import calendar
import copy
import datetime
+import functools
import hashlib
import itertools
import json
import sys
import time
import traceback
+import threading
from .common import InfoExtractor, SearchInfoExtractor
from ..compat import (
int_or_none,
is_html,
join_nonempty,
+ js_to_json,
mimetype2ext,
network_exceptions,
NO_DEFAULT,
try_get,
unescapeHTML,
unified_strdate,
+ unified_timestamp,
unsmuggle_url,
update_url_query,
url_or_none,
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
- 'clientVersion': '2.20210622.10.00',
+ 'clientVersion': '2.20211221.00.00',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_EMBEDDED_PLAYER',
- 'clientVersion': '1.20210620.0.1',
+ 'clientVersion': '1.20211215.00.01',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 56
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_REMIX',
- 'clientVersion': '1.20210621.00.00',
+ 'clientVersion': '1.20211213.00.00',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
},
'web_creator': {
- 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+ 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_CREATOR',
- 'clientVersion': '1.20210621.00.00',
+ 'clientVersion': '1.20211220.02.00',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
},
'android': {
- 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+ 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID',
- 'clientVersion': '16.20',
+ 'clientVersion': '16.49',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
'REQUIRE_JS_PLAYER': False
},
'android_embedded': {
- 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+ 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_EMBEDDED_PLAYER',
- 'clientVersion': '16.20',
+ 'clientVersion': '16.49',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
'REQUIRE_JS_PLAYER': False
},
'android_music': {
- 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
- 'INNERTUBE_HOST': 'music.youtube.com',
+ 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_MUSIC',
- 'clientVersion': '4.32',
+ 'clientVersion': '4.57',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
'REQUIRE_JS_PLAYER': False
},
'android_creator': {
+ 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_CREATOR',
- 'clientVersion': '21.24.100',
+ 'clientVersion': '21.47',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
'REQUIRE_JS_PLAYER': False
},
- # ios has HLS live streams
- # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680
+ # iOS clients have HLS live streams. Setting device model to get 60fps formats.
+ # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
'ios': {
- 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
+ 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS',
- 'clientVersion': '16.20',
+ 'clientVersion': '16.46',
+ 'deviceModel': 'iPhone14,3',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_JS_PLAYER': False
},
'ios_embedded': {
- 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MESSAGES_EXTENSION',
- 'clientVersion': '16.20',
+ 'clientVersion': '16.46',
+ 'deviceModel': 'iPhone14,3',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
'REQUIRE_JS_PLAYER': False
},
'ios_music': {
- 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og',
- 'INNERTUBE_HOST': 'music.youtube.com',
+ 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MUSIC',
- 'clientVersion': '4.32',
+ 'clientVersion': '4.57',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_CREATOR',
- 'clientVersion': '21.24.100',
+ 'clientVersion': '21.47',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
# mweb has 'ultralow' formats
# See: https://github.com/yt-dlp/yt-dlp/pull/557
'mweb': {
- 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
+ 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'MWEB',
- 'clientVersion': '2.20210721.07.00',
+ 'clientVersion': '2.20211221.01.00',
}
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2
- },
+ }
}
def build_innertube_clients():
- third_party = {
+ THIRD_PARTY = {
'embedUrl': 'https://google.com', # Can be any valid URL
}
- base_clients = ('android', 'web', 'ios', 'mweb')
- priority = qualities(base_clients[::-1])
+ BASE_CLIENTS = ('android', 'web', 'ios', 'mweb')
+ priority = qualities(BASE_CLIENTS[::-1])
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
- ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
- if client in base_clients:
- INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
+ base_client, *variant = client.split('_')
+ ytcfg['priority'] = 10 * priority(base_client)
+
+ if variant == ['embedded']:
+ ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
+ INNERTUBE_CLIENTS[f'{base_client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
- agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
agegate_ytcfg['priority'] -= 1
- elif client.endswith('_embedded'):
- ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
ytcfg['priority'] -= 2
- else:
+ elif variant:
ytcfg['priority'] -= 3
_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')
r'(?:www\.)?invidious\.zee\.li',
r'(?:www\.)?invidious\.ethibox\.fr',
r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
+ r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
+ r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
# youtube-dl invidious instances list
r'(?:(?:www|no)\.)?invidiou\.sh',
r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
except ValueError:
self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
- pref.update({'hl': 'en'})
+ pref.update({'hl': 'en', 'tz': 'UTC'})
self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
def _real_initialize(self):
def _extract_context(self, ytcfg=None, default_client='web'):
context = get_first(
(ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
- # Enforce language for extraction
- traverse_obj(context, 'client', expected_type=dict, default={})['hl'] = 'en'
+ # Enforce language and tz for extraction
+ client_context = traverse_obj(context, 'client', expected_type=dict, default={})
+ client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
return context
_SAPISID = None
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
if text:
return text
+ def _get_count(self, data, *path_list):
+ count_text = self._get_text(data, *path_list) or ''
+ count = parse_count(count_text)
+ if count is None:
+ count = str_to_int(
+ self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
+ return count
+
+ @staticmethod
+ def _extract_thumbnails(data, *path_list):
+ """
+ Extract thumbnails from thumbnails dict
+ @param path_list: path list to level that contains 'thumbnails' key
+ """
+ thumbnails = []
+ for path in path_list or [()]:
+ for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
+ thumbnail_url = url_or_none(thumbnail.get('url'))
+ if not thumbnail_url:
+ continue
+ # 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
+ if 'maxresdefault' in thumbnail_url:
+ thumbnail_url = thumbnail_url.split('?')[0]
+ thumbnails.append({
+ 'url': thumbnail_url,
+ 'height': int_or_none(thumbnail.get('height')),
