Merge da90df06c3b8e7e6cc66a124c196aef4eb856a89 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/doodstream.py

@@ -0,0 +1,132 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from random import choice as random_choice
+from string import ascii_letters, digits
+from time import time as time_time
+
+from ..compat import compat_filter as filter
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    get_element_by_class,
+    parse_duration,
+    parse_filesize,
+    update_url_query,
+    unified_strdate,
+    url_or_none,
+)
+
+from .common import InfoExtractor
+
+
+class DoodStreamIE(InfoExtractor):
+    # dood.* redirects
+    # .watch -> .re (but HEAD request fails in GenericIE)
+    # .so -> .li
+    _VALID_URL = r'https?://(?:www\.)?(?P<host>dood\.(?:to|la|li|pm|re|sh|watch|ws|one)|ds2play\.com)/[ed]/(?P<id>[a-z\d]+)'
+    _TESTS = [{
+        'url': 'https://dood.li/e/h7ecgw5oqn8k',
+        'md5': '90f2af170551c17fc78bee7426890054',
+        'info_dict': {
+            'id': 'h7ecgw5oqn8k',
+            'ext': 'mp4',
+            'title': 'Free-Slow-Music',
+            'upload_date': '20230814',
+            'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
+        },
+    }, {
+        'url': 'https://dood.to/d/is34uy8wvaet',
+        'md5': '04740d3ba93bcd638aa7a097d9226710',
+        'info_dict': {
+            'id': 'is34uy8wvaet',
+            'ext': 'mp4',
+            'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB',
+            'upload_date': '20211202',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
+            'filesize_approx': int,
+            'duration': 9886,
+        },
+        'skip': 'Video not found',
+    }, {
+        'url': 'https://dood.sh/d/wlihoael8uog',
+        'md5': '2c14444c89788cc309738c1560abe278',
+        'info_dict': {
+            'id': 'wlihoael8uog',
+            'ext': 'mp4',
+            'title': 'VID 20220319 161659',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
+            'upload_date': '20220319',
+            'filesize_approx': int,
+            'duration': 12.0,
+        },
+    }, {
+        'url': 'http://dood.ws/d/h7ecgw5oqn8k',
+        'only_matching': True,
+    }, {
+        'url': 'https://dood.li/d/wlihoael8uog',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        host = 'dood.li'
+        url = 'https://%s/e/%s' % (host, video_id)
+        webpage = self._download_webpage(url, video_id, note='Downloading "/e/" webpage')
+
+        def get_title(html, fatal=False):
+            return self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', html, 'title', fatal=fatal)
+
+        title = get_title(webpage)
+        if title == 'Video not found' or (
+                title == '' and 'Not Found' == self._html_search_regex(r'<h1\b[^>]*>([^<]+?)</h1', webpage, 'heading1', default=None)):
+            raise ExtractorError(title, expected=True)
+
+        pass_md5, token = self._search_regex(
+            r'["\']/(?P<pm>pass_md5/[\da-f-]+/(?P<tok>[\da-z]+))', webpage, 'tokens',
+            group=('pm', 'tok'))
+        headers = {
+            'Referer': url,
+        }
+        # construct the media link
+        final_url = self._download_webpage(
+            'https://%s/%s' % (host, pass_md5), video_id, headers={
+                'Referer': url,
+            }, note='Downloading authpage URL')
+        final_url += ''.join((random_choice(ascii_letters + digits)
+                              for _ in range(10)))
+        final_url = update_url_query(final_url, {
+            'token': token,
+            'expiry': int(time_time() * 1000),
+        })
+
+        # get additional metadata
+        thumb = next(filter(None, (url_or_none(self._html_search_meta(x, webpage, default=None))
+                                   for x in ('og:image', 'twitter:image'))), None)
+        description = self._html_search_meta(
+            ('og:description', 'description', 'twitter:description'), webpage, default=None)
+
+        webpage = self._download_webpage(
+            'https://%s/d/%s' % (host, video_id), video_id, fatal=False,
+            note='Downloading alternative "/d/" page') or ''
+
+        title = (
+            self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
+            or get_title(webpage, fatal=(title is not None))
+            or title)
+
+        def get_class_text(x):
+            return clean_html(get_element_by_class(x, webpage))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': final_url,
+            'http_headers': headers,
+            'ext': 'mp4',
+            'upload_date': unified_strdate(get_class_text('uploadate')),
+            'duration': parse_duration(get_class_text('length')),
+            'filesize_approx': parse_filesize(get_class_text('size')),
+            'description': description,
+            'thumbnail': thumb,
+        }

youtube_dl/extractor/extractors.py

@@ -304,6 +304,7 @@ from .dlf import (
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
+from .doodstream import DoodStreamIE
 from .dotsub import DotsubIE
 from .douyutv import (
     DouyuShowIE,

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)