mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-21 23:48:57 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into threads

Browse Source
This commit is contained in:
Renan D.
2024-07-25 03:55:32 -03:00
committed by GitHub
parent 32298c6d97 6b1e430d8e
commit e3a2c06121
946 changed files with 11894 additions and 9382 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
yt_dlp/extractor/_extractors.py
View File

@@ -76,6 +76,7 @@ from .aenetworks import (
)
from .aeonco import AeonCoIE
from .afreecatv import (
AfreecaTVCatchStoryIE,
AfreecaTVIE,
AfreecaTVLiveIE,
AfreecaTVUserIE,
@@ -503,7 +504,6 @@ from .dhm import DHMIE
from .digitalconcerthall import DigitalConcertHallIE
from .digiteka import DigitekaIE
from .discogs import DiscogsReleasePlaylistIE
from .discovery import DiscoveryIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .dlf import (
@@ -531,16 +531,12 @@ from .dplay import (
DiscoveryPlusIndiaShowIE,
DiscoveryPlusItalyIE,
DiscoveryPlusItalyShowIE,
DIYNetworkIE,
DPlayIE,
FoodNetworkIE,
GlobalCyclingNetworkPlusIE,
GoDiscoveryIE,
HGTVDeIE,
HGTVUsaIE,
InvestigationDiscoveryIE,
MotorTrendIE,
MotorTrendOnDemandIE,
ScienceChannelIE,
TravelChannelIE,
)
@@ -779,6 +775,7 @@ from .gopro import GoProIE
from .goshgay import GoshgayIE
from .gotostage import GoToStageIE
from .gputechconf import GPUTechConfIE
from .graspop import GraspopIE
from .gronkh import (
GronkhFeedIE,
GronkhIE,
@@ -969,6 +966,10 @@ from .la7 import (
LA7PodcastEpisodeIE,
LA7PodcastIE,
)
from .laracasts import (
LaracastsIE,
LaracastsPlaylistIE,
)
from .lastfm import (
LastFMIE,
LastFMPlaylistIE,
@@ -1113,12 +1114,15 @@ from .meipai import MeipaiIE
from .melonvod import MelonVODIE
from .metacritic import MetacriticIE
from .mgtv import MGTVIE
from .microsoftembed import MicrosoftEmbedIE
from .microsoftstream import MicrosoftStreamIE
from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyCourseIE,
MicrosoftVirtualAcademyIE,
from .microsoftembed import (
MicrosoftBuildIE,
MicrosoftEmbedIE,
MicrosoftLearnEpisodeIE,
MicrosoftLearnPlaylistIE,
MicrosoftLearnSessionIE,
MicrosoftMediusIE,
)
from .microsoftstream import MicrosoftStreamIE
from .mildom import (
MildomClipIE,
MildomIE,
@@ -1603,6 +1607,7 @@ from .qqmusic import (
QQMusicPlaylistIE,
QQMusicSingerIE,
QQMusicToplistIE,
QQMusicVideoIE,
)
from .r7 import (
R7IE,
@@ -1755,7 +1760,10 @@ from .rtve import (
RTVETelevisionIE,
)
from .rtvs import RTVSIE
from .rtvslo import RTVSLOIE
from .rtvslo import (
RTVSLOIE,
RTVSLOShowIE,
)
from .rudovideo import RudoVideoIE
from .rule34video import Rule34VideoIE
from .rumble import (
@@ -1925,6 +1933,10 @@ from .spreaker import (
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
from .sproutvideo import (
SproutVideoIE,
VidsIoIE,
)
from .srgssr import (
SRGSSRIE,
SRGSSRPlayIE,
@@ -2311,6 +2323,7 @@ from .vidio import (
)
from .vidlii import VidLiiIE
from .vidly import VidlyIE
from .vidyard import VidyardIE
from .viewlift import (
ViewLiftEmbedIE,
ViewLiftIE,
@@ -2376,6 +2389,10 @@ from .vrt import (
VrtNUIE,
)
from .vtm import VTMIE
from .vtv import (
VTVIE,
VTVGoIE,
)
from .vuclip import VuClipIE
from .vvvvid import (
VVVVIDIE,

28
yt_dlp/extractor/abc.py
View File

@@ -4,7 +4,6 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
dict_get,
@@ -67,7 +66,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'title': 'WWI Centenary',
'description': 'md5:c2379ec0ca84072e86b446e536954546',
}
},
}, {
'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
'info_dict': {
@@ -75,7 +74,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
}
},
}, {
'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
'info_dict': {
@@ -86,7 +85,7 @@ class ABCIE(InfoExtractor):
'upload_date': '20200813',
'uploader': 'Behind the News',
'uploader_id': 'behindthenews',
}
},
}, {
'url': 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540',
'info_dict': {
@@ -95,7 +94,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
}
},
}]
def _real_extract(self, url):
@@ -126,7 +125,7 @@ class ABCIE(InfoExtractor):
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError(f'{self.IE_NAME} said: {expired}', expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
@@ -164,7 +163,7 @@ class ABCIE(InfoExtractor):
'height': height,
'tbr': bitrate,
'filesize': int_or_none(url_info.get('filesize')),
'format_id': format_id
'format_id': format_id,
})
return {
@@ -288,13 +287,12 @@ class ABCIViewIE(InfoExtractor):
stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number)
path = f'/auth/hls/sign?ts={int(time.time())}&hn={house_number}&d=android-tablet'
sig = hmac.new(
b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest()
path.encode(), hashlib.sha256).hexdigest()
token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
f'http://iview.abc.net.au{path}&sig={sig}', video_id)
def tokenize_url(url, token):
return update_url_query(url, {
@@ -303,7 +301,7 @@ class ABCIViewIE(InfoExtractor):
for sd in ('1080', '720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
stream, lambda x: x['streams']['hls'][sd], str)
if not sd_url:
continue
formats = self._extract_m3u8_formats(
@@ -358,7 +356,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'description': 'md5:93119346c24a7c322d446d8eece430ff',
'series': 'Upper Middle Bogan',
'season': 'Series 1',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 8,
}, {
@@ -386,7 +384,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
'series': '7.30 Mark Humphries Satire',
'season': 'Episodes',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 15,
}]
@@ -398,7 +396,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
webpage, 'initial state')
video_data = self._parse_json(
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded']
highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])

2
yt_dlp/extractor/abcnews.py
View File

@@ -58,7 +58,7 @@ class AbcNewsVideoIE(AMPIE):
display_id = mobj.group('display_id')
video_id = mobj.group('id')
info_dict = self._extract_feed_info(
'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
f'http://abcnews.go.com/video/itemfeed?id={video_id}')
info_dict.update({
'id': video_id,
'display_id': display_id,

5
yt_dlp/extractor/abcotvs.py
View File

@@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
int_or_none,
@@ -57,11 +56,11 @@ class ABCOTVSIE(InfoExtractor):
data = self._download_json(
'https://api.abcotvs.com/v2/content', display_id, query={
'id': video_id,
'key': 'otv.web.%s.story' % station,
'key': f'otv.web.{station}.story',
'station': station,
})['data']
video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
video_id = str(dict_get(video, ('id', 'publishedKey'), video_id))
title = video.get('title') or video['linkText']
formats = []

93
yt_dlp/extractor/abematv.py
View File

@@ -9,12 +9,12 @@ import re
import struct
import time
import urllib.parse
import urllib.request
import urllib.response
import uuid
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..networking import RequestHandler, Response
from ..networking.exceptions import TransportError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@@ -26,37 +26,36 @@ from ..utils import (
traverse_obj,
update_url_query,
)
from ..utils.networking import clean_proxies
def add_opener(ydl, handler): # FIXME: Create proper API in .networking
"""Add a handler for opening URLs, like _download_webpage"""
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
rh = ydl._request_director.handlers['Urllib']
if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
return
headers = ydl.params['http_headers'].copy()
proxies = ydl.proxies.copy()
clean_proxies(proxies, headers)
opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
assert isinstance(opener, urllib.request.OpenerDirector)
opener.add_handler(handler)
rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
class AbemaLicenseRH(RequestHandler):
_SUPPORTED_URL_SCHEMES = ('abematv-license',)
_SUPPORTED_PROXY_SCHEMES = None
_SUPPORTED_FEATURES = None
RH_NAME = 'abematv_license'
_STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
_HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
class AbemaLicenseHandler(urllib.request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protocol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
super().__init__(**kwargs)
self.ie = ie
def _send(self, request):
url = request.url
ticket = urllib.parse.urlparse(url).netloc
try:
response_data = self._get_videokey_from_ticket(ticket)
except ExtractorError as e:
raise TransportError(cause=e.cause) from e
except (IndexError, KeyError, TypeError) as e:
raise TransportError(cause=repr(e)) from e
return Response(
io.BytesIO(response_data), url,
headers={'Content-Length': str(len(response_data))})
def _get_videokey_from_ticket(self, ticket):
to_show = self.ie.get_param('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show)
@@ -66,31 +65,23 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
query={'t': media_token},
data=json.dumps({
'kv': 'a',
'lt': ticket
}).encode('utf-8'),
'lt': ticket,
}).encode(),
headers={
'Content-Type': 'application/json',
})
res = decode_base_n(license_response['k'], table=self.STRTABLE)
res = decode_base_n(license_response['k'], table=self._STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new(
binascii.unhexlify(self.HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode('utf-8'),
binascii.unhexlify(self._HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode(),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': str(len(response_data)),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'abematv'
@@ -103,11 +94,11 @@ class AbemaTVBaseIE(InfoExtractor):
@classmethod
def _generate_aks(cls, deviceid):
deviceid = deviceid.encode('utf-8')
deviceid = deviceid.encode()
# add 1 hour and then drop minute and secs
ts_1hour = int((time_seconds() // 3600 + 1) * 3600)
time_struct = time.gmtime(ts_1hour)
ts_1hour_str = str(ts_1hour).encode('utf-8')
ts_1hour_str = str(ts_1hour).encode()
tmp = None
@@ -119,7 +110,7 @@ class AbemaTVBaseIE(InfoExtractor):
def mix_tmp(count):
nonlocal tmp
for i in range(count):
for _ in range(count):
mix_once(tmp)
def mix_twist(nonce):
@@ -139,7 +130,7 @@ class AbemaTVBaseIE(InfoExtractor):
if self._USERTOKEN:
return self._USERTOKEN
add_opener(self._downloader, AbemaLicenseHandler(self))
self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
username, _ = self._get_login_info()
auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
@@ -160,7 +151,7 @@ class AbemaTVBaseIE(InfoExtractor):
data=json.dumps({
'deviceId': self._DEVICE_ID,
'applicationKeySecret': aks,
}).encode('utf-8'),
}).encode(),
headers={
'Content-Type': 'application/json',
})
@@ -180,7 +171,7 @@ class AbemaTVBaseIE(InfoExtractor):
'osLang': 'ja_JP',
'osTimezone': 'Asia/Tokyo',
'appId': 'tv.abema',
'appVersion': '3.27.1'
'appVersion': '3.27.1',
}, headers={
'Authorization': f'bearer {self._get_device_token()}',
})['token']
@@ -202,8 +193,8 @@ class AbemaTVBaseIE(InfoExtractor):
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password
}).encode('utf-8'), headers={
'password': password,
}).encode(), headers={
'Authorization': f'bearer {self._get_device_token()}',
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
@@ -344,7 +335,7 @@ class AbemaTVIE(AbemaTVBaseIE):
description = self._html_search_regex(
(r'<p\s+class="com-video-EpisodeDetailsBlock__content"><span\s+class=".+?">(.+?)</span></p><div',
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div',),
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div'),
webpage, 'description', default=None, group=1)
if not description:
og_desc = self._html_search_meta(
@@ -368,6 +359,7 @@ class AbemaTVIE(AbemaTVBaseIE):
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
availability = 'public'
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
@@ -389,6 +381,7 @@ class AbemaTVIE(AbemaTVBaseIE):
if 3 not in ondemand_types:
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
info.update(traverse_obj(api_response, {
'series': ('series', 'title'),
'season': ('season', 'name'),
@@ -408,6 +401,7 @@ class AbemaTVIE(AbemaTVBaseIE):
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
@@ -425,6 +419,7 @@ class AbemaTVIE(AbemaTVBaseIE):
'description': description,
'formats': formats,
'is_live': is_live,
'availability': availability,
})
return info

