Merge branch 'yt-dlp:master' into feat/run-tests

- Support group /posts/ URLs
- Raise a proper error message if no formats are found

Closes #8669
Authored by: kclauhk

.github/workflows/build.yml

@@ -80,12 +80,12 @@ on:
         default: true
         type: boolean
       origin:
-        description: .
+        description: Origin
         required: false
-        default: ''
+        default: 'current repo'
         type: choice
         options:
-        - ''
+        - 'current repo'
 
 permissions:
   contents: read
@@ -99,7 +99,7 @@ jobs:
       - name: Process origin
         id: process_origin
         run: |
-          echo "origin=${{ inputs.origin || github.repository }}" >> "$GITHUB_OUTPUT"
+          echo "origin=${{ inputs.origin == 'current repo' && github.repository || inputs.origin }}" | tee "$GITHUB_OUTPUT"
 
   unix:
     needs: process

.github/workflows/core.yml

@@ -1,5 +1,25 @@
 name: Core Tests
-on: [push, pull_request]
+on:
+  push:
+    paths:
+      - .github/**
+      - devscripts/**
+      - test/**
+      - yt_dlp/**.py
+      - '!yt_dlp/extractor/*.py'
+      - yt_dlp/extractor/__init__.py
+      - yt_dlp/extractor/common.py
+      - yt_dlp/extractor/extractors.py
+  pull_request:
+    paths:
+      - .github/**
+      - devscripts/**
+      - test/**
+      - yt_dlp/**.py
+      - '!yt_dlp/extractor/*.py'
+      - yt_dlp/extractor/__init__.py
+      - yt_dlp/extractor/common.py
+      - yt_dlp/extractor/extractors.py
 permissions:
   contents: read
 

.github/workflows/release.yml

@@ -64,7 +64,6 @@ jobs:
       target_tag: ${{ steps.setup_variables.outputs.target_tag }}
       pypi_project: ${{ steps.setup_variables.outputs.pypi_project }}
       pypi_suffix: ${{ steps.setup_variables.outputs.pypi_suffix }}
-      pypi_token: ${{ steps.setup_variables.outputs.pypi_token }}
       head_sha: ${{ steps.get_target.outputs.head_sha }}
 
     steps:
@@ -153,7 +152,6 @@ jobs:
               ${{ !!secrets[format('{0}_archive_repo_token', env.target_repo)] }} || fallback_token
               pypi_project='${{ vars[format('{0}_pypi_project', env.target_repo)] }}'
               pypi_suffix='${{ vars[format('{0}_pypi_suffix', env.target_repo)] }}'
-              ${{ !secrets[format('{0}_pypi_token', env.target_repo)] }} || pypi_token='${{ env.target_repo }}_pypi_token'
             fi
           else
             target_tag="${source_tag:-${version}}"
@@ -163,7 +161,6 @@ jobs:
               ${{ !!secrets[format('{0}_archive_repo_token', env.source_repo)] }} || fallback_token
               pypi_project='${{ vars[format('{0}_pypi_project', env.source_repo)] }}'
               pypi_suffix='${{ vars[format('{0}_pypi_suffix', env.source_repo)] }}'
-              ${{ !secrets[format('{0}_pypi_token', env.source_repo)] }} || pypi_token='${{ env.source_repo }}_pypi_token'
             else
               target_repo='${{ github.repository }}'
             fi
@@ -172,13 +169,6 @@ jobs:
           if [[ "${target_repo}" == '${{ github.repository }}' ]] && ${{ !inputs.prerelease }}; then
             pypi_project='${{ vars.PYPI_PROJECT }}'
           fi
-          if [[ -z "${pypi_token}" && "${pypi_project}" ]]; then
-            if ${{ !secrets.PYPI_TOKEN }}; then
-              pypi_token=OIDC
-            else
-              pypi_token=PYPI_TOKEN
-            fi
-          fi
 
           echo "::group::Output variables"
           cat << EOF | tee -a "$GITHUB_OUTPUT"
@@ -189,7 +179,6 @@ jobs:
           target_tag=${target_tag}
           pypi_project=${pypi_project}
           pypi_suffix=${pypi_suffix}
-          pypi_token=${pypi_token}
           EOF
           echo "::endgroup::"
 
@@ -286,18 +275,7 @@ jobs:
           python devscripts/set-variant.py pip -M "You installed yt-dlp with pip or using the wheel from PyPi; Use that to update"
           python setup.py sdist bdist_wheel
 
-      - name: Publish to PyPI via token
-        env:
-          TWINE_USERNAME: __token__
-          TWINE_PASSWORD: ${{ secrets[needs.prepare.outputs.pypi_token] }}
-        if: |
-          needs.prepare.outputs.pypi_token != 'OIDC' && env.TWINE_PASSWORD
-        run: |
-          twine upload dist/*
-
-      - name: Publish to PyPI via trusted publishing
-        if: |
-          needs.prepare.outputs.pypi_token == 'OIDC'
+      - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           verbose: true

README.md

@@ -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

@@ -140,6 +140,8 @@ class TestFormatSelection(unittest.TestCase):
         test('example-with-dashes', 'example-with-dashes')
         test('all', '2', '47', '45', 'example-with-dashes', '35')
         test('mergeall', '2+47+45+example-with-dashes+35', multi=True)
+        # See: https://github.com/yt-dlp/yt-dlp/pulls/8797
+        test('7_a/worst', '35')
 
     def test_format_selection_audio(self):
         formats = [

test/test_networking.py

@@ -328,7 +328,7 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
         https_server_thread.start()
 
         with handler(verify=False) as rh:
-            with pytest.raises(SSLError, match='sslv3 alert handshake failure') as exc_info:
+            with pytest.raises(SSLError, match=r'ssl(?:v3|/tls) alert handshake failure') as exc_info:
                 validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 

test/test_update.py

@@ -11,6 +11,14 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import FakeYDL, report_warning
 from yt_dlp.update import Updater, UpdateInfo
 
+
+# XXX: Keep in sync with yt_dlp.update.UPDATE_SOURCES
+TEST_UPDATE_SOURCES = {
+    'stable': 'yt-dlp/yt-dlp',
+    'nightly': 'yt-dlp/yt-dlp-nightly-builds',
+    'master': 'yt-dlp/yt-dlp-master-builds',
+}
+
 TEST_API_DATA = {
     'yt-dlp/yt-dlp/latest': {
         'tag_name': '2023.12.31',
@@ -104,6 +112,7 @@ class FakeUpdater(Updater):
 
     _channel = 'stable'
     _origin = 'yt-dlp/yt-dlp'
+    _update_sources = TEST_UPDATE_SOURCES
 
     def _download_update_spec(self, *args, **kwargs):
         return TEST_LOCKFILE_ACTUAL

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],
@@ -2387,6 +2370,11 @@ Line 1
         headers4 = HTTPHeaderDict({'ytdl-test': 'data;'})
         self.assertEqual(set(headers4.items()), {('Ytdl-Test', 'data;')})
 
+        # common mistake: strip whitespace from values
+        # https://github.com/yt-dlp/yt-dlp/issues/8729
+        headers5 = HTTPHeaderDict({'ytdl-test': ' data; '})
+        self.assertEqual(set(headers5.items()), {('Ytdl-Test', 'data;')})
+
     def test_extract_basic_auth(self):
         assert extract_basic_auth('http://:foo.bar') == ('http://:foo.bar', None)
         assert extract_basic_auth('http://foo.bar') == ('http://foo.bar', None)

test/test_websockets.py

@@ -148,7 +148,7 @@ class TestWebsSocketRequestHandlerConformance:
     @pytest.mark.parametrize('handler', ['Websockets'], indirect=True)
     def test_ssl_error(self, handler):
         with handler(verify=False) as rh:
-            with pytest.raises(SSLError, match='sslv3 alert handshake failure') as exc_info:
+            with pytest.raises(SSLError, match=r'ssl(?:v3|/tls) alert handshake failure') as exc_info:
                 validate_and_send(rh, Request(self.bad_wss_host))
             assert not issubclass(exc_info.type, CertificateVerifyError)
 

yt_dlp/YoutubeDL.py

@@ -1201,6 +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('.'))]
@@ -1210,11 +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
@@ -2455,9 +2465,16 @@ class YoutubeDL:
                 return selector_function(ctx_copy)
             return final_selector
 
