from ..swfinterp import SWFInterpreter
from ..compat import (
compat_chr,
+ compat_HTTPError,
+ compat_kwargs,
compat_parse_qs,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_str,
)
from ..utils import (
+ bool_or_none,
clean_html,
error_to_compat_str,
+ extract_attributes,
ExtractorError,
float_or_none,
get_element_by_attribute,
int_or_none,
mimetype2ext,
orderedSet,
+ parse_codecs,
parse_duration,
remove_quotes,
remove_start,
- sanitized_Request,
smuggle_url,
+ str_or_none,
str_to_int,
+ try_get,
unescapeHTML,
unified_strdate,
unsmuggle_url,
uppercase_escape,
+ url_or_none,
urlencode_postdata,
- ISO3166Utils,
)
"""Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
+
+ _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
+ _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
+ _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
+
_NETRC_MACHINE = 'youtube'
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
+ _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
+
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&hl=en',
If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
"""
- (username, password) = self._get_login_info()
+ username, password = self._get_login_info()
# No authentication to be performed
if username is None:
- if self._LOGIN_REQUIRED:
+ if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return True
if login_page is False:
return
- galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
- login_page, 'Login GALX parameter')
-
- # Log in
- login_form_strs = {
- 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
- 'Email': username,
- 'GALX': galx,
- 'Passwd': password,
-
- 'PersistentCookie': 'yes',
- '_utf8': '霱',
- 'bgresponse': 'js_disabled',
- 'checkConnection': '',
- 'checkedDomains': 'youtube',
- 'dnConn': '',
- 'pstMsg': '0',
- 'rmShown': '1',
- 'secTok': '',
- 'signIn': 'Sign in',
- 'timeStmp': '',
- 'service': 'youtube',
- 'uilel': '3',
- 'hl': 'en_US',
- }
-
- login_data = urlencode_postdata(login_form_strs)
+ login_form = self._hidden_inputs(login_page)
+
+ def req(url, f_req, note, errnote):
+ data = login_form.copy()
+ data.update({
+ 'pstMsg': 1,
+ 'checkConnection': 'youtube',
+ 'checkedDomains': 'youtube',
+ 'hl': 'en',
+ 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
+ 'f.req': json.dumps(f_req),
+ 'flowName': 'GlifWebSignIn',
+ 'flowEntry': 'ServiceLogin',
+ # TODO: reverse actual botguard identifier generation algo
+ 'bgRequest': '["identifier",""]',
+ })
+ return self._download_json(
+ url, None, note=note, errnote=errnote,
+ transform_source=lambda s: re.sub(r'^[^[]*', '', s),
+ fatal=False,
+ data=urlencode_postdata(data), headers={
+ 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
+ 'Google-Accounts-XSRF': 1,
+ })
- req = sanitized_Request(self._LOGIN_URL, login_data)
- login_results = self._download_webpage(
- req, None,
- note='Logging in', errnote='unable to log in', fatal=False)
- if login_results is False:
+ def warn(message):
+ self._downloader.report_warning(message)
+
+ lookup_req = [
+ username,
+ None, [], None, 'US', None, None, 2, False, True,
+ [
+ None, None,
+ [2, 1, None, 1,
+ 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
+ None, [], 4],
+ 1, [None, None, []], None, None, None, True
+ ],
+ username,
+ ]
+
+ lookup_results = req(
+ self._LOOKUP_URL, lookup_req,
+ 'Looking up account info', 'Unable to look up account info')
+
+ if lookup_results is False:
return False
- error_msg = self._html_search_regex(
- r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
- login_results, 'error message', default=None)
- if error_msg:
- raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
-
- if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
- raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
-
- # Two-Factor
- # TODO add SMS and phone call support - these require making a request and then prompting the user
+ user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
+ if not user_hash:
+ warn('Unable to extract user hash')
+ return False
- if re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None:
- tfa_code = self._get_tfa_info('2-step verification code')
+ challenge_req = [
+ user_hash,
+ None, 1, None, [1, None, None, None, [password, None, True]],
+ [
+ None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
+ 1, [None, None, []], None, None, None, True
+ ]]
- if not tfa_code:
- self._downloader.report_warning(
- 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
- '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
- return False
+ challenge_results = req(
+ self._CHALLENGE_URL, challenge_req,
+ 'Logging in', 'Unable to log in')
- tfa_code = remove_start(tfa_code, 'G-')
+ if challenge_results is False:
+ return
- tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
+ login_res = try_get(challenge_results, lambda x: x[0][5], list)
+ if login_res:
+ login_msg = try_get(login_res, lambda x: x[5], compat_str)
+ warn(
+ 'Unable to login: %s' % 'Invalid password'
+ if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
+ return False
- tfa_form_strs.update({
- 'Pin': tfa_code,
- 'TrustDevice': 'on',
- })
+ res = try_get(challenge_results, lambda x: x[0][-1], list)
+ if not res:
+ warn('Unable to extract result entry')
+ return False
- tfa_data = urlencode_postdata(tfa_form_strs)
+ login_challenge = try_get(res, lambda x: x[0][0], list)
+ if login_challenge:
+ challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
+ if challenge_str == 'TWO_STEP_VERIFICATION':
+ # SEND_SUCCESS - TFA code has been successfully sent to phone
+ # QUOTA_EXCEEDED - reached the limit of TFA codes
+ status = try_get(login_challenge, lambda x: x[5], compat_str)
+ if status == 'QUOTA_EXCEEDED':
+ warn('Exceeded the limit of TFA codes, try later')
+ return False
+
+ tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
+ if not tl:
+ warn('Unable to extract TL')
+ return False
+
+ tfa_code = self._get_tfa_info('2-step verification code')
+
+ if not tfa_code:
+ warn(
+ 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
+ '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
+ return False
+
+ tfa_code = remove_start(tfa_code, 'G-')
+
+ tfa_req = [
+ user_hash, None, 2, None,
+ [
+ 9, None, None, None, None, None, None, None,
+ [None, tfa_code, True, 2]
+ ]]
+
+ tfa_results = req(
+ self._TFA_URL.format(tl), tfa_req,
+ 'Submitting TFA code', 'Unable to submit TFA code')
+
+ if tfa_results is False:
+ return False
+
+ tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
+ if tfa_res:
+ tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
+ warn(
+ 'Unable to finish TFA: %s' % 'Invalid TFA code'
+ if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
+ return False
+
+ check_cookie_url = try_get(
+ tfa_results, lambda x: x[0][-1][2], compat_str)
+ else:
+ CHALLENGES = {
+ 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
+ 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
+ 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
+ }
+ challenge = CHALLENGES.get(
+ challenge_str,
+ '%s returned error %s.' % (self.IE_NAME, challenge_str))
+ warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
+ return False
+ else:
+ check_cookie_url = try_get(res, lambda x: x[2], compat_str)
- tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
- tfa_results = self._download_webpage(
- tfa_req, None,
- note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
+ if not check_cookie_url:
+ warn('Unable to extract CheckCookie URL')
+ return False
- if tfa_results is False:
- return False
+ check_cookie_results = self._download_webpage(
+ check_cookie_url, None, 'Checking cookie', fatal=False)
- if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None:
- self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
- return False
- if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
- self._downloader.report_warning('unable to log in - did the page structure change?')
