Merge 00d8a07eb61fef134a9addb50a584ebb8d3efeb1 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

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/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

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/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: