+    }, {
+        'url': 'https://www.france.tv/enfants/six-huit-ans/foot2rue/saison-1/3066387-duel-au-vieux-port.html',
+        'info_dict': {
+            'id': 'a9050959-eedd-4b4a-9b0d-de6eeaa73e44',
+            'ext': 'mp4',
+            'title': 'Foot2Rue - Duel au vieux port',
+            'episode': 'Duel au vieux port',
+            'series': 'Foot2Rue',
+            'episode_number': 1,
+            'season_number': 1,
+            'timestamp': 1642761360,
+            'upload_date': '20220121',
+            'season': 'Season 1',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 1441,
+        },
     }, {
         # france3
         'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',

yt_dlp/extractor/joqrag.py

@@ -12,8 +12,7 @@ from ..utils import (
 
 class JoqrAgIE(InfoExtractor):
     IE_DESC = '超!A&G+ 文化放送 Nippon Cultural Broadcasting, Inc. (JOQR, AGQR)'
-    _VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/player\.php',
-                  r'https?://www\.uniqueradio\.jp/agplayer5/inc-player-hls\.php',
+    _VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/(?:player|inc-player-hls)\.php',
                   r'https?://(?:www\.)?joqr\.co\.jp/ag/',
                   r'https?://(?:www\.)?joqr\.co\.jp/qr/ag(?:daily|regular)program/?(?:$|[#?])']
     _TESTS = [{
@@ -44,22 +43,22 @@ class JoqrAgIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    def _extract_metadata(self, variable, html, name):
+    def _extract_metadata(self, variable, html):
         return clean_html(urllib.parse.unquote_plus(self._search_regex(
             rf'var\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
-            html, name, group='value', default=''))) or None
+            html, 'metadata', group='value', default=''))) or None
 
     def _extract_start_timestamp(self, video_id, is_live):
         def extract_start_time_from(date_str):
             dt = datetime_from_str(date_str) + datetime.timedelta(hours=9)
             date = dt.strftime('%Y%m%d')
             start_time = self._search_regex(
-                r'<h3[^>]+\bclass="dailyProgram-itemHeaderTime"[^>]*>[\s\d:]+–\s*(?P<time>\d{1,2}:\d{1,2})',
+                r'<h3[^>]+\bclass="dailyProgram-itemHeaderTime"[^>]*>[\s\d:]+–\s*(\d{1,2}:\d{1,2})',
                 self._download_webpage(
                     f'https://www.joqr.co.jp/qr/agdailyprogram/?date={date}', video_id,
                     note=f'Downloading program list of {date}', fatal=False,
                     errnote=f'Failed to download program list of {date}') or '',
-                'start time of the first program', default=None, group='time')
+                'start time', default=None)
             if start_time:
                 return unified_timestamp(f'{dt.strftime("%Y/%m/%d")} {start_time} +09:00')
             return None
@@ -79,7 +78,7 @@ class JoqrAgIE(InfoExtractor):
         metadata = self._download_webpage(
             'https://www.uniqueradio.jp/aandg', video_id,
             note='Downloading metadata', errnote='Failed to download metadata')
-        title = self._extract_metadata('Program_name', metadata, 'program title')
+        title = self._extract_metadata('Program_name', metadata)
 
         if title == '放送休止':
             formats = []
@@ -106,7 +105,7 @@ class JoqrAgIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'channel': '超!A&G+',
-            'description': self._extract_metadata('Program_text', metadata, 'program description'),
+            'description': self._extract_metadata('Program_text', metadata),
             'formats': formats,
             'live_status': live_status,
             'release_timestamp': release_timestamp,

yt_dlp/extractor/mediaset.py

@@ -73,6 +73,7 @@ class MediasetIE(ThePlatformBaseIE):
             'season_number': 5,
             'episode_number': 5,
             'chapters': [{'start_time': 0.0, 'end_time': 3409.08}, {'start_time': 3409.08, 'end_time': 6565.008}],
+            'categories': ['Informazione'],
         },
     }, {
         # DRM
@@ -149,6 +150,7 @@ class MediasetIE(ThePlatformBaseIE):
             'season_number': 12,
             'episode': 'Episode 8',
             'episode_number': 8,
+            'categories': ['Intrattenimento'],
         },
         'params': {
             'skip_download': True,

yt_dlp/extractor/mediastream.py

@@ -3,8 +3,11 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    filter_dict,
+    parse_qs,
     remove_end,
     traverse_obj,
+    update_url_query,
     urljoin,
 )
 