+ 'width': int_or_none(thumbnail.get('width')),
+ })
+ return thumbnails
+
@staticmethod
def extract_relative_time(relative_time_text):
"""
Extracts a relative time from string and converts to dt object
- e.g. 'streamed 6 days ago', '5 seconds ago (edited)'
+ e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
"""
- mobj = re.search(r'(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
+ mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
if mobj:
+ start = mobj.group('start')
+ if start:
+ return datetime_from_str(start)
try:
- return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')), precision='auto')
+ return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
except ValueError:
return None
timestamp = None
if isinstance(dt, datetime.datetime):
timestamp = calendar.timegm(dt.timetuple())
+
+ if timestamp is None:
+ timestamp = (
+ unified_timestamp(text) or unified_timestamp(
+ self._search_regex(
+ (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
+ text.lower(), 'time text', default=None)))
+
if text and timestamp is None:
self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
return timestamp, text
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
description = self._get_text(renderer, 'descriptionSnippet')
duration = parse_duration(self._get_text(
renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
- view_count_text = self._get_text(renderer, 'viewCountText') or ''
- view_count = str_to_int(self._search_regex(
- r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
- 'view count', default=None))
+ view_count = self._get_count(renderer, 'viewCountText')
uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
channel_id = traverse_obj(
overlay_style = traverse_obj(
renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
badges = self._extract_badges(renderer)
+ thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
+
return {
'_type': 'url',
'ie_key': YoutubeIE.ie_key(),
'view_count': view_count,
'uploader': uploader,
'channel_id': channel_id,
- 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
+ 'thumbnails': thumbnails,
+ 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
'live_status': ('is_upcoming' if scheduled_timestamp is not None
else 'was_live' if 'streamed' in time_text.lower()
else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
- (?:(?:v|embed|e|shorts)/(?!videoseries)) # v/ or embed/ or e/ or shorts/
+ (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
|(?: # or the v= param in all its forms
(?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
'duration': 10,
'view_count': int,
'like_count': int,
- # 'dislike_count': int,
'availability': 'public',
'playable_in_embed': True,
'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
'age_limit': 0,
'start_time': 1,
'end_time': 9,
+ 'channel_follower_count': int
}
},
{
'uploader': 'Philipp Hagemeister',
'uploader_id': 'phihag',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
+ 'channel': 'Philipp Hagemeister',
+ 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
+ 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
'upload_date': '20121002',
- 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
+ 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
'categories': ['Science & Technology'],
'tags': ['youtube-dl'],
'duration': 10,
'view_count': int,
'like_count': int,
- 'dislike_count': int,
+ 'availability': 'public',
+ 'playable_in_embed': True,
+ '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,
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
'abr': 129.495,
+ 'like_count': int,
+ 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
+ 'playable_in_embed': True,
+ 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
+ 'view_count': int,
+ 'track': 'The Spark',
+ 'live_status': 'not_live',
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
+ 'channel': 'Afrojack',
+ 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
+ 'tags': 'count:19',
+ 'availability': 'public',
+ 'categories': ['Music'],
+ 'age_limit': 0,
+ 'alt_title': 'The Spark',
+ 'channel_follower_count': int
},
'params': {
'youtube_include_dash_manifest': True,
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
'upload_date': '20140605',
'age_limit': 18,
+ 'categories': ['Gaming'],
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
+ 'availability': 'needs_auth',
+ 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
+ 'like_count': int,
+ 'channel': 'The Witcher',
+ 'live_status': 'not_live',
+ 'tags': 'count:17',
+ 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
+ 'playable_in_embed': True,
+ 'view_count': int,
+ 'channel_follower_count': int
},
},
{
'uploader_id': 'FlyingKitty900',
'uploader': 'FlyingKitty',
'age_limit': 18,
+ 'availability': 'needs_auth',
+ 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
+ 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
+ 'channel': 'FlyingKitty',
+ 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
+ 'view_count': int,
+ 'categories': ['Entertainment'],
+ 'live_status': 'not_live',
+ 'tags': ['Flyingkitty', 'godzilla 2'],
+ 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
+ 'like_count': int,
+ 'duration': 177,
+ 'playable_in_embed': True,
+ 'channel_follower_count': int
},
},
{
'uploader': 'Projekt Melody',
'description': 'md5:17eccca93a786d51bc67646756894066',
'age_limit': 18,
+ 'like_count': int,
+ 'availability': 'needs_auth',
+ 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
+ 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
+ 'view_count': int,
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
+ 'channel': 'Projekt Melody',
+ 'live_status': 'not_live',
+ 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
+ 'playable_in_embed': True,
+ 'categories': ['Entertainment'],
+ 'duration': 106,
+ 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
+ 'channel_follower_count': int
},
},
{
'uploader_id': 'st3in234',
'description': 'Fan Video. Music & Lyrics by OOMPH!.',
'upload_date': '20130730',
+ 'track': 'Such mich find mich',
+ 'age_limit': 0,
+ 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
+ 'like_count': int,
+ 'playable_in_embed': False,
+ 'creator': 'OOMPH!',
+ 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
+ 'view_count': int,
+ 'alt_title': 'Such mich find mich',
+ 'duration': 210,
+ 'channel': 'Herr Lurik',
+ 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
+ 'categories': ['Music'],
+ 'availability': 'public',
+ 'uploader_url': 'http://www.youtube.com/user/st3in234',
+ 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
+ 'live_status': 'not_live',
+ 'artist': 'OOMPH!',
+ 'channel_follower_count': int
},
},
{
'uploader': 'deadmau5',
'title': 'Deadmau5 - Some Chords (HD)',
'alt_title': 'Some Chords',
+ 'availability': 'public',
+ 'tags': 'count:14',
+ 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
+ 'view_count': int,
+ 'live_status': 'not_live',
+ 'channel': 'deadmau5',
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
+ 'like_count': int,
