Merge 00d8a07eb61fef134a9addb50a584ebb8d3efeb1 into 673277e510ebd996b62a2fcc76169bf3cce29910

* [YouTube] Extract playlist items from LOCKUP_VIEW_MODEL_...
* resolves #33073
* thx seproDev (yt-dlp/yt-dlp#11615)

Co-authored-by: sepro <sepro@sepr0.com>

youtube_dl/extractor/bandlab.py

@@ -0,0 +1,170 @@
+# 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/f5f04998635a44ea819cacdba7ae2076_f8d8574c3bdaec11b6562818783151a1',
+        'info_dict': {
+            'id': 'f5f04998635a44ea819cacdba7ae2076_f8d8574c3bdaec11b6562818783151a1',
+            'ext': 'm4a',
+            'title': 'ON MY OWN (unreleased)',
+            'artist': 'Michael MacDonald',
+        },
+    }]
+
+    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, ('track', 'sample', 'audioUrl', 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 = config['track']['name']
+
+        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/sbsdasani/albums/dc26e307-e51f-ed11-95d7-002248452390',
+        'playlist': [
+            {
+                'info_dict': {
+                    'id': '91feeb36-8e10-4c91-ae57-ffac0a98c6b4',
+                    'title': 'How\'d I Lose You? (Intro)',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': 'd87c50a2-70cb-4937-9b97-3ae8646ca3aa',
+                    'title': 'Money $$$',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': 'ff2909ff-348f-448d-9d2c-7edbf2f0ec5e',
+                    'title': 'You\'ll Be Mine',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '53786c38-1f3c-4921-9271-793a64af7186',
+                    'title': 'Who You Are',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '0394bb27-113f-4d19-b902-f9c1fe6ba8a8',
+                    'title': 'In Your Eyes',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '2aa44689-c7fa-4d0e-b28a-e0d1dd570372',
+                    'title': 'The Same',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '281fe589-a559-4260-802d-78a6c7a973d8',
+                    'title': 'Fall In Love',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '83a9dc0a-702f-40fd-82f6-ab847f6a7b46',
+                    'title': 'Tried So Hard',
+                    'ext': 'm4a',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '3f6a4a1c-eb73-449f-bd45-f7958d6f2de1',
+                    'title': 'The End Of Everything',
+                    'ext': 'm4a',
+                },
+            }
+        ],
+        'info_dict': {
+            'id': 'dc26e307-e51f-ed11-95d7-002248452390',
+            'album': 'ENDLESS SUMMER',
+            'artist': 'Michael MacDonald'
+        },
+    }, {
+        '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)),
+            }))

youtube_dl/extractor/extractors.py

@@ -98,6 +98,10 @@ 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,

youtube_dl/extractor/youtube.py

@@ -27,6 +27,7 @@ from ..compat import (
 )
 from ..jsinterp import JSInterpreter
 from ..utils import (
+    bug_reports_message,
     clean_html,
     dict_get,
     error_to_compat_str,
@@ -65,6 +66,7 @@ from ..utils import (
     url_or_none,
     urlencode_postdata,
     urljoin,
+    variadic,
 )
 
 
@@ -460,6 +462,26 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'uploader': uploader,
         }
 
+    @staticmethod
+    def _extract_thumbnails(data, *path_list, **kw_final_key):
+        """
+        Extract thumbnails from thumbnails dict
+        @param path_list: path list to level that contains 'thumbnails' key
+        """
+        final_key = kw_final_key.get('final_key', 'thumbnails')
+
+        return traverse_obj(data, ((
+            tuple(variadic(path) + (final_key, Ellipsis)
+                  for path in path_list or [()])), {
+            'url': ('url', T(url_or_none),
+                    # Sometimes youtube gives a wrong thumbnail URL. See:
+                    # https://github.com/yt-dlp/yt-dlp/issues/233
+                    # https://github.com/ytdl-org/youtube-dl/issues/28023
+                    T(lambda u: update_url(u, query=None) if u and 'maxresdefault' in u else u)),
+            'height': ('height', T(int_or_none)),
+            'width': ('width', T(int_or_none)),
+        }, T(lambda t: t if t.get('url') else None)))
+
     def _search_results(self, query, params):
         data = {
             'context': {
@@ -3183,8 +3205,12 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             expected_type=txt_or_none)
 
     def _grid_entries(self, grid_renderer):
-        for item in grid_renderer['items']:
+        for item in traverse_obj(grid_renderer, ('items', Ellipsis, T(dict))):
-            if not isinstance(item, dict):
+            lockup_view_model = traverse_obj(item, ('lockupViewModel', T(dict)))
+            if lockup_view_model:
+                entry = self._extract_lockup_view_model(lockup_view_model)
+                if entry:
+                    yield entry
                 continue
             renderer = self._extract_grid_item_renderer(item)
             if not isinstance(renderer, dict):
@@ -3268,6 +3294,25 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 continue
             yield self._extract_video(renderer)
 
+    def _extract_lockup_view_model(self, view_model):
+        content_id = view_model.get('contentId')
+        if not content_id:
+            return
+        content_type = view_model.get('contentType')
+        if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'):
+            self.report_warning(
+                'Unsupported lockup view model content type "{0}"{1}'.format(content_type, bug_reports_message()), only_once=True)
+            return
+        return merge_dicts(self.url_result(
+            update_url_query('https://www.youtube.com/playlist', {'list': content_id}),
+            ie=YoutubeTabIE.ie_key(), video_id=content_id), {
+                'title': traverse_obj(view_model, (
+                    'metadata', 'lockupMetadataViewModel', 'title', 'content', T(compat_str))),
+                'thumbnails': self._extract_thumbnails(view_model, (
+                    'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail',
+                    'thumbnailViewModel', 'image'), final_key='sources'),
+        })
+
     def _video_entry(self, video_renderer):
         video_id = video_renderer.get('videoId')
         if video_id: