Merging upstream version 2024.08.06.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 105 insertions, 50 deletions

diff --git a/yt_dlp/extractor/cbc.py b/yt_dlp/extractor/cbc.py
index 373c9d2..40224f6 100644
--- a/yt_dlp/extractor/cbc.py
+++ b/yt_dlp/extractor/cbc.py
@@ -806,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor):
                 'title': 'Ottawa',
                 'description': 'The live TV channel and local programming from Ottawa',
                 'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
-                'is_live': True,
+                'live_status': 'is_live',
                 'id': 'AyqZwxRqh8EH',
                 'ext': 'mp4',
-                'timestamp': 1492106160,
-                'upload_date': '20170413',
+                'release_timestamp': 1492106160,
+                'release_date': '20170413',
                 'uploader': 'CBCC-NEW',
             },
             'skip': 'Live might have ended',
@@ -839,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor):
                 'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
                 'live_status': 'is_live',
                 'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
-                'timestamp': 1679706000,
-                'upload_date': '20230325',
+                'release_timestamp': 1679706000,
+                'release_date': '20230325',
             },
             'params': {'skip_download': True},
             'skip': 'Live might have ended',
         },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/42314',
+            'md5': '297a9600f554f2258aed01514226a697',
+            'info_dict': {
+                'id': '42314',
+                'ext': 'mp4',
+                'live_status': 'was_live',
+                'title': 'Women\'s Soccer - Canada vs New Zealand',
+                'description': 'md5:36200e5f1a70982277b5a6ecea86155d',
+                'thumbnail': r're:https://.+default\.jpg',
+                'release_timestamp': 1721917200,
+                'release_date': '20240725',
+            },
+            'params': {'skip_download': True},
+            'skip': 'Replay might no longer be available',
+        },
+        {   # event replay (medianetlive)
+            'url': 'https://gem.cbc.ca/live-event/43273',
+            'only_matching': True,
+        },
     ]
+    _GEO_COUNTRIES = ['CA']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
 
-        # Two types of metadata JSON
+        # Three types of video_info JSON: info in root, freeTv stream/item, event replay
         if not video_info.get('formattedIdMedia'):
-            video_info = traverse_obj(
-                video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
-                get_all=False, default={})
+            if traverse_obj(video_info, ('event', 'key')) == video_id:
+                video_info = video_info['event']
+            else:
+                video_info = traverse_obj(video_info, (
+                    ('freeTv', ('streams', ...)), 'items',
+                    lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {}
 
         video_stream_id = video_info.get('formattedIdMedia')
         if not video_stream_id:
-            raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
-
-        stream_data = self._download_json(
-            'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
-                'appCode': 'mpx',
-                'connectionType': 'hd',
-                'deviceType': 'ipad',
-                'idMedia': video_stream_id,
-                'multibitrate': 'true',
-                'output': 'json',
-                'tech': 'hls',
-                'manifestType': 'desktop',
-            })
+            raise ExtractorError(
+                'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
+
+        live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live'
+        release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601}))
+
+        if live_status == 'is_live' and release_timestamp and release_timestamp > time.time():
+            formats = []
+            live_status = 'is_upcoming'
+            self.raise_no_formats('This livestream has not yet started', expected=True)
+        else:
+            stream_data = self._download_json(
+                'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
+                    'appCode': 'medianetlive',
+                    'connectionType': 'hd',
+                    'deviceType': 'ipad',
+                    'idMedia': video_stream_id,
+                    'multibitrate': 'true',
+                    'output': 'json',
+                    'tech': 'hls',
+                    'manifestType': 'desktop',
+                })
+            formats = self._extract_m3u8_formats(
+                stream_data['url'], video_id, 'mp4', live=live_status == 'is_live')
 
         return {
             'id': video_id,
-            'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
-            'is_live': True,
+            'formats': formats,
+            'live_status': live_status,
+            'release_timestamp': release_timestamp,
             **traverse_obj(video_info, {
-                'title': 'title',
-                'description': 'description',
+                'title': ('title', {str}),
+                'description': ('description', {str}),
                 'thumbnail': ('images', 'card', 'url'),
-                'timestamp': ('airDate', {parse_iso8601}),
             }),
         }
diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py
index cdf84c5..8d77072 100644
--- a/yt_dlp/extractor/dplay.py
+++ b/yt_dlp/extractor/dplay.py
@@ -1147,13 +1147,19 @@ class DiscoveryPlusShowBaseIE(DPlayBaseIE):
 
 
 class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
     _TESTS = [{
         'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi',
         'only_matching': True,
     }, {
         'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer',
         'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno',
+        'only_matching': True,
     }]
 