@@ -108,7 +111,9 @@ class MediaStreamIE(MediaStreamBaseIE):
 
         for message in [
             'Debido a tu ubicación no puedes ver el contenido',
-            'You are not allowed to watch this video: Geo Fencing Restriction'
+            'You are not allowed to watch this video: Geo Fencing Restriction',
+            'Este contenido no está disponible en tu zona geográfica.',
+            'El contenido sólo está disponible dentro de',
         ]:
             if message in webpage:
                 self.raise_geo_restricted()
@@ -118,7 +123,16 @@ class MediaStreamIE(MediaStreamBaseIE):
         formats, subtitles = [], {}
         for video_format in player_config['src']:
             if video_format == 'hls':
-                fmts, subs = self._extract_m3u8_formats_and_subtitles(player_config['src'][video_format], video_id)
+                params = {
+                    'at': 'web-app',
+                    'access_token': traverse_obj(parse_qs(url), ('access_token', 0)),
+                }
+                for name, key in (('MDSTRMUID', 'uid'), ('MDSTRMSID', 'sid'), ('MDSTRMPID', 'pid'), ('VERSION', 'av')):
+                    params[key] = self._search_regex(
+                        rf'window\.{name}\s*=\s*["\']([^"\']+)["\'];', webpage, key, default=None)
+
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    update_url_query(player_config['src'][video_format], filter_dict(params)), video_id)
                 formats.extend(fmts)
                 self._merge_subtitles(subs, target=subtitles)
             elif video_format == 'mpd':

yt_dlp/extractor/nbc.py

@@ -53,6 +53,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'chapters': 'count:1',
                 'tags': 'count:4',
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/The Tonight Show Starring Jimmy Fallon'],
+                'media_type': 'Full Episode',
             },
             'params': {
                 'skip_download': 'm3u8',
@@ -131,6 +133,8 @@ class NBCIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
                 'tags': 'count:10',
                 'age_limit': 0,
                 'thumbnail': r're:https?://.+\.jpg',
+                'categories': ['Series/Quantum Leap 2022'],
+                'media_type': 'Highlight',
             },
             'params': {
                 'skip_download': 'm3u8',

yt_dlp/extractor/ondemandkorea.py

@@ -3,7 +3,6 @@ import re
 import uuid
 
 from .common import InfoExtractor
-from ..networking import HEADRequest
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
@@ -84,15 +83,17 @@ class OnDemandKoreaIE(InfoExtractor):
         def try_geo_bypass(url):
             return traverse_obj(url, ({parse_qs}, 'stream_url', 0, {url_or_none})) or url
 
-        def try_upgrade_quality(url):
-            mod_url = re.sub(r'_720(p?)\.m3u8', r'_1080\1.m3u8', url)
-            return mod_url if mod_url != url and self._request_webpage(
-                HEADRequest(mod_url), video_id, note='Checking for higher quality format',
-                errnote='No higher quality format found', fatal=False) else url
-
         formats = []
         for m3u8_url in traverse_obj(data, (('sources', 'manifest'), ..., 'url', {url_or_none}, {try_geo_bypass})):
-            formats.extend(self._extract_m3u8_formats(try_upgrade_quality(m3u8_url), video_id, fatal=False))
+            mod_url = re.sub(r'_720(p?)\.m3u8', r'_1080\1.m3u8', m3u8_url)
+            if mod_url != m3u8_url:
+                mod_format = self._extract_m3u8_formats(
+                    mod_url, video_id, note='Checking for higher quality format',
+                    errnote='No higher quality format found', fatal=False)
+                if mod_format:
+                    formats.extend(mod_format)
+                    continue
+            formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, fatal=False))
 
         subtitles = {}
         for track in traverse_obj(data, ('text_tracks', lambda _, v: url_or_none(v['url']))):

yt_dlp/extractor/pr0gramm.py

@@ -4,7 +4,14 @@ from urllib.parse import unquote
 
 from .common import InfoExtractor
 from ..compat import functools
-from ..utils import ExtractorError, make_archive_id, urljoin
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    make_archive_id,
+    mimetype2ext,
+    urljoin,
+)
 from ..utils.traversal import traverse_obj
 
