Merge 853a2a22394d5f1d0b7dca7afe8fc60b6807802c 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/cnbc.py

@@ -1,71 +1,23 @@
-# coding: utf-8
 from __future__ import unicode_literals
-
 import re
-
 from .common import InfoExtractor
 from ..utils import smuggle_url
 
-
 class CNBCIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://video.cnbc.com/gallery/?video=3000503714',
-        'info_dict': {
-            'id': '3000503714',
-            'ext': 'mp4',
-            'title': 'Fighting zombies is big business',
-            'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
-            'timestamp': 1459332000,
-            'upload_date': '20160330',
-            'uploader': 'NBCU-CNBC',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
+    _VALID_URL = 'https?://video\\.cnbc\\.com/gallery/\\?video=(?P<id>[0-9]+)'
+    _TEST = {'url': 'http://video.cnbc.com/gallery/?video=3000503714', 'info_dict': {'id': '3000503714', 'ext': 'mp4', 'title': 'Fighting zombies is big business', 'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e', 'timestamp': 1459332000, 'upload_date': '20160330', 'uploader': 'NBCU-CNBC'}, 'params': {'skip_download': True}}
 
     def _real_extract(self, url):
+        """Auto-generated docstring for function _real_extract."""
         video_id = self._match_id(url)
-        return {
-            '_type': 'url_transparent',
-            'ie_key': 'ThePlatform',
-            'url': smuggle_url(
-                'http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id,
-                {'force_smil_url': True}),
-            'id': video_id,
-        }
-
+        return {'_type': 'url_transparent', 'ie_key': 'ThePlatform', 'url': smuggle_url('http://link.theplatform.com/s/gZWlPC/media/guid/2408950221/%s?mbr=true&manifest=m3u' % video_id, {'force_smil_url': True}), 'id': video_id}
 
 class CNBCVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cnbc\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\.html)'
-    _TEST = {
-        'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
-        'info_dict': {
-            'id': '7000031301',
-            'ext': 'mp4',
-            'title': "Trump: I don't necessarily agree with raising rates",
-            'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3',
-            'timestamp': 1531958400,
-            'upload_date': '20180719',
-            'uploader': 'NBCU-CNBC',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }
+    _VALID_URL = 'https?://(?:www\\.)?cnbc\\.com(?P<path>/video/(?:[^/]+/)+(?P<id>[^./?#&]+)\\.html)'
+    _TEST = {'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', 'info_dict': {'id': '7000031301', 'ext': 'mp4', 'title': "Trump: I don't necessarily agree with raising rates", 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', 'timestamp': 1531958400, 'upload_date': '20180719', 'uploader': 'NBCU-CNBC'}, 'params': {'skip_download': True}}
 
     def _real_extract(self, url):
+        """Auto-generated docstring for function _real_extract."""
         path, display_id = re.match(self._VALID_URL, url).groups()
-        video_id = self._download_json(
-            'https://webql-redesign.cnbcfm.com/graphql', display_id, query={
-                'query': '''{
-  page(path: "%s") {
-    vcpsId
-  }
-}''' % path,
-            })['data']['page']['vcpsId']
-        return self.url_result(
-            'http://video.cnbc.com/gallery/?video=%d' % video_id,
-            CNBCIE.ie_key())
+        video_id = self._download_json('https://webql-redesign.cnbcfm.com/graphql', display_id, query={'query': '{\n  page(path: "%s") {\n    vcpsId\n  }\n}' % path})['data']['page']['vcpsId']
+        return self.url_result('http://video.cnbc.com/gallery/?video=%d' % video_id, CNBCIE.ie_key())

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)