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 (
smuggle_url,
str_or_none,
str_to_int,
+ strftime_or_none,
traverse_obj,
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
- },
+ }
}
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',
consent_id = random.randint(100, 999)
self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
+ def _initialize_pref(self):
+ cookies = self._get_cookies('https://www.youtube.com/')
+ pref_cookie = cookies.get('PREF')
+ pref = {}
+ if pref_cookie:
+ try:
+ 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'})
+ self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
+
def _real_initialize(self):
+ self._initialize_pref()
self._initialize_consent()
self._login()
return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
def _extract_context(self, ytcfg=None, default_client='web'):
- _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
- context = _get_context(ytcfg)
- if context:
- return context
-
- context = _get_context(self._get_default_ytcfg(default_client))
- if not ytcfg:
- return context
-
- # Recreate the client context (required)
- context['client'].update({
- 'clientVersion': self._extract_client_version(ytcfg, default_client),
- 'clientName': self._extract_client_name(ytcfg, default_client),
- })
- visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
- if visitor_data:
- context['client']['visitorData'] = visitor_data
+ 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'
return context
_SAPISID = None
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)', 'updated today'
+ """
+ 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')))
+ except ValueError:
+ return None
+
+ def _extract_time_text(self, renderer, *path_list):
+ text = self._get_text(renderer, *path_list) or ''
+ dt = self.extract_relative_time(text)
+ 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
+
def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
default_client='web'):
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(
+ renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
+ timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
+ scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
+ 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',
'duration': duration,
'view_count': view_count,
'uploader': uploader,
+ 'channel_id': channel_id,
+ 'thumbnails': thumbnails,
+ 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
+ '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
+ else None),
+ 'release_timestamp': scheduled_timestamp,
+ 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' 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',
'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,
},
'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',
},
'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,
},
},
{
'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,
},
},
{
'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',
},
},
{
'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!',
},
},
{
'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',
},
'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',
},
'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',
},
},
# 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,
},
'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,
},
'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',
},
'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',
},
'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',
},
'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',
},
'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',
},
'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,
},
'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,
}
},
{
'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,
},
'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,
},
'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,
}, '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'),
(r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
regex), webpage, name, default='{}'), video_id, fatal=False)
- @staticmethod
- def parse_time_text(time_text):
- """
- Parse the comment time text
- time_text is in the format 'X units ago (edited)'
- """
- time_text_split = time_text.split(' ')
- if len(time_text_split) >= 3:
- try:
- return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
- except ValueError:
- return None
-
def _extract_comment(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
if not comment_id:
text = self._get_text(comment_renderer, 'contentText')
# note: timestamp is an estimate calculated from the current time and time_text
- time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
- time_text_dt = self.parse_time_text(time_text)
- if isinstance(time_text_dt, datetime.datetime):
- timestamp = calendar.timegm(time_text_dt.timetuple())
+ timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
author = self._get_text(comment_renderer, 'authorText')
author_id = try_get(comment_renderer,
lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
_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
yield from self._comment_entries(renderer, ytcfg, video_id)
max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
- # Force English regardless of account setting to prevent parsing issues
- # See: https://github.com/yt-dlp/yt-dlp/issues/532
- ytcfg = copy.deepcopy(ytcfg)
- traverse_obj(
- ytcfg, ('INNERTUBE_CONTEXT', 'client'), expected_type=dict, default={})['hl'] = 'en'
return itertools.islice(_real_comment_extract(contents), 0, max_comments)
@staticmethod
}.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):
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))
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)
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')),
- })
+ thumbnails = (
+ self._extract_thumbnails(renderer, 'avatar')
+ or 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_url': channel_url,
'thumbnails': thumbnails,
'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)
}
- availability = self._extract_availability(data)
- if availability:
- metadata['availability'] = availability
if not channel_id:
metadata.update(self._extract_uploader(data))
metadata.update({
'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',
},
}, {
'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',
},
}, {
'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'],
},
}, {
'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',
}
}, {
'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',
},
'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',
},
'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',
},
'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'],
},
'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'],
},
'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'],
},
'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',
},
}, {
'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': 'zpsbVPFwsqk', # 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': 1640164857,
+ 'channel': 'Sky News',
+ 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
+ 'age_limit': 0,
+ 'view_count': int,
+ 'thumbnail': 'https://i.ytimg.com/vi/zpsbVPFwsqk/maxresdefault_live.jpg',
+ 'playable_in_embed': True,
+ 'release_date': '20211222',
+ 'availability': 'public',
+ 'live_status': 'is_live',
+ 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
},
'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,
}, {
'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',
},
'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': {
'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',
projects / yt-dlp.git / blobdiff