 
@@ -26,6 +33,7 @@ class Pr0grammIE(InfoExtractor):
             'dislike_count': int,
             'age_limit': 0,
             'thumbnail': r're:^https://thumb\.pr0gramm\.com/.*\.jpg',
+            '_old_archive_ids': ['pr0grammstatic 5466437'],
         },
     }, {
         # Tags require account
@@ -43,6 +51,7 @@ class Pr0grammIE(InfoExtractor):
             'dislike_count': int,
             'age_limit': 0,
             'thumbnail': r're:^https://thumb\.pr0gramm\.com/.*\.jpg',
+            '_old_archive_ids': ['pr0grammstatic 3052805'],
         },
     }, {
         # Requires verified account
@@ -60,6 +69,7 @@ class Pr0grammIE(InfoExtractor):
             'dislike_count': int,
             'age_limit': 18,
             'thumbnail': r're:^https://thumb\.pr0gramm\.com/.*\.jpg',
+            '_old_archive_ids': ['pr0grammstatic 5848332'],
         },
     }, {
         'url': 'https://pr0gramm.com/static/5466437',
@@ -110,37 +120,61 @@ class Pr0grammIE(InfoExtractor):
 
         return data
 
+    @staticmethod
+    def _create_source_url(path):
+        return urljoin('https://img.pr0gramm.com', path)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_info = traverse_obj(
             self._call_api('get', video_id, {'id': video_id, 'flags': self._maximum_flags}),
             ('items', 0, {dict}))
 
-        source = urljoin('https://img.pr0gramm.com', video_info.get('image'))
+        source = video_info.get('image')
         if not source or not source.endswith('mp4'):
             self.raise_no_formats('Could not extract a video', expected=bool(source), video_id=video_id)
 
         tags = None
         if self._is_logged_in:
-            metadata = self._call_api('info', video_id, {'itemId': video_id})
+            metadata = self._call_api('info', video_id, {'itemId': video_id}, note='Downloading tags')
             tags = traverse_obj(metadata, ('tags', ..., 'tag', {str}))
             # Sorted by "confidence", higher confidence = earlier in list
             confidences = traverse_obj(metadata, ('tags', ..., 'confidence', ({int}, {float})))
             if confidences:
                 tags = [tag for _, tag in sorted(zip(confidences, tags), reverse=True)]
 
+        formats = traverse_obj(video_info, ('variants', ..., {
+            'format_id': ('name', {str}),
+            'url': ('path', {self._create_source_url}),
+            'ext': ('mimeType', {mimetype2ext}),
+            'vcodec': ('codec', {str}),
+            'width': ('width', {int_or_none}),
+            'height': ('height', {int_or_none}),
+            'bitrate': ('bitRate', {float_or_none}),
+            'filesize': ('fileSize', {int_or_none}),
+        })) if video_info.get('variants') else [{
+            'ext': 'mp4',
+            'format_id': 'source',
+            **traverse_obj(video_info, {
+                'url': ('image', {self._create_source_url}),
+                'width': ('width', {int_or_none}),
+                'height': ('height', {int_or_none}),
+            }),
+        }]
+
+        subtitles = {}
+        for subtitle in traverse_obj(video_info, ('subtitles', lambda _, v: v['language'])):
+            subtitles.setdefault(subtitle['language'], []).append(traverse_obj(subtitle, {
+                'url': ('path', {self._create_source_url}),
+                'note': ('label', {str}),
+            }))
+
         return {
             'id': video_id,
             'title': f'pr0gramm-{video_id} by {video_info.get("user")}',
-            'formats': [{
-                'url': source,
-                'ext': 'mp4',
-                **traverse_obj(video_info, {
-                    'width': ('width', {int}),
-                    'height': ('height', {int}),
-                }),
-            }],
             'tags': tags,
+            'formats': formats,
+            'subtitles': subtitles,
             'age_limit': 18 if traverse_obj(video_info, ('flags', {0b110.__and__})) else 0,
             '_old_archive_ids': [make_archive_id('Pr0grammStatic', video_id)],
             **traverse_obj(video_info, {

