int_or_none,
is_html,
join_nonempty,
+ js_to_json,
mimetype2ext,
network_exceptions,
NO_DEFAULT,
_RESERVED_NAMES = (
r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
- r'shorts|movies|results|shared|hashtag|trending|feed|feeds|'
+ r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
r'browse|oembed|get_video_info|iframe_api|s/player|'
r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
Appears to be used to track session state
"""
return get_first(
- args, (('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))),
+ args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
expected_type=str)
@property
note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
except ExtractorError as e:
if isinstance(e.cause, network_exceptions):
- if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)):
- e.cause.seek(0)
- yt_error = try_get(
- self._parse_json(e.cause.read().decode(), item_id, fatal=False),
- lambda x: x['error']['message'], compat_str)
- if yt_error:
- self._report_alerts([('ERROR', yt_error)], fatal=False)
+ if isinstance(e.cause, compat_HTTPError):
+ first_bytes = e.cause.read(512)
+ if not is_html(first_bytes):
+ yt_error = try_get(
+ self._parse_json(
+ self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
+ lambda x: x['error']['message'], compat_str)
+ if yt_error:
+ self._report_alerts([('ERROR', yt_error)], fatal=False)
# Downloading page may result in intermittent 5xx HTTP error
# Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
# We also want to catch all other network exceptions since errors in later pages can be troublesome
'age_limit': 0,
'start_time': 1,
'end_time': 9,
+ 'channel_follower_count': int
}
},
{
'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
'live_status': 'not_live',
'age_limit': 0,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'categories': ['Music'],
'age_limit': 0,
'alt_title': 'The Spark',
+ 'channel_follower_count': int
},
'params': {
'youtube_include_dash_manifest': True,
'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
'playable_in_embed': True,
'view_count': int,
+ 'channel_follower_count': int
},
},
{
'like_count': int,
'duration': 177,
'playable_in_embed': True,
+ 'channel_follower_count': int
},
},
{
'categories': ['Entertainment'],
'duration': 106,
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
+ 'channel_follower_count': int
},
},
{
'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
'live_status': 'not_live',
'artist': 'OOMPH!',
+ 'channel_follower_count': int
},
},
{
'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
'categories': ['Music'],
'album': 'Some Chords',
+ 'channel_follower_count': int
},
'expected_warnings': [
'DASH manifest missing',
'live_status': 'was_live',
'view_count': int,
'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
+ 'channel_follower_count': int
},
'params': {
'skip_download': 'requires avconv',
'like_count': int,
'live_status': 'not_live',
'availability': 'unlisted',
+ 'channel_follower_count': int
},
},
# url_encoded_fmt_stream_map is empty string
'playable_in_embed': True,
'like_count': int,
'age_limit': 0,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
'live_status': 'not_live',
'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'view_count': int,
'live_status': 'not_live',
'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'like_count': int,
'playable_in_embed': True,
'live_status': 'not_live',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
'tags': 'count:11',
'live_status': 'not_live',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'playable_in_embed': True,
'live_status': 'not_live',
'channel': 'ElevageOrVert',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'view_count': int,
'duration': 522,
'channel': 'kudvenkat',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
'categories': ['Music'],
'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'like_count': int,
'live_status': 'not_live',
'playable_in_embed': True,
+ 'channel_follower_count': int
}
},
{
'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
'live_status': 'not_live',
'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'like_count': int,
'live_status': 'not_live',
'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'format': '17', # 3gp format available on android
'duration': 248,
'categories': ['Education'],
'age_limit': 0,
+ 'channel_follower_count': int
}, 'params': {'format': 'mhtml', 'skip_download': True}
}
]
raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
def _extract_n_function_name(self, jscode):
- return self._search_regex(
- (r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})\([a-zA-Z0-9]\)',),
- jscode, 'Initial JS player n function name', group='nfunc')
+ nfunc, idx = self._search_regex(
+ r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
+ jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
+ if not idx:
+ return nfunc
+ return json.loads(js_to_json(self._search_regex(
+ rf'var {nfunc}\s*=\s*(\[.+?\]);', jscode,
+ f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
def _extract_n_function(self, video_id, player_url):
player_id = self._extract_player_info(player_url)
tbr = float_or_none(
fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
+ language_preference = (
+ 10 if audio_track.get('audioIsDefault') and 10
+ else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
+ else -1)
dct = {
'asr': int_or_none(fmt.get('audioSampleRate')),
'filesize': int_or_none(fmt.get('contentLength')),
'format_id': itag,
'format_note': join_nonempty(
'%s%s' % (audio_track.get('displayName') or '',
- ' (default)' if audio_track.get('audioIsDefault') else ''),
+ ' (default)' if language_preference > 0 else ''),
fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
throttled and 'THROTTLED', delim=', '),
'source_preference': -10 if throttled else -1,
'tbr': tbr,
'url': fmt_url,
'width': int_or_none(fmt.get('width')),
- 'language': audio_track.get('id', '').split('.')[0],
- 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
+ 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
+ 'desc' if language_preference < -1 else ''),
+ 'language_preference': language_preference,
}
mime_mobj = re.match(
r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
'uploader_url': owner_profile_url,
'channel_id': channel_id,
- 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
+ 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
'duration': duration,
'view_count': int_or_none(
get_first((video_details, microformats), (..., 'viewCount'))
trans_name += format_field(lang_name, template=' from %s')
process_language(
automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
+ if lang_code == f'a-{trans_code}':
+ process_language(
+ automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {'tlang': trans_code})
info['automatic_captions'] = automatic_captions
info['subtitles'] = subtitles
})
vsir = content.get('videoSecondaryInfoRenderer')
if vsir:
- info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
+ vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
+ info.update({
+ 'channel': self._get_text(vor, 'title'),
+ 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
+
rows = try_get(
vsir,
lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
+ @staticmethod
+ def passthrough_smuggled_data(func):
+ def _smuggle(entries, smuggled_data):
+ for entry in entries:
+ # TODO: Convert URL to music.youtube instead.
