Merge 0cca4de1ae173b4f2623ce317acfb9a1a0c15ab0 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/box.py

@@ -8,13 +8,13 @@ from .common import InfoExtractor
 from ..utils import (
     determine_ext,
     parse_iso8601,
-    # try_get,
+    try_get,
     update_url_query,
 )
 
 
 class BoxIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/]+)/file/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<prefix>(?:[^.]+\.)?)app\.box\.com/s/(?P<shared_name>[^/]+)(?:/file/(?P<id>\d+))?'
     _TEST = {
         'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
         'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@@ -30,20 +30,22 @@ class BoxIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        shared_name, file_id = re.match(self._VALID_URL, url).groups()
+        prefix, shared_name, file_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, file_id)
+        if not file_id:
+            file_id = re.search(r'"typedID":\s*"f_(\d+)"', webpage).group(1)
         request_token = self._parse_json(self._search_regex(
             r'Box\.config\s*=\s*({.+?});', webpage,
             'Box config'), file_id)['requestToken']
         access_token = self._download_json(
-            'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
+            'https://' + prefix + 'app.box.com/app-api/enduserapp/elements/tokens', file_id,
             'Downloading token JSON metadata',
             data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
                 'Content-Type': 'application/json',
                 'X-Request-Token': request_token,
                 'X-Box-EndUser-API': 'sharedName=' + shared_name,
             })[file_id]['read']
-        shared_link = 'https://app.box.com/s/' + shared_name
+        shared_link = 'https://' + prefix + 'app.box.com/s/' + shared_name
         f = self._download_json(
             'https://api.box.com/2.0/files/' + file_id, file_id,
             'Downloading file JSON metadata', headers={
@@ -51,7 +53,7 @@ class BoxIE(InfoExtractor):
                 'BoxApi': 'shared_link=' + shared_link,
                 'X-Rep-Hints': '[dash]',  # TODO: extract `hls` formats
             }, query={
-                'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
+                'fields': 'permissions,authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
             })
         title = f['name']
 
@@ -62,20 +64,24 @@ class BoxIE(InfoExtractor):
 
         formats = []
 
-        # for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
+        for entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
-        #     entry_url_template = try_get(
+            entry_url_template = try_get(
-        #         entry, lambda x: x['content']['url_template'])
+                entry, lambda x: x['content']['url_template'])
-        #     if not entry_url_template:
+            if not entry_url_template:
-        #         continue
+                continue
-        #     representation = entry.get('representation')
+            representation = entry.get('representation')
-        #     if representation == 'dash':
+            if representation == 'dash':
-        #         TODO: append query to every fragment URL
+                extracted = self._extract_mpd_formats(
-        #         formats.extend(self._extract_mpd_formats(
+                    entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
-        #             entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
+                    file_id, query=query)
-        #             file_id, query=query))
+                for extracted_format in extracted:
+                    for fragment in extracted_format['fragments']:
+                        fragment['path'] = update_url_query(fragment['path'], query)
+                formats.extend(extracted)
 
         authenticated_download_url = f.get('authenticated_download_url')
-        if authenticated_download_url and f.get('is_download_available'):
+        permissions = f.get('permissions') or {}
+        if authenticated_download_url and f.get('is_download_available') and permissions.get('can_download', True):
             formats.append({
                 'ext': f.get('extension') or determine_ext(title),
                 'filesize': f.get('size'),

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)