-        stream = io.BytesIO(format_spec.encode())
+        # HACK: Python 3.12 changed the underlying parser, rendering '7_a' invalid
+        #       Prefix numbers with random letters to avoid it being classified as a number
+        #       See: https://github.com/yt-dlp/yt-dlp/pulls/8797
+        # TODO: Implement parser not reliant on tokenize.tokenize
+        prefix = ''.join(random.choices(string.ascii_letters, k=32))
+        stream = io.BytesIO(re.sub(r'\d[_\d]*', rf'{prefix}\g<0>', format_spec).encode())
         try:
-            tokens = list(_remove_unused_ops(tokenize.tokenize(stream.readline)))
+            tokens = list(_remove_unused_ops(
+                token._replace(string=token.string.replace(prefix, ''))
+                for token in tokenize.tokenize(stream.readline)))
         except tokenize.TokenError:
             raise syntax_error('Missing closing/opening brackets or parenthesis', (0, len(format_spec)))
 

yt_dlp/extractor/_extractors.py

@@ -276,6 +276,7 @@ from .brilliantpala import (
 )
 from .businessinsider import BusinessInsiderIE
 from .bundesliga import BundesligaIE
+from .bundestag import BundestagIE
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
@@ -864,6 +865,7 @@ from .jiosaavn import (
 )
 from .jove import JoveIE
 from .joj import JojIE
+from .joqrag import JoqrAgIE
 from .jstream import JStreamIE
 from .jtbc import (
     JTBCIE,
@@ -991,6 +993,7 @@ from .lynda import (
     LyndaIE,
     LyndaCourseIE
 )
+from .maariv import MaarivIE
 from .magellantv import MagellanTVIE
 from .magentamusik360 import MagentaMusik360IE
 from .mailru import (
@@ -1590,6 +1593,7 @@ from .restudy import RestudyIE
 from .reuters import ReutersIE
 from .reverbnation import ReverbNationIE
 from .rheinmaintv import RheinMainTVIE
+from .rinsefm import RinseFMIE
 from .rmcdecouverte import RMCDecouverteIE
 from .rockstargames import RockstarGamesIE
 from .rokfin import (
@@ -1643,6 +1647,7 @@ from .rumble import (
     RumbleIE,
     RumbleChannelIE,
 )
+from .rudovideo import RudoVideoIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,

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/ard.py

@@ -292,7 +292,7 @@ class ARDIE(InfoExtractor):
     _TESTS = [{
         # available till 7.12.2023
         'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-video-424.html',
-        'md5': 'a438f671e87a7eba04000336a119ccc4',
+        'md5': '94812e6438488fb923c361a44469614b',
         'info_dict': {
             'id': 'maischberger-video-424',
             'display_id': 'maischberger-video-424',
@@ -403,26 +403,25 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
     _VALID_URL = r'''(?x)https://
         (?:(?:beta|www)\.)?ardmediathek\.de/
         (?:(?P<client>[^/]+)/)?
-        (?:player|live|video|(?P<playlist>sendung|sammlung))/
+        (?:player|live|video|(?P<playlist>sendung|serie|sammlung))/
         (?:(?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/)?
         (?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)
         (?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
 
     _TESTS = [{
-        'url': 'https://www.ardmediathek.de/video/filme-im-mdr/wolfsland-die-traurigen-schwestern/mdr-fernsehen/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy8xZGY0ZGJmZS00ZWQwLTRmMGItYjhhYy0wOGQ4ZmYxNjVhZDI',
-        'md5': '3fd5fead7a370a819341129c8d713136',
+        'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
+        'md5': 'b6e8ab03f2bcc6e1f9e6cef25fcc03c4',
         'info_dict': {
-            'display_id': 'filme-im-mdr/wolfsland-die-traurigen-schwestern/mdr-fernsehen',
-            'id': '12172961',
-            'title': 'Wolfsland - Die traurigen Schwestern',
-            'description': r're:^Als der Polizeiobermeister Raaben',
-            'duration': 5241,
-            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:efa186f7b0054957',
-            'timestamp': 1670710500,
-            'upload_date': '20221210',
+            'display_id': 'filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen',
+            'id': '12939099',
+            'title': 'Liebe auf vier Pfoten',
+            'description': r're:^Claudia Schmitt, Anwältin in Salzburg',
+            'duration': 5222,
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:aee7cbf8f06de976?w=960&ch=ae4d0f2ee47d8b9b',
+            'timestamp': 1701343800,
+            'upload_date': '20231130',
             'ext': 'mp4',
-            'age_limit': 12,
-            'episode': 'Wolfsland - Die traurigen Schwestern',
+            'episode': 'Liebe auf vier Pfoten',
             'series': 'Filme im MDR'
         },
     }, {
@@ -454,7 +453,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
             'duration': 915,
             'episode': 'tagesschau, 20:00 Uhr',
             'series': 'tagesschau',
-            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49',
+            'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49?w=960&ch=ee69108ae344f678',
         },
     }, {
         'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
@@ -475,6 +474,10 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
         # playlist of type 'sendung'
         'url': 'https://www.ardmediathek.de/ard/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw/',
         'only_matching': True,
+    }, {
+        # playlist of type 'serie'
+        'url': 'https://www.ardmediathek.de/serie/nachtstreife/staffel-1/Y3JpZDovL3N3ci5kZS9zZGIvc3RJZC8xMjQy/1',
+        'only_matching': True,
     }, {
         # playlist of type 'sammlung'
         'url': 'https://www.ardmediathek.de/ard/sammlung/team-muenster/5JpTzLSbWUAK8184IOvEir/',
@@ -487,10 +490,11 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
         'only_matching': True,
     }]
 
-    def _ARD_load_playlist_snipped(self, playlist_id, display_id, client, mode, pageNumber):
+    def _ARD_load_playlist_snippet(self, playlist_id, display_id, client, mode, page_number):
         """ Query the ARD server for playlist information
         and returns the data in "raw" format """
-        if mode == 'sendung':
+        assert mode in ('sendung', 'serie', 'sammlung')
+        if mode in ('sendung', 'serie'):
             graphQL = json.dumps({
                 'query': '''{
                     showPage(
@@ -507,7 +511,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
                             links { target { id href title } }
                             type
                         }
-                    }}''' % (client, playlist_id, pageNumber),
+                    }}''' % (client, playlist_id, page_number),
             }).encode()
         else:  # mode == 'sammlung'
             graphQL = json.dumps({
@@ -528,7 +532,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
                                 type
                             }
                         }
-                    }}''' % (client, playlist_id, pageNumber),
+                    }}''' % (client, playlist_id, page_number),
             }).encode()
         # Ressources for ARD graphQL debugging:
         # https://api-test.ardmediathek.de/public-gateway
@@ -538,7 +542,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
             data=graphQL,
             headers={'Content-Type': 'application/json'})['data']
         # align the structure of the returned data:
-        if mode == 'sendung':
+        if mode in ('sendung', 'serie'):
             show_page = show_page['showPage']
         else:  # mode == 'sammlung'
             show_page = show_page['morePage']['widget']
@@ -546,12 +550,12 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
 