yt_dlp/extractor/scrippsnetworks.py

@@ -114,6 +114,8 @@ class ScrippsNetworksIE(InfoExtractor):
             'timestamp': 1475678834,
             'upload_date': '20161005',
             'uploader': 'SCNI-SCND',
+            'tags': 'count:10',
+            'creator': 'Cooking Channel',
             'duration': 29.995,
             'chapters': [{'start_time': 0.0, 'end_time': 29.995, 'title': '<Untitled Chapter 1>'}],
             'thumbnail': 'https://images.dds.discovery.com/up/tp/Scripps_-_Food_Category_Prod/122/987/0260338_630x355.jpg',

yt_dlp/extractor/theplatform.py

@@ -104,6 +104,10 @@ class ThePlatformBaseIE(OnceIE):
                 _add_chapter(chapter.get('startTime'), chapter.get('endTime'))
             _add_chapter(tp_chapters[-1].get('startTime'), tp_chapters[-1].get('endTime') or duration)
 
+        def extract_site_specific_field(field):
+            # A number of sites have custom-prefixed keys, e.g. 'cbc$seasonNumber'
+            return traverse_obj(info, lambda k, v: v and k.endswith(f'${field}'), get_all=False)
+
         return {
             'title': info['title'],
             'subtitles': subtitles,
@@ -113,6 +117,14 @@ class ThePlatformBaseIE(OnceIE):
             'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
             'uploader': info.get('billingCode'),
             'chapters': chapters,
+            'creator': traverse_obj(info, ('author', {str})) or None,
+            'categories': traverse_obj(info, (
+                'categories', lambda _, v: v.get('label') in ('category', None), 'name', {str})) or None,
+            'tags': traverse_obj(info, ('keywords', {lambda x: re.split(r'[;,]\s?', x) if x else None})),
+            'location': extract_site_specific_field('region'),
+            'series': extract_site_specific_field('show'),
+            'season_number': int_or_none(extract_site_specific_field('seasonNumber')),
+            'media_type': extract_site_specific_field('programmingType') or extract_site_specific_field('type'),
         }
 
     def _extract_theplatform_metadata(self, path, video_id):

yt_dlp/extractor/youtube.py

@@ -428,7 +428,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         r'(?:www\.)?piped\.adminforge\.de',
         r'(?:www\.)?watch\.whatevertinfoil\.de',
         r'(?:www\.)?piped\.qdi\.fi',
-        r'(?:www\.)?piped\.video',
+        r'(?:(?:www|cf)\.)?piped\.video',
         r'(?:www\.)?piped\.aeong\.one',
         r'(?:www\.)?piped\.moomoo\.me',
         r'(?:www\.)?piped\.chauvet\.pro',
@@ -6469,6 +6469,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
     def _has_tab(self, tabs, tab_id):
         return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
 
+    def _empty_playlist(self, item_id, data):
+        return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data))
+
     @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
     def _real_extract(self, url, smuggled_data):
         item_id = self._match_id(url)
@@ -6534,6 +6537,10 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url)  # NB: Name may be translated
             self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
 
+            # /about is no longer a tab
+            if original_tab_id == 'about':
+                return self._empty_playlist(item_id, data)
+
             if not original_tab_id and selected_tab_name:
                 self.to_screen('Downloading all uploads of the channel. '
                                'To download only the videos in a specific tab, pass the tab\'s URL')
@@ -6546,7 +6553,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
                 if not extra_tabs and selected_tab_id != 'videos':
                     # Channel does not have streams, shorts or videos tabs
                     if item_id[:2] != 'UC':
-                        raise ExtractorError('This channel has no uploads', expected=True)
+                        return self._empty_playlist(item_id, data)
 
