Merge 45ecff5db023bb441ab3b9334b6dc5287b287a3b into da7223d4aa42ff9fc680b0951d043dd03cec2d30

[YouTube] Improve support for tce-style player JS
* 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>
2025-07-15 16:04:13 +09:00 · 2025-03-21 20:37:20 +01:00 · 2025-03-21 16:26:25 +00:00 · 2025-03-21 16:13:24 +00:00 · 2024-07-25 12:31:23 -04:00
4 changed files with 226 additions and 10 deletions
--- a/test/test_youtube_signature.py
+++ b/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',
    ),
 ]

--- a/youtube_dl/extractor/bandlab.py
+++ b/youtube_dl/extractor/bandlab.py
@ -0,0 +1,191 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+    ExtractorError,
+    merge_dicts,
+    T,
+    traverse_obj,
+    txt_or_none,
+    url_or_none,
+)
+
+
+class BandlabIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bandlab\.com/post/(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'https://www.bandlab.com/post/f117c6d9-9b14-ef11-96f5-000d3a425266',
+        'info_dict': {
+            'id': 'f117c6d9-9b14-ef11-96f5-000d3a425266',
+            'ext': 'm4a',
+            'title': 'essentials',
+            'artist': 'Nico Tranquility',
+        },
+    }]
+
+    def _real_extract(self, url):
+        track_id = self._match_id(url)
+        config = self._download_json(
+            'http://www.bandlab.com/api/v1.3/posts/%s' % track_id, track_id)
+        track_url = traverse_obj(config, ('revision', 'mixdown', 'file', T(url_or_none)))
+        if not track_url:
+            raise ExtractorError(
+                '[%s] No video formats found!' % (self.ie_key(), ),
+                video_id=track_id, expected=True)
+        title = traverse_obj(config, ('revision', 'song', 'name', T(txt_or_none)))
+
+        return {
+            'id': track_id,
+            'title': title,
+            'url': track_url,
+            'artist': traverse_obj(config, ('creator', 'name', T(txt_or_none))),
+        }
+
+
+class BandlabAlbumOrPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bandlab\.com/[^/]+/(?P<kind>albums|collections)/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://www.bandlab.com/nicoeskasenuatrans/albums/a7f108ca-74d6-ee11-85f9-00224845a8e0',
+        'playlist': [
+            {
+                "info_dict": {
+                    "id": "d30b09de-2320-4fc3-a778-c2cb8a01baf7",
+                    "title": "self made",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "2b08f655-7ae5-407c-afbb-f0d6f5dec4ed",
+                    "title": "pride",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "03259a33-613a-4e2b-a784-0cf67e82886a",
+                    "title": "free speech",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "5264bf91-9700-4603-9a78-c40d2aee2a56",
+                    "title": "legalize insanity",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "a32c22f5-945c-4bb5-91d6-3419f96b92bf",
+                    "title": "euphoria",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "df065a3c-a36d-4e6e-81a8-c2b94204b1c6",
+                    "title": "true colours (more euphoria)",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "e0bf4b18-deb2-4a09-99e2-07d45bcc9c1e",
+                    "title": "manifest",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "a6b0c087-8980-4699-954b-7ee0376be7f6",
+                    "title": "survivor's guilt",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "19b80025-6557-43d5-85b9-cd9f6075f27e",
+                    "title": "memories",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "ff6a0fdf-afb5-40d0-902f-1f1760b74c75",
+                    "title": "it gets better",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "12e77b89-43e6-42ef-b1c9-f7551f108f16",
+                    "title": "undeletable",
+                    "ext": "m4a"
+                }
+            },
+            {
+                "info_dict": {
+                    "id": "f2b959bf-4014-4c5d-8079-3f6d0b9ca5b9",
+                    "title": "antifascientist",
+                    "ext": "m4a"
+                }
+            }
+        ],
+        'info_dict': {
+            'id': 'a7f108ca-74d6-ee11-85f9-00224845a8e0',
+            'album': 'trans*',
+            'artist': 'Nico Tranquility'
+        },
+    }, {
+        'url': 'https://www.bandlab.com/hexatetrahedronx/collections/8fb1041c-e865-eb11-9889-0050f28a2802',
+        'playlist': [
+            {
+                'info_dict': {
+                    'id': '8f37e4aa-92c4-eb11-a7ad-0050f280467f',
+                    'title': 'psych ward',
+                    'ext': 'm4a'
+                }
+            }
+        ],
+        'info_dict': {
+            'id': '8fb1041c-e865-eb11-9889-0050f28a2802',
+            'album': 'DOOMTAPE',
+            'artist': '12days'
+        }
+    }]
+
+    def _real_extract(self, url):
+        resource_id, kind = self._match_valid_url(url).group('id', 'kind')
+        config = self._download_json(
+            'http://www.bandlab.com/api/v1.3/%s/%s' % (kind, resource_id), resource_id)
+        entries = []
+        for track in traverse_obj(config, ('posts', Ellipsis)):
+            url, name = (traverse_obj(track, ('track', {
+                'url': ('sample', 'audioUrl', T(url_or_none)),
+                'name': ('name', T(txt_or_none)),
+            }), ('revision', {
+                'url': ('mixdown', 'file', T(url_or_none)),
+                'name': ('song', 'name', T(txt_or_none)),
+            })).get(x) for x in ('url', 'name'))
+            if not (url and name):
+                continue
+            track_id = self._search_regex(
+                r'/([^/]+)\.m4a$', url, 'track id', default=None)
+            if not track_id:
+                continue
+            entries.append({
+                'url': url,
+                'id': track_id,
+                'title': name,
+            })
+
+        return merge_dicts(
+            self.playlist_result(entries, playlist_id=resource_id),
+            traverse_obj(config, {
+                'album': ('name', T(txt_or_none)),
+                'artist': ('creator', 'name', T(txt_or_none)),
+            }))
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@ -98,6 +98,7 @@ from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
 from .bandaichannel import BandaiChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
+from .bandlab import BandlabIE, BandlabAlbumOrPlaylistIE
 from .bbc import (
    BBCCoUkIE,
    BBCCoUkArticleIE,
--- a/youtube_dl/extractor/youtube.py
+++ b/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)
Author	SHA1	Message	Date
Aiur Adept	14872b36c8	Merge 45ecff5db023bb441ab3b9334b6dc5287b287a3b into da7223d4aa42ff9fc680b0951d043dd03cec2d30	2025-03-21 20:37:20 +01:00
dirkf	da7223d4aa	[YouTube] Improve support for tce-style player JS * 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>	2025-03-21 16:26:25 +00:00
dirkf	37c2440d6a	[YouTube] Update player client data thx seproDev (yt-dlp/yt-dlp#12603) Co-authored-by: sepro <sepro@sepr0.com>	2025-03-21 16:13:24 +00:00
nicole trinity	45ecff5db0	bandlab extractor	2024-07-25 12:31:23 -04:00