- return False
- if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
- self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
- return False
+ if check_cookie_results is False:
+ return False
- if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
- self._downloader.report_warning('unable to log in: bad username or password')
+ if 'https://myaccount.google.com/' not in check_cookie_results:
+ warn('Unable to log in')
return False
+
return True
+ def _download_webpage_handle(self, *args, **kwargs):
+ query = kwargs.get('query', {}).copy()
+ query['disable_polymer'] = 'true'
+ kwargs['query'] = query
+ return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
+ *args, **compat_kwargs(kwargs))
+
def _real_initialize(self):
if self._downloader is None:
return
if not mobj:
break
- more = self._download_json(
- 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
- 'Downloading page #%s' % page_num,
- transform_source=uppercase_escape)
+ count = 0
+ retries = 3
+ while count <= retries:
+ try:
+ # Downloading page may result in intermittent 5xx HTTP error
+ # that is usually worked around with a retry
+ more = self._download_json(
+ 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
+ 'Downloading page #%s%s'
+ % (page_num, ' (retry #%d)' % count if count else ''),
+ transform_source=uppercase_escape)
+ break
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
+ count += 1
+ if count <= retries:
+ continue
+ raise
+
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
for video_id, video_title in self.extract_videos_from_page(content):
yield self.url_result(video_id, 'Youtube', video_id, video_title)
- def extract_videos_from_page(self, page):
- ids_in_page = []
- titles_in_page = []
- for mobj in re.finditer(self._VIDEO_RE, page):
+ def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page):
+ for mobj in re.finditer(video_re, page):
# The link with index 0 is not the first video of the playlist (not sure if still actual)
if 'index' in mobj.groupdict() and mobj.group('id') == '0':
continue
video_id = mobj.group('id')
- video_title = unescapeHTML(mobj.group('title'))
+ video_title = unescapeHTML(
+ mobj.group('title')) if 'title' in mobj.groupdict() else None
if video_title:
video_title = video_title.strip()
+ if video_title == '► Play all':
+ video_title = None
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
+
+ def extract_videos_from_page(self, page):
+ ids_in_page = []
+ titles_in_page = []
+ self.extract_videos_from_page_impl(
+ self._VIDEO_RE, page, ids_in_page, titles_in_page)
return zip(ids_in_page, titles_in_page)
_VALID_URL = r"""(?x)^
(
(?:https?://|//) # http(s):// or protocol-independent URL
- (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
+ (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
(?:www\.)?pwnyoutube\.com/|
+ (?:www\.)?hooktube\.com/|
(?:www\.)?yourepeat\.com/|
tube\.majestyc\.net/|
+ # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
+ (?:(?:www|dev)\.)?invidio\.us/|
+ (?:(?:www|no)\.)?invidiou\.sh/|
+ (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
+ (?:www\.)?invidious\.kabi\.tk/|
+ (?:www\.)?invidious\.13ad\.de/|
+ (?:www\.)?invidious\.mastodon\.host/|
+ (?:www\.)?invidious\.nixnet\.xyz/|
+ (?:www\.)?invidious\.drycat\.fr/|
+ (?:www\.)?tube\.poal\.co/|
+ (?:www\.)?vid\.wxzm\.sx/|
+ (?:www\.)?yt\.elukerio\.org/|
+ (?:www\.)?yt\.lelux\.fi/|
+ (?:www\.)?kgg2m7yk5aybusll\.onion/|
+ (?:www\.)?qklhadlycap4cnod\.onion/|
+ (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
+ (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
+ (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
+ (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
+ (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
- (?!.*?&list=) # combined list/video URLs are handled by the playlist IE
+ (?!.*?\blist=
+ (?:
+ %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
+ WL # WL are handled by the watch later IE
+ )
+ )
(?(1).+)? # if we found the ID, everything can follow
- $"""
+ $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_formats = {
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
'151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
# DASH mp4 video
- '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
- '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
- '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
- '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
- '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
+ '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
+ '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
+ '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
+ '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
+ '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
# Dash mp4 audio
- '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
- '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
- '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
- '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
- '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
+ '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
+ '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
+ '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
+ '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
+ '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
+ '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
+ '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
# Dash webm
- '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
- '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
- '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
+ '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+ '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
+ '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
# itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
- '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
- '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
- '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
- '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
- '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
+ '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+ '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+ '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+ '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+ '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
# Dash webm audio
- '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
- '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
+ '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
+ '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
# Dash webm audio with opus inside
- '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
- '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
- '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
+ '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
+ '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
+ '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
+
+ # av01 video only formats sometimes served with "unknown" codecs
+ '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+ '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+ '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+ '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
}
- _SUBTITLE_FORMATS = ('ttml', 'vtt')
+ _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
+
+ _GEO_BYPASS = False
IE_NAME = 'youtube'
_TESTS = [
{
- 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
+ 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
'info_dict': {
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
'uploader': 'Philipp Hagemeister',
'uploader_id': 'phihag',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
+ 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
+ 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
'upload_date': '20121002',
- 'license': 'Standard YouTube License',
'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 .',
'categories': ['Science & Technology'],
'tags': ['youtube-dl'],
+ 'duration': 10,
+ 'view_count': int,
'like_count': int,
'dislike_count': int,
'start_time': 1,
}
},
{
- 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY',
+ 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
'note': 'Test generic use_cipher_signature video (#897)',
'info_dict': {
'id': 'UxxajLWwzqY',
'upload_date': '20120506',
'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
'alt_title': 'I Love It (feat. Charli XCX)',
- 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
+ 'description': 'md5:19a2f98d9032b9311e686ed039564f63',
'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
'iconic ep', 'iconic', 'love', 'it'],
+ 'duration': 180,
'uploader': 'Icona Pop',
'uploader_id': 'IconaPop',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IconaPop',
- 'license': 'Standard YouTube License',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
'creator': 'Icona Pop',
+ 'track': 'I Love It (feat. Charli XCX)',
+ 'artist': 'Icona Pop',
}
},
{
'id': '07FYdnEawAQ',
'ext': 'mp4',
'upload_date': '20130703',
- 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
+ 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
'alt_title': 'Tunnel Vision',
- 'description': 'md5:64249768eec3bc4276236606ea996373',
+ 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
+ 'duration': 419,
'uploader': 'justintimberlakeVEVO',
'uploader_id': 'justintimberlakeVEVO',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
- 'license': 'Standard YouTube License',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
'creator': 'Justin Timberlake',
+ 'track': 'Tunnel Vision',
+ 'artist': 'Justin Timberlake',
'age_limit': 18,
}
},
'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
'uploader': 'SET India',
'uploader_id': 'setindia',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/setindia',
- 'license': 'Standard YouTube License',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
'age_limit': 18,
}
},
{
- 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
+ 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
'note': 'Use the first video ID in the URL',
'info_dict': {
'id': 'BaW_jenozKc',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
'uploader': 'Philipp Hagemeister',
'uploader_id': 'phihag',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
'upload_date': '20121002',
- 'license': 'Standard YouTube License',
'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 .',
'categories': ['Science & Technology'],
'tags': ['youtube-dl'],
+ 'duration': 10,
+ 'view_count': int,
'like_count': int,
'dislike_count': int,
},
},
},
{
- 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
+ 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
'note': '256k DASH audio (format 141) via DASH manifest',
'info_dict': {
'id': 'a9LDPn-MO4I',
'ext': 'm4a',
'upload_date': '20121002',
'uploader_id': '8KVIDEO',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
'description': '',
'uploader': '8KVIDEO',
- 'license': 'Standard YouTube License',
'title': 'UHDTV TEST 8K VIDEO.mp4'
},
'params': {
'info_dict': {
'id': 'IB3lcPjvWLA',
'ext': 'm4a',
- 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
- 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
+ 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
+ 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
+ 'duration': 244,
'uploader': 'AfrojackVEVO',
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
- 'license': 'Standard YouTube License',
},
'params': {
'youtube_include_dash_manifest': True,
'id': 'nfWlot6h_JM',
'ext': 'm4a',
'title': 'Taylor Swift - Shake It Off',
- 'alt_title': 'Shake It Off',
- 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
+ 'description': 'md5:307195cd21ff7fa352270fe884570ef0',
+ 'duration': 242,
'uploader': 'TaylorSwiftVEVO',
'uploader_id': 'TaylorSwiftVEVO',
'upload_date': '20140818',
- 'license': 'Standard YouTube License',
- 'creator': 'Taylor Swift',
},
'params': {
'youtube_include_dash_manifest': True,
'info_dict': {
'id': 'T4XJQO3qol8',
'ext': 'mp4',
+ 'duration': 219,
'upload_date': '20100909',
- 'uploader': 'The Amazing Atheist',
+ 'uploader': 'Amazing Atheist',
'uploader_id': 'TheAmazingAtheist',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
- 'license': 'Standard YouTube License',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
'title': 'Burning Everyone\'s Koran',
'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
}
},
# Normal age-gate video (No vevo, embed allowed)
{
- 'url': 'http://youtube.com/watch?v=HtVdAasjOgU',
+ 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
'info_dict': {
'id': 'HtVdAasjOgU',
'ext': 'mp4',
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
- 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
+ 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
+ 'duration': 142,
'uploader': 'The Witcher',
'uploader_id': 'WitcherGame',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
'upload_date': '20140605',
