Merge 517af8b6e01654d70340509922f85869e9950741 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/vimeo.py

@@ -390,6 +390,29 @@ class VimeoIE(VimeoBaseInfoExtractor):
             },
             'expected_warnings': ['Unable to download JSON metadata'],
         },
+        {
+            'url': 'https://vimeo.com/channels/bestofstaffpicks/543188947',
+            'note': 'channel video with no data-config-url',
+            'info_dict': {
+                'id': '543188947',
+                'ext': 'mp4',
+                'title': "THE CHEMICAL BROTHERS 'THE DARKNESS THAT YOU FEAR' - OFFICIAL VIDEO",
+                'description': 'md5:a3949dd6e4a3dc5161871d195ee46cf0',
+                'uploader_url': r're:https?://(?:www\.)?vimeo\.com/ruffmercy',
+                'uploader_id': 'ruffmercy',
+                'uploader': 'RUFFMERCY',
+                'channel_id': 'bestofstaffpicks',
+                'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/bestofstaffpicks',
+                'timestamp': 1619693770,
+                'upload_date': '20210429',
+                'duration': 237,
+            },
+            'params': {
+                # avoid selecting DASH/HLS which only send 1 fragment and fail expected size check
+                'format': 'best[protocol=https]',
+            },
+            'expected_warnings': ['Unable to download JSON metadata'],
+        },
         {
             'url': 'http://vimeo.com/76979871',
             'note': 'Video with subtitles',
@@ -704,14 +727,18 @@ class VimeoIE(VimeoBaseInfoExtractor):
         channel_id = self._search_regex(
             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
         if channel_id:
+            # look for data-config-url=, but it may not be present
             config_url = self._html_search_regex(
-                r'\bdata-config-url="([^"]+)"', webpage, 'config URL')
+                r'\bdata-config-url\s*=\s*("|\')(?P<config_url>[^"\']+)\1',
+                webpage, 'config URL', group='config_url', default=None)
             video_description = clean_html(get_element_by_class('description', webpage))
             info_dict.update({
                 'channel_id': channel_id,
                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
             })
         else:
+            config_url = None
+        if not config_url:
             page_config = self._parse_json(self._search_regex(
                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
                 webpage, 'page config', default='{}'), video_id, fatal=False)
@@ -721,6 +748,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             cc_license = page_config.get('cc_license')
             clip = page_config.get('clip') or {}
             timestamp = clip.get('uploaded_on')
+            if not video_description:
                 video_description = clean_html(
                     clip.get('description') or page_config.get('description_html_escaped'))
         config = self._download_json(config_url, video_id)

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)