+ 'track': 'Some Chords',
+ 'artist': 'deadmau5',
+ 'playable_in_embed': True,
+ 'age_limit': 0,
+ 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
+ 'categories': ['Music'],
+ 'album': 'Some Chords',
+ 'channel_follower_count': int
},
'expected_warnings': [
'DASH manifest missing',
'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
'uploader': 'Olympics',
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
+ 'like_count': int,
+ 'release_timestamp': 1343767800,
+ 'playable_in_embed': True,
+ 'categories': ['Sports'],
+ 'release_date': '20120731',
+ 'channel': 'Olympics',
+ 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
+ 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
+ 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
+ 'age_limit': 0,
+ 'availability': 'public',
+ 'live_status': 'was_live',
+ 'view_count': int,
+ 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
+ 'channel_follower_count': int
},
'params': {
'skip_download': 'requires avconv',
'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
'uploader': '孫ᄋᄅ',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
+ 'playable_in_embed': True,
+ 'channel': '孫ᄋᄅ',
+ 'age_limit': 0,
+ 'tags': 'count:11',
+ 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
+ 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
+ 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
+ 'view_count': int,
+ 'categories': ['People & Blogs'],
+ 'like_count': int,
+ 'live_status': 'not_live',
+ 'availability': 'unlisted',
+ 'channel_follower_count': int
},
},
# url_encoded_fmt_stream_map is empty string
'track': 'Dark Walk',
'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
+ 'categories': ['Film & Animation'],
+ 'view_count': int,
+ 'live_status': 'not_live',
+ 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
+ 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
+ 'tags': 'count:13',
+ 'availability': 'public',
+ 'channel': 'IronSoulElf',
+ 'playable_in_embed': True,
+ 'like_count': int,
+ 'age_limit': 0,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
'uploader': 'The Berkman Klein Center for Internet & Society',
'license': 'Creative Commons Attribution license (reuse allowed)',
+ 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
+ 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
+ 'like_count': int,
+ 'age_limit': 0,
+ 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
+ 'channel': 'The Berkman Klein Center for Internet & Society',
+ 'availability': 'public',
+ 'view_count': int,
+ 'categories': ['Education'],
+ '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,
'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
'license': 'Creative Commons Attribution license (reuse allowed)',
+ 'playable_in_embed': True,
+ 'tags': 'count:12',
+ 'like_count': int,
+ 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
+ 'age_limit': 0,
+ 'availability': 'public',
+ 'categories': ['News & Politics'],
+ 'channel': 'Bernie Sanders',
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
+ 'view_count': int,
+ 'live_status': 'not_live',
+ 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'series': 'Mind Field',
'season_number': 1,
'episode_number': 1,
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
+ 'tags': 'count:12',
+ 'view_count': int,
+ 'availability': 'public',
+ 'age_limit': 0,
+ 'channel': 'Vsauce',
+ 'episode': 'Episode 1',
+ 'categories': ['Entertainment'],
+ 'season': 'Season 1',
+ 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
+ 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
+ 'like_count': int,
+ 'playable_in_embed': True,
+ 'live_status': 'not_live',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'album': 'it\'s too much love to know my dear',
'release_date': '20190313',
'release_year': 2019,
+ 'alt_title': 'Voyeur Girl',
+ 'view_count': int,
+ 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
+ 'playable_in_embed': True,
+ 'like_count': int,
+ 'categories': ['Music'],
+ 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
+ 'channel': 'Stephen',
+ 'availability': 'public',
+ 'creator': 'Stephen',
+ 'duration': 169,
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
+ 'age_limit': 0,
+ 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
+ 'tags': 'count:11',
+ 'live_status': 'not_live',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'upload_date': '20170613',
'uploader_id': 'ElevageOrVert',
'uploader': 'ElevageOrVert',
+ 'view_count': int,
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
+ 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
+ 'like_count': int,
+ 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
+ 'tags': [],
+ 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
+ 'availability': 'public',
+ 'age_limit': 0,
+ 'categories': ['Pets & Animals'],
+ 'duration': 7,
+ 'playable_in_embed': True,
+ 'live_status': 'not_live',
+ 'channel': 'ElevageOrVert',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'upload_date': '20130831',
'uploader_id': 'kudvenkat',
'uploader': 'kudvenkat',
+ 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
+ 'like_count': int,
+ 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
+ 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
+ 'live_status': 'not_live',
+ 'categories': ['Education'],
+ 'availability': 'public',
+ 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
+ 'tags': 'count:12',
+ 'playable_in_embed': True,
+ 'age_limit': 0,
+ 'view_count': int,
+ 'duration': 522,
+ 'channel': 'kudvenkat',
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'artist': 'The Cinematic Orchestra',
'track': 'Burn Out',
'album': 'Every Day',
- 'release_data': None,
- 'release_year': None,
+ 'like_count': int,
+ 'live_status': 'not_live',
+ 'alt_title': 'Burn Out',
+ 'duration': 614,
+ 'age_limit': 0,
+ 'view_count': int,
+ 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
+ 'creator': 'The Cinematic Orchestra',
+ 'channel': 'The Cinematic Orchestra',
+ 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
+ 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
+ 'availability': 'public',
+ 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
+ 'categories': ['Music'],
+ 'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'skip_download': True,
'ext': 'mp4',
'title': 'San Diego teen commits suicide after bullying over embarrassing video',
'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
- 'uploader': 'CBS This Morning',
+ 'uploader': 'CBS Mornings',
'uploader_id': 'CBSThisMorning',
'upload_date': '20140716',
- 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
+ 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
+ 'duration': 170,
+ 'categories': ['News & Politics'],
+ 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
+ 'view_count': int,
+ 'channel': 'CBS Mornings',
+ 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
+ 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
+ 'age_limit': 18,
+ 'availability': 'needs_auth',
+ 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