     def _ARD_extract_playlist(self, url, playlist_id, display_id, client, mode):
         """ Collects all playlist entries and returns them as info dict.
-        Supports playlists of mode 'sendung' and 'sammlung', and also nested
-        playlists. """
+        Supports playlists of mode 'sendung', 'serie', and 'sammlung',
+        as well as nested playlists. """
         entries = []
         pageNumber = 0
         while True:  # iterate by pageNumber
-            show_page = self._ARD_load_playlist_snipped(
+            show_page = self._ARD_load_playlist_snippet(
                 playlist_id, display_id, client, mode, pageNumber)
             for teaser in show_page['teasers']:  # process playlist items
                 if '/compilation/' in teaser['links']['target']['href']:

yt_dlp/extractor/bbc.py

@@ -317,16 +317,25 @@ class BBCCoUkIE(InfoExtractor):
 
     def _download_media_selector(self, programme_id):
         last_exception = None
+        formats, subtitles = [], {}
         for media_set in self._MEDIA_SETS:
             try:
-                return self._download_media_selector_url(
+                fmts, subs = self._download_media_selector_url(
                     self._MEDIA_SELECTOR_URL_TEMPL % (media_set, programme_id), programme_id)
+                formats.extend(fmts)
+                if subs:
+                    self._merge_subtitles(subs, target=subtitles)
             except BBCCoUkIE.MediaSelectionError as e:
                 if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
                     last_exception = e
                     continue
                 self._raise_extractor_error(e)
-        self._raise_extractor_error(last_exception)
+        if last_exception:
+            if formats or subtitles:
+                self.report_warning(f'{self.IE_NAME} returned error: {last_exception.id}')
+            else:
+                self._raise_extractor_error(last_exception)
+        return formats, subtitles
 
     def _download_media_selector_url(self, url, programme_id=None):
         media_selection = self._download_json(
@@ -1188,7 +1197,7 @@ class BBCIE(BBCCoUkIE):  # XXX: Do not subclass from concrete IE
         if initial_data is None:
             initial_data = self._search_regex(
                 r'window\.__INITIAL_DATA__\s*=\s*({.+?})\s*;', webpage,
-                'preload state', default={})
+                'preload state', default='{}')
         else:
             initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
         initial_data = self._parse_json(initial_data, playlist_id, fatal=False)

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/bundestag.py

@@ -0,0 +1,123 @@
+import re
+from functools import partial
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    bug_reports_message,
+    clean_html,
+    format_field,
+    get_element_text_and_html_by_tag,
+    int_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BundestagIE(InfoExtractor):
+    _VALID_URL = [
+        r'https?://dbtg\.tv/[cf]vid/(?P<id>\d+)',
+        r'https?://www\.bundestag\.de/mediathek/?\?(?:[^#]+&)?videoid=(?P<id>\d+)',
+    ]
+    _TESTS = [{
+        'url': 'https://dbtg.tv/cvid/7605304',
+        'info_dict': {
+            'id': '7605304',
+            'ext': 'mp4',
+            'title': '145. Sitzung vom 15.12.2023, TOP 24 Barrierefreiheit',
+            'description': 'md5:321a9dc6bdad201264c0045efc371561',
+        },
+    }, {
+        'url': 'https://www.bundestag.de/mediathek?videoid=7602120&url=L21lZGlhdGhla292ZXJsYXk=&mod=mediathek',
+        'info_dict': {
+            'id': '7602120',
+            'ext': 'mp4',
+            'title': '130. Sitzung vom 18.10.2023, TOP 1 Befragung der Bundesregierung',
+            'description': 'Befragung der Bundesregierung',
+        },
+    }, {
+        'url': 'https://www.bundestag.de/mediathek?videoid=7604941#url=L21lZGlhdGhla292ZXJsYXk/dmlkZW9pZD03NjA0OTQx&mod=mediathek',
+        'only_matching': True,
+    }, {
+        'url': 'http://dbtg.tv/fvid/3594346',
+        'only_matching': True,
+    }]
+
+    _OVERLAY_URL = 'https://www.bundestag.de/mediathekoverlay'
+    _INSTANCE_FORMAT = 'https://cldf-wzw-od.r53.cdn.tv1.eu/13014bundestagod/_definst_/13014bundestag/ondemand/3777parlamentsfernsehen/archiv/app144277506/145293313/{0}/{0}_playlist.smil/playlist.m3u8'
+
+    _SHARE_URL = 'https://webtv.bundestag.de/player/macros/_x_s-144277506/shareData.json?contentId='
+    _SHARE_AUDIO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<bitrate>\d+)kb_(?P<channels>\w+)_\w+_\d+\.(?P<ext>\w+)'
+    _SHARE_VIDEO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<width>\w+)_(?P<height>\w+)_(?P<bitrate>\d+)kb_\w+_\w+_\d+\.(?P<ext>\w+)'
+
+    def _bt_extract_share_formats(self, video_id):
+        share_data = self._download_json(
+            f'{self._SHARE_URL}{video_id}', video_id, note='Downloading share format JSON')
+        if traverse_obj(share_data, ('status', 'code', {int})) != 1:
+            self.report_warning(format_field(
+                share_data, [('status', 'message', {str})],
+                'Share API response: %s', default='Unknown Share API Error')
+                + bug_reports_message())
+            return
+
+        for name, url in share_data.items():
+            if not isinstance(name, str) or not url_or_none(url):
+                continue
+
+            elif name.startswith('audio'):
+                match = re.search(self._SHARE_AUDIO_REGEX, url)
+                yield {
+                    'format_id': name,
+                    'url': url,
+                    'vcodec': 'none',
+                    **traverse_obj(match, {
+                        'acodec': 'codec',
+                        'audio_channels': ('channels', {{'mono': 1, 'stereo': 2}.get}),
+                        'abr': ('bitrate', {int_or_none}),
+                        'ext': 'ext',
+                    }),
+                }
+
+            elif name.startswith('download'):
+                match = re.search(self._SHARE_VIDEO_REGEX, url)
+                yield {
+                    'format_id': name,
+                    'url': url,
+                    **traverse_obj(match, {
+                        'vcodec': 'codec',
+                        'tbr': ('bitrate', {int_or_none}),
+                        'width': ('width', {int_or_none}),
+                        'height': ('height', {int_or_none}),
+                        'ext': 'ext',
+                    }),
+                }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        formats = []
+        result = {'id': video_id, 'formats': formats}
+
+        try:
+            formats.extend(self._extract_m3u8_formats(
+                self._INSTANCE_FORMAT.format(video_id), video_id, m3u8_id='instance'))
+        except ExtractorError as error:
+            if isinstance(error.cause, HTTPError) and error.cause.status == 404:
+                raise ExtractorError('Could not find video id', expected=True)
+            self.report_warning(f'Error extracting hls formats: {error}', video_id)
+        formats.extend(self._bt_extract_share_formats(video_id))
+        if not formats:
+            self.raise_no_formats('Could not find suitable formats', video_id=video_id)
+
+        result.update(traverse_obj(self._download_webpage(
+            self._OVERLAY_URL, video_id,
+            query={'videoid': video_id, 'view': 'main'},
+            note='Downloading metadata overlay', fatal=False,
+        ), {
+            'title': (
+                {partial(get_element_text_and_html_by_tag, 'h3')}, 0,
+                {partial(re.sub, r'<span[^>]*>[^<]+</span>', '')}, {clean_html}),
+            'description': ({partial(get_element_text_and_html_by_tag, 'p')}, 0, {clean_html}),
+        }))
+
+        return result

