Merge 3ecfa9f9f79bf570b24b4d82ab909e10f14cee67 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/extractors.py

@@ -817,6 +817,7 @@ from .nick import (
     NickDeIE,
     NickNightIE,
     NickRuIE,
+    NickIlIE,
 )
 from .niconico import (
     NiconicoIE,

youtube_dl/extractor/nick.py

@@ -3,8 +3,14 @@ from __future__ import unicode_literals
 
 import re
 
+from .common import InfoExtractor
 from .mtv import MTVServicesInfoExtractor
-from ..utils import update_url_query
+from ..utils import (
+    try_get,
+    update_url_query,
+    int_or_none,
+    ExtractorError,
+)
 
 
 class NickIE(MTVServicesInfoExtractor):
@@ -247,3 +253,42 @@ class NickRuIE(MTVServicesInfoExtractor):
         webpage = self._download_webpage(url, video_id)
         mgid = self._extract_mgid(webpage)
         return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
+
+
+class NickIlIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nick\.co\.il/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.nick.co.il/video/17360',
+        'md5': '0974ad5949022e0477a5a28ee5b85634',
+        'info_dict': {
+            'id': '17360',
+            'ext': 'mp4',
+            'title': '\u05e9\u05d9\u05e8 \u05d4\u05e4\u05ea\u05d9\u05d7\u05d4 \u05e9\u05dc \u05d3\u05d5\u05e8\u05d2 \u05d5\u05d0\u05df \u05d3\u05e0\u05d2\u05d5',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        items = self._download_json(
+            'http://nickplay.ilovegames.co.il/api/nicktogoapi/GetItems', video_id,
+            query={
+                'countryCode': 'IL',
+                'deviceId': '',
+                'isApp': 0,
+                'itemId': video_id,
+            }).get('items')
+        if items is None:
+            raise ExtractorError('Unable to extract video data', expected=True, video_id=video_id)
+        video = try_get([i for i in items if i.get('id') == int(video_id)], lambda x: x[0], dict)
+        if video is None:
+            raise ExtractorError('Unable to find video ID', expected=True, video_id=video_id)
+        url = video.get('url')
+        if url is None:
+            raise ExtractorError('Unable to extract video data', expected=True, video_id=video_id)
+        formats = self._extract_m3u8_formats(url, video_id, ext='mp4')
+        return {
+            'id': video_id,
+            'title': video.get('title'),
+            'duration': int_or_none(video.get('duration'), scale=1000),
+            'formats': formats,
+        }

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)