+ 'like_count': int,
+ 'live_status': 'not_live',
+ 'playable_in_embed': True,
+ 'channel_follower_count': int
}
},
{
'uploader': 'Walk around Japan',
'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
+ 'duration': 1456,
+ 'categories': ['Travel & Events'],
+ 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
+ 'view_count': int,
+ 'channel': 'Walk around Japan',
+ 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
+ 'age_limit': 0,
+ 'availability': 'public',
+ '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,
'uploader': 'colinfurze',
'uploader_id': 'colinfurze',
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
- 'description': 'md5:b5096f56af7ccd7a555c84db81738b22'
+ 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
+ 'duration': 596,
+ 'categories': ['Entertainment'],
+ 'uploader_url': 'http://www.youtube.com/user/colinfurze',
+ 'view_count': int,
+ 'channel': 'colinfurze',
+ 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
+ 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
+ 'age_limit': 0,
+ 'availability': 'public',
+ 'like_count': int,
+ 'live_status': 'not_live',
+ 'playable_in_embed': True,
+ 'channel_follower_count': int
},
'params': {
'format': '17', # 3gp format available on android
'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
'upload_date': '20140324',
'uploader': 'SciShow',
+ 'like_count': int,
+ 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
+ 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
+ 'view_count': int,
+ 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
+ 'playable_in_embed': True,
+ 'tags': 'count:12',
+ 'uploader_url': 'http://www.youtube.com/user/scishow',
+ 'availability': 'public',
+ 'channel': 'SciShow',
+ 'live_status': 'not_live',
+ 'duration': 248,
+ 'categories': ['Education'],
+ 'age_limit': 0,
+ 'channel_follower_count': int
}, 'params': {'format': 'mhtml', 'skip_download': True}
}
]
self._code_cache = {}
self._player_cache = {}
+ def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
+ lock = threading.Lock()
+
+ is_live = True
+ start_time = time.time()
+ formats = [f for f in formats if f.get('is_from_start')]
+
+ def refetch_manifest(format_id, delay):
+ nonlocal formats, start_time, is_live
+ if time.time() <= start_time + delay:
+ return
+
+ _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
+ video_details = traverse_obj(
+ prs, (..., 'videoDetails'), expected_type=dict, default=[])
+ microformats = traverse_obj(
+ prs, (..., 'microformat', 'playerMicroformatRenderer'),
+ expected_type=dict, default=[])
+ _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
+ start_time = time.time()
+
+ def mpd_feed(format_id, delay):
+ """
+ @returns (manifest_url, manifest_stream_number, is_live) or None
+ """
+ with lock:
+ refetch_manifest(format_id, delay)
+
+ f = next((f for f in formats if f['format_id'] == format_id), None)
+ if not f:
+ if not is_live:
+ self.to_screen(f'{video_id}: Video is no longer live')
+ else:
+ self.report_warning(
+ f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
+ return None
+ return f['manifest_url'], f['manifest_stream_number'], is_live
+
+ for f in formats:
+ f['protocol'] = 'http_dash_segments_generator'
+ f['fragments'] = functools.partial(
+ self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
+
+ def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
+ FETCH_SPAN, MAX_DURATION = 5, 432000
+
+ mpd_url, stream_number, is_live = None, None, True
+
+ begin_index = 0
+ download_start_time = ctx.get('start') or time.time()
+
+ lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
+ if lack_early_segments:
+ self.report_warning(bug_reports_message(
+ 'Starting download from the last 120 hours of the live stream since '
+ 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
+ lack_early_segments = True
+
+ known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
+ fragments, fragment_base_url = None, None
+
+ def _extract_sequence_from_mpd(refresh_sequence):
+ nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
+ # Obtain from MPD's maximum seq value
+ old_mpd_url = mpd_url
+ last_error = ctx.pop('last_error', None)
+ expire_fast = last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
+ mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
+ or (mpd_url, stream_number, False))
+ if not refresh_sequence:
+ if expire_fast and not is_live:
+ return False, last_seq
+ elif old_mpd_url == mpd_url:
+ return True, last_seq
+ try:
+ fmts, _ = self._extract_mpd_formats_and_subtitles(
+ mpd_url, None, note=False, errnote=False, fatal=False)
+ except ExtractorError:
+ fmts = None
+ if not fmts:
+ no_fragment_score += 1
+ return False, last_seq
+ fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
+ fragments = fmt_info['fragments']
+ fragment_base_url = fmt_info['fragment_base_url']
+ assert fragment_base_url
+
+ _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
+ return True, _last_seq
+
+ while is_live:
+ fetch_time = time.time()
+ if no_fragment_score > 30:
+ return
+ if last_segment_url:
+ # Obtain from "X-Head-Seqnum" header value from each segment
+ try:
+ urlh = self._request_webpage(
+ last_segment_url, None, note=False, errnote=False, fatal=False)
+ except ExtractorError:
+ urlh = None
+ last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
+ if last_seq is None:
+ no_fragment_score += 1
+ last_segment_url = None
+ continue
+ else:
+ should_continue, last_seq = _extract_sequence_from_mpd(True)
+ if not should_continue:
+ continue
+
+ if known_idx > last_seq:
+ last_segment_url = None
+ continue
+
+ last_seq += 1
+
+ if begin_index < 0 and known_idx < 0:
+ # skip from the start when it's negative value
+ known_idx = last_seq + begin_index
+ if lack_early_segments:
+ known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
+ try:
+ for idx in range(known_idx, last_seq):
+ # do not update sequence here or you'll get skipped some part of it
+ should_continue, _ = _extract_sequence_from_mpd(False)
+ if not should_continue:
+ known_idx = idx - 1
+ raise ExtractorError('breaking out of outer loop')
+ last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
+ yield {
+ 'url': last_segment_url,
+ }
+ if known_idx == last_seq:
+ no_fragment_score += 5
+ else:
+ no_fragment_score = 0
+ known_idx = last_seq
+ except ExtractorError:
+ continue
+
+ time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
+
def _extract_player_url(self, *ytcfgs, webpage=None):
player_url = traverse_obj(
ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
get_all=False, expected_type=compat_str)
if not player_url:
return
- if player_url.startswith('//'):
- player_url = 'https:' + player_url
- elif not re.match(r'https?://', player_url):
- player_url = compat_urlparse.urljoin(
- 'https://www.youtube.com', player_url)
- return player_url
+ return urljoin('https://www.youtube.com', player_url)
def _download_player_url(self, video_id, fatal=False):
res = self._download_webpage(
"""Turn the encrypted n field into a working signature"""