8
yt_dlp/extractor/acast.py
View File

@@ -67,7 +67,7 @@ class ACastIE(ACastBaseIE):
'display_id': '2.raggarmordet-rosterurdetforflutna',
'season_number': 4,
'season': 'Season 4',
}
},
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
@@ -93,13 +93,13 @@ class ACastIE(ACastBaseIE):
'series': 'Democracy Sausage with Mark Kenny',
'timestamp': 1684826362,
'description': 'md5:feabe1fc5004c78ee59c84a46bf4ba16',
}
},
}]
def _real_extract(self, url):
channel, display_id = self._match_valid_url(url).groups()
episode = self._call_api(
'%s/episodes/%s' % (channel, display_id),
f'{channel}/episodes/{display_id}',
display_id, {'showInfo': 'true'})
return self._extract_episode(
episode, self._extract_show_info(episode.get('show') or {}))
@@ -130,7 +130,7 @@ class ACastChannelIE(ACastBaseIE):
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
return False if ACastIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
show_slug = self._match_id(url)

4
yt_dlp/extractor/acfun.py
View File

@@ -25,7 +25,7 @@ class AcFunVideoBaseIE(InfoExtractor):
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'tbr': float_or_none(video.get('avgBitrate')),
**parse_codecs(video.get('codecs', ''))
**parse_codecs(video.get('codecs', '')),
})
return {
@@ -77,7 +77,7 @@ class AcFunVideoIE(AcFunVideoBaseIE):
'comment_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
'description': 'md5:67583aaf3a0f933bd606bc8a2d3ebb17',
}
},
}]
def _real_extract(self, url):

42
yt_dlp/extractor/adn.py
View File

@@ -7,7 +7,6 @@ import time
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import compat_b64decode
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
@@ -17,6 +16,7 @@ from ..utils import (
float_or_none,
int_or_none,
intlist_to_bytes,
join_nonempty,
long_to_bytes,
parse_iso8601,
pkcs1pad,
@@ -49,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
class ADNIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '9841',
@@ -71,10 +71,10 @@ class ADNIE(ADNBaseIE):
},
'skip': 'Only available in French and German speaking Europe',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}, {
'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1',
'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1',
'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
'info_dict': {
'id': '23550',
@@ -111,9 +111,9 @@ class ADNIE(ADNBaseIE):
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
base64.b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + '7fac1178830cfe0c'),
compat_b64decode(enc_subtitles[:24])))
base64.b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
if not subtitles_json:
return None
@@ -136,7 +136,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
if start is None or end is None or text is None:
continue
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
ssa += os.linesep + 'Dialogue: Marked=0,{},{},Default,,0,0,0,,{}{}'.format(
ass_subtitles_timecode(start),
ass_subtitles_timecode(end),
'{\\a%d}' % alignment if alignment != 2 else '',
@@ -178,7 +178,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
def _real_extract(self, url):
lang, video_id = self._match_valid_url(url).group('lang', 'id')
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
player = self._download_json(
video_base_url + 'configuration', video_id,
'Downloading player config JSON metadata',
@@ -218,13 +218,13 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization,
'X-Target-Distribution': lang,
**self._HEADERS
'X-Target-Distribution': lang or 'fr',
**self._HEADERS,
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
'source': 'Web',
})
break
except ExtractorError as e:
@@ -256,7 +256,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
for quality, load_balancer_url in qualities.items():
load_balancer_data = self._download_json(
load_balancer_url, video_id,
'Downloading %s %s JSON metadata' % (format_id, quality),
f'Downloading {format_id} {quality} JSON metadata',
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
@@ -276,7 +276,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
self.raise_login_required('This video requires a subscription', method='password')
video = (self._download_json(
self._API_BASE_URL + 'video/%s' % video_id, video_id,
self._API_BASE_URL + f'video/{video_id}', video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
show = video.get('show') or {}
@@ -299,9 +299,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
class ADNSeasonIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new',
'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new',
'playlist_count': 12,
'info_dict': {
'id': '911',
@@ -319,8 +319,8 @@ class ADNSeasonIE(ADNBaseIE):
episodes = self._download_json(
f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
'Downloading episode list', headers={
'X-Target-Distribution': lang,
**self._HEADERS
'X-Target-Distribution': lang or 'fr',
**self._HEADERS,
}, query={
'order': 'asc',
'limit': '-1',
@@ -328,8 +328,8 @@ class ADNSeasonIE(ADNBaseIE):
def entries():
for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
yield self.url_result(
f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
ADNIE, episode_id)
yield self.url_result(join_nonempty(
'https://animationdigitalnetwork.com', lang, 'video',
video_show_slug, episode_id, delim='/'), ADNIE, episode_id)
return self.playlist_result(entries(), show_id, show.get('title'))

10
yt_dlp/extractor/adobeconnect.py
View File

@@ -1,8 +1,6 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
class AdobeConnectIE(InfoExtractor):
@@ -12,13 +10,13 @@ class AdobeConnectIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_extract_title(webpage)
qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
qs = urllib.parse.parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
is_live = qs.get('isLive', ['false'])[0] == 'true'
formats = []
for con_string in qs['conStrings'][0].split(','):
formats.append({
'format_id': con_string.split('://')[0],
'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'app': urllib.parse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'ext': 'flv',
'play_path': 'mp4:' + qs['streamName'][0],
'rtmp_conn': 'S:' + qs['ticket'][0],

866
yt_dlp/extractor/adobepass.py
View File

File diff suppressed because it is too large Load Diff

5
yt_dlp/extractor/adobetv.py
View File

@@ -2,7 +2,6 @@ import functools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ISO639Utils,
OnDemandPagedList,
@@ -36,7 +35,7 @@ class AdobeTVBaseIE(InfoExtractor):
return subtitles
def _parse_video_data(self, video_data):
video_id = compat_str(video_data['id'])
video_id = str(video_data['id'])
title = video_data['title']
s3_extracted = False
@@ -151,7 +150,7 @@ class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, 'Download Page %d' % page):
self._RESOURCE, display_id, query, f'Download Page {page}'):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):

6
yt_dlp/extractor/adultswim.py
View File

@@ -91,7 +91,7 @@ class AdultSwimIE(TurnerBaseIE):
getShowBySlug(slug:"%s") {
%%s
}
}''' % show_path
}''' % show_path # noqa: UP031
if episode_path:
query = query % '''title
getVideoBySlug(slug:"%s") {
@@ -128,7 +128,7 @@ class AdultSwimIE(TurnerBaseIE):
episode_title = title = video_data['title']
series = show_data.get('title')
if series:
title = '%s - %s' % (series, title)
title = f'{series} - {title}'
info = {
'id': video_id,
'title': title,
@@ -191,7 +191,7 @@ class AdultSwimIE(TurnerBaseIE):
if not slug:
continue
entries.append(self.url_result(
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
f'http://adultswim.com/videos/{show_path}/{slug}',
'AdultSwim', video.get('_id')))
return self.playlist_result(
entries, show_path, show_data.get('title'),

34
yt_dlp/extractor/aenetworks.py
View File

@@ -73,8 +73,8 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
filter_value, query={'filter[%s]' % filter_key: filter_value})
f'https://feeds.video.aetnd.com/api/v2/{brand}/videos',
filter_value, query={f'filter[{filter_key}]': filter_value})
result = traverse_obj(
result, ('results',
lambda k, v: k == 0 and v[filter_key] == filter_value),
@@ -142,7 +142,7 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'Geo-restricted - This content is not available in your location.'
'skip': 'Geo-restricted - This content is not available in your location.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
@@ -171,28 +171,28 @@ class AENetworksIE(AENetworksBaseIE):
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
'only_matching': True,
}]
def _real_extract(self, url):
@@ -209,14 +209,14 @@ class AENetworksListBaseIE(AENetworksBaseIE):
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}''' % (resource, slug, fields), # noqa: UP031
}))['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
base_url = f'http://watch.{domain}'
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
@@ -248,10 +248,10 @@ class AENetworksCollectionIE(AENetworksListBaseIE):
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
'only_matching': True,
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
@@ -309,7 +309,7 @@ class HistoryTopicIE(AENetworksBaseIE):
'info_dict': {
'id': '40700995724',
'ext': 'mp4',
'title': "History of Valentine’s Day",
'title': 'History of Valentine’s Day',
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
@@ -364,6 +364,6 @@ class BiographyIE(AENetworksBaseIE):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_url = self._search_regex(
r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
rf'<phoenix-iframe[^>]+src="({HistoryPlayerIE._VALID_URL})',
webpage, 'player URL')
return self.url_result(player_url, HistoryPlayerIE.ie_key())

8
yt_dlp/extractor/aeonco.py
View File

@@ -16,8 +16,8 @@ class AeonCoIE(InfoExtractor):
'uploader': 'Semiconductor',
'uploader_id': 'semiconductor',
'uploader_url': 'https://vimeo.com/semiconductor',
'duration': 348
}
'duration': 348,
},
}, {
'url': 'https://aeon.co/videos/dazzling-timelapse-shows-how-microbes-spoil-our-food-and-sometimes-enrich-it',
'md5': '03582d795382e49f2fd0b427b55de409',
@@ -29,8 +29,8 @@ class AeonCoIE(InfoExtractor):
'uploader': 'Aeon Video',
'uploader_id': 'aeonvideo',
'uploader_url': 'https://vimeo.com/aeonvideo',
'duration': 1344
}
'duration': 1344,
},
}, {
'url': 'https://aeon.co/videos/chew-over-the-prisoners-dilemma-and-see-if-you-can-find-the-rational-path-out',
'md5': '1cfda0bf3ae24df17d00f2c0cb6cc21b',

