Merge a87561248a2cf7283bead4b4f4d323d3d5ae0c94 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/canalrcn.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+import json
+
+
+class CanalrcnIE(InfoExtractor):
+    """Information extractor for canalrcn.com"""
+
+    _VALID_URL = r'https?://(?:www\.)?canalrcn\.com/(?:[^/]+/)+(?P<id>[^/?&#]+)'
+
+    # Specify geo-restriction
+    _GEO_COUNTRIES = ['CO']
+
+    _TESTS = [{
+        'url': 'https://www.canalrcn.com/la-rosa-de-guadalupe/capitulos/la-rosa-de-guadalupe-capitulo-58-los-enamorados-3619',
+        'info_dict': {
+            'id': 'x8ecrn2',
+            'ext': 'mp4',
+            'title': 'La rosa de Guadalupe | Capítulo 58 | Los enamorados',
+            'description': 'Pamela conoce a un hombre, pero sus papás no se lo aprueban porque no tiene recursos.',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png|webp)',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Video is geo-restricted to Colombia'],
+        'skip': 'Geo-restricted to Colombia'
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        json_ld = self._search_regex(
+            r'<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json>[^<]+)</script>',
+            webpage, 'JSON-LD', group='json', default='{}')
+
+        try:
+            json_data = json.loads(json_ld)
+        except json.JSONDecodeError:
+            raise ExtractorError('Could not parse JSON-LD data')
+
+        video_data = None
+        if isinstance(json_data, list):
+            for item in json_data:
+                if isinstance(item, dict) and item.get('@type') == 'VideoObject':
+                    video_data = item
+                    break
+
+        if not video_data:
+            raise ExtractorError('Could not find video information in JSON-LD data')
+
+        embed_url = video_data.get('embedUrl')
+        if not embed_url:
+            raise ExtractorError('Could not find video embed URL')
+
+        dailymotion_id = self._search_regex(
+            r'dailymotion\.com/(?:embed/)?video/([a-zA-Z0-9]+)',
+            embed_url,
+            'dailymotion id'
+        )
+        # geo-restriction handling
+        self.raise_geo_restricted(
+            msg='This video is only available in Colombia',
+            countries=self._GEO_COUNTRIES
+        )
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'http://www.dailymotion.com/video/%s' % dailymotion_id,
+            'ie_key': 'Dailymotion',
+            'id': dailymotion_id,
+            'title': video_data.get('name'),
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailUrl'),
+            'duration': video_data.get('duration'),
+        }

youtube_dl/extractor/extractors.py

@@ -169,6 +169,7 @@ from .cammodels import CamModelsIE
 from .camtube import CamTubeIE
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
+from .canalrcn import CanalrcnIE
 from .canalc2 import Canalc2IE
 from .canvas import (
     CanvasIE,

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)