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/facebook.py

@@ -52,7 +52,7 @@ class FacebookIE(InfoExtractor):
                             )\?(?:.*?)(?:v|video_id|story_fbid)=|
                             [^/]+/videos/(?:[^/]+/)?|
                             [^/]+/posts/|
-                            groups/[^/]+/permalink/|
+                            groups/[^/]+/(?:permalink|posts)/|
                             watchparty/
                         )|
                     facebook:
@@ -232,6 +232,21 @@ class FacebookIE(InfoExtractor):
             'uploader_id': '100013949973717',
         },
         'skip': 'Requires logging in',
+    }, {
+        # data.node.comet_sections.content.story.attachments[].throwbackStyles.attachment_target_renderer.attachment.target.attachments[].styles.attachment.media
+        'url': 'https://www.facebook.com/groups/1645456212344334/posts/3737828833107051/',
+        'info_dict': {
+            'id': '1569199726448814',
+            'ext': 'mp4',
+            'title': 'Pence MUST GO!',
+            'description': 'Vickie Gentry shared a memory.',
+            'timestamp': 1511548260,
+            'upload_date': '20171124',
+            'uploader': 'Vickie Gentry',
+            'uploader_id': 'pfbid0FuZhHCeWDAxWxEbr3yKPFaRstXvRxgsp9uCPG6GjD4J2AitB35NUAuJ4Q75KcjiDl',
+            'thumbnail': r're:^https?://.*',
+            'duration': 148.435,
+        },
     }, {
         'url': 'https://www.facebook.com/video.php?v=10204634152394104',
         'only_matching': True,
@@ -612,9 +627,11 @@ class FacebookIE(InfoExtractor):
                 nodes = variadic(traverse_obj(data, 'nodes', 'node') or [])
                 attachments = traverse_obj(nodes, (
                     ..., 'comet_sections', 'content', 'story', (None, 'attached_story'), 'attachments',
-                    ..., ('styles', 'style_type_renderer'), 'attachment'), expected_type=dict) or []
+                    ..., ('styles', 'style_type_renderer', ('throwbackStyles', 'attachment_target_renderer')),
+                    'attachment', {dict}))
                 for attachment in attachments:
-                    ns = try_get(attachment, lambda x: x['all_subattachments']['nodes'], list) or []
+                    ns = traverse_obj(attachment, ('all_subattachments', 'nodes', ..., {dict}),
+                                      ('target', 'attachments', ..., 'styles', 'attachment', {dict}))
                     for n in ns:
                         parse_attachment(n)
                     parse_attachment(attachment)
@@ -637,7 +654,7 @@ class FacebookIE(InfoExtractor):
                 if len(entries) > 1:
                     return self.playlist_result(entries, video_id)
 
-                video_info = entries[0]
+                video_info = entries[0] if entries else {'id': video_id}
                 webpage_info = extract_metadata(webpage)
                 # honor precise duration in video info
                 if video_info.get('duration'):

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/iheart.py

@@ -23,7 +23,7 @@ class IHeartRadioBaseIE(InfoExtractor):
 
 
 class IHeartRadioIE(IHeartRadioBaseIE):
-    IENAME = 'iheartradio'
+    IE_NAME = 'iheartradio'
     _VALID_URL = r'(?:https?://(?:www\.)?iheart\.com/podcast/[^/]+/episode/(?P<display_id>[^/?&#]+)-|iheartradio:)(?P<id>\d+)'
     _TEST = {
         'url': 'https://www.iheart.com/podcast/105-behind-the-bastards-29236323/episode/part-one-alexander-lukashenko-the-dictator-70346499/?embed=true',

yt_dlp/extractor/instagram.py

@@ -10,6 +10,7 @@ from ..utils import (
     ExtractorError,
     decode_base_n,
     encode_base_n,
+    filter_dict,
     float_or_none,
     format_field,
     get_element_by_attribute,
@@ -703,28 +704,31 @@ class InstagramStoryIE(InstagramBaseIE):
         user_info = self._search_json(r'"user":', story_info, 'user info', story_id, fatal=False)
         if not user_info:
             self.raise_login_required('This content is unreachable')
-        user_id = user_info.get('id')
 
+        user_id = traverse_obj(user_info, 'pk', 'id', expected_type=str)
         story_info_url = user_id if username != 'highlights' else f'highlight:{story_id}'
+        if not story_info_url:  # user id is only mandatory for non-highlights
+            raise ExtractorError('Unable to extract user id')
+
         videos = traverse_obj(self._download_json(
             f'{self._API_BASE_URL}/feed/reels_media/?reel_ids={story_info_url}',
             story_id, errnote=False, fatal=False, headers=self._API_HEADERS), 'reels')
         if not videos:
             self.raise_login_required('You need to log in to access this content')
 
-        full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (str(user_id), 'user', 'full_name'))
+        full_name = traverse_obj(videos, (f'highlight:{story_id}', 'user', 'full_name'), (user_id, 'user', 'full_name'))
         story_title = traverse_obj(videos, (f'highlight:{story_id}', 'title'))
         if not story_title:
             story_title = f'Story by {username}'
 
-        highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (str(user_id), 'items'))
+        highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (user_id, 'items'))
         info_data = []
         for highlight in highlights:
             highlight_data = self._extract_product(highlight)
             if highlight_data.get('formats'):
                 info_data.append({
-                    **highlight_data,
                     'uploader': full_name,
                     'uploader_id': user_id,
+                    **filter_dict(highlight_data),
                 })
         return self.playlist_result(info_data, playlist_id=story_id, playlist_title=story_title)

yt_dlp/extractor/joqrag.py

@@ -0,0 +1,112 @@
+import datetime
+import urllib.parse
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    datetime_from_str,
+    unified_timestamp,
+    urljoin,
+)
+
+
+class JoqrAgIE(InfoExtractor):
+    IE_DESC = '超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)'
+    _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 = [{
+        'url': 'https://www.uniqueradio.jp/agplayer5/player.php',
+        'info_dict': {
+            'id': 'live',
+            'title': str,
+            'channel': '超!A&G+',
+            'description': str,
+            'live_status': 'is_live',
+            'release_timestamp': int,
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+    }, {
+        'url': 'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.joqr.co.jp/ag/article/103760/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.joqr.co.jp/qr/agdailyprogram/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.joqr.co.jp/qr/agregularprogram/',
+        'only_matching': True,
+    }]
+
+    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, '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*(\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', default=None)
+            if start_time:
+                return unified_timestamp(f'{dt.strftime("%Y/%m/%d")} {start_time} +09:00')
+            return None
+
+        start_timestamp = extract_start_time_from('today')
+        if not start_timestamp:
+            return None
+
+        if not is_live or start_timestamp < datetime_from_str('now').timestamp():
+            return start_timestamp
+        else:
+            return extract_start_time_from('yesterday')
+
+    def _real_extract(self, url):
+        video_id = 'live'
+
+        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)
+
+        if title == '放送休止':
+            formats = []
+            live_status = 'is_upcoming'
+            release_timestamp = self._extract_start_timestamp(video_id, False)
+            msg = 'This stream is not currently live'
+            if release_timestamp:
+                msg += (' and will start at '
+                        + datetime.datetime.fromtimestamp(release_timestamp).strftime('%Y-%m-%d %H:%M:%S'))
+            self.raise_no_formats(msg, expected=True)
+        else:
+            m3u8_path = self._search_regex(
+                r'<source\s[^>]*\bsrc="([^"]+)"',
+                self._download_webpage(
+                    'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php', video_id,
+                    note='Downloading player data', errnote='Failed to download player data'),
+                'm3u8 url')
+            formats = self._extract_m3u8_formats(
+                urljoin('https://www.uniqueradio.jp/', m3u8_path), video_id)
+            live_status = 'is_live'
+            release_timestamp = self._extract_start_timestamp(video_id, True)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'channel': '超!A&G+',
+            'description': self._extract_metadata('Program_text', metadata),
+            'formats': formats,
+            'live_status': live_status,
+            'release_timestamp': release_timestamp,
+        }

yt_dlp/extractor/kinja.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class KinjaEmbedIE(InfoExtractor):
-    IENAME = 'kinja:embed'
+    IE_NAME = 'kinja:embed'
     _DOMAIN_REGEX = r'''(?:[^.]+\.)?
         (?:
             avclub|

yt_dlp/extractor/litv.py

@@ -6,6 +6,7 @@ from ..utils import (
     int_or_none,
     smuggle_url,
     traverse_obj,
+    try_call,
     unsmuggle_url,
 )
 