if player_url is None:
raise ExtractorError('Cannot decrypt nsig without player_url')
- if player_url.startswith('//'):
- player_url = 'https:' + player_url
- elif not re.match(r'https?://', player_url):
- player_url = compat_urlparse.urljoin(
- 'https://www.youtube.com', player_url)
+ player_url = urljoin('https://www.youtube.com', player_url)
sig_id = ('nsig_value', s)
if sig_id in self._player_cache:
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$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
+ 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 {re.escape(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)
_continuation = None
for content in contents:
comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
- expected_comment_count = parse_count(self._get_text(
- comments_header_renderer, 'countText', 'commentsCount', max_runs=1))
+ expected_comment_count = self._get_count(
+ comments_header_renderer, 'countText', 'commentsCount')
if expected_comment_count:
tracker['est_total'] = expected_comment_count
}.get(client)
if not url:
return {}
- webpage = self._download_webpage(url, video_id, fatal=False, note=f'Downloading {client} config')
+ webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
return self.extract_ytcfg(video_id, webpage) or {}
def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
])
streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
+ approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None
for fmt in streaming_formats:
if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
itags[itag] = 'https'
stream_ids.append(stream_id)
- tbr = float_or_none(
- fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
+ 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)
+ # Some formats may have much smaller duration than others (possibly damaged during encoding)
+ # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
+ is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000)
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=', '),
+ throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
'source_preference': -10 if throttled else -1,
'fps': int_or_none(fmt.get('fps')) or None,
'height': height,
'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,
+ 'preference': -10 if is_damaged else None,
}
mime_mobj = re.match(
r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
dct['container'] = dct['ext'] + '_dash'
yield dct
+ live_from_start = is_live and self.get_param('live_from_start')
skip_manifests = self._configuration_arg('skip')
- get_dash = (
- (not is_live or self._configuration_arg('include_live_dash'))
- and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True))
- get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
+ if not self.get_param('youtube_include_hls_manifest', True):
+ skip_manifests.append('hls')
+ get_dash = 'dash' not in skip_manifests and (
+ not is_live or live_from_start or self._configuration_arg('include_live_dash'))
+ get_hls = not live_from_start and 'hls' not in skip_manifests
def process_manifest_format(f, proto, itag):
if itag in itags:
if process_manifest_format(f, 'dash', f['format_id']):
f['filesize'] = int_or_none(self._search_regex(
r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
+ if live_from_start:
+ f['is_from_start'] = True
+
yield f
def _extract_storyboard(self, player_responses, duration):
spec = get_first(
player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
- if not spec:
+ base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
+ if not base_url:
return
- base_url = spec.pop()
L = len(spec) - 1
for i, args in enumerate(spec):
args = args.split('#')
} for j in range(math.ceil(fragment_count))],
}
- def _real_extract(self, url):
- url, smuggled_data = unsmuggle_url(url, {})
- video_id = self._match_id(url)
-
- base_url = self.http_scheme() + '//www.youtube.com/'
- webpage_url = base_url + 'watch?v=' + video_id
+ def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
webpage = None
if 'webpage' not in self._configuration_arg('player_skip'):
webpage = self._download_webpage(
self._get_requested_clients(url, smuggled_data),
video_id, webpage, master_ytcfg)
+ return webpage, master_ytcfg, player_responses, player_url
+
+ def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
+ live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
+ is_live = get_first(video_details, 'isLive')
+ if is_live is None:
+ is_live = get_first(live_broadcast_details, 'isLiveNow')
+
+ streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
+ formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
+
+ return live_broadcast_details, is_live, streaming_data, formats
+
+ def _real_extract(self, url):
+ url, smuggled_data = unsmuggle_url(url, {})
+ video_id = self._match_id(url)
+
+ base_url = self.http_scheme() + '//www.youtube.com/'
+ webpage_url = base_url + 'watch?v=' + video_id
+
+ webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
+
playability_statuses = traverse_obj(
player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
return self.playlist_result(
entries, video_id, video_title, video_description)
- live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
- is_live = get_first(video_details, 'isLive')
- if is_live is None:
- is_live = get_first(live_broadcast_details, 'isLiveNow')
-
- streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
- formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
+ live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
if not formats:
if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
if f.get('vcodec') != 'none':
f['stretched_ratio'] = ratio
break
-
- thumbnails = []
- thumbnail_dicts = traverse_obj(
- (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...),
- expected_type=dict, default=[])
- for thumbnail in thumbnail_dicts:
- thumbnail_url = thumbnail.get('url')
- if not thumbnail_url:
- continue
- # 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
- if 'maxresdefault' in thumbnail_url:
- thumbnail_url = thumbnail_url.split('?')[0]
- thumbnails.append({
- 'url': thumbnail_url,
- 'height': int_or_none(thumbnail.get('height')),
- 'width': int_or_none(thumbnail.get('width')),
- })
+ thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
thumbnail_url = search_meta(['og:image', 'twitter:image'])
if thumbnail_url:
thumbnails.append({
is_live = False
if is_upcoming is None and (live_content or is_live):
is_upcoming = False
- live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
- live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
- if not duration and live_endtime and live_starttime:
- duration = live_endtime - live_starttime
+ live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
+ live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
+ if not duration and live_end_time and live_start_time:
+ duration = live_end_time - live_start_time
+
+ if is_live and self.get_param('live_from_start'):
+ self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
