Merge e29f8e8707b3c37eb10d9e2944d76550d43d297a 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

@@ -1534,6 +1534,7 @@ from .voxmedia import (
     VoxMediaVolumeIE,
     VoxMediaIE,
 )
+from .voe import VOEIE
 from .vrt import VRTIE
 from .vrak import VrakIE
 from .vrv import (

youtube_dl/extractor/voe.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_base64_b64decode
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    url_or_none,
+)
+
+
+class VOEIE(InfoExtractor):
+    IE_NAME = 'voe'
+    IE_DESC = 'VOE.SX'
+    _VALID_URL = r'https?://voe\.sx(?P<path>/(e/)?(?P<id>[a-z0-9]+))'
+    _TESTS = [{
+        'url': 'https://voe.sx/e/ng7ja5n5n2y8',
+        'info_dict': {
+            'id': 'ng7ja5n5n2y8',
+            'title': 'md5:8dd774de9b73851151d80ef6baaea7f1',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'ext': 'm3u8',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id, video_path = self._match_valid_url(url).group('id', 'path')
+
+        webpage = self._download_webpage(
+            'https://voe.sx/e/%s' % video_id, video_id)
+
+        player_url = self._search_regex(
+            r'''("|')(?P<url>https://(?!voe\.sx/)[^/]+%s)\1\s*;''' % (video_path,),
+            webpage, 'redirect', group='url', default=None)
+        if player_url:
+            webpage = self._download_webpage(
+                player_url, video_id, note='Redirecting to player page')
+
+        sources = self._search_json(
+            r'\bsources\s*=', webpage, 'sources', video_id, transform_source=js_to_json)
+
+        title = self._search_regex(
+            r'<title>(?:Watch\s+)?(?P<title>.+?)(?:-\s+VOE\s+\|.+)?</title>',
+            webpage, 'title', group='title')
+
+        formats = []
+        for fmt in ('mp4', 'hls'):
+            if fmt not in sources:
+                continue
+            sources[fmt] = url_or_none(sources[fmt]) or url_or_none(compat_base64_b64decode(sources[fmt]).decode('utf-8'))
+            f_url = sources.get('hls')
+        if f_url:
+            formats.extend(self._extract_m3u8_formats(
+                f_url, video_id, entry_protocol='m3u8_native', fatal=False))
+        f_url = sources.get('mp4')
+        if f_url:
+            formats.append({
+                'url': f_url,
+                'ext': 'mp4',
+                'height': int_or_none(sources.get('video_height')),
+            })
+
+        self._sort_formats(formats)
+
+        thumbnail = url_or_none(self._search_regex(
+            r'''(?:VOEPlayer\s*\.\s*|data-)poster\s*=\s*("|')(?P<thumbnail>(?:(?!\1)\S)+)\1''',
+            webpage, 'thumbnail', group='thumbnail', default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

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)