Merge b8f7389a712f0962a17927b8ce9557d50fb6a3ca into da7223d4aa42ff9fc680b0951d043dd03cec2d30

* improve extraction of global "useful data" Array from player JS
* also handle tv-player and add tests: thx seproDev (yt-dlp/yt-dlp#12684)

Co-Authored-By: sepro <sepro@sepr0.com>

test/test_youtube_signature.py

@@ -232,8 +232,32 @@ _NSIG_TESTS = [
         'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
     ),
     (
-        'https://www.youtube.com/s/player/91201489/player_ias_tce.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'U48vOZHaeYS6vO',
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+        'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
+    ),
+    (
+        'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
+        'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
+    ),
+    (
+        'https://www.youtube.com/s/player/d50f54ef/player_ias_tce.vflset/en_US/base.js',
+        'Ha7507LzRmH3Utygtj', 'XFTb2HoeOE5MHg',
+    ),
+    (
+        'https://www.youtube.com/s/player/074a8365/player_ias_tce.vflset/en_US/base.js',
+        'Ha7507LzRmH3Utygtj', 'ufTsrE0IVYrkl8v',
+    ),
+    (
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+        'N5uAlLqm0eg1GyHO', 'dCBQOejdq5s-ww',
+    ),
+    (
+        'https://www.youtube.com/s/player/69f581a5/tv-player-ias.vflset/tv-player-ias.js',
+        '-qIP447rVlTTwaZjY', 'KNcGOksBAvwqQg',
+    ),
+    (
+        'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
+        'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
     ),
 ]
 

youtube_dl/extractor/chelseafc.py

@@ -0,0 +1,83 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    traverse_obj,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+class ChelseafcIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chelseafc\.com(?:/[a-z]+)?/video/(?P<id>[a-z0-9]+(?:-[a-z0-9]+)*)'
+    _TESTS = [{
+        'url': 'https://www.chelseafc.com/en/video/full-match-chelsea-2-2-everton',
+        'md5': '2fda617911b7148a2a19bec55b75d30a',
+        'info_dict': {
+            'id': 'full-match-chelsea-2-2-everton',
+            'ext': 'mp4',
+            'title': 'Full Match: Chelsea 2-2 Everton',
+            'description': 'Full match highlights from Chelsea\'s 2-2 Premier League draw with Everton at Stamford Bridge.',
+            'duration': 2842.0,
+            'timestamp': 1679184000,
+            'tags': ['Premier League', 'Everton', 'Video and article choice'],
+            'upload_date': '20230319',
+            'thumbnail': r're:https?://.*\.png'
+        }
+    },
+        {
+        'url': 'https://www.chelseafc.com/en/video/manchester-city-vs-chelsea-2-0-or-highlights-or-efl-cup',
+        'md5': '2905365c3c9cf4612f303fbb99c2f4ca',
+        'info_dict': {
+            'id': 'manchester-city-vs-chelsea-2-0-or-highlights-or-efl-cup',
+            'ext': 'mp4',
+            'title': 'Manchester City 2-0 Chelsea | Highlights | EFL Cup',
+            'description': 'Highlights from our EFL Cup match against Man City.',
+            'duration': 120.0,
+            'timestamp': 1668042000,
+            'upload_date': '20221110',
+            'tags': ['Highlights', 'League Cup', 'Manchester City'],
+            'thumbnail': r're:https?://.*\.jpg'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_details_div = self._search_regex(
+            r'(<div\s[^>]*\bdata-component\s*=\s*(?:"|\')\s*VideoDetails\s*(?:"|\')[^>]*>)',
+            webpage,
+            'div'
+        )
+        raw_data = self._html_search_regex(
+            r'<div[^>]*\sdata-props\s*=\s*(?:"|\')\s*([^"\']*)\s*(?:"|\')[^>]*>',
+            video_details_div,
+            'data'
+        )
+
+        data = self._parse_json(raw_data, video_id)
+        manifest_url = data['videoDetail']['signedUrl']
+
+        data = data['videoDetail']
+
+        title = data['title']
+
+        formats = self._extract_m3u8_formats(manifest_url, video_id, 'mp4')
+        self._sort_formats(formats)
+
+        txt_or_none = lambda x: x.strip() or None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': txt_or_none(data.get('description')),
+            'formats': formats,
+            'duration': parse_duration(data.get('duration')),
+            'timestamp': unified_timestamp(data.get('releaseDate')),
+            'tags': traverse_obj(data, ('tags', Ellipsis, 'title'), expected_type=txt_or_none),
+            'thumbnail': traverse_obj(data, ('image', 'file', 'url'), expected_type=url_or_none),
+        }

youtube_dl/extractor/extractors.py

@@ -215,6 +215,7 @@ from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
+from .chelseafc import ChelseafcIE
 from .chilloutzone import ChilloutzoneIE
 from .chirbit import (
     ChirbitIE,
@@ -989,6 +990,10 @@ from .puhutv import (
     PuhuTVIE,
     PuhuTVSerieIE,
 )
+from .pr0gramm import (
+    Pr0grammIE,
+    Pr0grammStaticIE,
+)
 from .presstv import PressTVIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE

youtube_dl/extractor/youtube.py

@@ -91,12 +91,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'IOS',
-                    'clientVersion': '19.45.4',
+                    'clientVersion': '20.10.4',
                     'deviceMake': 'Apple',
                     'deviceModel': 'iPhone16,2',
-                    'userAgent': 'com.google.ios.youtube/19.45.4 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
+                    'userAgent': 'com.google.ios.youtube/20.10.4 (iPhone16,2; U; CPU iOS 18_3_2 like Mac OS X;)',
                     'osName': 'iPhone',
-                    'osVersion': '18.1.0.22B83',
+                    'osVersion': '18.3.2.22D82',
                 },
             },
             'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
@@ -109,7 +109,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'MWEB',
-                    'clientVersion': '2.20241202.07.00',
+                    'clientVersion': '2.20250311.03.00',
                     # mweb previously did not require PO Token with this UA
                     'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)',
                 },
@@ -122,7 +122,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'TVHTML5',
-                    'clientVersion': '7.20250120.19.00',
+                    'clientVersion': '7.20250312.16.00',
                     'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
                 },
             },
@@ -133,7 +133,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'INNERTUBE_CONTEXT': {
                 'client': {
                     'clientName': 'WEB',
-                    'clientVersion': '2.20241126.01.00',
+                    'clientVersion': '2.20250312.04.00',
                 },
             },
             'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
@@ -692,7 +692,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         'invidious': '|'.join(_INVIDIOUS_SITES),
     }
     _PLAYER_INFO_RE = (
-        r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
+        r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})//(?:tv-)?player',
         r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
         r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
     )
@@ -1857,7 +1857,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
 
         var_ay = self._search_regex(
-            r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"[^"]+"\s*\.\s*split\("\{"\))(?=\s*[,;])',
+            r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"(?:\\"|[^"])+"\s*\.\s*split\("\W+"\))(?=\s*[,;])',
             jsi.code, 'useful values', default='')
 
         func_name = self._extract_n_function_name(jsi.code)