formats.extend(self._extract_storyboard(player_responses, duration))
'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'))
else None if is_live is None or is_upcoming is None
else live_content),
'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
- 'release_timestamp': live_starttime,
+ 'release_timestamp': live_start_time,
}
pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
})
lang_subs.append({
'ext': fmt,
- 'url': update_url_query(base_url, query),
+ 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
'name': sub_name,
})
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}]}),
def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
playlist_id = title = description = channel_url = channel_name = channel_id = None
- thumbnails_list = []
tags = []
selected_tab = self._extract_selected_tab(tabs)
+ primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
renderer = try_get(
data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
if renderer:
description = renderer.get('description', '')
playlist_id = channel_id
tags = renderer.get('keywords', '').split()
- thumbnails_list = (
- try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
- or try_get(
- self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
- lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
- list)
- or [])
- thumbnails = []
- for t in thumbnails_list:
- if not isinstance(t, dict):
- continue
- thumbnail_url = url_or_none(t.get('url'))
- if not thumbnail_url:
- continue
- thumbnails.append({
- 'url': thumbnail_url,
- 'width': int_or_none(t.get('width')),
- 'height': int_or_none(t.get('height')),
- })
+ # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
+ # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
+ def _get_uncropped(url):
+ return url_or_none((url or '').split('=')[0] + '=s0')
+
+ avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
+ if avatar_thumbnails:
+ uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
+ if uncropped_avatar:
+ avatar_thumbnails.append({
+ 'url': uncropped_avatar,
+ 'id': 'avatar_uncropped',
+ 'preference': 1
+ })
+
+ channel_banners = self._extract_thumbnails(
+ data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
+ for banner in channel_banners:
+ banner['preference'] = -10
+
+ if channel_banners:
+ uncropped_banner = _get_uncropped(channel_banners[0]['url'])
+ if uncropped_banner:
+ channel_banners.append({
+ 'url': uncropped_banner,
+ 'id': 'banner_uncropped',
+ 'preference': -5
+ })
+
+ primary_thumbnails = self._extract_thumbnails(
+ primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
+
if playlist_id is None:
playlist_id = item_id
+
+ playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
+ last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
if title is None:
- title = (
- try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
- or playlist_id)
+ title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
title += format_field(selected_tab, 'title', ' - %s')
title += format_field(selected_tab, 'expandedText', ' - %s')
+
metadata = {
'playlist_id': playlist_id,
'playlist_title': title,
'uploader': channel_name,
'uploader_id': channel_id,
'uploader_url': channel_url,
- 'thumbnails': thumbnails,
+ 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
'tags': tags,
+ '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),
+ 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
}
- availability = self._extract_availability(data)
- if availability:
- metadata['availability'] = availability
if not channel_id:
metadata.update(self._extract_uploader(data))
metadata.update({
if 'webpage' not in self._configuration_arg('skip'):
webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
+ # Reject webpage data if redirected to home page without explicitly requesting
+ selected_tab = self._extract_selected_tab(traverse_obj(
+ data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[])) or {}
+ if (url != 'https://www.youtube.com/feed/recommended'
+ and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
+ and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
+ msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
+ if fatal:
+ raise ExtractorError(msg, expected=True)
+ self.report_warning(msg, only_once=True)
if not data:
if not ytcfg and self.is_authenticated:
msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
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
'playlist_mincount': 94,
'info_dict': {
'id': 'UCqj7Cz7revf5maW9g5pgNcg',
- 'title': 'Игорь Клейнер - Playlists',
+ 'title': 'Igor Kleiner - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
- 'uploader': 'Игорь Клейнер',
+ 'uploader': 'Igor Kleiner',
'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
+ 'channel': 'Igor Kleiner',
+ 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
+ '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',
'playlist_mincount': 94,
'info_dict': {
'id': 'UCqj7Cz7revf5maW9g5pgNcg',
- 'title': 'Игорь Клейнер - Playlists',
+ 'title': 'Igor Kleiner - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
- 'uploader': 'Игорь Клейнер',
+ 'uploader': 'Igor Kleiner',
+ 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
+ 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
+ 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
+ 'channel': 'Igor Kleiner',
+ 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
+ 'channel_follower_count': int
},
}, {
'note': 'playlists, series',
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
'uploader': '3Blue1Brown',
+ 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
+ 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
+ 'channel': '3Blue1Brown',
+ 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
+ 'tags': ['Mathematics'],
+ 'channel_follower_count': int
},
}, {
'note': 'playlists, singlepage',
'description': 'md5:609399d937ea957b0f53cbffb747a14c',
'uploader': 'ThirstForScience',
'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
+ 'tags': 'count:13',
+ 'channel': 'ThirstForScience',
+ 'channel_follower_count': int
}
}, {
'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
'uploader': 'Sergey M.',
'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
'title': 'youtube-dl public playlist',
+ 'description': '',
+ 'tags': [],
+ 'view_count': int,
+ 'modified_date': '20201130',
+ 'channel': 'Sergey M.',
+ 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
+ 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
},
'playlist_count': 1,
}, {
'uploader': 'Sergey M.',
'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
'title': 'youtube-dl empty playlist',
+ 'tags': [],
+ 'channel': 'Sergey M.',
+ 'description': '',
+ 'modified_date': '20160902',
+ 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
},
'playlist_count': 0,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'tags': ['bible', 'history', 'prophesy'],
+ '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,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'tags': ['bible', 'history', 'prophesy'],