- 'license': 'Standard YouTube License',
'age_limit': 18,
},
},
# Age-gate video with encrypted signature
{
- 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
+ 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
'info_dict': {
'id': '6kLq3WMV1nU',
'ext': 'mp4',
'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
+ 'duration': 246,
'uploader': 'LloydVEVO',
'uploader_id': 'LloydVEVO',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
'upload_date': '20110629',
- 'license': 'Standard YouTube License',
'age_limit': 18,
},
},
- # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
+ # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
+ # YouTube Red ad is not captured for creator
{
'url': '__2ABJjxzNo',
'info_dict': {
'id': '__2ABJjxzNo',
'ext': 'mp4',
+ 'duration': 266,
'upload_date': '20100430',
'uploader_id': 'deadmau5',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/deadmau5',
- 'creator': 'deadmau5',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
+ 'creator': 'Dada Life, deadmau5',
'description': 'md5:12c56784b8032162bb936a5f76d55360',
'uploader': 'deadmau5',
- 'license': 'Standard YouTube License',
'title': 'Deadmau5 - Some Chords (HD)',
- 'alt_title': 'Some Chords',
+ 'alt_title': 'This Machine Kills Some Chords',
},
'expected_warnings': [
'DASH manifest missing',
]
},
- # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
+ # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
{
'url': 'lqQg6PlCWgI',
'info_dict': {
'id': 'lqQg6PlCWgI',
'ext': 'mp4',
+ 'duration': 6085,
'upload_date': '20150827',
'uploader_id': 'olympic',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/olympic',
- 'license': 'Standard YouTube License',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
'uploader': 'Olympic',
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
'id': '_b-2C3KPAM0',
'ext': 'mp4',
'stretched_ratio': 16 / 9.,
+ 'duration': 85,
'upload_date': '20110310',
'uploader_id': 'AllenMeow',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
'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': '孫艾倫',
- 'license': 'Standard YouTube License',
+ 'uploader': '孫ᄋᄅ',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
},
},
},
'skip': 'This live event has ended.',
},
- # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
+ # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
{
'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
'info_dict': {
'id': 'FIl7x6_3R5Y',
- 'ext': 'mp4',
+ 'ext': 'webm',
'title': 'md5:7b81415841e02ecd4313668cde88737a',
'description': 'md5:116377fd2963b81ec4ce64b542173306',
+ 'duration': 220,
'upload_date': '20150625',
'uploader_id': 'dorappi2000',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
'uploader': 'dorappi2000',
- 'license': 'Standard YouTube License',
- 'formats': 'mincount:32',
+ 'formats': 'mincount:31',
},
+ 'skip': 'not actual anymore',
},
# DASH manifest with segment_list
{
'uploader': 'Airtek',
'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
- 'license': 'Standard YouTube License',
'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
},
'params': {
'ext': 'mp4',
'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
'description': 'md5:dc7872fb300e143831327f1bae3af010',
+ 'duration': 7335,
'upload_date': '20150721',
'uploader': 'Beer Games Beer',
'uploader_id': 'beergamesbeer',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
'license': 'Standard YouTube License',
},
}, {
'ext': 'mp4',
'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
'description': 'md5:dc7872fb300e143831327f1bae3af010',
+ 'duration': 7337,
'upload_date': '20150721',
'uploader': 'Beer Games Beer',
'uploader_id': 'beergamesbeer',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
'license': 'Standard YouTube License',
},
}, {
'ext': 'mp4',
'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
'description': 'md5:dc7872fb300e143831327f1bae3af010',
+ 'duration': 7337,
'upload_date': '20150721',
'uploader': 'Beer Games Beer',
'uploader_id': 'beergamesbeer',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
'license': 'Standard YouTube License',
},
}, {
'ext': 'mp4',
'title': 'teamPGP: Rocket League Noob Stream (zim)',
'description': 'md5:dc7872fb300e143831327f1bae3af010',
+ 'duration': 7334,
'upload_date': '20150721',
'uploader': 'Beer Games Beer',
'uploader_id': 'beergamesbeer',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
'license': 'Standard YouTube License',
},
}],
'params': {
'skip_download': True,
},
+ 'skip': 'This video is not available.',
},
{
- # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
+ # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
'info_dict': {
'id': 'gVfLd0zydlo',
'skip': 'Not multifeed anymore',
},
{
- 'url': 'http://vid.plus/FlRa-iH7PGw',
+ 'url': 'https://vid.plus/FlRa-iH7PGw',
'only_matching': True,
},
{
- 'url': 'http://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
+ 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
'only_matching': True,
},
{
- # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
+ # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
# Also tests cut-off URL expansion in video description (see
- # https://github.com/rg3/youtube-dl/issues/1892,
- # https://github.com/rg3/youtube-dl/issues/8164)
+ # https://github.com/ytdl-org/youtube-dl/issues/1892,
+ # https://github.com/ytdl-org/youtube-dl/issues/8164)
'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
'info_dict': {
'id': 'lsguqyKfVQg',
'ext': 'mp4',
'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
- 'alt_title': 'Dark Walk',
+ 'alt_title': 'Dark Walk - Position Music',
'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
+ 'duration': 133,
'upload_date': '20151119',
'uploader_id': 'IronSoulElf',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
'uploader': 'IronSoulElf',
- 'license': 'Standard YouTube License',
- 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
+ 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
+ 'track': 'Dark Walk - Position Music',
+ 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
+ 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
},
'params': {
'skip_download': True,
},
},
{
- # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
+ # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
'only_matching': True,
},
'ext': 'mp4',
'title': 'md5:e41008789470fc2533a3252216f1c1d1',
'description': 'md5:a677553cf0840649b731a3024aeff4cc',
+ 'duration': 721,
'upload_date': '20150127',
'uploader_id': 'BerkmanCenter',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
- 'uploader': 'BerkmanCenter',
+ '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)',
},
'params': {
'ext': 'mp4',
'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
'description': 'md5:dda0d780d5a6e120758d1711d062a867',
+ 'duration': 4060,
'upload_date': '20151119',
- 'uploader': 'Bernie 2016',
+ 'uploader': 'Bernie Sanders',
'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
'license': 'Creative Commons Attribution license (reuse allowed)',
},
'params': {
{
'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
'only_matching': True,
- }
+ },
+ {
+ # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
+ 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
+ 'only_matching': True,
+ },
+ {
+ # Rental video preview
+ 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
+ 'info_dict': {
+ 'id': 'uGpuVWrhIzE',
+ 'ext': 'mp4',
+ 'title': 'Piku - Trailer',
+ 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
+ 'upload_date': '20150811',
+ 'uploader': 'FlixMatrix',
+ 'uploader_id': 'FlixMatrixKaravan',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
+ 'license': 'Standard YouTube License',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'skip': 'This video is not available.',
+ },
+ {
+ # YouTube Red video with episode data
+ 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
+ 'info_dict': {
+ 'id': 'iqKdEhx-dD4',
+ 'ext': 'mp4',
+ 'title': 'Isolation - Mind Field (Ep 1)',
+ 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
+ 'duration': 2085,
+ 'upload_date': '20170118',
+ 'uploader': 'Vsauce',
+ 'uploader_id': 'Vsauce',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
+ 'series': 'Mind Field',
+ 'season_number': 1,
+ 'episode_number': 1,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': [
+ 'Skipping DASH manifest',
+ ],
+ },
+ {
+ # The following content has been identified by the YouTube community
+ # as inappropriate or offensive to some audiences.
+ 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
+ 'info_dict': {
+ 'id': '6SJNVb0GnPI',
+ 'ext': 'mp4',
+ 'title': 'Race Differences in Intelligence',
+ 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
+ 'duration': 965,
+ 'upload_date': '20140124',
+ 'uploader': 'New Century Foundation',
+ 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # itag 212
+ 'url': '1t24XAntNCY',
+ 'only_matching': True,
+ },
+ {
+ # geo restricted to JP
+ 'url': 'sJL6WA-aGkQ',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
+ 'only_matching': True,
+ },
+ {
+ # DRM protected
+ 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
+ 'only_matching': True,
+ },
+ {
+ # Video with unsupported adaptive stream type formats
+ 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
+ 'info_dict': {
+ 'id': 'Z4Vy8R84T1U',
+ 'ext': 'mp4',
+ 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
+ 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+ 'duration': 433,
+ 'upload_date': '20130923',
+ 'uploader': 'Amelia Putri Harwita',
+ 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
+ 'formats': 'maxcount:10',
+ },
+ 'params': {
+ 'skip_download': True,
+ 'youtube_include_dash_manifest': False,
+ },
+ 'skip': 'not actual anymore',
+ },
+ {
+ # Youtube Music Auto-generated description
+ 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
+ 'info_dict': {
+ 'id': 'MgNrAu2pzNs',
+ 'ext': 'mp4',
+ 'title': 'Voyeur Girl',
+ 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
+ 'upload_date': '20190312',
+ 'uploader': 'Stephen - Topic',
+ 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
+ 'artist': 'Stephen',
+ 'track': 'Voyeur Girl',
+ 'album': 'it\'s too much love to know my dear',
+ 'release_date': '20190313',
+ 'release_year': 2019,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # Youtube Music Auto-generated description
+ # Retrieve 'artist' field from 'Artist:' in video description
+ # when it is present on youtube music video
+ 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
+ 'info_dict': {
+ 'id': 'k0jLE7tTwjY',
+ 'ext': 'mp4',
+ 'title': 'Latch Feat. Sam Smith',
+ 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
+ 'upload_date': '20150110',
+ 'uploader': 'Various Artists - Topic',
+ 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
+ 'artist': 'Disclosure',
+ 'track': 'Latch Feat. Sam Smith',
+ 'album': 'Latch Featuring Sam Smith',
+ 'release_date': '20121008',
+ 'release_year': 2012,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # Youtube Music Auto-generated description
+ # handle multiple artists on youtube music video
+ 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
+ 'info_dict': {
+ 'id': '74qn0eJSjpA',
+ 'ext': 'mp4',
+ 'title': 'Eastside',
+ 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
+ 'upload_date': '20180710',
+ 'uploader': 'Benny Blanco - Topic',
+ 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
+ 'artist': 'benny blanco, Halsey, Khalid',
+ 'track': 'Eastside',
+ 'album': 'Eastside',
+ 'release_date': '20180713',
+ 'release_year': 2018,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ # Youtube Music Auto-generated description
+ # handle youtube music video with release_year and no release_date
+ 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
+ 'info_dict': {
+ 'id': '-hcAI0g-f5M',
+ 'ext': 'mp4',
+ 'title': 'Put It On Me',
+ 'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
+ 'upload_date': '20180426',
+ 'uploader': 'Matt Maeson - Topic',
+ 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
+ 'artist': 'Matt Maeson',
+ 'track': 'Put It On Me',
+ 'album': 'The Hearse',
+ 'release_date': None,
+ 'release_year': 2018,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
+ 'only_matching': True,
+ },
]
def __init__(self, *args, **kwargs):
def _extract_signature_function(self, video_id, player_url, example_sig):
id_m = re.match(
- r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
+ r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
player_url)
if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url)
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
- r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
- 'Initial JS player signature function name')
+ (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+ r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
+ # Obsolete patterns
+ r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+ r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
+ jscode, 'Initial JS player signature function name', group='sig')
jsi = JSInterpreter(jscode)
initial_function = jsi.extract_function(funcname)
