Merge 5b088ccdd9ebb83ccd32a0a0a2cacd537fd2e03e 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',
+        'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
-        'W9HJZKktxuYoDTqW', 'U48vOZHaeYS6vO',
+        '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

@@ -560,6 +560,7 @@ from .jwplatform import JWPlatformIE
 from .kakao import KakaoIE
 from .kaltura import KalturaIE
 from .kankan import KankanIE
+from .kankids import KanKidsIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE

youtube_dl/extractor/kankids.py

@@ -0,0 +1,76 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+
+CONTENT_DIR = r'/content/kids/'
+DOMAIN = r'kankids.org.il'
+
+
+class KanKidsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?' +\
+        DOMAIN.replace('.', '\\.') + CONTENT_DIR +\
+        r'(?P<category>[a-z]+)-main/(?P<id>[\w\-0-9]+)/(?P<season>\w+)?/?$'
+    _TESTS = [
+        {
+            'url': 'https://www.kankids.org.il/content/kids/ktantanim-main/p-11732/',
+            'info_dict': {
+                '_type': 'playlist',
+                'id': 'p-11732',
+                'title': 'בית ספר לקוסמים',
+            },
+            'playlist_count': 60,
+        },
+        {
+            'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/cramel_main/s1/',
+            'info_dict': {
+                '_type': 'playlist',
+                'id': 'cramel_main',
+                'title': 'כראמל - עונה 1',
+            },
+            'playlist_count': 21,
+        },
+    ]
+
+    def _real_extract(self, url):
+        m = super()._match_valid_url(url)
+        series_id = m.group('id')
+        category = m.group('category')
+        playlist_season = m.group('season')
+
+        webpage = self._download_webpage(url, series_id)
+
+        title_pattern = r'<title>(?P<title>.+) \|'
+        series_title = re.search(title_pattern, webpage)
+        if not series_title:
+            series_title = re.search(title_pattern[:-1] + r'-', webpage)
+        if series_title:
+            series_title = series_title.group('title')
+
+        season = playlist_season if playlist_season else r'(?P<season>\w+)'
+        content_dir = CONTENT_DIR + category + r'-main/'
+        playlist = set(re.findall(
+            r'href="' + content_dir         # Content dir
+            + series_id + r'/'              # Series
+            + season + r'/'                 # Season
+            + r'(?P<id>[0-9]+)/"'           # Episode
+            + r'.+title="(?P<title>.+)"',   # Title
+            webpage))
+
+        entries = []
+        content_dir = r'https://www.' + DOMAIN + content_dir
+        for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
+            entries.append(self.url_result(
+                content_dir + season + r'/' + video_id + r'/',
+                ie='Generic',
+                video_id=video_id,
+                video_title=title,
+            ))
+
+        return {
+            '_type': 'playlist',
+            'id': series_id,
+            'title': series_title,
+            'entries': entries,
+        }

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)