+ 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'channel_follower_count': int
},
'playlist_mincount': 975,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'tags': ['bible', 'history', 'prophesy'],
+ 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_follower_count': int
},
'playlist_mincount': 199,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 17,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 18,
}, {
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
'uploader': 'lex will',
'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel': 'lex will',
+ 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ 'tags': ['bible', 'history', 'prophesy'],
+ 'channel_follower_count': int
},
'playlist_mincount': 12,
}, {
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
'uploader': '3Blue1Brown',
'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
+ 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
+ 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
+ 'tags': ['Mathematics'],
+ 'channel': '3Blue1Brown',
+ 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
+ 'channel_follower_count': int
},
}, {
'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
'uploader': 'Christiaan008',
'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
+ 'tags': [],
+ 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
+ 'view_count': int,
+ 'modified_date': '20150605',
+ 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
+ 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
+ 'channel': 'Christiaan008',
},
'playlist_count': 96,
}, {
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
'uploader': 'Cauchemar',
'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
+ 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
+ 'tags': [],
+ 'modified_date': r're:\d{8}',
+ 'channel': 'Cauchemar',
+ 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
+ 'view_count': int,
+ 'description': '',
+ 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
},
'playlist_mincount': 1123,
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'note': 'even larger playlist, 8832 videos',
'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
'uploader': 'Interstellar Movie',
'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
+ 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
+ 'tags': [],
+ 'view_count': int,
+ 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
+ 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
+ 'channel': 'Interstellar Movie',
+ 'description': '',
+ 'modified_date': r're:\d{8}',
},
'playlist_mincount': 21,
}, {
'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
'uploader': 'Phim Siêu Nhân Nhật Bản',
'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
+ 'view_count': int,
+ 'channel': 'Phim Siêu Nhân Nhật Bản',
+ 'tags': [],
+ 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
+ 'description': '',
+ 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
+ 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
+ 'modified_date': r're:\d{8}',
},
'playlist_mincount': 200,
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'note': 'Playlist with unavailable videos in page 7',
'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
'id': 'UU8l9frL61Yl5KFOl87nIm2w',
'uploader': 'BlankTV',
'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
+ 'channel': 'BlankTV',
+ 'channel_url': 'https://www.youtube.com/c/blanktv',
+ 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
+ 'view_count': int,
+ 'tags': [],
+ 'uploader_url': 'https://www.youtube.com/c/blanktv',
+ 'modified_date': r're:\d{8}',
+ 'description': '',
},
'playlist_mincount': 1000,
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
'uploader': 'Computerphile',
'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
+ 'uploader_url': 'https://www.youtube.com/user/Computerphile',
+ 'tags': [],
+ 'view_count': int,
+ 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
+ 'channel_url': 'https://www.youtube.com/user/Computerphile',
+ 'channel': 'Computerphile',
},
'playlist_mincount': 11,
}, {
'tags': list,
'view_count': int,
'like_count': int,
- 'dislike_count': int,
},
'params': {
'skip_download': True,
}, {
'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
'info_dict': {
- 'id': '3yImotZU3tw', # This will keep changing
+ 'id': 'GgL890LIznQ', # This will keep changing
'ext': 'mp4',
- 'title': compat_str,
+ 'title': str,
'uploader': 'Sky News',
'uploader_id': 'skynews',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
'upload_date': r're:\d{8}',
- 'description': compat_str,
+ 'description': str,
'categories': ['News & Politics'],
'tags': list,
'like_count': int,
- 'dislike_count': int,
+ 'release_timestamp': 1642502819,
+ 'channel': 'Sky News',
+ 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
+ 'age_limit': 0,
+ 'view_count': int,
+ 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
+ 'playable_in_embed': True,
+ '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,
},
- 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
+ 'expected_warnings': ['Ignoring subtitle tracks found in '],
}, {
'url': 'https://www.youtube.com/user/TheYoungTurks/live',
'info_dict': {
'categories': ['News & Politics'],
'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
'like_count': int,
- 'dislike_count': int,
},
'params': {
'skip_download': True,
'info_dict': {
'id': 'cctv9',
'title': '#cctv9',
+ 'tags': [],
},
'playlist_mincount': 350,
}, {
'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'title': 'NCS Releases',
+ 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
+ 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
+ 'modified_date': r're:\d{8}',
+ 'view_count': int,
+ 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
+ 'tags': [],
+ 'channel': 'NoCopyrightSounds',
},
'playlist_mincount': 166,
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'note': 'Topic, should redirect to playlist?list=UU...',
'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'title': 'Uploads from Royalty Free Music - Topic',
'uploader': 'Royalty Free Music - Topic',
+ 'tags': [],
+ 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'channel': 'Royalty Free Music - Topic',
+ 'view_count': int,
+ 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'modified_date': r're:\d{8}',
+ 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'description': '',
},
'expected_warnings': [
- 'A channel/user page was given',
'The URL does not have a videos tab',
+ r'[Uu]navailable videos (are|will be) hidden',
],
'playlist_mincount': 101,
}, {
'info_dict': {
'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
+ 'tags': [],
},
'expected_warnings': [
- 'A channel/user page was given',
- 'The URL does not have a videos tab',
- 'Falling back to channel URL',
+ 'the playlist redirect gave error',
],
'playlist_mincount': 9,
}, {
'info_dict': {
'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
+ 'tags': [],
+ 'view_count': int,
+ 'description': '',
+ 'availability': 'unlisted',
