parse_duration,
remove_quotes,
remove_start,
- sanitized_Request,
smuggle_url,
str_to_int,
try_get,
"""Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
- _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
+
+ _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)[0-9A-Za-z-_]{10,}'
+
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&hl=en',
login_form = self._hidden_inputs(login_page)
- login_form.update({
- 'checkConnection': 'youtube',
- 'Email': username,
- 'Passwd': password,
- })
+ 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',
+ })
+ 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,
+ })
- login_results = self._download_webpage(
- self._PASSWORD_CHALLENGE_URL, None,
- note='Logging in', errnote='unable to log in', fatal=False,
- data=urlencode_postdata(login_form))
- if login_results is False:
- return 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,
+ ]
- 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)
+ lookup_results = req(
+ self._LOOKUP_URL, lookup_req,
+ 'Looking up account info', 'Unable to look up account info')
- 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)
+ if lookup_results is False:
+ return False
- # 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)
+ tfa = try_get(res, lambda x: x[0][0], list)
+ if tfa:
+ tfa_str = try_get(tfa, lambda x: x[2], compat_str)
+ if tfa_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(tfa, 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:
+ 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 _real_initialize(self):
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
- (?!.*?\blist=) # 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},
- '212': {'ext': 'mp4', 'height': 480, '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/rg3/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'},
- '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
- '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', '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'},
'url': 'sJL6WA-aGkQ',
'only_matching': True,
},
+ {
+ 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
+ '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}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
player_url)
if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url)
video_id = mobj.group(2)
return video_id
- def _extract_from_m3u8(self, manifest_url, video_id):
- url_map = {}
-
- def _get_urls(_manifest):
- lines = _manifest.split('\n')
- urls = filter(lambda l: l and not l.startswith('#'),
- lines)
- return urls
- manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
- formats_urls = _get_urls(manifest)
- for format_url in formats_urls:
- itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
- url_map[itag] = format_url
- return url_map
-
def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
+ @staticmethod
+ def _extract_chapters(description, duration):
+ if not description:
+ return None
+ chapter_lines = re.findall(
+ r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<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
+ end_time = (duration if next_num == len(chapter_lines)
+ else parse_duration(chapter_lines[next_num][1]))
+ if end_time is None:
+ continue
+ 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, {})
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)
+ description_original = video_description = re.sub(r'''(?x)
<a\s+
(?:[a-zA-Z-]+="[^"]*"\s+)*?
(?:title|href)="([^"]+)"\s+
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
+ chapters = self._extract_chapters(description_original, video_duration)
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
player_desc = 'flash player %s' % player_version
else:
player_version = self._search_regex(
- [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
+ [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
+ r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'],
player_url,
'html5 player', fatal=False)
player_desc = 'html5 player %s' % player_version
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:
+ 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:
unavailable_message = self._html_search_regex(
r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
'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,
)
.*
|
- ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
- )"""
+ (%(playlist_id)s)
+ )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
IE_NAME = 'youtube:playlist'
Rapsys Git / youtubedl / blobdiff