Merge f7a7601f27951db481cd23c3bc8491d6bf86524b 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/extractors.py

@@ -1566,6 +1566,7 @@ from .wdr import (
     WDRElefantIE,
     WDRMobileIE,
 )
+from .webarchive import WebArchiveIE
 from .webcaster import (
     WebcasterIE,
     WebcasterFeedIE,

youtube_dl/extractor/webarchive.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class WebArchiveIE(InfoExtractor):
+    _VALID_URL = r'https?:\/\/(?:www\.)?web\.archive\.org\/web\/([0-9]+)\/https?:\/\/(?:www\.)?youtube\.com\/watch\?v=(?P<id>[0-9A-Za-z_-]{1,11})$'
+    _TEST = {
+        'url': 'https://web.archive.org/web/20150415002341/https://www.youtube.com/watch?v=aYAGB11YrSs',
+        'md5': 'ec44dc1177ae37189a8606d4ca1113ae',
+        'info_dict': {
+            'url': 'https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/aYAGB11YrSs',
+            'id': 'aYAGB11YrSs',
+            'ext': 'mp4',
+            'title': 'Team Fortress 2 - Sandviches!',
+            'author': 'Zeurel',
+        }
+    }
+
+    def _real_extract(self, url):
+        # Get video ID and page
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Extract title and author
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title').strip()
+        author = self._html_search_regex(r'"author":"([a-zA-Z0-9]+)"', webpage, 'author').strip()
+
+        # Parse title
+        if title.endswith(' - YouTube'):
+            title = title[:-10]
+
+        # Use link translator mentioned in https://github.com/ytdl-org/youtube-dl/issues/13655
+        link_stub = "https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/"
+
+        # Extract hash from url
+        hash_idx = url.find("watch?v=") + len("watch?v=")
+        youtube_hash = url[hash_idx:]
+
+        # If there's an ampersand, cut off before it
+        ampersand = youtube_hash.find('&')
+        if ampersand != -1:
+            youtube_hash = youtube_hash[:ampersand]
+
+        # Recreate the fixed pattern url and return
+        reconstructed_url = link_stub + youtube_hash
+        return {
+            'url': reconstructed_url,
+            'id': video_id,
+            'title': title,
+            'author': author,
+            'ext': "mp4"
+        }

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)