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)
try:
player_id = (player_url, self._signature_cache_id(s))
if player_id not in self._player_cache:
# regex won't capture the whole JSON. Yet working around by trying more
# concrete regex first keeping in mind proper quoted string handling
# to be implemented in future that will replace this workaround (see
- # https://github.com/rg3/youtube-dl/issues/7468,
- # https://github.com/rg3/youtube-dl/pull/7599)
+ # https://github.com/ytdl-org/youtube-dl/issues/7468,
+ # https://github.com/ytdl-org/youtube-dl/pull/7599)
r';ytplayer\.config\s*=\s*({.+?});ytplayer',
r';ytplayer\.config\s*=\s*({.+?});',
)
sub_lang_list[sub_lang] = sub_formats
return sub_lang_list
+ def make_captions(sub_url, sub_langs):
+ parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
+ caption_qs = compat_parse_qs(parsed_sub_url.query)
+ captions = {}
+ for sub_lang in sub_langs:
+ sub_formats = []
+ for ext in self._SUBTITLE_FORMATS:
+ caption_qs.update({
+ 'tlang': [sub_lang],
+ 'fmt': [ext],
+ })
+ sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
+ query=compat_urllib_parse_urlencode(caption_qs, True)))
+ sub_formats.append({
+ 'url': sub_url,
+ 'ext': ext,
+ })
+ captions[sub_lang] = sub_formats
+ return captions
+
+ # New captions format as of 22.06.2017
+ player_response = args.get('player_response')
+ if player_response and isinstance(player_response, compat_str):
+ player_response = self._parse_json(
+ player_response, video_id, fatal=False)
+ if player_response:
+ renderer = player_response['captions']['playerCaptionsTracklistRenderer']
+ base_url = renderer['captionTracks'][0]['baseUrl']
+ sub_lang_list = []
+ for lang in renderer['translationLanguages']:
+ lang_code = lang.get('languageCode')
+ if lang_code:
+ sub_lang_list.append(lang_code)
+ return make_captions(base_url, sub_lang_list)
+
# Some videos don't provide ttsurl but rather caption_tracks and
# caption_translation_languages (e.g. 20LmZk1hakA)
+ # Does not used anymore as of 22.06.2017
caption_tracks = args['caption_tracks']
caption_translation_languages = args['caption_translation_languages']
caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
- parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
- caption_qs = compat_parse_qs(parsed_caption_url.query)
-
- sub_lang_list = {}
+ sub_lang_list = []
for lang in caption_translation_languages.split(','):
lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
sub_lang = lang_qs.get('lc', [None])[0]
- if not sub_lang:
- continue
- sub_formats = []
- for ext in self._SUBTITLE_FORMATS:
- caption_qs.update({
- 'tlang': [sub_lang],
- 'fmt': [ext],
- })
- sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
- query=compat_urllib_parse_urlencode(caption_qs, True)))
- sub_formats.append({
- 'url': sub_url,
- 'ext': ext,
- })
- sub_lang_list[sub_lang] = sub_formats
- return sub_lang_list
+ if sub_lang:
+ sub_lang_list.append(sub_lang)
+ return make_captions(caption_url, sub_lang_list)
# An extractor error can be raise by the download process if there are
# no automatic captions but there are subtitles
- except (KeyError, ExtractorError):
+ except (KeyError, IndexError, ExtractorError):
self._downloader.report_warning(err_msg)
return {}
- def _mark_watched(self, video_id, video_info):
- playback_url = video_info.get('videostats_playback_base_url', [None])[0]
+ def _mark_watched(self, video_id, video_info, player_response):
+ playback_url = url_or_none(try_get(
+ player_response,
+ lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
+ video_info, lambda x: x['videostats_playback_base_url'][0]))
if not playback_url:
return
parsed_playback_url = compat_urlparse.urlparse(playback_url)
playback_url, video_id, 'Marking watched',
'Unable to mark watched', fatal=False)
+ @staticmethod
+ def _extract_urls(webpage):
+ # Embedded YouTube player
+ entries = [
+ unescapeHTML(mobj.group('url'))
+ for mobj in re.finditer(r'''(?x)
+ (?:
+ <iframe[^>]+?src=|
+ data-video-url=|
+ <embed[^>]+?src=|
+ embedSWF\(?:\s*|
+ <object[^>]+data=|
+ new\s+SWFObject\(
+ )
+ (["\'])
+ (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
+ (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
+ \1''', webpage)]
+
+ # lazyYT YouTube embed
+ entries.extend(list(map(
+ unescapeHTML,
+ re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
+
+ # Wordpress "YouTube Video Importer" plugin
+ matches = re.findall(r'''(?x)<div[^>]+
+ class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
+ data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
+ entries.extend(m[-1] for m in matches)
+
+ return entries
+
+ @staticmethod
+ def _extract_url(webpage):
+ urls = YoutubeIE._extract_urls(webpage)
+ return urls[0] if urls else None
+
@classmethod
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
video_id = mobj.group(2)
return video_id
- def _extract_from_m3u8(self, manifest_url, video_id):
- url_map = {}
-
- def _get_urls(_manifest):
- lines = _manifest.split('\n')
- urls = filter(lambda l: l and not l.startswith('#'),
- lines)
- return urls
- manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
- formats_urls = _get_urls(manifest)
- for format_url in formats_urls:
- itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
- url_map[itag] = format_url
- return url_map
-
- def _extract_annotations(self, video_id):
- url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
- return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
+ @staticmethod
+ def _extract_chapters(description, duration):
+ if not description:
+ return None
+ chapter_lines = re.findall(
+ r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
+ description)
+ if not chapter_lines:
+ return None
+ chapters = []
+ for next_num, (chapter_line, time_point) in enumerate(
+ chapter_lines, start=1):
+ start_time = parse_duration(time_point)
+ if start_time is None:
+ continue
+ if start_time > duration:
+ break
+ end_time = (duration if next_num == len(chapter_lines)
+ else parse_duration(chapter_lines[next_num][1]))
+ if end_time is None:
+ continue
+ if end_time > duration:
+ end_time = duration
+ if start_time > end_time:
+ break
+ chapter_title = re.sub(
+ r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
+ chapter_title = re.sub(r'\s+', ' ', chapter_title)
+ chapters.append({
+ 'start_time': start_time,
+ 'end_time': end_time,
+ 'title': chapter_title,
+ })
+ return chapters
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
if dash_mpd and dash_mpd[0] not in dash_mpds:
dash_mpds.append(dash_mpd[0])
+ def add_dash_mpd_pr(pl_response):
+ dash_mpd = url_or_none(try_get(
+ pl_response, lambda x: x['streamingData']['dashManifestUrl'],
+ compat_str))
+ if dash_mpd and dash_mpd not in dash_mpds:
+ dash_mpds.append(dash_mpd)
+
+ is_live = None
+ view_count = None
+
+ def extract_view_count(v_info):
+ return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
+
+ def extract_player_response(player_response, video_id):
+ pl_response = str_or_none(player_response)
+ if not pl_response:
+ return
+ pl_response = self._parse_json(pl_response, video_id, fatal=False)
+ if isinstance(pl_response, dict):
+ add_dash_mpd_pr(pl_response)
+ return pl_response
+
+ player_response = {}
+
# Get video info
+ video_info = {}
embed_webpage = None
- is_live = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id}
r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
})
video_info_url = proto + '://www.youtube.com/get_video_info?' + data
- video_info_webpage = self._download_webpage(
- video_info_url, video_id,
- note='Refetching age-gated info webpage',
- errnote='unable to download video info webpage')
- video_info = compat_parse_qs(video_info_webpage)
- add_dash_mpd(video_info)
+ try:
+ video_info_webpage = self._download_webpage(
+ video_info_url, video_id,
+ note='Refetching age-gated info webpage',
+ errnote='unable to download video info webpage')
+ except ExtractorError:
+ video_info_webpage = None
+ if video_info_webpage:
+ video_info = compat_parse_qs(video_info_webpage)
+ pl_response = video_info.get('player_response', [None])[0]
+ player_response = extract_player_response(pl_response, video_id)
+ add_dash_mpd(video_info)
+ view_count = extract_view_count(video_info)
else:
age_gate = False
- video_info = None
# Try looking directly into the video webpage
ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
if ytplayer_config:
args = ytplayer_config['args']
- if args.get('url_encoded_fmt_stream_map'):
+ if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
# Convert to the same format returned by compat_parse_qs
video_info = dict((k, [v]) for k, v in args.items())
add_dash_mpd(video_info)
+ # Rental video is not rented but preview is available (e.g.
+ # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
+ # https://github.com/ytdl-org/youtube-dl/issues/10532)
+ if not video_info and args.get('ypc_vid'):
+ return self.url_result(
+ args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
if args.get('livestream') == '1' or args.get('live_playback') == 1:
is_live = True
+ if not player_response:
+ player_response = extract_player_response(args.get('player_response'), video_id)
if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
- # We also try looking in get_video_info since it may contain different dashmpd
- # URL that points to a DASH manifest with possibly different itag set (some itags
- # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
- # manifest pointed by get_video_info's dashmpd).
- # The general idea is to take a union of itags of both DASH manifests (for example
- # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = (
- '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (proto, video_id, el_type))
- video_info_webpage = self._download_webpage(
- video_info_url,
- video_id, note=False,
- errnote='unable to download video info webpage')
- get_video_info = compat_parse_qs(video_info_webpage)
- if get_video_info.get('use_cipher_signature') != ['True']:
- add_dash_mpd(get_video_info)
- if not video_info:
- video_info = get_video_info
- if 'token' in get_video_info:
- # Different get_video_info requests may report different results, e.g.
- # some may report video unavailability, but some may serve it without
- # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
- # the original webpage as well as el=info and el=embedded get_video_info
- # requests report video unavailability due to geo restriction while
- # el=detailpage succeeds and returns valid data). This is probably
- # due to YouTube measures against IP ranges of hosting providers.
- # Working around by preferring the first succeeded video_info containing
- # the token if no such video_info yet was found.
- if 'token' not in video_info:
- video_info = get_video_info
- break
- if 'token' not in video_info:
- if 'reason' in video_info:
- if 'The uploader has not made this video available in your country.' in video_info['reason']:
- regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
- if regions_allowed:
- raise ExtractorError('YouTube said: This video is available in %s only' % (
- ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
- expected=True)
- raise ExtractorError(
- 'YouTube said: %s' % video_info['reason'][0],
- expected=True, video_id=video_id)
- else:
- raise ExtractorError(
- '"token" parameter not in video info for unknown reason',
- video_id=video_id)
+ add_dash_mpd_pr(player_response)
+
+ def extract_unavailable_message():
+ messages = []
+ for tag, kind in (('h1', 'message'), ('div', 'submessage')):
+ msg = self._html_search_regex(
+ r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind),
+ video_webpage, 'unavailable %s' % kind, default=None)
+ if msg:
+ messages.append(msg)
+ if messages:
+ return '\n'.join(messages)
+
+ if not video_info and not player_response:
+ unavailable_message = extract_unavailable_message()
+ if not unavailable_message:
+ unavailable_message = 'Unable to extract video data'
+ raise ExtractorError(
+ 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
- # title
- if 'title' in video_info:
- video_title = video_info['title'][0]
- else:
+ if not isinstance(video_info, dict):
+ video_info = {}
+
+ video_details = try_get(
+ player_response, lambda x: x['videoDetails'], dict) or {}
+
+ video_title = video_info.get('title', [None])[0] or video_details.get('title')
+ if not video_title:
self._downloader.report_warning('Unable to extract video title')
video_title = '_'
- # description
- video_description = get_element_by_id("eow-description", video_webpage)
+ description_original = video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
- video_description = re.sub(r'''(?x)
+
+ def replace_url(m):
+ redir_url = compat_urlparse.urljoin(url, m.group(1))
+ parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
+ if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
+ qs = compat_parse_qs(parsed_redir_url.query)
+ q = qs.get('q')
+ if q and q[0]:
+ return q[0]
+ return redir_url
+
+ description_original = video_description = re.sub(r'''(?x)
<a\s+
(?:[a-zA-Z-]+="[^"]*"\s+)*?