57
yt_dlp/extractor/afreecatv.py
View File

@@ -1,6 +1,7 @@
import functools
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
ExtractorError,
OnDemandPagedList,
@@ -55,9 +56,16 @@ class AfreecaTVBaseIE(InfoExtractor):
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
f'Unable to login: {self.IE_NAME} said: {error}',
expected=True)
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
return self._download_json(Request(
f'https://api.m.afreecatv.com/{endpoint}',
data=data, headers=headers, query=query,
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
@@ -72,7 +80,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)
(?P<id>\d+)/?(?:$|[?#&])
'''
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
@@ -184,9 +192,9 @@ class AfreecaTVIE(AfreecaTVBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api.m.afreecatv.com/station/video/a/view', video_id,
headers={'Referer': url}, data=urlencode_postdata({
data = self._call_api(
'station/video/a/view', video_id, headers={'Referer': url},
data=urlencode_postdata({
'nTitleNo': video_id,
'nApiLevel': 10,
}))['data']
@@ -227,7 +235,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
**traverse_obj(file_element, {
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('file_start', {unified_timestamp}),
})
}),
})
if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
@@ -253,6 +261,43 @@ class AfreecaTVIE(AfreecaTVBaseIE):
return self.playlist_result(entries, video_id, multi_video=True, **common_info)
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:catchstory'
IE_DESC = 'afreecatv.com catch story'
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
_TESTS = [{
'url': 'https://vod.afreecatv.com/player/103247/catchstory',
'info_dict': {
'id': '103247',
},
'playlist_count': 2,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._call_api(
'catchstory/a/view', video_id, headers={'Referer': url},
query={'aStoryListIdx': '', 'nStoryIdx': video_id})
return self.playlist_result(self._entries(data), video_id)
@staticmethod
def _entries(data):
# 'files' is always a list with 1 element
yield from traverse_obj(data, (
'data', lambda _, v: v['story_type'] == 'catch',
'catch_list', lambda _, v: v['files'][0]['file'], {
'id': ('files', 0, 'file_info_key', {str}),
'url': ('files', 0, 'file', {url_or_none}),
'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}),
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('writer_id', {str}),
'thumbnail': ('thumb', {url_or_none}),
'timestamp': ('write_timestamp', {int_or_none}),
}))
class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live'
IE_DESC = 'afreecatv.com livestreams'

6
yt_dlp/extractor/agora.py
View File

@@ -168,7 +168,7 @@ class TokFMPodcastIE(InfoExtractor):
for ext in ('aac', 'mp3'):
url_data = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
media_id, 'Downloading podcast %s URL' % ext)
media_id, f'Downloading podcast {ext} URL')
# prevents inserting the mp3 (default) multiple times
if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
formats.append({
@@ -206,8 +206,8 @@ class TokFMAuditionIE(InfoExtractor):
}
@staticmethod
def _create_url(id):
return f'https://audycje.tokfm.pl/audycja/{id}'
def _create_url(video_id):
return f'https://audycje.tokfm.pl/audycja/{video_id}'
def _real_extract(self, url):
audition_id = self._match_id(url)

4
yt_dlp/extractor/airtv.py
View File

@@ -26,7 +26,7 @@ class AirTVIE(InfoExtractor):
'view_count': int,
'thumbnail': 'https://cdn-sp-gcs.air.tv/videos/W/8/W87jcWleSn2hXZN47zJZsQ/b13fc56464f47d9d62a36d110b9b5a72-4096x2160_9.jpg',
'timestamp': 1664792603,
}
},
}, {
# with youtube_id
'url': 'https://www.air.tv/watch?v=sv57EC8tRXG6h8dNXFUU1Q',
@@ -54,7 +54,7 @@ class AirTVIE(InfoExtractor):
'channel': 'Newsflare',
'duration': 37,
'upload_date': '20180511',
}
},
}]
def _get_formats_and_subtitle(self, json_data, video_id):

2
yt_dlp/extractor/aitube.py
View File

@@ -22,7 +22,7 @@ class AitubeKZVideoIE(InfoExtractor):
'timestamp': 1667370519,
'title': 'Ангел хранитель 1 серия',
'channel_follower_count': int,
}
},
}, {
# embed url
'url': 'https://aitube.kz/embed/?id=9291d29b-c038-49a1-ad42-3da2051d353c',

3
yt_dlp/extractor/aliexpress.py
View File

@@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
try_get,
@@ -44,7 +43,7 @@ class AliExpressLiveIE(InfoExtractor):
'title': title,
'thumbnail': data.get('coverUrl'),
'uploader': try_get(
data, lambda x: x['followBar']['name'], compat_str),
data, lambda x: x['followBar']['name'], str),
'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
'formats': formats,
}

14
yt_dlp/extractor/aljazeera.py
View File

@@ -18,7 +18,7 @@ class AlJazeeraIE(InfoExtractor):
'timestamp': 1636219149,
'description': 'U sarajevskim naseljima Rajlovac i Reljevo stambeni objekti, ali i industrijska postrojenja i dalje su pod vodom.',
'upload_date': '20211106',
}
},
}, {
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/djokovic-usao-u-finale-mastersa-u-parizu',
'info_dict': {
@@ -33,7 +33,7 @@ class AlJazeeraIE(InfoExtractor):
BRIGHTCOVE_URL_RE = r'https?://players.brightcove.net/(?P<account>\d+)/(?P<player_id>[a-zA-Z0-9]+)_(?P<embed>[^/]+)/index.html\?videoId=(?P<id>\d+)'
def _real_extract(self, url):
base, post_type, id = self._match_valid_url(url).groups()
base, post_type, display_id = self._match_valid_url(url).groups()
wp = {
'balkans.aljazeera.net': 'ajb',
'chinese.aljazeera.net': 'chinese',
@@ -47,11 +47,11 @@ class AlJazeeraIE(InfoExtractor):
'news': 'news',
}[post_type.split('/')[0]]
video = self._download_json(
f'https://{base}/graphql', id, query={
f'https://{base}/graphql', display_id, query={
'wp-site': wp,
'operationName': 'ArchipelagoSingleArticleQuery',
'variables': json.dumps({
'name': id,
'name': display_id,
'postType': post_type,
}),
}, headers={
@@ -64,7 +64,7 @@ class AlJazeeraIE(InfoExtractor):
embed = 'default'
if video_id is None:
webpage = self._download_webpage(url, id)
webpage = self._download_webpage(url, display_id)
account, player_id, embed, video_id = self._search_regex(self.BRIGHTCOVE_URL_RE, webpage, 'video id',
group=(1, 2, 3, 4), default=(None, None, None, None))
@@ -73,11 +73,11 @@ class AlJazeeraIE(InfoExtractor):
return {
'_type': 'url_transparent',
'url': url,
'ie_key': 'Generic'
'ie_key': 'Generic',
}
return {
'_type': 'url_transparent',
'url': f'https://players.brightcove.net/{account}/{player_id}_{embed}/index.html?videoId={video_id}',
'ie_key': 'BrightcoveNew'
'ie_key': 'BrightcoveNew',
}

5
yt_dlp/extractor/allocine.py
View File

@@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
qualities,
@@ -95,11 +94,11 @@ class AllocineIE(InfoExtractor):
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
video, lambda x: x['added_at']['date'], str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
f'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media={video_id}', display_id)
title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
for key, value in media_data['video'].items():
if not key.endswith('Path'):

26
yt_dlp/extractor/allstar.py
View File

@@ -33,27 +33,27 @@ _QUERIES = {
video: getClip(clipIdentifier: $id) {
%s %s
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'montage': '''query ($id: String!) {
video: getMontage(clipIdentifier: $id) {
%s
}
}''' % _FIELDS,
}''' % _FIELDS, # noqa: UP031
'Clips': '''query ($page: Int!, $user: String!, $game: Int) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: false, game: $game) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'Montages': '''query ($page: Int!, $user: String!) {
videos: montages(search: createdDate, page: $page, user: $user) {
data { %s }
}
}''' % _FIELDS,
}''' % _FIELDS, # noqa: UP031
'Mobile Clips': '''query ($page: Int!, $user: String!) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: true) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
}
@@ -121,7 +121,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230425',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/clip?clip=8LJLY4JKB',
'info_dict': {
@@ -139,7 +139,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230702',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/montage?montage=643e64089da7e9363e1fa66c',
'info_dict': {
@@ -155,7 +155,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230418',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/montage?montage=RILJMH6QOS',
'info_dict': {
@@ -171,7 +171,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230703',
'view_count': int,
}
},
}]
def _real_extract(self, url):
@@ -191,28 +191,28 @@ class AllstarProfileIE(AllstarBaseIE):
'id': '62b8bdfc9021052f7905882d-clips',
'title': 'cherokee - Clips',
},
'playlist_mincount': 15
'playlist_mincount': 15,
}, {
'url': 'https://allstar.gg/u/cherokee?game=730&view=Clips',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-clips-730',
'title': 'cherokee - Clips - 730',
},
'playlist_mincount': 15
'playlist_mincount': 15,
}, {
'url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d?view=Montages',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-montages',
'title': 'cherokee - Montages',
},
'playlist_mincount': 4
'playlist_mincount': 4,
}, {
'url': 'https://allstar.gg/profile?user=cherokee&view=Mobile Clips',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-mobile',
'title': 'cherokee - Mobile Clips',
},
'playlist_mincount': 1
'playlist_mincount': 1,
}]
_PAGE_SIZE = 10

2
yt_dlp/extractor/alphaporno.py
View File

@@ -25,7 +25,7 @@ class AlphaPornoIE(InfoExtractor):
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
},
}
def _real_extract(self, url):

6
yt_dlp/extractor/alsace20tv.py
View File

@@ -12,7 +12,7 @@ from ..utils import (
class Alsace20TVBaseIE(InfoExtractor):
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
f'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key={video_id}&habillage=0&mode=html',
video_id) or {}
title = info.get('titre')
@@ -24,9 +24,9 @@ class Alsace20TVBaseIE(InfoExtractor):
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
thumbnail = url_or_none(dict_get(info, ('image', 'preview')) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
upload_date = unified_strdate(f'20{upload_date[:2]}-{upload_date[2:4]}-{upload_date[4:]}') if upload_date else None
return {
'id': video_id,
'title': title,