+ 'modified_date': r're:\d{8}',
},
'playlist_count': 50,
}, {
'uploader': 'colethedj',
'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
'title': 'yt-dlp unlisted playlist test',
- 'availability': 'unlisted'
+ 'availability': 'unlisted',
+ 'tags': [],
+ 'modified_date': '20211208',
+ 'channel': 'colethedj',
+ 'view_count': int,
+ 'description': '',
+ 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
+ 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
+ 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
},
'playlist_count': 1,
}, {
'info_dict': {
'id': 'recommended',
'title': 'recommended',
+ 'tags': [],
},
'playlist_mincount': 50,
'params': {
'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
'uploader': 'Cody\'sLab',
'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
+ 'channel': 'Cody\'sLab',
+ 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
+ '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': {
'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
'title': 'Uploads from Royalty Free Music - Topic',
'uploader': 'Royalty Free Music - Topic',
+ 'modified_date': r're:\d{8}',
+ 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'description': '',
+ 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
+ 'tags': [],
+ 'channel': 'Royalty Free Music - Topic',
+ 'view_count': int,
+ 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
},
'expected_warnings': [
- 'A channel/user page was given',
- 'The URL does not have a videos tab',
+ 'does not have a videos tab',
+ r'[Uu]navailable videos (are|will be) hidden',
],
'playlist_mincount': 101,
'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})(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$')
+ _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
- 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'))
elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
pre = f'https://www.youtube.com/channel/{item_id}'
+ original_tab_name = tab
if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
# Home URLs should redirect to /videos/
redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
if tabs:
selected_tab = self._extract_selected_tab(tabs)
- tab_name = selected_tab.get('title', '')
+ selected_tab_name = selected_tab.get('title', '').lower()
+ if selected_tab_name == 'home':
+ selected_tab_name = 'featured'
+ requested_tab_name = mobj['tab'][1:]
if 'no-youtube-channel-redirect' not in compat_opts:
- if mobj['tab'] == '/live':
+ if requested_tab_name == 'live':
# Live tab should have redirected to the video
raise ExtractorError('The channel is not currently live', expected=True)
- if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
- redirect_warning = f'The URL does not have a {mobj["tab"][1:]} tab'
- if not mobj['not_channel'] and item_id[:2] == 'UC':
- # Topic channels don't have /videos. Use the equivalent playlist instead
- pl_id = f'UU{item_id[2:]}'
- pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
- try:
- data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True)
- except ExtractorError:
- redirect_warning += ' and the playlist redirect gave error'
- else:
- item_id, url, tab_name = pl_id, pl_url, mobj['tab'][1:]
- redirect_warning += f'. Redirecting to playlist {pl_id} instead'
- if tab_name.lower() != mobj['tab'][1:]:
- redirect_warning += f'. {tab_name} tab is being downloaded instead'
+ if requested_tab_name not in ('', selected_tab_name):
+ redirect_warning = f'The channel does not have a {requested_tab_name} tab'
+ if not original_tab_name:
+ if item_id[:2] == 'UC':
+ # Topic channels don't have /videos. Use the equivalent playlist instead
+ pl_id = f'UU{item_id[2:]}'
+ pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
+ try:
+ data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
+ except ExtractorError:
+ redirect_warning += ' and the playlist redirect gave error'
+ else:
+ item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
+ redirect_warning += f'. Redirecting to playlist {pl_id} instead'
+ if selected_tab_name and selected_tab_name != requested_tab_name:
+ redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
+ else:
+ raise ExtractorError(redirect_warning, expected=True)
if redirect_warning:
- self.report_warning(redirect_warning)
+ self.to_screen(redirect_warning)
self.write_debug(f'Final URL: {url}')
# YouTube sometimes provides a button to reload playlist with unavailable videos.
'info_dict': {
'title': '[OLD]Team Fortress 2 (Class-based LP)',
'id': 'PLBB231211A4F62143',
- 'uploader': 'Wickydoo',
+ 'uploader': 'Wickman',
'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
+ 'view_count': int,
+ 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
+ 'modified_date': r're:\d{8}',
+ 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
+ 'channel': 'Wickman',
+ 'tags': [],
+ 'channel_url': 'https://www.youtube.com/user/Wickydoo',
},
'playlist_mincount': 29,
}, {
'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
'uploader': 'milan',
'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
- }
+ 'description': '',
+ 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
+ 'tags': [],
+ 'modified_date': '20140919',
+ 'view_count': int,
+ 'channel': 'milan',
+ 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
+ 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
+ },
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
'playlist_mincount': 654,
'uploader': 'LBK',
'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
'description': 'md5:da521864744d60a198e3a88af4db0d9d',
- }
+ 'channel': 'LBK',
+ 'view_count': int,
+ 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
+ 'tags': [],
+ 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
+ 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
+ 'modified_date': r're:\d{8}',
+ },
+ 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
'categories': ['Nonprofits & Activism'],
'tags': list,
'like_count': int,
- 'dislike_count': int,
+ 'age_limit': 0,
+ 'playable_in_embed': True,
+ 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
+ 'channel': 'Backus-Page House Museum',
+ 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
+ 'live_status': 'not_live',
+ 'view_count': int,
+ 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
+ 'availability': 'public',
+ 'duration': 59,
},
'params': {
'noplaylist': True,
}), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
+class YoutubeLivestreamEmbedIE(InfoExtractor):
+ IE_DESC = 'YouTube livestream embeds'
+ _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
+ _TESTS = [{
+ 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ channel_id = self._match_id(url)
+ return self.url_result(
+ f'https://www.youtube.com/channel/{channel_id}/live',
+ ie=YoutubeTabIE.ie_key(), video_id=channel_id)
+
+
class YoutubeYtUserIE(InfoExtractor):
IE_DESC = 'YouTube user videos; "ytuser:" prefix'
+ IE_NAME = 'youtube:user'
_VALID_URL = r'ytuser:(?P<id>.+)'
_TESTS = [{
'url': 'ytuser:phihag',
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