(?:title|href)="([^"]+)"\s+
class="[^"]*"[^>]*>
[^<]+\.{3}\s*
</a>
- ''', r'\1', video_description)
+ ''', replace_url, video_description)
video_description = clean_html(video_description)
else:
- fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
- if fd_mobj:
- video_description = unescapeHTML(fd_mobj.group(1))
- else:
- video_description = ''
+ video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
- if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
+ if not smuggled_data.get('force_singlefeed', False):
if not self._downloader.params.get('noplaylist'):
- entries = []
- feed_ids = []
- multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
- for feed in multifeed_metadata_list.split(','):
- # Unquote should take place before split on comma (,) since textual
- # fields may contain comma as well (see
- # https://github.com/rg3/youtube-dl/issues/8536)
- feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
- entries.append({
- '_type': 'url_transparent',
- 'ie_key': 'Youtube',
- 'url': smuggle_url(
- '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
- {'force_singlefeed': True}),
- 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
- })
- feed_ids.append(feed_data['id'][0])
- self.to_screen(
- 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
- % (', '.join(feed_ids), video_id))
- return self.playlist_result(entries, video_id, video_title, video_description)
- self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
-
- if 'view_count' in video_info:
- view_count = int(video_info['view_count'][0])
- else:
- view_count = None
+ multifeed_metadata_list = try_get(
+ player_response,
+ lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
+ compat_str) or try_get(
+ video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
+ if multifeed_metadata_list:
+ entries = []
+ feed_ids = []
+ for feed in multifeed_metadata_list.split(','):
+ # Unquote should take place before split on comma (,) since textual
+ # fields may contain comma as well (see
+ # https://github.com/ytdl-org/youtube-dl/issues/8536)
+ feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
+ entries.append({
+ '_type': 'url_transparent',
+ 'ie_key': 'Youtube',
+ 'url': smuggle_url(
+ '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
+ {'force_singlefeed': True}),
+ 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
+ })
+ feed_ids.append(feed_data['id'][0])
+ self.to_screen(
+ 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
+ % (', '.join(feed_ids), video_id))
+ return self.playlist_result(entries, video_id, video_title, video_description)
+ else:
+ self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
+
+ if view_count is None:
+ view_count = extract_view_count(video_info)
+ if view_count is None and video_details:
+ view_count = int_or_none(video_details.get('viewCount'))
+
+ if is_live is None:
+ is_live = bool_or_none(video_details.get('isLive'))
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
- raise ExtractorError('"rental" videos not supported')
+ raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
- # Start extracting information
- self.report_information_extraction(video_id)
+ def _extract_filesize(media_url):
+ return int_or_none(self._search_regex(
+ r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
+
+ streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or []
+ streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or [])
+
+ if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ formats = [{
+ 'format_id': '_rtmp',
+ 'protocol': 'rtmp',
+ 'url': video_info['conn'][0],
+ 'player_url': player_url,
+ }]
+ elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
+ encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
+ if 'rtmpe%3Dyes' in encoded_url_map:
+ raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
+ formats = []
+ formats_spec = {}
+ fmt_list = video_info.get('fmt_list', [''])[0]
+ if fmt_list:
+ for fmt in fmt_list.split(','):
+ spec = fmt.split('/')
+ if len(spec) > 1:
+ width_height = spec[1].split('x')
+ if len(width_height) == 2:
+ formats_spec[spec[0]] = {
+ 'resolution': spec[1],
+ 'width': int_or_none(width_height[0]),
+ 'height': int_or_none(width_height[1]),
+ }
+ for fmt in streaming_formats:
+ itag = str_or_none(fmt.get('itag'))
+ if not itag:
+ continue
+ quality = fmt.get('quality')
+ quality_label = fmt.get('qualityLabel') or quality
+ formats_spec[itag] = {
+ 'asr': int_or_none(fmt.get('audioSampleRate')),
+ 'filesize': int_or_none(fmt.get('contentLength')),
+ 'format_note': quality_label,
+ 'fps': int_or_none(fmt.get('fps')),
+ 'height': int_or_none(fmt.get('height')),
+ # bitrate for itag 43 is always 2147483647
+ 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
+ 'width': int_or_none(fmt.get('width')),
+ }
+
+ for fmt in streaming_formats:
+ if fmt.get('drm_families'):
+ continue
+ url = url_or_none(fmt.get('url'))
+
+ if not url:
+ cipher = fmt.get('cipher')
+ if not cipher:
+ continue
+ url_data = compat_parse_qs(cipher)
+ url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str))
+ if not url:
+ continue
+ else:
+ cipher = None
+ url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+
+ stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
+ # Unsupported FORMAT_STREAM_TYPE_OTF
+ if stream_type == 3:
+ continue
+
+ format_id = fmt.get('itag') or url_data['itag'][0]
+ if not format_id:
+ continue
+ format_id = compat_str(format_id)
+
+ if cipher:
+ if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
+ ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
+ jsplayer_url_json = self._search_regex(
+ ASSETS_RE,
+ embed_webpage if age_gate else video_webpage,
+ 'JS player URL (1)', default=None)
+ if not jsplayer_url_json and not age_gate:
+ # We need the embed website after all
+ if embed_webpage is None:
+ embed_url = proto + '://www.youtube.com/embed/%s' % video_id
+ embed_webpage = self._download_webpage(
+ embed_url, video_id, 'Downloading embed webpage')
+ jsplayer_url_json = self._search_regex(
+ ASSETS_RE, embed_webpage, 'JS player URL')
+
+ player_url = json.loads(jsplayer_url_json)
+ if player_url is None:
+ player_url_json = self._search_regex(
+ r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
+ video_webpage, 'age gate player URL')
+ player_url = json.loads(player_url_json)
+
+ if 'sig' in url_data:
+ url += '&signature=' + url_data['sig'][0]
+ elif 's' in url_data:
+ encrypted_sig = url_data['s'][0]
+
+ if self._downloader.params.get('verbose'):
+ if player_url is None:
+ player_version = 'unknown'
+ player_desc = 'unknown'
+ else:
+ if player_url.endswith('swf'):
+ player_version = self._search_regex(
+ r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
+ 'flash player', fatal=False)
+ player_desc = 'flash player %s' % player_version
+ else:
+ player_version = self._search_regex(
+ [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
+ r'(?:www|player(?:_ias)?)[-.]([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
+ player_url,
+ 'html5 player', fatal=False)
+ player_desc = 'html5 player %s' % player_version
+
+ parts_sizes = self._signature_cache_id(encrypted_sig)
+ self.to_screen('{%s} signature length %s, %s' %
+ (format_id, parts_sizes, player_desc))
+
+ signature = self._decrypt_signature(
+ encrypted_sig, video_id, player_url, age_gate)
+ sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
+ url += '&%s=%s' % (sp, signature)
+ if 'ratebypass' not in url:
+ url += '&ratebypass=yes'
+
+ dct = {
+ 'format_id': format_id,
+ 'url': url,
+ 'player_url': player_url,
+ }
+ if format_id in self._formats:
+ dct.update(self._formats[format_id])
+ if format_id in formats_spec:
+ dct.update(formats_spec[format_id])
+
+ # Some itags are not included in DASH manifest thus corresponding formats will
+ # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
+ # Trying to extract metadata from url_encoded_fmt_stream_map entry.
+ mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
+ width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
+
+ if width is None:
+ width = int_or_none(fmt.get('width'))
+ if height is None:
+ height = int_or_none(fmt.get('height'))
+
+ filesize = int_or_none(url_data.get(
+ 'clen', [None])[0]) or _extract_filesize(url)
+
+ quality = url_data.get('quality', [None])[0] or fmt.get('quality')
+ quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
+
+ tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
+ or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
+ fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
+
+ more_fields = {
+ 'filesize': filesize,
+ 'tbr': tbr,
+ 'width': width,
+ 'height': height,
+ 'fps': fps,
+ 'format_note': quality_label or quality,
+ }
+ for key, value in more_fields.items():
+ if value:
+ dct[key] = value
+ type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
+ if type_:
+ type_split = type_.split(';')
+ kind_ext = type_split[0].split('/')
+ if len(kind_ext) == 2:
+ kind, _ = kind_ext
+ dct['ext'] = mimetype2ext(type_split[0])
+ if kind in ('audio', 'video'):
+ codecs = None
+ for mobj in re.finditer(
+ r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
+ if mobj.group('key') == 'codecs':
+ codecs = mobj.group('val')
+ break
+ if codecs:
+ dct.update(parse_codecs(codecs))
+ if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
+ dct['downloader_options'] = {
+ # Youtube throttles chunks >~10M
+ 'http_chunk_size': 10485760,
+ }
+ formats.append(dct)
+ else:
+ manifest_url = (
+ url_or_none(try_get(
+ player_response,
+ lambda x: x['streamingData']['hlsManifestUrl'],
+ compat_str))
+ or url_or_none(try_get(
+ video_info, lambda x: x['hlsvp'][0], compat_str)))
+ if manifest_url:
+ formats = []
+ m3u8_formats = self._extract_m3u8_formats(
+ manifest_url, video_id, 'mp4', fatal=False)
+ for a_format in m3u8_formats:
+ itag = self._search_regex(
+ r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
+ if itag:
+ a_format['format_id'] = itag
+ if itag in self._formats:
+ dct = self._formats[itag].copy()
+ dct.update(a_format)
+ a_format = dct
+ a_format['player_url'] = player_url
+ # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
+ a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
+ formats.append(a_format)
+ else:
+ error_message = extract_unavailable_message()
+ if not error_message:
+ error_message = clean_html(try_get(
+ player_response, lambda x: x['playabilityStatus']['reason'],
+ compat_str))
+ if not error_message:
+ error_message = clean_html(
+ try_get(video_info, lambda x: x['reason'][0], compat_str))
+ if error_message:
+ raise ExtractorError(error_message, expected=True)
+ raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
# uploader
- if 'author' not in video_info:
- raise ExtractorError('Unable to extract uploader name')
- video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
+ video_uploader = try_get(
+ video_info, lambda x: x['author'][0],
+ compat_str) or str_or_none(video_details.get('author'))
+ if video_uploader:
+ video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
+ else:
+ self._downloader.report_warning('unable to extract uploader name')
# uploader_id
video_uploader_id = None
video_uploader_url = None
mobj = re.search(
- r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
+ r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
video_webpage)
if mobj is not None:
video_uploader_id = mobj.group('uploader_id')
else:
self._downloader.report_warning('unable to extract uploader nickname')
+ channel_id = (
+ str_or_none(video_details.get('channelId'))
+ or self._html_search_meta(
+ 'channelId', video_webpage, 'channel id', default=None)
+ or self._search_regex(
+ r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+ video_webpage, 'channel id', default=None, group='id'))
+ channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
+
# thumbnail image
# We try first to get a high quality image:
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
if not upload_date:
upload_date = self._search_regex(
[r'(?s)id="eow-date.*?>(.*?)</span>',
- r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
+ r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
video_webpage, 'upload date', default=None)
- if upload_date:
- upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
video_license = self._html_search_regex(
video_webpage, 'license', default=None)
m_music = re.search(
- r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
+ r'''(?x)
+ <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
+ <ul[^>]*>\s*
+ <li>(?P<title>.+?)