2
yt_dlp/extractor/altcensored.py
View File

@@ -34,7 +34,7 @@ class AltCensoredIE(InfoExtractor):
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int,
'categories': ['News & Politics'],
}
},
}]
def _real_extract(self, url):

16
yt_dlp/extractor/alura.py
View File

@@ -1,7 +1,7 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
clean_html,
@@ -21,7 +21,7 @@ class AluraIE(InfoExtractor):
'info_dict': {
'id': '60095',
'ext': 'mp4',
'title': 'Referências, ref-set e alter'
'title': 'Referências, ref-set e alter',
},
'skip': 'Requires alura account credentials'},
{
@@ -30,7 +30,7 @@ class AluraIE(InfoExtractor):
'only_matching': True},
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True}
'only_matching': True},
]
def _real_extract(self, url):
@@ -62,7 +62,7 @@ class AluraIE(InfoExtractor):
return {
'id': video_id,
'title': video_title,
"formats": formats
'formats': formats,
}
def _perform_login(self, username, password):
@@ -91,7 +91,7 @@ class AluraIE(InfoExtractor):
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
post_url = urllib.parse.urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in',
@@ -103,7 +103,7 @@ class AluraIE(InfoExtractor):
r'(?s)<p[^>]+class="alert-message[^"]*">(.+?)</p>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError(f'Unable to login: {error}', expected=True)
raise ExtractorError('Unable to log in')
@@ -119,7 +119,7 @@ class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE
@classmethod
def suitable(cls, url):
return False if AluraIE.suitable(url) else super(AluraCourseIE, cls).suitable(url)
return False if AluraIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
@@ -157,7 +157,7 @@ class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE
'url': video_url,
'id_key': self.ie_key(),
'chapter': chapter,
'chapter_number': chapter_number
'chapter_number': chapter_number,
}
entries.append(entry)
return self.playlist_result(entries, course_path, course_title)

2
yt_dlp/extractor/amadeustv.py
View File

@@ -24,7 +24,7 @@ class AmadeusTVIE(InfoExtractor):
'display_id': '65091a87ff85af59d9fc54c3',
'view_count': int,
'description': 'md5:a0357b9c215489e2067cbae0b777bb95',
}
},
}]
def _real_extract(self, url):

10
yt_dlp/extractor/amara.py
View File

@@ -25,7 +25,7 @@ class AmaraIE(InfoExtractor):
'uploader': 'PBS NewsHour',
'uploader_id': 'PBSNewsHour',
'timestamp': 1549639570,
}
},
}, {
# Vimeo
'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011',
@@ -40,8 +40,8 @@ class AmaraIE(InfoExtractor):
'timestamp': 1294763658,
'upload_date': '20110111',
'uploader': 'Sam Morrill',
'uploader_id': 'sammorrill'
}
'uploader_id': 'sammorrill',
},
}, {
# Direct Link
'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/',
@@ -55,13 +55,13 @@ class AmaraIE(InfoExtractor):
'subtitles': dict,
'upload_date': '20091007',
'timestamp': 1254942511,
}
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(
'https://amara.org/api/videos/%s/' % video_id,
f'https://amara.org/api/videos/{video_id}/',
video_id, query={'format': 'json'})
title = meta['title']
video_url = meta['all_urls'][0]

8
yt_dlp/extractor/amazon.py
View File

@@ -61,13 +61,13 @@ class AmazonStoreIE(InfoExtractor):
}]
def _real_extract(self, url):
id = self._match_id(url)
playlist_id = self._match_id(url)
for retry in self.RetryManager():
webpage = self._download_webpage(url, id)
webpage = self._download_webpage(url, playlist_id)
try:
data_json = self._search_json(
r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', id,
r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', playlist_id,
transform_source=js_to_json)
except ExtractorError as e:
retry.error = e
@@ -81,7 +81,7 @@ class AmazonStoreIE(InfoExtractor):
'height': int_or_none(video.get('videoHeight')),
'width': int_or_none(video.get('videoWidth')),
} for video in (data_json.get('videos') or []) if video.get('isVideo') and video.get('url')]
return self.playlist_result(entries, playlist_id=id, playlist_title=data_json.get('title'))
return self.playlist_result(entries, playlist_id=playlist_id, playlist_title=data_json.get('title'))
class AmazonReviewsIE(InfoExtractor):

2
yt_dlp/extractor/amazonminitv.py
View File

@@ -25,7 +25,7 @@ class AmazonMiniTVBaseIE(InfoExtractor):
asin, note=note, headers={
'Content-Type': 'application/json',
'currentpageurl': '/',
'currentplatform': 'dWeb'
'currentplatform': 'dWeb',
}, data=json.dumps(data).encode() if data else None,
query=None if data else {
'deviceType': 'A1WMMUXPCUJL4N',

12
yt_dlp/extractor/amcnetworks.py
View File

@@ -64,8 +64,8 @@ class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
site, display_id = self._match_valid_url(url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
page_data = self._download_json(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
% (requestor_id.lower(), display_id), display_id)['data']
f'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/{requestor_id.lower()}/url/{display_id}',
display_id)['data']
properties = page_data.get('properties') or {}
query = {
'mbr': 'true',
@@ -76,15 +76,15 @@ class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
try:
for v in page_data['children']:
if v.get('type') == 'video-player':
releasePid = v['properties']['currentVideo']['meta']['releasePid']
tp_path = 'M_UwQC/' + releasePid
release_pid = v['properties']['currentVideo']['meta']['releasePid']
tp_path = 'M_UwQC/' + release_pid
media_url = 'https://link.theplatform.com/s/' + tp_path
video_player_count += 1
except KeyError:
pass
if video_player_count > 1:
self.report_warning(
'The JSON data has %d video players. Only one will be extracted' % video_player_count)
f'The JSON data has {video_player_count} video players. Only one will be extracted')
# Fall back to videoPid if releasePid not found.
# TODO: Fall back to videoPid if releasePid manifest uses DRM.
@@ -131,7 +131,7 @@ class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
ns = next(iter(ns_keys))
episode = theplatform_metadata.get(ns + '$episodeTitle') or None
episode_number = int_or_none(
theplatform_metadata.get(ns + '$episode'))

14
yt_dlp/extractor/americastestkitchen.py
View File

@@ -87,13 +87,13 @@ class AmericasTestKitchenIE(InfoExtractor):
resource_type = 'episodes'
resource = self._download_json(
'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
f'https://www.americastestkitchen.com/api/v6/{resource_type}/{video_id}', video_id)
video = resource['video'] if is_episode else resource
episode = resource if is_episode else resource.get('episode') or {}
return {
'_type': 'url_transparent',
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'url': 'https://player.zype.com/embed/{}.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ'.format(video['zypeId']),
'ie_key': 'Zype',
'description': clean_html(video.get('description')),
'timestamp': unified_timestamp(video.get('publishDate')),
@@ -174,22 +174,22 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
]
if season_number:
playlist_id = 'season_%d' % season_number
playlist_title = 'Season %d' % season_number
playlist_id = f'season_{season_number}'
playlist_title = f'Season {season_number}'
facet_filters.append('search_season_list:' + playlist_title)
else:
playlist_id = show
playlist_title = title
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
f'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_{slug}_season_desc_production',
playlist_id, headers={
'Origin': 'https://www.americastestkitchen.com',
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps(facet_filters),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title,search_atk_episode_season' % slug,
'attributesToRetrieve': f'description,search_{slug}_episode_number,search_document_date,search_url,title,search_atk_episode_season',
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
@@ -207,7 +207,7 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
'season_number': season_number,
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
'episode_number': int_or_none(episode.get(f'search_{slug}_episode_number')),
'ie_key': AmericasTestKitchenIE.ie_key(),
}

4
yt_dlp/extractor/amp.py
View File

@@ -19,12 +19,12 @@ class AMPIE(InfoExtractor): # XXX: Conventionally, base classes should end with
'Unable to download Akamai AMP feed', transform_source=strip_jsonp)
item = feed.get('channel', {}).get('item')
if not item:
raise ExtractorError('%s said: %s' % (self.IE_NAME, feed['error']))
raise ExtractorError('{} said: {}'.format(self.IE_NAME, feed['error']))
video_id = item['guid']
def get_media_node(name, default=None):
media_name = 'media-%s' % name
media_name = f'media-{name}'
media_group = item.get('media-group') or item
return media_group.get(media_name) or item.get(media_name) or item.get(name, default)

6
yt_dlp/extractor/anchorfm.py
View File

@@ -29,7 +29,7 @@ class AnchorFMEpisodeIE(InfoExtractor):
'release_date': '20230121',
'release_timestamp': 1674285179,
'episode_id': 'e1tpt3d',
}
},
}, {
# embed url
'url': 'https://anchor.fm/apakatatempo/embed/episodes/S2E75-Perang-Bintang-di-Balik-Kasus-Ferdy-Sambo-dan-Ismail-Bolong-e1shjqd',
@@ -50,7 +50,7 @@ class AnchorFMEpisodeIE(InfoExtractor):
'season': 'Season 2',
'season_number': 2,
'episode_id': 'e1shjqd',
}
},
}]
_WEBPAGE_TESTS = [{
@@ -72,7 +72,7 @@ class AnchorFMEpisodeIE(InfoExtractor):
'thumbnail': 'https://s3-us-west-2.amazonaws.com/anchor-generated-image-bank/production/podcast_uploaded_episode400/2627805/2627805-1671590688729-4db3882ac9e4b.jpg',
'uploader': 'Podcast Tempo',
'channel': 'apakatatempo',
}
},
}]
def _real_extract(self, url):

10
yt_dlp/extractor/angel.py
View File

@@ -15,8 +15,8 @@ class AngelIE(InfoExtractor):
'title': 'Tuttle Twins Season 1, Episode 1: When Laws Give You Lemons',
'description': 'md5:73b704897c20ab59c433a9c0a8202d5e',
'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
'duration': 1359.0
}
'duration': 1359.0,
},
}, {
'url': 'https://www.angel.com/watch/the-chosen/episode/8dfb714d-bca5-4812-8125-24fb9514cd10/season-1/episode-1/i-have-called-you-by-name',
'md5': 'e4774bad0a5f0ad2e90d175cafdb797d',
@@ -26,8 +26,8 @@ class AngelIE(InfoExtractor):
'title': 'The Chosen Season 1, Episode 1: I Have Called You By Name',
'description': 'md5:aadfb4827a94415de5ff6426e6dee3be',
'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
'duration': 3276.0
}
'duration': 3276.0,
},
}]
def _real_extract(self, url):
@@ -44,7 +44,7 @@ class AngelIE(InfoExtractor):
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'formats': formats,
'subtitles': subtitles
'subtitles': subtitles,
}
# Angel uses cloudinary in the background and supports image transformations.