@@ -96,13 +97,22 @@ class LiTVIE(InfoExtractor):
             r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
             webpage, 'video data', default='{}'), video_id)
         if not video_data:
-            payload = {
-                'assetId': program_info['assetId'],
-                'watchDevices': program_info['watchDevices'],
-                'contentType': program_info['contentType'],
-            }
+            payload = {'assetId': program_info['assetId']}
+            puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
+            if puid:
+                payload.update({
+                    'type': 'auth',
+                    'puid': puid,
+                })
+                endpoint = 'getUrl'
+            else:
+                payload.update({
+                    'watchDevices': program_info['watchDevices'],
+                    'contentType': program_info['contentType'],
+                })
+                endpoint = 'getMainUrlNoAuth'
             video_data = self._download_json(
-                'https://www.litv.tv/vod/ajax/getMainUrlNoAuth', video_id,
+                f'https://www.litv.tv/vod/ajax/{endpoint}', video_id,
                 data=json.dumps(payload).encode('utf-8'),
                 headers={'Content-Type': 'application/json'})
 

yt_dlp/extractor/maariv.py

@@ -0,0 +1,62 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_resolution,
+    unified_timestamp,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class MaarivIE(InfoExtractor):
+    IE_NAME = 'maariv.co.il'
+    _VALID_URL = r'https?://player\.maariv\.co\.il/public/player\.html\?(?:[^#]+&)?media=(?P<id>\d+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
+    _TESTS = [{
+        'url': 'https://player.maariv.co.il/public/player.html?player=maariv-desktop&media=3611585',
+        'info_dict': {
+            'id': '3611585',
+            'duration': 75,
+            'ext': 'mp4',
+            'upload_date': '20231009',
+            'title': 'מבצע חרבות ברזל',
+            'timestamp': 1696851301,
+        },
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://www.maariv.co.il/news/law/Article-1044008',
+        'info_dict': {
+            'id': '3611585',
+            'duration': 75,
+            'ext': 'mp4',
+            'upload_date': '20231009',
+            'title': 'מבצע חרבות ברזל',
+            'timestamp': 1696851301,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            f'https://dal.walla.co.il/media/{video_id}?origin=player.maariv.co.il', video_id)['data']
+
+        formats = []
+        if hls_url := traverse_obj(data, ('video', 'url', {url_or_none})):
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, m3u8_id='hls', fatal=False))
+
+        for http_format in traverse_obj(data, ('video', 'stream_urls', ..., 'stream_url', {url_or_none})):
+            formats.append({
+                'url': http_format,
+                'format_id': 'http',
+                **parse_resolution(http_format),
+            })
+
+        return {
+            'id': video_id,
+            **traverse_obj(data, {
+                'title': 'title',
+                'duration': ('video', 'duration', {int_or_none}),
+                'timestamp': ('upload_date', {unified_timestamp}),
+            }),
+            'formats': formats,
+        }

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/nba.py

@@ -97,7 +97,7 @@ class NBAWatchBaseIE(NBACVPBaseIE):
 
 
 class NBAWatchEmbedIE(NBAWatchBaseIE):
-    IENAME = 'nba:watch:embed'
+    IE_NAME = 'nba:watch:embed'
     _VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'embed\?.*?\bid=(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://watch.nba.com/embed?id=659395',
@@ -339,7 +339,7 @@ class NBABaseIE(NBACVPBaseIE):
 
 
 class NBAEmbedIE(NBABaseIE):
-    IENAME = 'nba:embed'
+    IE_NAME = 'nba:embed'
     _VALID_URL = r'https?://secure\.nba\.com/assets/amp/include/video/(?:topI|i)frame\.html\?.*?\bcontentId=(?P<id>[^?#&]+)'
     _TESTS = [{
         'url': 'https://secure.nba.com/assets/amp/include/video/topIframe.html?contentId=teams/bulls/2020/12/04/3478774/1607105587854-20201204_SCHEDULE_RELEASE_FINAL_DRUPAL-3478774&team=bulls&adFree=false&profile=71&videoPlayerName=TAMPCVP&baseUrl=&videoAdsection=nba.com_mobile_web_teamsites_chicagobulls&ampEnv=',
@@ -361,7 +361,7 @@ class NBAEmbedIE(NBABaseIE):
 
 
 class NBAIE(NBABaseIE):
-    IENAME = 'nba'
+    IE_NAME = 'nba'
     _VALID_URL = NBABaseIE._VALID_URL_BASE + '(?!%s)video/(?P<id>(?:[^/]+/)*[^/?#&]+)' % NBABaseIE._CHANNEL_PATH_REGEX
     _TESTS = [{
         'url': 'https://www.nba.com/bulls/video/teams/bulls/2020/12/04/3478774/1607105587854-20201204schedulereleasefinaldrupal-3478774',
@@ -388,7 +388,7 @@ class NBAIE(NBABaseIE):
 
 
 class NBAChannelIE(NBABaseIE):
-    IENAME = 'nba:channel'
+    IE_NAME = 'nba:channel'
     _VALID_URL = NBABaseIE._VALID_URL_BASE + '(?:%s)/(?P<id>[^/?#&]+)' % NBABaseIE._CHANNEL_PATH_REGEX
     _TESTS = [{
         'url': 'https://www.nba.com/blazers/video/channel/summer_league',

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/rinsefm.py

@@ -0,0 +1,33 @@
+from .common import InfoExtractor
+from ..utils import format_field, parse_iso8601
+
+
+class RinseFMIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rinse\.fm/episodes/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://rinse.fm/episodes/club-glow-15-12-2023-2000/',
+        'md5': '76ee0b719315617df42e15e710f46c7b',
+        'info_dict': {
+            'id': '1536535',
+            'ext': 'mp3',
+            'title': 'Club Glow - 15/12/2023 - 20:00',
+            'thumbnail': r're:^https://.+\.(?:jpg|JPG)$',
+            'release_timestamp': 1702598400,
+            'release_date': '20231215'
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
+
+        return {
+            'id': entry['id'],
+            'title': entry.get('title'),
+            'url': entry['fileUrl'],
+            'vcodec': 'none',
+            'release_timestamp': parse_iso8601(entry.get('episodeDate')),
+            'thumbnail': format_field(
+                entry, [('featuredImage', 0, 'filename')], 'https://rinse.imgix.net/media/%s', default=None),
+        }