+ by (?P<creator>.+?)
+ (?:
+ \(.+?\)|
+ <a[^>]*
+ (?:
+ \bhref=["\']/red[^>]*>| # drop possible
+ >\s*Listen ad-free with YouTube Red # YouTube Red ad
+ )
+ .*?
+ )?</li
+ ''',
video_webpage)
if m_music:
video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
else:
video_alt_title = video_creator = None
+ def extract_meta(field):
+ return self._html_search_regex(
+ r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
+ video_webpage, field, default=None)
+
+ track = extract_meta('Song')
+ artist = extract_meta('Artist')
+ album = extract_meta('Album')
+
+ # Youtube Music Auto-generated description
+ release_date = release_year = None
+ if video_description:
+ mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?', video_description)
+ if mobj:
+ if not track:
+ track = mobj.group('track').strip()
+ if not artist:
+ artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
+ if not album:
+ album = mobj.group('album'.strip())
+ release_year = mobj.group('release_year')
+ release_date = mobj.group('release_date')
+ if release_date:
+ release_date = release_date.replace('-', '')
+ if not release_year:
+ release_year = int(release_date[:4])
+ if release_year:
+ release_year = int(release_year)
+
+ m_episode = re.search(
+ r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
+ video_webpage)
+ if m_episode:
+ series = unescapeHTML(m_episode.group('series'))
+ season_number = int(m_episode.group('season'))
+ episode_number = int(m_episode.group('episode'))
+ else:
+ series = season_number = episode_number = None
+
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_webpage, 'categories', default=None)
like_count = _extract_count('like')
dislike_count = _extract_count('dislike')
+ if view_count is None:
+ view_count = str_to_int(self._search_regex(
+ r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
+ 'view count', default=None))
+
+ average_rating = (
+ float_or_none(video_details.get('averageRating'))
+ or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
+
# subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage)
automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
- if 'length_seconds' not in video_info:
- self._downloader.report_warning('unable to extract video duration')
- video_duration = None
- else:
- video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
+ video_duration = try_get(
+ video_info, lambda x: int_or_none(x['length_seconds'][0]))
+ if not video_duration:
+ video_duration = int_or_none(video_details.get('lengthSeconds'))
+ if not video_duration:
+ video_duration = parse_duration(self._html_search_meta(
+ 'duration', video_webpage, 'video duration'))
# annotations
video_annotations = None
if self._downloader.params.get('writeannotations', False):
- video_annotations = self._extract_annotations(video_id)
-
- def _map_to_format_list(urlmap):
- formats = []
- for itag, video_real_url in urlmap.items():
- dct = {
- 'format_id': itag,
- 'url': video_real_url,
- 'player_url': player_url,
- }
- if itag in self._formats:
- dct.update(self._formats[itag])
- formats.append(dct)
- return formats
-
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- formats = [{
- 'format_id': '_rtmp',
- 'protocol': 'rtmp',
- 'url': video_info['conn'][0],
- 'player_url': player_url,
- }]
- elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
- encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
- if 'rtmpe%3Dyes' in encoded_url_map:
- raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
- formats_spec = {}
- fmt_list = video_info.get('fmt_list', [''])[0]
- if fmt_list:
- for fmt in fmt_list.split(','):
- spec = fmt.split('/')
- if len(spec) > 1:
- width_height = spec[1].split('x')
- if len(width_height) == 2:
- formats_spec[spec[0]] = {
- 'resolution': spec[1],
- 'width': int_or_none(width_height[0]),
- 'height': int_or_none(width_height[1]),
- }
- formats = []
- for url_data_str in encoded_url_map.split(','):
- url_data = compat_parse_qs(url_data_str)
- if 'itag' not in url_data or 'url' not in url_data:
- continue
- format_id = url_data['itag'][0]
- url = url_data['url'][0]
-
- if 'sig' in url_data:
- url += '&signature=' + url_data['sig'][0]
- elif 's' in url_data:
- encrypted_sig = url_data['s'][0]
- ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
-
- jsplayer_url_json = self._search_regex(
- ASSETS_RE,
- embed_webpage if age_gate else video_webpage,
- 'JS player URL (1)', default=None)
- if not jsplayer_url_json and not age_gate:
- # We need the embed website after all
- if embed_webpage is None:
- embed_url = proto + '://www.youtube.com/embed/%s' % video_id
- embed_webpage = self._download_webpage(
- embed_url, video_id, 'Downloading embed webpage')
- jsplayer_url_json = self._search_regex(
- ASSETS_RE, embed_webpage, 'JS player URL')
-
- player_url = json.loads(jsplayer_url_json)
- if player_url is None:
- player_url_json = self._search_regex(
- r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
- video_webpage, 'age gate player URL')
- player_url = json.loads(player_url_json)
-
- if self._downloader.params.get('verbose'):
- if player_url is None:
- player_version = 'unknown'
- player_desc = 'unknown'
- else:
- if player_url.endswith('swf'):
- player_version = self._search_regex(
- r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
- 'flash player', fatal=False)
- player_desc = 'flash player %s' % player_version
- else:
- player_version = self._search_regex(
- [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
- player_url,
- 'html5 player', fatal=False)
- player_desc = 'html5 player %s' % player_version
-
- parts_sizes = self._signature_cache_id(encrypted_sig)
- self.to_screen('{%s} signature length %s, %s' %
- (format_id, parts_sizes, player_desc))
-
- signature = self._decrypt_signature(
- encrypted_sig, video_id, player_url, age_gate)
- url += '&signature=' + signature
- if 'ratebypass' not in url:
- url += '&ratebypass=yes'
-
- dct = {
- 'format_id': format_id,
- 'url': url,
- 'player_url': player_url,
- }
- if format_id in self._formats:
- dct.update(self._formats[format_id])
- if format_id in formats_spec:
- dct.update(formats_spec[format_id])
-
- # Some itags are not included in DASH manifest thus corresponding formats will
- # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
- # Trying to extract metadata from url_encoded_fmt_stream_map entry.
- mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
- width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
-
- more_fields = {
- 'filesize': int_or_none(url_data.get('clen', [None])[0]),
- 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
- 'width': width,
- 'height': height,
- 'fps': int_or_none(url_data.get('fps', [None])[0]),
- 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
- }
- for key, value in more_fields.items():
- if value:
- dct[key] = value
- type_ = url_data.get('type', [None])[0]
- if type_:
- type_split = type_.split(';')
- kind_ext = type_split[0].split('/')
- if len(kind_ext) == 2:
- kind, _ = kind_ext
- dct['ext'] = mimetype2ext(type_split[0])
- if kind in ('audio', 'video'):
- codecs = None
- for mobj in re.finditer(
- r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
- if mobj.group('key') == 'codecs':
- codecs = mobj.group('val')
- break
- if codecs:
- codecs = codecs.split(',')
- if len(codecs) == 2:
- acodec, vcodec = codecs[1], codecs[0]
- else:
- acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
- dct.update({
- 'acodec': acodec,
- 'vcodec': vcodec,
- })
- formats.append(dct)
- elif video_info.get('hlsvp'):
- manifest_url = video_info['hlsvp'][0]
- url_map = self._extract_from_m3u8(manifest_url, video_id)
- formats = _map_to_format_list(url_map)
- # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
- for a_format in formats:
- a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
- else:
- unavailable_message = self._html_search_regex(
- r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
- video_webpage, 'unavailable message', default=None)
- if unavailable_message:
- raise ExtractorError(unavailable_message, expected=True)
- raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
+ xsrf_token = self._search_regex(
+ r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
+ video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
+ invideo_url = try_get(
+ player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
+ if xsrf_token and invideo_url:
+ xsrf_field_name = self._search_regex(
+ r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
+ video_webpage, 'xsrf field name',
+ group='xsrf_field_name', default='session_token')
+ video_annotations = self._download_webpage(
+ self._proto_relative_url(invideo_url),
+ video_id, note='Downloading annotations',
+ errnote='Unable to download video annotations', fatal=False,
+ data=urlencode_postdata({xsrf_field_name: xsrf_token}))
+
+ chapters = self._extract_chapters(description_original, video_duration)
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
for df in self._extract_mpd_formats(
mpd_url, video_id, fatal=dash_mpd_fatal,
formats_dict=self._formats):
+ if not df.get('filesize'):
+ df['filesize'] = _extract_filesize(df['url'])
# Do not overwrite DASH format found in some previous DASH manifest
if df['format_id'] not in dash_formats:
dash_formats[df['format_id']] = df
# Remove the formats we found through non-DASH, they
# contain less info and it can be wrong, because we use
# fixed values (for example the resolution). See
- # https://github.com/rg3/youtube-dl/issues/5774 for an
+ # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
# example.
formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
formats.extend(dash_formats.values())
if f.get('vcodec') != 'none':
f['stretched_ratio'] = ratio
+ if not formats:
+ if 'reason' in video_info:
+ if 'The uploader has not made this video available in your country.' in video_info['reason']:
+ regions_allowed = self._html_search_meta(
+ 'regionsAllowed', video_webpage, default=None)
+ countries = regions_allowed.split(',') if regions_allowed else None
+ self.raise_geo_restricted(
+ msg=video_info['reason'][0], countries=countries)
+ reason = video_info['reason'][0]
+ if 'Invalid parameters' in reason:
+ unavailable_message = extract_unavailable_message()
+ if unavailable_message:
+ reason = unavailable_message
+ raise ExtractorError(
+ 'YouTube said: %s' % reason,
+ expected=True, video_id=video_id)
+ if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
+ raise ExtractorError('This video is DRM protected.', expected=True)
+
self._sort_formats(formats)
- self.mark_watched(video_id, video_info)
+ self.mark_watched(video_id, video_info, player_response)
return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'uploader_url': video_uploader_url,
+ 'channel_id': channel_id,
+ 'channel_url': channel_url,
'upload_date': upload_date,
'license': video_license,
- 'creator': video_creator,
+ 'creator': video_creator or artist,
'title': video_title,
- 'alt_title': video_alt_title,
+ 'alt_title': video_alt_title or track,
'thumbnail': video_thumbnail,
'description': video_description,
'categories': video_categories,
'duration': video_duration,
'age_limit': 18 if age_gate else 0,
'annotations': video_annotations,
+ 'chapters': chapters,
'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
- 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
+ 'average_rating': average_rating,
'formats': formats,
'is_live': is_live,
'start_time': start_time,
'end_time': end_time,
+ 'series': series,
+ 'season_number': season_number,
+ 'episode_number': episode_number,
+ 'track': track,
+ 'artist': artist,
+ 'album': album,
+ 'release_date': release_date,
+ 'release_year': release_year,
}
_VALID_URL = r"""(?x)(?:
(?:https?://)?
(?:\w+\.)?
- youtube\.com/
(?:
- (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
- \? (?:.*?[&;])*? (?:p|a|list)=
- | p/
+ (?:
+ youtube(?:kids)?\.com|
+ invidio\.us
+ )
+ /
+ (?:
+ (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
+ \? (?:.*?[&;])*? (?:p|a|list)=
+ | p/
+ )|
+ youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
)
(
- (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
+ (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
# Top tracks, they can also include dots
|(?:MC)[\w\.]*
)
.*
|
- ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
- )"""
+ (%(playlist_id)s)
+ )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
- _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
+ _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
+ _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
IE_NAME = 'youtube:playlist'
_TESTS = [{
- 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+ 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
'info_dict': {
- 'title': 'ytdl test PL',
- 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+ 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader': 'Sergey M.',
+ 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
+ 'title': 'youtube-dl public playlist',
},
- 'playlist_count': 3,
+ 'playlist_count': 1,
}, {
- 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+ 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
'info_dict': {
- 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
- 'title': 'YDL_Empty_List',
+ 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+ 'uploader': 'Sergey M.',
+ 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
+ 'title': 'youtube-dl empty playlist',
},
'playlist_count': 0,
}, {
'info_dict': {
'title': '29C3: Not my department',
'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
+ 'uploader': 'Christiaan008',
+ 'uploader_id': 'ChRiStIaAn008',
},
- 'playlist_count': 95,
+ 'playlist_count': 96,
}, {
'note': 'issue #673',
'url': 'PLBB231211A4F62143',
'info_dict': {
'title': '[OLD]Team Fortress 2 (Class-based LP)',
'id': 'PLBB231211A4F62143',
+ 'uploader': 'Wickydoo',
+ 'uploader_id': 'Wickydoo',
},
'playlist_mincount': 26,
}, {
'info_dict': {
'title': 'Uploads from Cauchemar',
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
+ 'uploader': 'Cauchemar',
+ 'uploader_id': 'Cauchemar89',
},
'playlist_mincount': 799,
}, {
'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
},
'playlist_count': 2,
+ 'skip': 'This playlist is private',
}, {
'note': 'embedded',
- 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
+ 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
'playlist_count': 4,
'info_dict': {
'title': 'JODA15',
'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
+ 'uploader': 'milan',
+ 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
+ }
+ }, {
+ 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
+ 'playlist_mincount': 485,
+ 'info_dict': {
+ 'title': '2018 Chinese New Singles (11/6 updated)',
+ 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
+ 'uploader': 'LBK',
+ 'uploader_id': 'sdragonfang',
}
}, {
'note': 'Embedded SWF player',
- 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
+ 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
'playlist_count': 4,
'info_dict': {
'title': 'JODA7',
'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
- }
+ },
+ 'skip': 'This playlist does not exist',
}, {
'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
'info_dict': {
'title': 'Uploads from Interstellar Movie',
'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
+ 'uploader': 'Interstellar Movie',
+ 'uploader_id': 'InterstellarMovie1',
},
- 'playlist_mincout': 21,
+ 'playlist_mincount': 21,
+ }, {
+ # Playlist URL that does not actually serve a playlist
+ 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
+ 'info_dict': {
+ 'id': 'FqZTN594JQw',
+ 'ext': 'webm',
+ 'title': "Smiley's People 01 detective, Adventure Series, Action",
+ 'uploader': 'STREEM',
+ 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
+ 'upload_date': '20150526',
+ 'license': 'Standard YouTube License',
+ 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
+ 'categories': ['People & Blogs'],
+ 'tags': list,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'skip': 'This video is not available.',
+ 'add_ie': [YoutubeIE.ie_key()],
+ }, {
+ 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
+ 'info_dict': {
+ 'id': 'yeWKywCrFtk',
+ 'ext': 'mp4',
+ 'title': 'Small Scale Baler and Braiding Rugs',
+ 'uploader': 'Backus-Page House Museum',
+ 'uploader_id': 'backuspagemuseum',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
+ 'upload_date': '20161008',
+ 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
+ 'categories': ['Nonprofits & Activism'],
+ 'tags': list,
+ 'like_count': int,
+ 'dislike_count': int,
+ },
+ 'params': {
+ 'noplaylist': True,
+ 'skip_download': True,
+ },
+ }, {
+ # https://github.com/ytdl-org/youtube-dl/issues/21844
+ 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
+ 'info_dict': {
+ 'title': 'Data Analysis with Dr Mike Pound',
+ 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
+ 'uploader_id': 'Computerphile',
+ 'uploader': 'Computerphile',
+ },
+ 'playlist_mincount': 11,
+ }, {
+ 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
+ 'only_matching': True,
+ }, {
+ 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
+ 'only_matching': True,
+ }, {
+ # music album playlist
+ 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
+ 'only_matching': True,
}]
def _real_initialize(self):
self._login()
+ def extract_videos_from_page(self, page):
+ ids_in_page = []
+ titles_in_page = []
+
+ for item in re.findall(
+ r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
+ attrs = extract_attributes(item)
+ video_id = attrs['data-video-id']
+ video_title = unescapeHTML(attrs.get('data-title'))
+ if video_title:
+ video_title = video_title.strip()
+ ids_in_page.append(video_id)
+ titles_in_page.append(video_title)
+
+ # Fallback with old _VIDEO_RE
+ self.extract_videos_from_page_impl(
+ self._VIDEO_RE, page, ids_in_page, titles_in_page)
+
+ # Relaxed fallbacks
+ self.extract_videos_from_page_impl(
+ r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page,
+ ids_in_page, titles_in_page)
+ self.extract_videos_from_page_impl(
+ r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
+ ids_in_page, titles_in_page)
+
+ return zip(ids_in_page, titles_in_page)
+
def _extract_mix(self, playlist_id):
# The mixes are generated from a single video
# the id of the playlist is just 'RD' + video_id
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
title_span = (
- search_title('playlist-title') or
- search_title('title long-title') or
- search_title('title'))
+ search_title('playlist-title')
+ or search_title('title long-title')
+ or search_title('title'))
title = clean_html(title_span)
return self.playlist_result(url_results, playlist_id, title)
url = self._TEMPLATE_URL % playlist_id
page = self._download_webpage(url, playlist_id)
- for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
+ # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
+ for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
match = match.strip()
# Check if the playlist exists or is private
- if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
- raise ExtractorError(
- 'The playlist doesn\'t exist or is private, use --username or '
- '--netrc to access it.',
- expected=True)
+ mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
+ if mobj:
+ reason = mobj.group('reason')
+ message = 'This playlist %s' % reason
+ if 'private' in reason:
+ message += ', use --username or --netrc to access it'
+ message += '.'
+ raise ExtractorError(message, expected=True)
elif re.match(r'[^<]*Invalid parameters[^<]*', match):
raise ExtractorError(
'Invalid parameters. Maybe URL is incorrect.',
playlist_title = self._html_search_regex(
r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
- page, 'title')
+ page, 'title', default=None)
- return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
+ _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
+ uploader = self._html_search_regex(
+ r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
+ page, 'uploader', default=None)
+ mobj = re.search(
+ r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
+ page)
+ if mobj:
+ uploader_id = mobj.group('uploader_id')
+ uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
+ else:
+ uploader_id = uploader_url = None
+
+ has_videos = True
+
+ if not playlist_title:
+ try:
+ # Some playlist URLs don't actually serve a playlist (e.g.
+ # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
+ next(self._entries(page, playlist_id))
+ except StopIteration:
+ has_videos = False
+
+ playlist = self.playlist_result(
+ self._entries(page, playlist_id), playlist_id, playlist_title)
+ playlist.update({
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'uploader_url': uploader_url,
+ })
+
+ return has_videos, playlist
def _check_download_just_video(self, url, playlist_id):
# Check if it's a video-specific URL
query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
- if 'v' in query_dict:
- video_id = query_dict['v'][0]
+ video_id = query_dict.get('v', [None])[0] or self._search_regex(
+ r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
+ 'video id', default=None)
+ if video_id:
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
- return self.url_result(video_id, 'Youtube', video_id=video_id)
+ return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+ return video_id, None
+ return None, None
def _real_extract(self, url):
# Extract playlist id
raise ExtractorError('Invalid URL: %s' % url)
playlist_id = mobj.group(1) or mobj.group(2)
- video = self._check_download_just_video(url, playlist_id)
+ video_id, video = self._check_download_just_video(url, playlist_id)
if video:
return video
# Mixes require a custom extraction process
return self._extract_mix(playlist_id)
- return self._extract_playlist(playlist_id)
+ has_videos, playlist = self._extract_playlist(playlist_id)
+ if has_videos or not video_id:
+ return playlist
+
+ # Some playlist URLs don't actually serve a playlist (see
+ # https://github.com/ytdl-org/youtube-dl/issues/10537).