     _PRODUCT = 'dplus_it'
diff --git a/yt_dlp/extractor/niconico.py b/yt_dlp/extractor/niconico.py
index 9d7b010..179e7a9 100644
--- a/yt_dlp/extractor/niconico.py
+++ b/yt_dlp/extractor/niconico.py
@@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
-        'md5': 'd1a75c0823e2f629128c43e1212760f9',
         'info_dict': {
             'id': 'sm22312215',
             'ext': 'mp4',
@@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['未設定'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # File downloaded with and without credentials are different, so omit
         # the md5 field
@@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor):
             'view_count': int,
             'genres': ['音楽・サウンド'],
             'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # 'video exists but is marked as "deleted"
         # md5 is unstable
@@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor):
     }, {
         # video not available via `getflv`; "old" HTML5 video
         'url': 'http://www.nicovideo.jp/watch/sm1151009',
-        'md5': 'f95a3d259172667b293530cc2e41ebda',
         'info_dict': {
             'id': 'sm1151009',
             'ext': 'mp4',
@@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['ゲーム'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # "New" HTML5 video
-        # md5 is unstable
         'url': 'http://www.nicovideo.jp/watch/sm31464864',
         'info_dict': {
             'id': 'sm31464864',
@@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['アニメ'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         # Video without owner
         'url': 'http://www.nicovideo.jp/watch/sm18238488',
-        'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
         'info_dict': {
             'id': 'sm18238488',
             'ext': 'mp4',
@@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor):
             'comment_count': int,
             'genres': ['エンターテイメント'],
             'tags': [],
-            'expected_protocol': str,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
         'only_matching': True,
@@ -458,9 +454,11 @@ class NiconicoIE(InfoExtractor):
             if video_id.startswith('so'):
                 video_id = self._match_id(handle.url)
 
-            api_data = self._parse_json(self._html_search_regex(
-                'data-api-data="([^"]+)"', webpage,
-                'API data', default='{}'), video_id)
+            api_data = traverse_obj(
+                self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
+                ('data', 'response', {dict}))
+            if not api_data:
+                raise ExtractorError('Server response data not found')
         except ExtractorError as e:
             try:
                 api_data = self._download_json(
diff --git a/yt_dlp/extractor/olympics.py b/yt_dlp/extractor/olympics.py
index a50c510..bbf83e5 100644
--- a/yt_dlp/extractor/olympics.py
+++ b/yt_dlp/extractor/olympics.py
@@ -4,7 +4,9 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
+    parse_qs,
     try_get,
+    update_url,
     url_or_none,
 )
 from ..utils.traversal import traverse_obj
@@ -24,9 +26,6 @@ class OlympicsReplayIE(InfoExtractor):
             'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2',
             'duration': 7017.0,
         },
-        'params': {
-            'skip_download': True,
-        },
     }, {
         'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024',
         'info_dict': {
@@ -74,7 +73,7 @@ class OlympicsReplayIE(InfoExtractor):
 
         is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE'
         m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl']
-        tokenized_url = m3u8_url if is_live else self._tokenize_url(m3u8_url, video_id)
+        tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id)
 
         try:
             formats, subtitles = self._extract_m3u8_formats_and_subtitles(
@@ -95,10 +94,20 @@ class OlympicsReplayIE(InfoExtractor):
             }),
         }
 
-    def _tokenize_url(self, url, video_id):
+    def _tokenize_url(self, url, token, is_live, video_id):
+        return self._download_json(
+            'https://metering.olympics.com/tokengenerator', video_id,
+            'Downloading tokenized m3u8 url', query={
+                **parse_qs(url),
+                'url': update_url(url, query=None),
+                'service-id': 'live' if is_live else 'vod',
+                'user-auth': token,
+            })['data']['url']
+
+    def _legacy_tokenize_url(self, url, video_id):
         return self._download_json(
             'https://olympics.com/tokenGenerator', video_id,
-            'Downloading tokenized m3u8 url', query={'url': url})
+            'Downloading legacy tokenized m3u8 url', query={'url': url})
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -130,7 +139,7 @@ class OlympicsReplayIE(InfoExtractor):
             })
 
         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-            self._tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
+            self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
 
         return {
             'id': video_uuid,
diff --git a/yt_dlp/extractor/youku.py b/yt_dlp/extractor/youku.py
index fa6b053..3bdfa6c 100644
--- a/yt_dlp/extractor/youku.py
+++ b/yt_dlp/extractor/youku.py
@@ -136,7 +136,7 @@ class YoukuIE(InfoExtractor):
         # request basic data
         basic_data_params = {
             'vid': video_id,
-            'ccode': '0524',
+            'ccode': '0564',
             'client_ip': '192.168.1.1',
             'utid': cna,
             'client_ts': time.time() / 1000,
diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py
index 88e1a28..224c9b9 100644
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@@ -3180,6 +3180,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # *  b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c)
         # *  a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
         # *  a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("")
+        # *  a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
         funcname, idx = self._search_regex(
             r'''(?x)
             (?:
@@ -3187,7 +3188,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 (?:
                     b=String\.fromCharCode\(110\)|
                     (?P<str_idx>[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\]
-                ),c=a\.get\(b\)\)&&\(c=|
+                )
+                (?:
+                    ,[a-zA-Z0-9_$]+\(a\))?,c=a\.
+                    (?:
+                        get\(b\)|
+                        [a-zA-Z0-9_$]+\[b\]\|\|null
+                    )\)&&\(c=|
                 \b(?P<var>[a-zA-Z0-9_$]+)=
             )(?P<nfunc>[a-zA-Z0-9_$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z]\)
             (?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''',
@@ -3737,7 +3744,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _get_requested_clients(self, url, smuggled_data):
         requested_clients = []
         broken_clients = []
-        default = ['ios', 'tv']
+        default = ['ios', 'web_creator']
         allowed_clients = sorted(
             (client for client in INNERTUBE_CLIENTS if client[:1] != '_'),
             key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)