yt_dlp/extractor/rudovideo.py

@@ -0,0 +1,135 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    js_to_json,
+    traverse_obj,
+    update_url_query,
+    url_or_none,
+)
+
+
+class RudoVideoIE(InfoExtractor):
+    _VALID_URL = r'https?://rudo\.video/(?P<type>vod|podcast|live)/(?P<id>[^/?&#]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)//rudo\.video/(?:vod|podcast|live)/[^\'"]+)']
+    _TESTS = [{
+        'url': 'https://rudo.video/podcast/cz2wrUy8l0o',
+        'md5': '28ed82b477708dc5e12e072da2449221',
+        'info_dict': {
+            'id': 'cz2wrUy8l0o',
+            'title': 'Diego Cabot',
+            'ext': 'mp4',
+            'thumbnail': r're:^(?:https?:)?//.*\.(png|jpg)$',
+        },
+    }, {
+        'url': 'https://rudo.video/podcast/bQkt07',
+        'md5': '36b22a9863de0f47f00fc7532a32a898',
+        'info_dict': {
+            'id': 'bQkt07',
+            'title': 'Tubular Bells',
+            'ext': 'mp4',
+            'thumbnail': r're:^(?:https?:)?//.*\.(png|jpg)$',
+        },
+    }, {
+        'url': 'https://rudo.video/podcast/b42ZUznHX0',
+        'md5': 'b91c70d832938871367f8ad10c895821',
+        'info_dict': {
+            'id': 'b42ZUznHX0',
+            'title': 'Columna Ruperto Concha',
+            'ext': 'mp3',
+            'thumbnail': r're:^(?:https?:)?//.*\.(png|jpg)$',
+        },
+    }, {
+        'url': 'https://rudo.video/vod/bN5AaJ',
+        'md5': '01324a329227e2591530ecb4f555c881',
+        'info_dict': {
+            'id': 'bN5AaJ',
+            'title': 'Ucrania 19.03',
+            'creator': 'La Tercera',
+            'ext': 'mp4',
+            'thumbnail': r're:^(?:https?:)?//.*\.(png|jpg)$',
+        },
+    }, {
+        'url': 'https://rudo.video/live/bbtv',
+        'info_dict': {
+            'id': 'bbtv',
+            'ext': 'mp4',
+            'creator': 'BioBioTV',
+            'live_status': 'is_live',
+            'title': r're:^LIVE BBTV\s\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}$',
+            'thumbnail': r're:^(?:https?:)?//.*\.(png|jpg)$',
+        },
+    }, {
+        'url': 'https://rudo.video/live/c13',
+        'info_dict': {
+            'id': 'c13',
+            'title': 'CANAL13',
+            'ext': 'mp4',
+        },
+        'skip': 'Geo-restricted to Chile',
+    }, {
+        'url': 'https://rudo.video/live/t13-13cl',
+        'info_dict': {
+            'id': 't13-13cl',
+            'title': 'T13',
+            'ext': 'mp4',
+        },
+        'skip': 'Geo-restricted to Chile',
+    }]
+
+    def _real_extract(self, url):
+        video_id, type_ = self._match_valid_url(url).group('id', 'type')
+        is_live = type_ == 'live'
+
+        webpage = self._download_webpage(url, video_id)
+        if 'Streaming is not available in your area' in webpage:
+            self.raise_geo_restricted()
+
+        media_url = (
+            self._search_regex(
+                r'var\s+streamURL\s*=\s*[\'"]([^?\'"]+)', webpage, 'stream url', default=None)
+            # Source URL must be used only if streamURL is unavailable
+            or self._search_regex(
+                r'<source[^>]+src=[\'"]([^\'"]+)', webpage, 'source url', default=None))
+        if not media_url:
+            youtube_url = self._search_regex(r'file:\s*[\'"]((?:https?:)//(?:www\.)?youtube\.com[^\'"]+)',
+                                             webpage, 'youtube url', default=None)
+            if youtube_url:
+                return self.url_result(youtube_url, 'Youtube')
+            raise ExtractorError('Unable to extract stream url')
+
+        token_array = self._search_json(
+            r'<script>var\s+_\$_[a-zA-Z0-9]+\s*=', webpage, 'access token array', video_id,
+            contains_pattern=r'\[(?s:.+)\]', default=None, transform_source=js_to_json)
+        if token_array:
+            token_url = traverse_obj(token_array, (..., {url_or_none}), get_all=False)
+            if not token_url:
+                raise ExtractorError('Invalid access token array')
+            access_token = self._download_json(
+                token_url, video_id, note='Downloading access token')['data']['authToken']
+            media_url = update_url_query(media_url, {'auth-token': access_token})
+
+        ext = determine_ext(media_url)
+        if ext == 'm3u8':
+            formats = self._extract_m3u8_formats(media_url, video_id, live=is_live)
+        elif ext == 'mp3':
+            formats = [{
+                'url': media_url,
+                'vcodec': 'none',
+            }]
+        else:
+            formats = [{'url': media_url}]
+
+        return {
+            'id': video_id,
+            'title': (self._search_regex(r'var\s+titleVideo\s*=\s*[\'"]([^\'"]+)',
+                                         webpage, 'title', default=None)
+                      or self._og_search_title(webpage)),
+            'creator': self._search_regex(r'var\s+videoAuthor\s*=\s*[\'"]([^?\'"]+)',
+                                          webpage, 'videoAuthor', default=None),
+            'thumbnail': (self._search_regex(r'var\s+posterIMG\s*=\s*[\'"]([^?\'"]+)',
+                                             webpage, 'thumbnail', default=None)
+                          or self._og_search_thumbnail(webpage)),
+            'formats': formats,
+            'is_live': is_live,
+        }

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/twitter.py

@@ -10,6 +10,7 @@ from ..compat import (
     compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
 )
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     dict_get,
@@ -479,9 +480,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': [],
             'age_limit': 18,
+            '_old_archive_ids': ['twitter 643211948184596480'],
         },
     }, {
         'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
@@ -515,6 +516,7 @@ class TwitterIE(TwitterBaseIE):
             'like_count': int,
             'tags': ['TV', 'StarWars', 'TheForceAwakens'],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 665052190608723968'],
         },
     }, {
         'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880',
@@ -558,9 +560,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': ['Damndaniel'],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 700207533655363584'],
         },
     }, {
         'url': 'https://twitter.com/Filmdrunk/status/713801302971588609',
@@ -599,9 +601,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': [],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 719944021058060289'],
         },
     }, {
         'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
@@ -616,6 +618,7 @@ class TwitterIE(TwitterBaseIE):
             'thumbnail': r're:^https?://.*\.jpg',
         },
         'add_ie': ['Periscope'],
+        'skip': 'Broadcast not found',
     }, {
         # has mp4 formats via mobile API
         'url': 'https://twitter.com/news_al3alm/status/852138619213144067',
@@ -635,9 +638,9 @@ class TwitterIE(TwitterBaseIE):
             'thumbnail': r're:^https?://.*\.jpg',
             'tags': [],
             'repost_count': int,
-            'view_count': int,
             'like_count': int,
             'comment_count': int,
+            '_old_archive_ids': ['twitter 852138619213144067'],
         },
     }, {
         'url': 'https://twitter.com/i/web/status/910031516746514432',
@@ -657,9 +660,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': ['Maria'],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 910031516746514432'],
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -683,9 +686,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': [],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1001551623938805763'],
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -749,6 +752,7 @@ class TwitterIE(TwitterBaseIE):
             'like_count': int,
             'tags': [],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1349794411333394432'],
         },
         'params': {
             'skip_download': True,
@@ -771,18 +775,18 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': [],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1577855540407197696'],
         },
         'params': {'skip_download': True},
     }, {
         'url': 'https://twitter.com/UltimaShadowX/status/1577719286659006464',
         'info_dict': {
             'id': '1577719286659006464',
-            'title': 'Ultima📛| New Era - Test',
+            'title': 'Ultima - Test',
             'description': 'Test https://t.co/Y3KEZD7Dad',
-            'uploader': 'Ultima📛| New Era',
+            'uploader': 'Ultima',
             'uploader_id': 'UltimaShadowX',
             'uploader_url': 'https://twitter.com/UltimaShadowX',
             'upload_date': '20221005',
@@ -813,9 +817,9 @@ class TwitterIE(TwitterBaseIE):
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
-            'view_count': int,
             'tags': ['HurricaneIan'],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1575560063510810624'],
         },
     }, {
         # Adult content, fails if not logged in
@@ -951,10 +955,10 @@ class TwitterIE(TwitterBaseIE):
             'uploader_url': 'https://twitter.com/CTVJLaidlaw',
             'display_id': '1600649710662213632',
             'like_count': int,
-            'view_count': int,
             'description': 'md5:591c19ce66fadc2359725d5cd0d1052c',
             'upload_date': '20221208',
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1600649710662213632'],
         },
         'params': {'noplaylist': True},
     }, {
@@ -979,7 +983,7 @@ class TwitterIE(TwitterBaseIE):
             'like_count': int,
             'repost_count': int,
             'comment_count': int,
-            'view_count': int,
+            '_old_archive_ids': ['twitter 1621117700482416640'],
         },
     }, {
         'url': 'https://twitter.com/hlo_again/status/1599108751385972737/video/2',
@@ -995,13 +999,13 @@ class TwitterIE(TwitterBaseIE):
             'repost_count': int,
             'duration': 9.531,
             'comment_count': int,
-            'view_count': int,
             'upload_date': '20221203',
             'age_limit': 0,
             'timestamp': 1670092210.0,
             'tags': [],
             'uploader': '\u06ea',
             'description': '\U0001F48B https://t.co/bTj9Qz7vQP',
+            '_old_archive_ids': ['twitter 1599108751385972737'],
         },
         'params': {'noplaylist': True},
     }, {
@@ -1012,7 +1016,6 @@ class TwitterIE(TwitterBaseIE):
             'ext': 'mp4',
             'uploader_url': 'https://twitter.com/MunTheShinobi',
             'description': 'This is a genius ad by Apple. \U0001f525\U0001f525\U0001f525\U0001f525\U0001f525 https://t.co/cNsA0MoOml',
-            'view_count': int,
             'thumbnail': 'https://pbs.twimg.com/ext_tw_video_thumb/1600009362759733248/pu/img/XVhFQivj75H_YxxV.jpg?name=orig',
             'age_limit': 0,
             'uploader': 'Mün',
@@ -1025,6 +1028,7 @@ class TwitterIE(TwitterBaseIE):
             'uploader_id': 'MunTheShinobi',
             'duration': 139.987,
             'timestamp': 1670306984.0,
+            '_old_archive_ids': ['twitter 1600009574919962625'],
         },
     }, {
         # retweeted_status (private)
@@ -1068,8 +1072,8 @@ class TwitterIE(TwitterBaseIE):
             'thumbnail': r're:https://pbs\.twimg\.com/amplify_video_thumb/.+',
             'like_count': int,
             'repost_count': int,
-            'view_count': int,
             'comment_count': int,
+            '_old_archive_ids': ['twitter 1695424220702888009'],
         },
     }, {
         # retweeted_status w/ legacy API
@@ -1091,18 +1095,24 @@ class TwitterIE(TwitterBaseIE):
             'thumbnail': r're:https://pbs\.twimg\.com/amplify_video_thumb/.+',
             'like_count': int,
             'repost_count': int,
+            '_old_archive_ids': ['twitter 1695424220702888009'],
         },
         'params': {'extractor_args': {'twitter': {'api': ['legacy']}}},
     }, {
         # Broadcast embedded in tweet
-        'url': 'https://twitter.com/JessicaDobsonWX/status/1693057346933600402',
+        'url': 'https://twitter.com/JessicaDobsonWX/status/1731121063248175384',
         'info_dict': {
-            'id': '1yNGaNLjEblJj',
+            'id': '1rmxPMjLzAXKN',
             'ext': 'mp4',
-            'title': 'Jessica Dobson - WAVE Weather Now - Saturday 8/19/23 Update',
+            'title': 'WAVE Weather Now - Saturday 12/2/23 Update',
             'uploader': 'Jessica Dobson',
-            'uploader_id': '1DZEoDwDovRQa',
-            'thumbnail': r're:^https?://.*\.jpg',
+            'uploader_id': 'JessicaDobsonWX',
+            'uploader_url': 'https://twitter.com/JessicaDobsonWX',
+            'timestamp': 1701566398,
+            'upload_date': '20231203',
+            'live_status': 'was_live',
+            'thumbnail': r're:https://[^/]+pscp\.tv/.+\.jpg',
+            'concurrent_view_count': int,
             'view_count': int,
         },
         'add_ie': ['TwitterBroadcast'],
@@ -1125,6 +1135,30 @@ class TwitterIE(TwitterBaseIE):
         },
         'params': {'extractor_args': {'twitter': {'api': ['syndication']}}},
         'expected_warnings': ['Not all metadata'],
+    }, {
+        # "stale tweet" with typename "TweetWithVisibilityResults"
+        'url': 'https://twitter.com/RobertKennedyJr/status/1724884212803834154',
+        'md5': '62b1e11cdc2cdd0e527f83adb081f536',
+        'info_dict': {
+            'id': '1724883339285544960',
+            'ext': 'mp4',
+            'title': 'md5:cc56716f9ed0b368de2ba54c478e493c',
+            'description': 'md5:9dc14f5b0f1311fc7caf591ae253a164',
+            'display_id': '1724884212803834154',
+            'uploader': 'Robert F. Kennedy Jr',
+            'uploader_id': 'RobertKennedyJr',
+            'uploader_url': 'https://twitter.com/RobertKennedyJr',
+            'upload_date': '20231115',
+            'timestamp': 1700079417.0,
+            'duration': 341.048,
+            'thumbnail': r're:https://pbs\.twimg\.com/amplify_video_thumb/.+',
+            'tags': ['Kennedy24'],
+            'repost_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'age_limit': 0,
+            '_old_archive_ids': ['twitter 1724884212803834154'],
+        },
     }, {
         # onion route
         'url': 'https://twitter3e4tixl4xyajtrzo62zg5vztmjuricljdp2c5kshju4avyoid.onion/TwitterBlue/status/1484226494708662273',
@@ -1179,19 +1213,23 @@ class TwitterIE(TwitterBaseIE):
         ), default={}, get_all=False) if self.is_logged_in else traverse_obj(
             data, ('tweetResult', 'result', {dict}), default={})
 
-        if result.get('__typename') not in ('Tweet', 'TweetTombstone', 'TweetUnavailable', None):
-            self.report_warning(f'Unknown typename: {result.get("__typename")}', twid, only_once=True)
+        typename = result.get('__typename')
+        if typename not in ('Tweet', 'TweetWithVisibilityResults', 'TweetTombstone', 'TweetUnavailable', None):
+            self.report_warning(f'Unknown typename: {typename}', twid, only_once=True)
 
         if 'tombstone' in result:
             cause = remove_end(traverse_obj(result, ('tombstone', 'text', 'text', {str})), '. Learn more')
             raise ExtractorError(f'Twitter API says: {cause or "Unknown error"}', expected=True)
-        elif result.get('__typename') == 'TweetUnavailable':
+        elif typename == 'TweetUnavailable':
             reason = result.get('reason')
             if reason == 'NsfwLoggedOut':
                 self.raise_login_required('NSFW tweet requires authentication')
             elif reason == 'Protected':
                 self.raise_login_required('You are not authorized to view this protected tweet')
             raise ExtractorError(reason or 'Requested tweet is unavailable', expected=True)
+        # Result for "stale tweet" needs additional transformation
+        elif typename == 'TweetWithVisibilityResults':
+            result = traverse_obj(result, ('tweet', {dict})) or {}
 
         status = result.get('legacy', {})
         status.update(traverse_obj(result, {
@@ -1280,41 +1318,51 @@ class TwitterIE(TwitterBaseIE):
             }
         }
 
-    def _extract_status(self, twid):
-        if self.is_logged_in or self._selected_api == 'graphql':
-            status = self._graphql_to_legacy(self._call_graphql_api(self._GRAPHQL_ENDPOINT, twid), twid)
-
-        elif self._selected_api == 'legacy':
-            status = self._call_api(f'statuses/show/{twid}.json', twid, {
-                'cards_platform': 'Web-12',
-                'include_cards': 1,
-                'include_reply_count': 1,
-                'include_user_entities': 0,
-                'tweet_mode': 'extended',
+    def _call_syndication_api(self, twid):
+        self.report_warning(
+            'Not all metadata or media is available via syndication endpoint', twid, only_once=True)
+        status = self._download_json(
+            'https://cdn.syndication.twimg.com/tweet-result', twid, 'Downloading syndication JSON',
+            headers={'User-Agent': 'Googlebot'}, query={
+                'id': twid,
+                # TODO: token = ((Number(twid) / 1e15) * Math.PI).toString(36).replace(/(0+|\.)/g, '')
+                'token': ''.join(random.choices('123456789abcdefghijklmnopqrstuvwxyz', k=10)),
             })
+        if not status:
+            raise ExtractorError('Syndication endpoint returned empty JSON response')
+        # Transform the result so its structure matches that of legacy/graphql
+        media = []
+        for detail in traverse_obj(status, ((None, 'quoted_tweet'), 'mediaDetails', ..., {dict})):
+            detail['id_str'] = traverse_obj(detail, (
+                'video_info', 'variants', ..., 'url', {self._MEDIA_ID_RE.search}, 1), get_all=False) or twid
+            media.append(detail)
+        status['extended_entities'] = {'media': media}
 
-        elif self._selected_api == 'syndication':
-            self.report_warning(
-                'Not all metadata or media is available via syndication endpoint', twid, only_once=True)
-            status = self._download_json(
-                'https://cdn.syndication.twimg.com/tweet-result', twid, 'Downloading syndication JSON',
-                headers={'User-Agent': 'Googlebot'}, query={
-                    'id': twid,
-                    # TODO: token = ((Number(twid) / 1e15) * Math.PI).toString(36).replace(/(0+|\.)/g, '')
-                    'token': ''.join(random.choices('123456789abcdefghijklmnopqrstuvwxyz', k=10)),
+        return status
+
+    def _extract_status(self, twid):
+        if self._selected_api not in ('graphql', 'legacy', 'syndication'):
+            raise ExtractorError(f'{self._selected_api!r} is not a valid API selection', expected=True)
+
+        try:
+            if self.is_logged_in or self._selected_api == 'graphql':
+                status = self._graphql_to_legacy(self._call_graphql_api(self._GRAPHQL_ENDPOINT, twid), twid)
+            elif self._selected_api == 'legacy':
+                status = self._call_api(f'statuses/show/{twid}.json', twid, {
+                    'cards_platform': 'Web-12',
+                    'include_cards': 1,
+                    'include_reply_count': 1,
+                    'include_user_entities': 0,
+                    'tweet_mode': 'extended',
                 })
-            if not status:
-                raise ExtractorError('Syndication endpoint returned empty JSON response')
-            # Transform the result so its structure matches that of legacy/graphql
-            media = []
-            for detail in traverse_obj(status, ((None, 'quoted_tweet'), 'mediaDetails', ..., {dict})):
-                detail['id_str'] = traverse_obj(detail, (
-                    'video_info', 'variants', ..., 'url', {self._MEDIA_ID_RE.search}, 1), get_all=False) or twid
-                media.append(detail)
-            status['extended_entities'] = {'media': media}
+        except ExtractorError as e:
+            if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
+                raise
+            self.report_warning('Rate-limit exceeded; falling back to syndication endpoint')
+            status = self._call_syndication_api(twid)
 
-        else:
-            raise ExtractorError(f'"{self._selected_api}" is not a valid API selection', expected=True)
+        if self._selected_api == 'syndication':
+            status = self._call_syndication_api(twid)
 
         return traverse_obj(status, 'retweeted_status', None, expected_type=dict) or {}
 
@@ -1377,10 +1425,10 @@ class TwitterIE(TwitterBaseIE):
                 'formats': formats,
                 'subtitles': subtitles,
                 'thumbnails': thumbnails,
-                'view_count': traverse_obj(media, ('mediaStats', 'viewCount', {int_or_none})),
+                'view_count': traverse_obj(media, ('mediaStats', 'viewCount', {int_or_none})),  # No longer available
                 'duration': float_or_none(traverse_obj(media, ('video_info', 'duration_millis')), 1000),
-                # The codec of http formats are unknown
-                '_format_sort_fields': ('res', 'br', 'size', 'proto'),
+                # Prioritize m3u8 formats for compat, see https://github.com/yt-dlp/yt-dlp/issues/8117
+                '_format_sort_fields': ('res', 'proto:m3u8', 'br', 'size'),  # http format codec is unknown
             }
 
         def extract_from_card_info(card):

yt_dlp/extractor/youtube.py

@@ -4480,14 +4480,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             if mobj:
                                 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
                                 break
-            sbr_tooltip = try_get(
-                vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
-            if sbr_tooltip:
-                like_count, dislike_count = sbr_tooltip.split(' / ')
-                info.update({
-                    'like_count': str_to_int(like_count),
-                    'dislike_count': str_to_int(dislike_count),
-                })
+
+            info['like_count'] = traverse_obj(vpir, (
+                'videoActions', 'menuRenderer', 'topLevelButtons', ...,
+                'segmentedLikeDislikeButtonViewModel', 'likeButtonViewModel', 'likeButtonViewModel',
+                'toggleButtonViewModel', 'toggleButtonViewModel', 'defaultButtonViewModel',
+                'buttonViewModel', 'accessibilityText', {parse_count}), get_all=False)
+
             vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
             if vcr:
                 vc = self._get_count(vcr, 'viewCount')

yt_dlp/update.py

@@ -206,13 +206,14 @@ class Updater:
     # XXX: use class variables to simplify testing
     _channel = CHANNEL
     _origin = ORIGIN
+    _update_sources = UPDATE_SOURCES
 
     def __init__(self, ydl, target: str | None = None):
         self.ydl = ydl
         # For backwards compat, target needs to be treated as if it could be None
         self.requested_channel, sep, self.requested_tag = (target or self._channel).rpartition('@')
         # Check if requested_tag is actually the requested repo/channel
-        if not sep and ('/' in self.requested_tag or self.requested_tag in UPDATE_SOURCES):
+        if not sep and ('/' in self.requested_tag or self.requested_tag in self._update_sources):
             self.requested_channel = self.requested_tag
             self.requested_tag: str = None  # type: ignore (we set it later)
         elif not self.requested_channel:
@@ -237,11 +238,11 @@ class Updater:
                 self._block_restart('Automatically restarting into custom builds is disabled for security reasons')
         else:
             # Check if requested_channel resolves to a known repository or else raise
-            self.requested_repo = UPDATE_SOURCES.get(self.requested_channel)
+            self.requested_repo = self._update_sources.get(self.requested_channel)
             if not self.requested_repo:
                 self._report_error(
                     f'Invalid update channel {self.requested_channel!r} requested. '
-                    f'Valid channels are {", ".join(UPDATE_SOURCES)}', True)
+                    f'Valid channels are {", ".join(self._update_sources)}', True)
 
         self._identifier = f'{detect_variant()} {system_identifier()}'
 

yt_dlp/utils/networking.py

@@ -67,7 +67,7 @@ class HTTPHeaderDict(collections.UserDict, dict):
     def __setitem__(self, key, value):
         if isinstance(value, bytes):
             value = value.decode('latin-1')
-        super().__setitem__(key.title(), str(value))
+        super().__setitem__(key.title(), str(value).strip())
 
     def __getitem__(self, key):
         return super().__getitem__(key.title())

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

@@ -286,8 +286,8 @@ class CueBlock(Block):
         m1 = parser.consume(_REGEX_TS)
         if not m1:
             return None
-        parser.consume(_REGEX_OPTIONAL_WHITESPACE)
         m2 = parser.consume(cls._REGEX_SETTINGS)
+        parser.consume(_REGEX_OPTIONAL_WHITESPACE)
         if not parser.consume(_REGEX_NL):
             return None