+ # Fallback to plain video extraction if there is a video id
+ # along with playlist id.
+ return self.url_result(video_id, 'Youtube', video_id=video_id)
class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com channels'
- _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
+ _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
_VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
IE_NAME = 'youtube:channel'
'info_dict': {
'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
'title': 'Uploads from lex will',
+ 'uploader': 'lex will',
+ 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
}
}, {
'note': 'Age restricted channel',
'info_dict': {
'id': 'UUs0ifCMCm1icqRbqhUINa0w',
'title': 'Uploads from Deus Ex',
+ 'uploader': 'Deus Ex',
+ 'uploader_id': 'DeusExOfficial',
},
+ }, {
+ 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
+ 'only_matching': True,
}]
@classmethod
return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
else super(YoutubeChannelIE, cls).suitable(url))
+ def _build_template_url(self, url, channel_id):
+ return self._TEMPLATE_URL % channel_id
+
def _real_extract(self, url):
channel_id = self._match_id(url)
- url = self._TEMPLATE_URL % channel_id
+ url = self._build_template_url(url, channel_id)
# Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
# Workaround by extracting as a playlist if managed to obtain channel playlist URL
channel_playlist_id = self._html_search_meta(
'channelId', channel_page, 'channel id', default=None)
if not channel_playlist_id:
- channel_playlist_id = self._search_regex(
- r'data-(?:channel-external-|yt)id="([^"]+)"',
- channel_page, 'channel id', default=None)
+ channel_url = self._html_search_meta(
+ ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
+ channel_page, 'channel url', default=None)
+ if channel_url:
+ channel_playlist_id = self._search_regex(
+ r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
+ channel_url, 'channel id', default=None)
if channel_playlist_id and channel_playlist_id.startswith('UC'):
playlist_id = 'UU' + channel_playlist_id[2:]
return self.url_result(
for video_id, video_title in self.extract_videos_from_page(channel_page)]
return self.playlist_result(entries, channel_id)
+ try:
+ next(self._entries(channel_page, channel_id))
+ except StopIteration:
+ alert_message = self._html_search_regex(
+ r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
+ channel_page, 'alert', default=None, group='alert')
+ if alert_message:
+ raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
+
return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
class YoutubeUserIE(YoutubeChannelIE):
IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
- _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/|c/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
- _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
+ _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
+ _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
IE_NAME = 'youtube:user'
_TESTS = [{
'url': 'https://www.youtube.com/user/TheLinuxFoundation',
'playlist_mincount': 320,
'info_dict': {
- 'title': 'TheLinuxFoundation',
+ 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
+ 'title': 'Uploads from The Linux Foundation',
+ 'uploader': 'The Linux Foundation',
+ 'uploader_id': 'TheLinuxFoundation',
+ }
+ }, {
+ # Only available via https://www.youtube.com/c/12minuteathlete/videos
+ # but not https://www.youtube.com/user/12minuteathlete/videos
+ 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
+ 'playlist_mincount': 249,
+ 'info_dict': {
+ 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
+ 'title': 'Uploads from 12 Minute Athlete',
+ 'uploader': '12 Minute Athlete',
+ 'uploader_id': 'the12minuteathlete',
}
}, {
'url': 'ytuser:phihag',
}, {
'url': 'https://www.youtube.com/c/gametrailers',
'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/gametrailers',
+ 'only_matching': True,
+ }, {
+ # This channel is not available, geo restricted to JP
+ 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
+ 'only_matching': True,
}]
@classmethod
else:
return super(YoutubeUserIE, cls).suitable(url)
+ def _build_template_url(self, url, channel_id):
+ mobj = re.match(self._VALID_URL, url)
+ return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
+
class YoutubeLiveIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com live streams'
- _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+))/live'
+ _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
IE_NAME = 'youtube:live'
_TESTS = [{
- 'url': 'http://www.youtube.com/user/TheYoungTurks/live',
+ 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
'info_dict': {
'id': 'a48o2S1cPoo',
'ext': 'mp4',
'title': 'The Young Turks - Live Main Show',
'uploader': 'The Young Turks',
'uploader_id': 'TheYoungTurks',
- 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
+ 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
'upload_date': '20150715',
'license': 'Standard YouTube License',
'description': 'md5:438179573adcdff3c97ebb1ee632b891',
'skip_download': True,
},
}, {
- 'url': 'http://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
+ 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/TheYoungTurks/live',
'only_matching': True,
}]
webpage = self._download_webpage(url, channel_id, fatal=False)
if webpage:
page_type = self._og_search_property(
- 'type', webpage, 'page type', default=None)
+ 'type', webpage, 'page type', default='')
video_id = self._html_search_meta(
'videoId', webpage, 'video id', default=None)
- if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
+ if page_type.startswith('video') and video_id and re.match(
+ r'^[0-9A-Za-z_-]{11}$', video_id):
return self.url_result(video_id, YoutubeIE.ie_key())
return self.url_result(base_url)
IE_NAME = 'youtube:playlists'
_TESTS = [{
- 'url': 'http://www.youtube.com/user/ThirstForScience/playlists',
+ 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
'playlist_mincount': 4,
'info_dict': {
'id': 'ThirstForScience',
- 'title': 'Thirst for Science',
+ 'title': 'ThirstForScience',
},
}, {
# with "Load more" button
- 'url': 'http://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
+ 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
'playlist_mincount': 70,
'info_dict': {
'id': 'igorkle1',
'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
'title': 'Chem Player',
},
+ 'skip': 'Blocked',
}]
-class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
+class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
+ _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
+
+
+class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
IE_DESC = 'YouTube.com searches'
# there doesn't appear to be a real limit, for example if you search for
# 'python' you get more than 8.000.000 results
videos = []
limit = n
+ url_query = {
+ 'search_query': query.encode('utf-8'),
+ }
+ url_query.update(self._EXTRA_QUERY_ARGS)
+ result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
+
for pagenum in itertools.count(1):
- url_query = {
- 'search_query': query.encode('utf-8'),
- 'page': pagenum,
- 'spf': 'navigate',
- }
- url_query.update(self._EXTRA_QUERY_ARGS)
- result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
data = self._download_json(
result_url, video_id='query "%s"' % query,
note='Downloading page %s' % pagenum,
- errnote='Unable to download API page')
+ errnote='Unable to download API page',
+ query={'spf': 'navigate'})
html_content = data[1]['body']['content']
if 'class="search-message' in html_content:
raise ExtractorError(
'[youtube] No video results', expected=True)
- new_videos = self._ids_to_results(orderedSet(re.findall(
- r'href="/watch\?v=(.{11})', html_content)))
+ new_videos = list(self._process_page(html_content))
videos += new_videos
if not new_videos or len(videos) > limit:
break
+ next_link = self._html_search_regex(
+ r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
+ html_content, 'next link', default=None)
+ if next_link is None:
+ break
+ result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
if len(videos) > n:
videos = videos[:n]
_EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
-class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
+class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
IE_DESC = 'YouTube.com search URLs'
IE_NAME = 'youtube:search_url'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
- _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
_TESTS = [{
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
'playlist_mincount': 5,
class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
IE_DESC = 'YouTube.com (multi-season) shows'
- _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
IE_NAME = 'youtube:show'
_TESTS = [{
'url': 'https://www.youtube.com/show/airdisasters',
def _real_initialize(self):
self._login()
- def _real_extract(self, url):
- page = self._download_webpage(
- 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
-
+ def _entries(self, page):
# The extraction process is the same as for playlists, but the regex
# for the video ids doesn't contain an index
ids = []
# 'recommended' feed has infinite 'load more' and each new portion spins
# the same videos in (sometimes) slightly different order, so we'll check
# for unicity and break when portion has no new videos
- new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
+ new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
if not new_ids:
break
ids.extend(new_ids)
+ for entry in self._ids_to_results(new_ids):
+ yield entry
+
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']
+ def _real_extract(self, url):
+ page = self._download_webpage(
+ 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
+ self._PLAYLIST_TITLE)
return self.playlist_result(
- self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
+ self._entries(page), playlist_title=self._PLAYLIST_TITLE)
class YoutubeWatchLaterIE(YoutubePlaylistIE):
IE_NAME = 'youtube:watchlater'
IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
_TESTS = [{
'url': 'https://www.youtube.com/playlist?list=WL',
}]
def _real_extract(self, url):
- video = self._check_download_just_video(url, 'WL')
+ _, video = self._check_download_just_video(url, 'WL')
if video:
return video
- return self._extract_playlist('WL')
+ _, playlist = self._extract_playlist('WL')
+ return playlist
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:favorites'
IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
_LOGIN_REQUIRED = True
def _real_extract(self, url):
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
_FEED_NAME = 'recommended'
_PLAYLIST_TITLE = 'Youtube Recommended videos'
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
- _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
_FEED_NAME = 'subscriptions'
_PLAYLIST_TITLE = 'Youtube Subscriptions'
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
- _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
_FEED_NAME = 'history'
_PLAYLIST_TITLE = 'Youtube History'
'''
_TESTS = [{
- 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041',
+ 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
'only_matching': True,
}, {
- 'url': 'http://www.youtube.com/watch?',
+ 'url': 'https://www.youtube.com/watch?',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
'Did you forget to quote the URL? Remember that & is a meta '
'character in most shells, so you want to put the URL in quotes, '
'like youtube-dl '
- '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
+ '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
' or simply youtube-dl BaW_jenozKc .',
expected=True)
Rapsys Git / youtubedl / blobdiff