                     # Topic channels don't have /videos. Use the equivalent playlist instead
                     pl_id = f'UU{item_id[2:]}'
@@ -6554,7 +6561,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
                     try:
                         data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
                     except ExtractorError:
-                        raise ExtractorError('This channel has no uploads', expected=True)
+                        return self._empty_playlist(item_id, data)
                     else:
                         item_id, url = pl_id, pl_url
                         self.to_screen(

yt_dlp/utils/_utils.py

@@ -4789,6 +4789,7 @@ def parse_http_range(range):
 
 
 def read_stdin(what):
+    if what:
         eof = 'Ctrl+Z' if compat_os_name == 'nt' else 'Ctrl+D'
         write_string(f'Reading {what} from STDIN - EOF ({eof}) to end:\n')
     return sys.stdin

yt_dlp/utils/traversal.py

@@ -8,7 +8,7 @@ from ._utils import (
     IDENTITY,
     NO_DEFAULT,
     LazyList,
-    int_or_none,
+    deprecation_warning,
     is_iterable_like,
     try_call,
     variadic,
@@ -17,7 +17,7 @@ from ._utils import (
 
 def traverse_obj(
         obj, *paths, default=NO_DEFAULT, expected_type=None, get_all=True,
-        casesense=True, is_user_input=False, traverse_string=False):
+        casesense=True, is_user_input=NO_DEFAULT, traverse_string=False):
     """
     Safely traverse nested `dict`s and `Iterable`s
 
@@ -63,10 +63,8 @@ def traverse_obj(
     @param get_all          If `False`, return the first matching result, otherwise all matching ones.
     @param casesense        If `False`, consider string dictionary keys as case insensitive.
 
-    The following are only meant to be used by YoutubeDL.prepare_outtmpl and are not part of the API
+    `traverse_string` is only meant to be used by YoutubeDL.prepare_outtmpl and is not part of the API
 
-    @param is_user_input    Whether the keys are generated from user input.
-                            If `True` strings get converted to `int`/`slice` if needed.
     @param traverse_string  Whether to traverse into objects as strings.
                             If `True`, any non-compatible object will first be
                             converted into a string and then traversed into.
@@ -80,6 +78,9 @@ def traverse_obj(
                             If no `default` is given and the last path branches, a `list` of results
                             is always returned. If a path ends on a `dict` that result will always be a `dict`.
     """
+    if is_user_input is not NO_DEFAULT:
+        deprecation_warning('The is_user_input parameter is deprecated and no longer works')
+
     casefold = lambda k: k.casefold() if isinstance(k, str) else k
 
     if isinstance(expected_type, type):
@@ -195,14 +196,6 @@ def traverse_obj(
 
         key = None
         for last, key in lazy_last(variadic(path, (str, bytes, dict, set))):
-            if is_user_input and isinstance(key, str):
-                if key == ':':
-                    key = ...
-                elif ':' in key:
-                    key = slice(*map(int_or_none, key.split(':')))
-                elif int_or_none(key) is not None:
-                    key = int(key)
-
             if not casesense and isinstance(key, str):
                 key = key.casefold()
 

yt_dlp/webvtt.py

@@ -95,6 +95,7 @@ _REGEX_TS = re.compile(r'''(?x)
 _REGEX_EOF = re.compile(r'\Z')
 _REGEX_NL = re.compile(r'(?:\r\n|[\r\n]|$)')
 _REGEX_BLANK = re.compile(r'(?:\r\n|[\r\n])+')
+_REGEX_OPTIONAL_WHITESPACE = re.compile(r'[ \t]*')
 
 
 def _parse_ts(ts):
@@ -285,6 +286,7 @@ class CueBlock(Block):
         m1 = parser.consume(_REGEX_TS)
         if not m1:
             return None
+        parser.consume(_REGEX_OPTIONAL_WHITESPACE)
         m2 = parser.consume(cls._REGEX_SETTINGS)
         if not parser.consume(_REGEX_NL):
             return None