[rudovideo] forgot to rename a variable

Authored by: bashonly

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_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_utils.py

@@ -2370,6 +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/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 (

yt_dlp/extractor/aenetworks.py

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

yt_dlp/extractor/bitchute.py

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

yt_dlp/extractor/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/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/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/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/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

@@ -1,6 +1,7 @@
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    determine_ext,
     js_to_json,
     traverse_obj,
     update_url_query,
@@ -29,6 +30,15 @@ class RudoVideoIE(InfoExtractor):
             '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',
@@ -75,13 +85,13 @@ class RudoVideoIE(InfoExtractor):
         if 'Streaming is not available in your area' in webpage:
             self.raise_geo_restricted()
 
-        m3u8_url = (
+        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 m3u8_url:
+        if not media_url:
             youtube_url = self._search_regex(r'file:\s*[\'"]((?:https?:)//(?:www\.)?youtube\.com[^\'"]+)',
                                              webpage, 'youtube url', default=None)
             if youtube_url:
@@ -97,7 +107,12 @@ class RudoVideoIE(InfoExtractor):
                 raise ExtractorError('Invalid access token array')
             access_token = self._download_json(
                 token_url, video_id, note='Downloading access token')['data']['authToken']
-            m3u8_url = update_url_query(m3u8_url, {'auth-token': access_token})
+            media_url = update_url_query(media_url, {'auth-token': access_token})
+
+        if determine_ext(media_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(media_url, video_id, live=is_live)
+        else:
+            formats = [{'url': media_url}]
 
         return {
             'id': video_id,
@@ -109,6 +124,6 @@ class RudoVideoIE(InfoExtractor):
             'thumbnail': (self._search_regex(r'var\s+posterIMG\s*=\s*[\'"]([^?\'"]+)',
                                              webpage, 'thumbnail', default=None)
                           or self._og_search_thumbnail(webpage)),
-            'formats': self._extract_m3u8_formats(m3u8_url, video_id, live=is_live),
+            '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

@@ -479,9 +479,9 @@ 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 +515,7 @@ 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 +559,9 @@ 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 +600,9 @@ 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 +617,7 @@ 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 +637,9 @@ 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 +659,9 @@ 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 +685,9 @@ 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 +751,7 @@ class TwitterIE(TwitterBaseIE):
             'like_count': int,
             'tags': [],
             'age_limit': 0,
+            '_old_archive_ids': ['twitter 1349794411333394432'],
         },
         'params': {
             'skip_download': True,
@@ -771,18 +774,18 @@ 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 +816,9 @@ 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 +954,10 @@ 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 +982,7 @@ 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 +998,13 @@ 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 +1015,6 @@ 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 +1027,7 @@ class TwitterIE(TwitterBaseIE):
             'uploader_id': 'MunTheShinobi',
             'duration': 139.987,
             'timestamp': 1670306984.0,
+            '_old_archive_ids': ['twitter 1600009574919962625'],
         },
     }, {
         # retweeted_status (private)
@@ -1068,8 +1071,8 @@ 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 +1094,24 @@ 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 +1134,30 @@ 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 +1212,23 @@ 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, {
@@ -1377,7 +1414,7 @@ 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'),

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/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/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