+ # Do we need to passthrough any other smuggled_data?
+ entry['url'] = smuggle_url(entry['url'], smuggled_data)
+ yield entry
+
+ @functools.wraps(func)
+ def wrapper(self, url):
+ url, smuggled_data = unsmuggle_url(url, {})
+ if self.is_music_url(url):
+ smuggled_data['is_music_url'] = True
+ info_dict = func(self, url, smuggled_data)
+ if smuggled_data and info_dict.get('entries'):
+ info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
+ return info_dict
+ return wrapper
+
def _extract_channel_id(self, webpage):
channel_id = self._html_search_meta(
'channelId', webpage, 'channel id', default=None)
ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
break
+ def _music_reponsive_list_entry(self, renderer):
+ video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
+ if video_id:
+ return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
+ ie=YoutubeIE.ie_key(), video_id=video_id)
+ playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
+ if playlist_id:
+ video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
+ if video_id:
+ return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
+ ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
+ return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
+ ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
+ browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
+ if browse_id:
+ return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
+ ie=YoutubeTabIE.ie_key(), video_id=browse_id)
+
def _shelf_entries_from_content(self, shelf_renderer):
content = shelf_renderer.get('content')
if not isinstance(content, dict):
for content in contents:
if not isinstance(content, dict):
continue
- is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
+ is_renderer = traverse_obj(
+ content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
+ expected_type=dict)
if not is_renderer:
renderer = content.get('richItemRenderer')
if renderer:
'playlistVideoListRenderer': self._playlist_entries,
'gridRenderer': self._grid_entries,
'shelfRenderer': lambda x: self._shelf_entries(x),
+ 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
'backstagePostThreadRenderer': self._post_thread_entries,
'videoRenderer': lambda x: [self._video_entry(x)],
'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
'view_count': self._get_count(playlist_stats, 1),
'availability': self._extract_availability(data),
'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
- 'playlist_count': self._get_count(playlist_stats, 0)
+ 'playlist_count': self._get_count(playlist_stats, 0),
+ 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
}
if not channel_id:
metadata.update(self._extract_uploader(data))
raise ExtractorError(err_note, expected=True)
self.report_warning(err_note, item_id)
- @staticmethod
- def _smuggle_data(entries, data):
- for entry in entries:
- if data:
- entry['url'] = smuggle_url(entry['url'], data)
- yield entry
-
_SEARCH_PARAMS = None
- def _search_results(self, query, params=NO_DEFAULT):
+ def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
data = {'query': query}
if params is NO_DEFAULT:
params = self._SEARCH_PARAMS
if params:
data['params'] = params
+
+ content_keys = (
+ ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
+ ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
+ # ytmusic search
+ ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
+ ('continuationContents', ),
+ )
+ check_get_keys = tuple(set(keys[0] for keys in content_keys))
+
continuation_list = [None]
for page_num in itertools.count(1):
data.update(continuation_list[0] or {})
search = self._extract_response(
item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
- check_get_keys=('contents', 'onResponseReceivedCommands'))
- slr_contents = try_get(
- search,
- (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
- lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
- list)
- yield from self._extract_entries({'contents': slr_contents}, continuation_list)
+ default_client=default_client, check_get_keys=check_get_keys)
+ slr_contents = traverse_obj(search, *content_keys)
+ yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
if not continuation_list[0]:
break
'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
+ 'channel_follower_count': int
},
}, {
'note': 'playlists, multipage, different order',
'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
'channel': 'Igor Kleiner',
'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
+ 'channel_follower_count': int
},
}, {
'note': 'playlists, series',
'channel': '3Blue1Brown',
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
'tags': ['Mathematics'],
+ 'channel_follower_count': int
},
}, {
'note': 'playlists, singlepage',
'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
'tags': 'count:13',
'channel': 'ThirstForScience',
+ 'channel_follower_count': int
}
}, {
'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_follower_count': int
},
'playlist_mincount': 2,
}, {
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel': 'lex will',
+ 'channel_follower_count': int
},
'playlist_mincount': 975,
}, {
'channel': 'lex will',
'tags': ['bible', 'history', 'prophesy'],
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_follower_count': int
},
'playlist_mincount': 199,
}, {
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 17,
}, {
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 18,
}, {
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 12,
}, {
'tags': ['Mathematics'],
'channel': '3Blue1Brown',
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
+ 'channel_follower_count': int
},
}, {
'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
}, {
'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
'info_dict': {
- 'id': 'zpsbVPFwsqk', # This will keep changing
+ 'id': 'GgL890LIznQ', # This will keep changing
'ext': 'mp4',
'title': str,
'uploader': 'Sky News',
'categories': ['News & Politics'],
'tags': list,
'like_count': int,
- 'release_timestamp': 1640164857,
+ 'release_timestamp': 1642502819,
'channel': 'Sky News',
'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
'age_limit': 0,
'view_count': int,
- 'thumbnail': 'https://i.ytimg.com/vi/zpsbVPFwsqk/maxresdefault_live.jpg',
+ 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
'playable_in_embed': True,
- 'release_date': '20211222',
+ 'release_date': '20220118',
'availability': 'public',
'live_status': 'is_live',
'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'info_dict': {
'id': 'recommended',
'title': 'recommended',
+ 'tags': [],
},
'playlist_mincount': 50,
'params': {
'tags': [],
'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
+ 'channel_follower_count': int
},
'playlist_mincount': 650,
'params': {
return False if YoutubeIE.suitable(url) else super(
YoutubeTabIE, cls).suitable(url)
- def _real_extract(self, url):
- url, smuggled_data = unsmuggle_url(url, {})
- if self.is_music_url(url):
- smuggled_data['is_music_url'] = True
- info_dict = self.__real_extract(url, smuggled_data)
- if info_dict.get('entries'):
- info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
- return info_dict
-
_URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
- def __real_extract(self, url, smuggled_data):
+ @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
+ def _real_extract(self, url, smuggled_data):
item_id = self._match_id(url)
url = compat_urlparse.urlunparse(
compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
IE_NAME = 'youtube:search'
_SEARCH_KEY = 'ytsearch'
_SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
- _TESTS = []
+ _TESTS = [{
+ 'url': 'ytsearch5:youtube-dl test video',
+ 'playlist_count': 5,
+ 'info_dict': {
+ 'id': 'youtube-dl test video',
+ 'title': 'youtube-dl test video',
+ }
+ }]
class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
_SEARCH_KEY = 'ytsearchdate'
IE_DESC = 'YouTube search, newest videos first'
_SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
+ _TESTS = [{
+ 'url': 'ytsearchdate5:youtube-dl test video',
+ 'playlist_count': 5,
+ 'info_dict': {
+ 'id': 'youtube-dl test video',
+ 'title': 'youtube-dl test video',
+ }
+ }]
class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
IE_DESC = 'YouTube search URLs with sorting and filter support'
IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
- _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
_TESTS = [{
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
'playlist_mincount': 5,
return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
-class YoutubeFeedsInfoExtractor(YoutubeTabIE):
+class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
+ IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
+ IE_NAME = 'youtube:music:search_url'
+ _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
+ _TESTS = [{
+ 'url': 'https://music.youtube.com/search?q=royalty+free+music',
+ 'playlist_count': 16,
+ 'info_dict': {
+ 'id': 'royalty free music',
+ 'title': 'royalty free music',
+ }
+ }, {
+ 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
+ 'playlist_mincount': 30,
+ 'info_dict': {
+ 'id': 'royalty free music - songs',
+ 'title': 'royalty free music - songs',
+ },
+ 'params': {'extract_flat': 'in_playlist'}
+ }, {
+ 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
+ 'playlist_mincount': 30,
+ 'info_dict': {
+ 'id': 'royalty free music - community playlists',
+ 'title': 'royalty free music - community playlists',
+ },
+ 'params': {'extract_flat': 'in_playlist'}
+ }]
+
+ _SECTIONS = {
+ 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
+ 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
+ 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
+ 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
+ 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
+ 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
+ }
+
+ def _real_extract(self, url):
+ qs = parse_qs(url)
+ query = (qs.get('search_query') or qs.get('q'))[0]
+ params = qs.get('sp', (None,))[0]
+ if params:
+ section = next((k for k, v in self._SECTIONS.items() if v == params), params)
+ else:
+ section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
+ params = self._SECTIONS.get(section)
+ if not params:
+ section = None
+ title = join_nonempty(query, section, delim=' - ')
+ return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
+
+
+class YoutubeFeedsInfoExtractor(InfoExtractor):
"""
Base class for feed extractors
Subclasses must define the _FEED_NAME property.
def _real_extract(self, url):
return self.url_result(
- 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
- ie=YoutubeTabIE.ie_key())
+ f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
class YoutubeWatchLaterIE(InfoExtractor):
projects / yt-dlp.git / blobdiff