2
yt_dlp/extractor/antenna.py
View File

@@ -105,7 +105,7 @@ class Ant1NewsGrArticleIE(AntennaBaseIE):
info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage))
if not embed_urls:
raise ExtractorError('no videos found for %s' % video_id, expected=True)
raise ExtractorError(f'no videos found for {video_id}', expected=True)
return self.playlist_from_matches(
embed_urls, video_id, info.get('title'), ie=Ant1NewsGrEmbedIE.ie_key(),
video_kwargs={'url_transparent': True, 'timestamp': info.get('timestamp')})

8
yt_dlp/extractor/anvato.py
View File

@@ -238,7 +238,7 @@ class AnvatoIE(InfoExtractor):
'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582',
}
def _generate_nfl_token(self, anvack, mcp_id):
@@ -255,7 +255,7 @@ class AnvatoIE(InfoExtractor):
token
}
}
}''' % (anvack, mcp_id),
}''' % (anvack, mcp_id), # noqa: UP031
}).encode(), headers={
'Authorization': auth_token,
'Content-Type': 'application/json',
@@ -299,7 +299,7 @@ class AnvatoIE(InfoExtractor):
return self._download_json(
video_data_url, video_id, transform_source=strip_jsonp, query=query,
data=json.dumps({'api': api}, separators=(',', ':')).encode('utf-8'))
data=json.dumps({'api': api}, separators=(',', ':')).encode())
def _get_anvato_videos(self, access_key, video_id, token):
video_data = self._get_video_json(access_key, video_id, token)
@@ -358,7 +358,7 @@ class AnvatoIE(InfoExtractor):
for caption in video_data.get('captions', []):
a_caption = {
'url': caption['url'],
'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None
'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None,
}
subtitles.setdefault(caption['language'], []).append(a_caption)
subtitles = self._merge_subtitles(subtitles, hls_subs, vtt_subs)

8
yt_dlp/extractor/aol.py
View File

@@ -30,7 +30,7 @@ class AolIE(YahooIE): # XXX: Do not subclass from concrete IE
'params': {
# m3u8 download
'skip_download': True,
}
},
}, {
# video with vidible ID
'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
@@ -46,7 +46,7 @@ class AolIE(YahooIE): # XXX: Do not subclass from concrete IE
'params': {
# m3u8 download
'skip_download': True,
}
},
}, {
'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
'only_matching': True,
@@ -83,10 +83,10 @@ class AolIE(YahooIE): # XXX: Do not subclass from concrete IE
return self._extract_yahoo_video(video_id, 'us')
response = self._download_json(
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
f'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/{video_id}/details',
video_id)['response']
if response['statusText'] != 'Ok':
raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
raise ExtractorError('{} said: {}'.format(self.IE_NAME, response['statusText']), expected=True)
video_data = response['data']
formats = []

4
yt_dlp/extractor/apa.py
View File

@@ -34,7 +34,7 @@ class APAIE(InfoExtractor):
video_id, base_url = mobj.group('id', 'base_url')
webpage = self._download_webpage(
'%s/player/%s' % (base_url, video_id), video_id)
f'{base_url}/player/{video_id}', video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
@@ -47,7 +47,7 @@ class APAIE(InfoExtractor):
def extract(field, name=None):
return self._search_regex(
r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
rf'\b{field}["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, name or field, default=None, group='value')
title = extract('title') or video_id

2
yt_dlp/extractor/applepodcasts.py
View File

@@ -24,7 +24,7 @@ class ApplePodcastsIE(InfoExtractor):
'duration': 6454,
'series': 'The Tim Dillon Show',
'thumbnail': 're:.+[.](png|jpe?g|webp)',
}
},
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'only_matching': True,

31
yt_dlp/extractor/appletrailers.py
View File

@@ -1,8 +1,8 @@
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
parse_duration,
@@ -64,7 +64,7 @@ class AppleTrailersIE(InfoExtractor):
'uploader_id': 'wb',
},
},
]
],
}, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': {
@@ -99,7 +99,7 @@ class AppleTrailersIE(InfoExtractor):
webpage = self._download_webpage(url, movie)
film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id')
film_data = self._download_json(
'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id,
f'http://trailers.apple.com/trailers/feeds/data/{film_id}.json',
film_id, fatal=False)
if film_data:
@@ -114,7 +114,7 @@ class AppleTrailersIE(InfoExtractor):
if not src:
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'format_id': f'{version}-{size}',
'url': re.sub(r'_(\d+p\.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
@@ -134,7 +134,7 @@ class AppleTrailersIE(InfoExtractor):
page_data = film_data.get('page', {})
return self.playlist_result(entries, film_id, page_data.get('movie_title'))
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
playlist_url = urllib.parse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
@@ -143,10 +143,9 @@ class AppleTrailersIE(InfoExtractor):
# like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m):
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
return 'iTunes.playURL({});'.format(m.group(1).replace('\'', '&#39;'))
s = re.sub(self._JSON_RE, _clean_json, s)
s = '<html>%s</html>' % s
return s
return f'<html>{s}</html>'
doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
playlist = []
@@ -170,18 +169,18 @@ class AppleTrailersIE(InfoExtractor):
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
settings_json_url = urllib.parse.urljoin(url, f'includes/settings/{trailer_id}.json')
settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
formats = []
for format in settings['metadata']['sizes']:
for fmt in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', format['src'])
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', fmt['src'])
formats.append({
'url': format_url,
'format': format['type'],
'width': int_or_none(format['width']),
'height': int_or_none(format['height']),
'format': fmt['type'],
'width': int_or_none(fmt['width']),
'height': int_or_none(fmt['height']),
})
playlist.append({
@@ -229,7 +228,7 @@ class AppleTrailersSectionIE(InfoExtractor):
'title': 'Movie Studios',
},
}
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>%s)' % '|'.join(_SECTIONS)
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/#section=(?P<id>{})'.format('|'.join(_SECTIONS))
_TESTS = [{
'url': 'http://trailers.apple.com/#section=justadded',
'info_dict': {
@@ -270,7 +269,7 @@ class AppleTrailersSectionIE(InfoExtractor):
def _real_extract(self, url):
section = self._match_id(url)
section_data = self._download_json(
'http://trailers.apple.com/trailers/home/feeds/%s.json' % self._SECTIONS[section]['feed_path'],
'http://trailers.apple.com/trailers/home/feeds/{}.json'.format(self._SECTIONS[section]['feed_path']),
section)
entries = [
self.url_result('http://trailers.apple.com' + e['location'])

105
yt_dlp/extractor/archiveorg.py
View File

@@ -1,10 +1,11 @@
from __future__ import annotations
import json
import re
import urllib.parse
from .common import InfoExtractor
from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
from ..compat import compat_urllib_parse_unquote
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
@@ -145,7 +146,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'Bells Of Rostov',
'ext': 'mp3',
},
'skip': 'restricted'
'skip': 'restricted',
}, {
'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02.+Song+And+Chorus+In+The+Polovetsian+Camp+From+%22Prince+Igor%22+(Act+2%2C+Scene+1).mp3',
'md5': '1d0aabe03edca83ca58d9ed3b493a3c3',
@@ -158,7 +159,7 @@ class ArchiveOrgIE(InfoExtractor):
'description': 'md5:012b2d668ae753be36896f343d12a236',
'upload_date': '20190928',
},
'skip': 'restricted'
'skip': 'restricted',
}, {
# Original formats are private
'url': 'https://archive.org/details/irelandthemakingofarepublic',
@@ -202,8 +203,8 @@ class ArchiveOrgIE(InfoExtractor):
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
'display_id': 'irelandthemakingofarepublicreel2.mov',
},
}
]
},
],
}]
@staticmethod
@@ -220,7 +221,7 @@ class ArchiveOrgIE(InfoExtractor):
def _real_extract(self, url):
video_id = urllib.parse.unquote_plus(self._match_id(url))
identifier, entry_id = (video_id.split('/', 1) + [None])[:2]
identifier, _, entry_id = video_id.partition('/')
# Archive.org metadata API doesn't clearly demarcate playlist entries
# or subtitle tracks, so we get them from the embeddable player.
@@ -246,7 +247,7 @@ class ArchiveOrgIE(InfoExtractor):
if track['kind'] != 'subtitles':
continue
entries[p['orig']][track['label']] = {
'url': 'https://archive.org/' + track['file'].lstrip('/')
'url': 'https://archive.org/' + track['file'].lstrip('/'),
}
metadata = self._download_json('http://archive.org/metadata/' + identifier, identifier)
@@ -293,7 +294,9 @@ class ArchiveOrgIE(InfoExtractor):
'height': int_or_none(f.get('width')),
'filesize': int_or_none(f.get('size'))})
extension = (f['name'].rsplit('.', 1) + [None])[1]
_, has_ext, extension = f['name'].rpartition('.')
if not has_ext:
extension = None
# We don't want to skip private formats if the user has access to them,
# however without access to an account with such privileges we can't implement/test this.
@@ -308,7 +311,7 @@ class ArchiveOrgIE(InfoExtractor):
'filesize': int_or_none(f.get('size')),
'protocol': 'https',
'source_preference': 0 if f.get('source') == 'original' else -1,
'format_note': f.get('source')
'format_note': f.get('source'),
})
for entry in entries.values():
@@ -371,7 +374,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/user/Zeurel',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'channel_url': 'https://www.youtube.com/channel/UCukCyHaD-bK3in_pKpfH9Eg',
}
},
}, {
# Internal link
'url': 'https://web.archive.org/web/2oe/http://wayback-fakeurl.archive.org/yt/97t7Xj_iBv0',
@@ -388,7 +391,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/user/1veritasium',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'channel_url': 'https://www.youtube.com/channel/UCHnyfMqiRRG1u-2MsSQLbXA',
}
},
}, {
# Video from 2012, webm format itag 45. Newest capture is deleted video, with an invalid description.
# Should use the date in the link. Title ends with '- Youtube'. Capture has description in eow-description
@@ -403,8 +406,8 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader_id': 'machinima',
'uploader_url': 'https://www.youtube.com/user/machinima',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'uploader': 'machinima'
}
'uploader': 'machinima',
},
}, {
# FLV video. Video file URL does not provide itag information
'url': 'https://web.archive.org/web/20081211103536/http://www.youtube.com/watch?v=jNQXAC9IVRw',
@@ -421,7 +424,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'channel_url': 'https://www.youtube.com/channel/UC4QobU6STFB0P71PMvOGN5A',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'uploader': 'jawed',
}
},
}, {
'url': 'https://web.archive.org/web/20110712231407/http://www.youtube.com/watch?v=lTx3G6h2xyA',
'info_dict': {
@@ -437,7 +440,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/user/itsmadeon',
'channel_url': 'https://www.youtube.com/channel/UCqMDNf3Pn5L7pcNkuSEeO3w',
'thumbnail': r're:https?://.*\.(jpg|webp)',
}
},
}, {
# First capture is of dead video, second is the oldest from CDX response.
'url': 'https://web.archive.org/https://www.youtube.com/watch?v=1JYutPM8O6E',
@@ -454,7 +457,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'channel_url': 'https://www.youtube.com/channel/UCdIaNUarhzLSXGoItz7BHVA',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'uploader': 'ETC News',
}
},
}, {
# First capture of dead video, capture date in link links to dead capture.
'url': 'https://web.archive.org/web/20180803221945/https://www.youtube.com/watch?v=6FPhZJGvf4E',
@@ -473,15 +476,15 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader': 'ETC News',
},
'expected_warnings': [
r'unable to download capture webpage \(it may not be archived\)'
]
r'unable to download capture webpage \(it may not be archived\)',
],
}, { # Very old YouTube page, has - YouTube in title.
'url': 'http://web.archive.org/web/20070302011044/http://youtube.com/watch?v=-06-KB9XTzg',
'info_dict': {
'id': '-06-KB9XTzg',
'ext': 'flv',
'title': 'New Coin Hack!! 100% Safe!!'
}
'title': 'New Coin Hack!! 100% Safe!!',
},
}, {
'url': 'web.archive.org/https://www.youtube.com/watch?v=dWW7qP423y8',
'info_dict': {
@@ -495,7 +498,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'description': 'md5:7b567f898d8237b256f36c1a07d6d7bc',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'uploader': 'DankPods',
}
},
}, {
# player response contains '};' See: https://github.com/ytdl-org/youtube-dl/issues/27093
'url': 'https://web.archive.org/web/20200827003909if_/http://www.youtube.com/watch?v=6Dh-RL__uN4',
@@ -512,7 +515,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader_id': 'PewDiePie',
'uploader_url': 'https://www.youtube.com/user/PewDiePie',
'thumbnail': r're:https?://.*\.(jpg|webp)',
}
},
}, {
# ~June 2010 Capture. swfconfig
'url': 'https://web.archive.org/web/0/https://www.youtube.com/watch?v=8XeW5ilk-9Y',
@@ -527,7 +530,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'thumbnail': r're:https?://.*\.(jpg|webp)',
'uploader_url': 'https://www.youtube.com/user/HowTheWorldWorks',
'upload_date': '20090520',
}
},
}, {
# Jan 2011: watch-video-date/eow-date surrounded by whitespace
'url': 'https://web.archive.org/web/20110126141719/http://www.youtube.com/watch?v=Q_yjX80U7Yc',
@@ -542,7 +545,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'thumbnail': r're:https?://.*\.(jpg|webp)',
'duration': 132,
'uploader_url': 'https://www.youtube.com/user/claybutlermusic',
}
},
}, {
# ~May 2009 swfArgs. ytcfg is spread out over various vars
'url': 'https://web.archive.org/web/0/https://www.youtube.com/watch?v=c5uJgG05xUY',
@@ -557,7 +560,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'description': 'md5:4ca77d79538064e41e4cc464e93f44f0',
'thumbnail': r're:https?://.*\.(jpg|webp)',
'duration': 754,
}
},
}, {
# ~June 2012. Upload date is in another lang so cannot extract.
'url': 'https://web.archive.org/web/20120607174520/http://www.youtube.com/watch?v=xWTLLl-dQaA',
@@ -571,7 +574,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'uploader': 'BlackNerdComedy',
'duration': 182,
'thumbnail': r're:https?://.*\.(jpg|webp)',
}
},
}, {
# ~July 2013
'url': 'https://web.archive.org/web/*/https://www.youtube.com/watch?v=9eO1aasHyTM',
@@ -587,7 +590,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'channel_url': 'https://www.youtube.com/channel/UC62R2cBezNBOqxSerfb1nMQ',
'upload_date': '20060428',
'uploader': 'punkybird',
}
},
}, {
# April 2020: Player response in player config
'url': 'https://web.archive.org/web/20200416034815/https://www.youtube.com/watch?v=Cf7vS8jc7dY&gl=US&hl=en',
@@ -604,7 +607,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'thumbnail': r're:https?://.*\.(jpg|webp)',
'description': 'md5:c625bb3c02c4f5fb4205971e468fa341',
'uploader_url': 'https://www.youtube.com/user/GameGrumps',
}
},
}, {
# watch7-user-header with yt-user-info
'url': 'ytarchive:kbh4T_b4Ixw:20160307085057',
@@ -619,7 +622,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
'thumbnail': r're:https?://.*\.(jpg|webp)',
'upload_date': '20150503',
'channel_id': 'UCnTaGvsHmMy792DWeT6HbGA',
}
},
}, {
# April 2012
'url': 'https://web.archive.org/web/0/https://www.youtube.com/watch?v=SOm7mPoPskU',
@@ -634,35 +637,35 @@ class YoutubeWebArchiveIE(InfoExtractor):
'duration': 200,
'upload_date': '20120407',
'uploader_id': 'thecomputernerd01',
}
},
}, {
'url': 'https://web.archive.org/web/http://www.youtube.com/watch?v=kH-G_aIBlFw',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://web.archive.org/web/20050214000000_if/http://www.youtube.com/watch?v=0altSZ96U4M',
'only_matching': True
'only_matching': True,
}, {
# Video not archived, only capture is unavailable video page
'url': 'https://web.archive.org/web/20210530071008/https://www.youtube.com/watch?v=lHJTf93HL1s&spfreload=10',
'only_matching': True
'only_matching': True,
}, { # Encoded url
'url': 'https://web.archive.org/web/20120712231619/http%3A//www.youtube.com/watch%3Fgl%3DUS%26v%3DAkhihxRKcrs%26hl%3Den',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://web.archive.org/web/20120712231619/http%3A//www.youtube.com/watch%3Fv%3DAkhihxRKcrs%26gl%3DUS%26hl%3Den',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://web.archive.org/web/20060527081937/http://www.youtube.com:80/watch.php?v=ELTFsLT73fA&amp;search=soccer',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://web.archive.org/http://www.youtube.com:80/watch?v=-05VVye-ffg',
'only_matching': True
'only_matching': True,
}, {
'url': 'ytarchive:BaW_jenozKc:20050214000000',
'only_matching': True
'only_matching': True,
}, {
'url': 'ytarchive:BaW_jenozKc',
'only_matching': True
'only_matching': True,
},
]
_YT_INITIAL_DATA_RE = YoutubeBaseInfoExtractor._YT_INITIAL_DATA_RE
@@ -673,13 +676,13 @@ class YoutubeWebArchiveIE(InfoExtractor):
_YT_DEFAULT_THUMB_SERVERS = ['i.ytimg.com'] # thumbnails most likely archived on these servers
_YT_ALL_THUMB_SERVERS = orderedSet(
_YT_DEFAULT_THUMB_SERVERS + ['img.youtube.com', *[f'{c}{n or ""}.ytimg.com' for c in ('i', 's') for n in (*range(0, 5), 9)]])
[*_YT_DEFAULT_THUMB_SERVERS, 'img.youtube.com', *[f'{c}{n or ""}.ytimg.com' for c in ('i', 's') for n in (*range(5), 9)]])
_WAYBACK_BASE_URL = 'https://web.archive.org/web/%sif_/'
_OLDEST_CAPTURE_DATE = 20050214000000
_NEWEST_CAPTURE_DATE = 20500101000000
def _call_cdx_api(self, item_id, url, filters: list = None, collapse: list = None, query: dict = None, note=None, fatal=False):
def _call_cdx_api(self, item_id, url, filters: list | None = None, collapse: list | None = None, query: dict | None = None, note=None, fatal=False):
# CDX docs: https://github.com/internetarchive/wayback/blob/master/wayback-cdx-server/README.md
query = {
'url': url,
@@ -688,14 +691,14 @@ class YoutubeWebArchiveIE(InfoExtractor):
'limit': 500,
'filter': ['statuscode:200'] + (filters or []),
'collapse': collapse or [],
**(query or {})
**(query or {}),
}
res = self._download_json(
'https://web.archive.org/cdx/search/cdx', item_id,
note or 'Downloading CDX API JSON', query=query, fatal=fatal)
if isinstance(res, list) and len(res) >= 2:
# format response to make it easier to use
return list(dict(zip(res[0], v)) for v in res[1:])
return [dict(zip(res[0], v)) for v in res[1:]]
elif not isinstance(res, list) or len(res) != 0:
self.report_warning('Error while parsing CDX API response' + bug_reports_message())
@@ -852,7 +855,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
{
'url': (self._WAYBACK_BASE_URL % (int_or_none(thumbnail_dict.get('timestamp')) or self._OLDEST_CAPTURE_DATE)) + thumbnail_dict.get('original'),
'filesize': int_or_none(thumbnail_dict.get('length')),
'preference': int_or_none(thumbnail_dict.get('length'))
'preference': int_or_none(thumbnail_dict.get('length')),
} for thumbnail_dict in response)
if not try_all:
break
@@ -893,7 +896,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
for retry in retry_manager:
try:
urlh = self._request_webpage(
HEADRequest('https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/%s' % video_id),
HEADRequest(f'https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/{video_id}'),
video_id, note='Fetching archived video file url', expected_status=True)
except ExtractorError as e:
# HTTP Error 404 is expected if the video is not saved.
@@ -924,21 +927,21 @@ class YoutubeWebArchiveIE(InfoExtractor):
info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh:
url = compat_urllib_parse_unquote(urlh.url)
url = urllib.parse.unquote(urlh.url)
video_file_url_qs = parse_qs(url)
# Attempt to recover any ext & format info from playback url & response headers
format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
fmt = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
itag = try_get(video_file_url_qs, lambda x: x['itag'][0])
if itag and itag in YoutubeIE._formats:
format.update(YoutubeIE._formats[itag])
format.update({'format_id': itag})
fmt.update(YoutubeIE._formats[itag])
fmt.update({'format_id': itag})
else:
mime = try_get(video_file_url_qs, lambda x: x['mime'][0])
ext = (mimetype2ext(mime)
or urlhandle_detect_ext(urlh)
or mimetype2ext(urlh.headers.get('x-archive-guessed-content-type')))
format.update({'ext': ext})
info['formats'] = [format]
fmt.update({'ext': ext})
info['formats'] = [fmt]
if not info.get('duration'):
info['duration'] = str_to_int(try_get(video_file_url_qs, lambda x: x['dur'][0]))

11
yt_dlp/extractor/arcpublishing.py
View File

@@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..utils import (
extract_attributes,
int_or_none,
join_nonempty,
parse_iso8601,
try_get,
)
@@ -11,7 +12,7 @@ from ..utils import (
class ArcPublishingIE(InfoExtractor):
_UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
_VALID_URL = r'arcpublishing:(?P<org>[a-z]+):(?P<id>%s)' % _UUID_REGEX
_VALID_URL = rf'arcpublishing:(?P<org>[a-z]+):(?P<id>{_UUID_REGEX})'
_TESTS = [{
# https://www.adn.com/politics/2020/11/02/video-senate-candidates-campaign-in-anchorage-on-eve-of-election-day/
'url': 'arcpublishing:adn:8c99cb6e-b29c-4bc9-9173-7bf9979225ab',
@@ -74,12 +75,12 @@ class ArcPublishingIE(InfoExtractor):
def _extract_embed_urls(cls, url, webpage):
entries = []
# https://arcpublishing.atlassian.net/wiki/spaces/POWA/overview
for powa_el in re.findall(r'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="%s"[^>]*>)' % ArcPublishingIE._UUID_REGEX, webpage):
for powa_el in re.findall(rf'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="{ArcPublishingIE._UUID_REGEX}"[^>]*>)', webpage):
powa = extract_attributes(powa_el) or {}
org = powa.get('data-org')
uuid = powa.get('data-uuid')
if org and uuid:
entries.append('arcpublishing:%s:%s' % (org, uuid))
entries.append(f'arcpublishing:{org}:{uuid}')
return entries
def _real_extract(self, url):
@@ -122,7 +123,7 @@ class ArcPublishingIE(InfoExtractor):
elif stream_type in ('ts', 'hls'):
m3u8_formats = self._extract_m3u8_formats(
s_url, uuid, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
if all([f.get('acodec') == 'none' for f in m3u8_formats]):
if all(f.get('acodec') == 'none' for f in m3u8_formats):
continue
for f in m3u8_formats:
height = f.get('height')
@@ -136,7 +137,7 @@ class ArcPublishingIE(InfoExtractor):
else:
vbr = int_or_none(s.get('bitrate'))
formats.append({
'format_id': '%s-%d' % (stream_type, vbr) if vbr else stream_type,
'format_id': join_nonempty(stream_type, vbr),
'vbr': vbr,
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),

6
yt_dlp/extractor/ard.py
View File

@@ -85,7 +85,7 @@ class ARDMediathekBaseIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
update_url_query(stream_url, {
'hdcore': '3.1.1',
'plugin': 'aasp-3.1.1.69.124'
'plugin': 'aasp-3.1.1.69.124',
}), video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
@@ -96,12 +96,12 @@ class ARDMediathekBaseIE(InfoExtractor):
f = {
'url': server,
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
'format_id': f'a{num}-rtmp-{quality}',
}
else:
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
'format_id': f'a{num}-{ext}-{quality}',
}
m = re.search(
r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',

6
yt_dlp/extractor/arkena.py
View File

@@ -64,7 +64,7 @@ class ArkenaIE(InfoExtractor):
raise ExtractorError('Invalid URL', expected=True)
media = self._download_json(
'https://video.qbrick.com/api/v1/public/accounts/%s/medias/%s' % (account_id, video_id),
f'https://video.qbrick.com/api/v1/public/accounts/{account_id}/medias/{video_id}',
video_id, query={
# https://video.qbrick.com/docs/api/examples/library-api.html
'fields': 'asset/resources/*/renditions/*(height,id,language,links/*(href,mimeType),type,size,videos/*(audios/*(codec,sampleRate),bitrate,codec,duration,height,width),width),created,metadata/*(title,description),tags',
@@ -131,8 +131,8 @@ class ArkenaIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/dash+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
href, video_id, mpd_id='dash', fatal=False))
elif mime_type == 'application/vnd.ms-sstr+xml':
formats.extend(self._extract_ism_formats(
href, video_id, ism_id='mss', fatal=False))

12
yt_dlp/extractor/arnes.py
View File

@@ -1,8 +1,6 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
float_or_none,
format_field,
@@ -35,7 +33,7 @@ class ArnesIE(InfoExtractor):
'view_count': int,
'tags': ['linearna_algebra'],
'start_time': 10,
}
},
}, {
'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
'only_matching': True,
@@ -93,6 +91,6 @@ class ArnesIE(InfoExtractor):
'duration': float_or_none(video.get('duration'), 1000),
'view_count': int_or_none(video.get('views')),
'tags': video.get('hashtags'),
'start_time': int_or_none(compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
'start_time': int_or_none(urllib.parse.parse_qs(
urllib.parse.urlparse(url).query).get('t', [None])[0]),
}

2
yt_dlp/extractor/art19.py
View File

@@ -153,7 +153,7 @@ class Art19IE(InfoExtractor):
'series_id': ('series_id', {str}),
'timestamp': ('created_at', {parse_iso8601}),
'release_timestamp': ('released_at', {parse_iso8601}),
'modified_timestamp': ('updated_at', {parse_iso8601})
'modified_timestamp': ('updated_at', {parse_iso8601}),
})),
**traverse_obj(rss_metadata, ('content', {
'title': ('episode_title', {str}),

24
yt_dlp/extractor/arte.py
View File

@@ -20,15 +20,15 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVIE(ArteTVBaseIE):
_VALID_URL = r'''(?x)
_VALID_URL = rf'''(?x)
(?:https?://
(?:
(?:www\.)?arte\.tv/(?P<lang>%(langs)s)/videos|
api\.arte\.tv/api/player/v\d+/config/(?P<lang_2>%(langs)s)
(?:www\.)?arte\.tv/(?P<lang>{ArteTVBaseIE._ARTE_LANGUAGES})/videos|
api\.arte\.tv/api/player/v\d+/config/(?P<lang_2>{ArteTVBaseIE._ARTE_LANGUAGES})
)
|arte://program)
/(?P<id>\d{6}-\d{3}-[AF]|LIVE)
''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES}
/(?P<id>\d{{6}}-\d{{3}}-[AF]|LIVE)
'''
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'only_matching': True,
@@ -145,7 +145,7 @@ class ArteTVIE(ArteTVBaseIE):
language_code = self._LANG_MAP.get(lang)
config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id, headers={
'x-validated-age': '18'
'x-validated-age': '18',
})
geoblocking = traverse_obj(config, ('data', 'attributes', 'restriction', 'geoblocking')) or {}
@@ -247,7 +247,7 @@ class ArteTVEmbedIE(InfoExtractor):
'description': 'md5:be40b667f45189632b78c1425c7c2ce1',
'upload_date': '20201116',
},
'skip': 'No video available'
'skip': 'No video available',
}, {
'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
@@ -262,7 +262,7 @@ class ArteTVEmbedIE(InfoExtractor):
class ArteTVPlaylistIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>RC-\d{6})' % ArteTVBaseIE._ARTE_LANGUAGES
_VALID_URL = rf'https?://(?:www\.)?arte\.tv/(?P<lang>{ArteTVBaseIE._ARTE_LANGUAGES})/videos/(?P<id>RC-\d{{6}})'
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'only_matching': True,
@@ -298,7 +298,7 @@ class ArteTVPlaylistIE(ArteTVBaseIE):
class ArteTVCategoryIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$' % ArteTVBaseIE._ARTE_LANGUAGES
_VALID_URL = rf'https?://(?:www\.)?arte\.tv/(?P<lang>{ArteTVBaseIE._ARTE_LANGUAGES})/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$'
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/politics-and-society/',
'info_dict': {
@@ -312,7 +312,7 @@ class ArteTVCategoryIE(ArteTVBaseIE):
@classmethod
def suitable(cls, url):
return (
not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, ))
not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE))
and super().suitable(url))
def _real_extract(self, url):
@@ -321,12 +321,12 @@ class ArteTVCategoryIE(ArteTVBaseIE):
items = []
for video in re.finditer(
r'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/%s/videos/[\w/-]+)(?P=q)' % lang,
rf'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/{lang}/videos/[\w/-]+)(?P=q)',
webpage):
video = video.group('url')
if video == url:
continue
if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )):
if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE)):
items.append(video)
title = strip_or_none(self._generic_title('', webpage, default='').rsplit('|', 1)[0]) or None

23
yt_dlp/extractor/atresplayer.py
View File

@@ -20,7 +20,7 @@ class AtresPlayerIE(InfoExtractor):
'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
'duration': 3413,
},
'skip': 'This video is only available for registered users'
'skip': 'This video is only available for registered users',
},
{
'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
@@ -33,14 +33,6 @@ class AtresPlayerIE(InfoExtractor):
]
_API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code):
if isinstance(e.cause, HTTPError) and e.cause.status == code:
error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
def _perform_login(self, username, password):
self._request_webpage(
self._API_BASE + 'login', None, 'Downloading login page')
@@ -49,13 +41,15 @@ class AtresPlayerIE(InfoExtractor):
target_url = self._download_json(
'https://account.atresmedia.com/api/login', None,
'Logging in', headers={
'Content-Type': 'application/x-www-form-urlencoded'
'Content-Type': 'application/x-www-form-urlencoded',
}, data=urlencode_postdata({
'username': username,
'password': password,
}))['targetUrl']
except ExtractorError as e:
self._handle_error(e, 400)
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise ExtractorError('Invalid username and/or password', expected=True)
raise
self._request_webpage(target_url, None, 'Following Target URL')
@@ -66,7 +60,12 @@ class AtresPlayerIE(InfoExtractor):
episode = self._download_json(
self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
except ExtractorError as e:
self._handle_error(e, 403)
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
title = episode['titulo']

10
yt_dlp/extractor/atscaleconf.py
View File

@@ -12,7 +12,7 @@ class AtScaleConfEventIE(InfoExtractor):
'info_dict': {
'id': 'data-scale-spring-2022',
'title': 'Data @Scale Spring 2022',
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55'
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55',
},
}, {
'url': 'https://atscaleconference.com/events/video-scale-2021/',
@@ -20,15 +20,15 @@ class AtScaleConfEventIE(InfoExtractor):
'info_dict': {
'id': 'video-scale-2021',
'title': 'Video @Scale 2021',
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55'
'description': 'md5:7d7ca1c42ac9c6d8a785092a1aea4b55',
},
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
return self.playlist_from_matches(
re.findall(r'data-url\s*=\s*"(https?://(?:www\.)?atscaleconference\.com/videos/[^"]+)"', webpage),
ie='Generic', playlist_id=id,
ie='Generic', playlist_id=playlist_id,
title=self._og_search_title(webpage), description=self._og_search_description(webpage))

16
yt_dlp/extractor/atvat.py
View File

@@ -19,7 +19,7 @@ class ATVAtIE(InfoExtractor):
'id': 'v-ce9cgn1e70n5-1',
'ext': 'mp4',
'title': 'Bauer sucht Frau - Staffel 18 Folge 3 - Die Hofwochen',
}
},
}, {
'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/episode-01/bauer-sucht-frau-staffel-18-vorstellungsfolge-1',
'only_matching': True,
@@ -66,10 +66,10 @@ class ATVAtIE(InfoExtractor):
video_id=video_id)
video_title = json_data['views']['default']['page']['title']
contentResource = json_data['views']['default']['page']['contentResource']
content_id = contentResource[0]['id']
content_ids = [{'id': id, 'subclip_start': content['start'], 'subclip_end': content['end']}
for id, content in enumerate(contentResource)]
content_resource = json_data['views']['default']['page']['contentResource']
content_id = content_resource[0]['id']
content_ids = [{'id': id_, 'subclip_start': content['start'], 'subclip_end': content['end']}
for id_, content in enumerate(content_resource)]
time_of_request = dt.datetime.now()
not_before = time_of_request - dt.timedelta(minutes=5)
@@ -87,17 +87,17 @@ class ATVAtIE(InfoExtractor):
videos = self._download_json(
'https://vas-v4.p7s1video.net/4.0/getsources',
content_id, 'Downloading videos JSON', query={
'token': jwt_token.decode('utf-8')
'token': jwt_token.decode('utf-8'),
})
video_id, videos_data = list(videos['data'].items())[0]
video_id, videos_data = next(iter(videos['data'].items()))
error_msg = try_get(videos_data, lambda x: x['error']['title'])
if error_msg == 'Geo check failed':
self.raise_geo_restricted(error_msg)
elif error_msg:
raise ExtractorError(error_msg)
entries = [
self._extract_video_info(url, contentResource[video['id']], video)
self._extract_video_info(url, content_resource[video['id']], video)
for video in videos_data]
return {

4
yt_dlp/extractor/audimedia.py
View File

@@ -19,7 +19,7 @@ class AudiMediaIE(InfoExtractor):
'timestamp': 1448354940,
'duration': 74022,
'view_count': int,
}
},
}, {
'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
'only_matching': True,
@@ -73,7 +73,7 @@ class AudiMediaIE(InfoExtractor):
bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
if bitrate:
f.update({
'format_id': 'http-%s' % bitrate,
'format_id': f'http-{bitrate}',
})
formats.append(f)

4
yt_dlp/extractor/audioboom.py
View File

@@ -15,7 +15,7 @@ class AudioBoomIE(InfoExtractor):
'duration': 4000.99,
'uploader': 'Sue Perkins: An hour or so with...',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
}
},
}, { # Direct mp3-file link
'url': 'https://audioboom.com/posts/8128496.mp3',
'md5': 'e329edf304d450def95c7f86a9165ee1',
@@ -27,7 +27,7 @@ class AudioBoomIE(InfoExtractor):
'duration': 1689.7,
'uploader': 'Lost Dot Podcast: The Trans Pyrenees and Transcontinental Race',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channels/5003904',
}
},
}, {
'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
'only_matching': True,

13
yt_dlp/extractor/audiodraft.py
View File

@@ -9,7 +9,7 @@ class AudiodraftBaseIE(InfoExtractor):
headers={
'Content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
'X-Requested-With': 'XMLHttpRequest',
}, data=f'id={player_entry_id}'.encode('utf-8'))
}, data=f'id={player_entry_id}'.encode())
return {
'id': str(data_json['entry_id']),
@@ -65,9 +65,10 @@ class AudiodraftCustomIE(AudiodraftBaseIE):
}]
def _real_extract(self, url):
id = self._match_id(url)
webpage = self._download_webpage(url, id)
player_entry_id = self._search_regex(r'playAudio\(\'(player_entry_\d+)\'\);', webpage, id, 'play entry id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_entry_id = self._search_regex(
r'playAudio\(\'(player_entry_\d+)\'\);', webpage, video_id, 'play entry id')
return self._audiodraft_extract_from_id(player_entry_id)
@@ -89,5 +90,5 @@ class AudiodraftGenericIE(AudiodraftBaseIE):
}]
def _real_extract(self, url):
id = self._match_id(url)
return self._audiodraft_extract_from_id(f'player_entry_{id}')
video_id = self._match_id(url)
return self._audiodraft_extract_from_id(f'player_entry_{video_id}')

27
yt_dlp/extractor/audiomack.py
View File

@@ -3,7 +3,6 @@ import time
from .common import InfoExtractor
from .soundcloud import SoundcloudIE
from ..compat import compat_str
from ..utils import (
ExtractorError,
url_basename,
@@ -22,8 +21,8 @@ class AudiomackIE(InfoExtractor):
'id': '310086',
'ext': 'mp3',
'uploader': 'Roosh Williams',
'title': 'Extraordinary'
}
'title': 'Extraordinary',
},
},
# audiomack wrapper around soundcloud song
# Needs new test URL.
@@ -56,7 +55,7 @@ class AudiomackIE(InfoExtractor):
# API is inconsistent with errors
if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
raise ExtractorError('Invalid url %s' % url)
raise ExtractorError(f'Invalid url {url}')
# Audiomack wraps a lot of soundcloud tracks in their branded wrapper
# if so, pass the work off to the soundcloud extractor
@@ -64,7 +63,7 @@ class AudiomackIE(InfoExtractor):
return self.url_result(api_response['url'], SoundcloudIE.ie_key())
return {
'id': compat_str(api_response.get('id', album_url_tag)),
'id': str(api_response.get('id', album_url_tag)),
'uploader': api_response.get('artist'),
'title': api_response.get('title'),
'url': api_response['url'],
@@ -82,8 +81,8 @@ class AudiomackAlbumIE(InfoExtractor):
'info_dict':
{
'id': '812251',
'title': 'Tha Tour: Part 2 (Official Mixtape)'
}
'title': 'Tha Tour: Part 2 (Official Mixtape)',
},
},
# Album playlist ripped from fakeshoredrive with no metadata
{
@@ -98,16 +97,16 @@ class AudiomackAlbumIE(InfoExtractor):
'id': '837576',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
},
}, {
'info_dict': {
'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
'id': '837580',
'ext': 'mp3',
'uploader': 'Lil Herb a.k.a. G Herbo',
}
},
}],
}
},
]
def _real_extract(self, url):
@@ -123,12 +122,12 @@ class AudiomackAlbumIE(InfoExtractor):
api_response = self._download_json(
'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
% (album_url_tag, track_no, time.time()), album_url_tag,
note='Querying song information (%d)' % (track_no + 1))
note=f'Querying song information ({track_no + 1})')
# Total failure, only occurs when url is totally wrong
# Won't happen in middle of valid playlist (next case)
if 'url' not in api_response or 'error' in api_response:
raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
raise ExtractorError(f'Invalid url for track {track_no} of album url {url}')
# URL is good but song id doesn't exist - usually means end of playlist
elif not api_response['url']:
break
@@ -136,10 +135,10 @@ class AudiomackAlbumIE(InfoExtractor):
# Pull out the album metadata and add to result (if it exists)
for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
if apikey in api_response and resultkey not in result:
result[resultkey] = compat_str(api_response[apikey])
result[resultkey] = str(api_response[apikey])
song_id = url_basename(api_response['url']).rpartition('.')[0]
result['entries'].append({
'id': compat_str(api_response.get('id', song_id)),
'id': str(api_response.get('id', song_id)),
'uploader': api_response.get('artist'),
'title': api_response.get('title', song_id),
'url': api_response['url'],

46
yt_dlp/extractor/audius.py
View File

@@ -1,7 +1,7 @@
import random
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_str, compat_urllib_parse_unquote
from ..utils import ExtractorError, str_or_none, try_get
@@ -15,13 +15,13 @@ class AudiusBaseIE(InfoExtractor):
if response_data is not None:
return response_data
if len(response) == 1 and 'message' in response:
raise ExtractorError('API error: %s' % response['message'],
raise ExtractorError('API error: {}'.format(response['message']),
expected=True)
raise ExtractorError('Unexpected API response')
def _select_api_base(self):
"""Selecting one of the currently available API hosts"""
response = super(AudiusBaseIE, self)._download_json(
response = super()._download_json(
'https://api.audius.co/', None,
note='Requesting available API hosts',
errnote='Unable to request available API hosts')
@@ -41,8 +41,8 @@ class AudiusBaseIE(InfoExtractor):
anything from this link, since the Audius API won't be able to resolve
this url
"""
url = compat_urllib_parse_unquote(url)
title = compat_urllib_parse_unquote(title)
url = urllib.parse.unquote(url)
title = urllib.parse.unquote(title)
if '/' in title or '%2F' in title:
fixed_title = title.replace('/', '%5C').replace('%2F', '%5C')
return url.replace(title, fixed_title)
@@ -54,19 +54,19 @@ class AudiusBaseIE(InfoExtractor):
if self._API_BASE is None:
self._select_api_base()
try:
response = super(AudiusBaseIE, self)._download_json(
'%s%s%s' % (self._API_BASE, self._API_V, path), item_id, note=note,
response = super()._download_json(
f'{self._API_BASE}{self._API_V}{path}', item_id, note=note,
errnote=errnote, expected_status=expected_status)
except ExtractorError as exc:
# some of Audius API hosts may not work as expected and return HTML
if 'Failed to parse JSON' in compat_str(exc):
if 'Failed to parse JSON' in str(exc):
raise ExtractorError('An error occurred while receiving data. Try again',
expected=True)
raise exc
return self._get_response_data(response)
def _resolve_url(self, url, item_id):
return self._api_request('/resolve?url=%s' % url, item_id,
return self._api_request(f'/resolve?url={url}', item_id,
expected_status=404)
@@ -91,7 +91,7 @@ class AudiusIE(AudiusBaseIE):
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
},
{
# Regular track
@@ -109,14 +109,14 @@ class AudiusIE(AudiusBaseIE):
'view_count': int,
'like_count': int,
'repost_count': int,
}
},
},
]
_ARTWORK_MAP = {
"150x150": 150,
"480x480": 480,
"1000x1000": 1000
'150x150': 150,
'480x480': 480,
'1000x1000': 1000,
}
def _real_extract(self, url):
@@ -130,7 +130,7 @@ class AudiusIE(AudiusBaseIE):
else: # API link
title = None
# uploader = None
track_data = self._api_request('/tracks/%s' % track_id, track_id)
track_data = self._api_request(f'/tracks/{track_id}', track_id)
if not isinstance(track_data, dict):
raise ExtractorError('Unexpected API response')
@@ -144,7 +144,7 @@ class AudiusIE(AudiusBaseIE):
if isinstance(artworks_data, dict):
for quality_key, thumbnail_url in artworks_data.items():
thumbnail = {
"url": thumbnail_url
'url': thumbnail_url,
}
quality_code = self._ARTWORK_MAP.get(quality_key)
if quality_code is not None:
@@ -154,12 +154,12 @@ class AudiusIE(AudiusBaseIE):
return {
'id': track_id,
'title': track_data.get('title', title),
'url': '%s/v1/tracks/%s/stream' % (self._API_BASE, track_id),
'url': f'{self._API_BASE}/v1/tracks/{track_id}/stream',
'ext': 'mp3',
'description': track_data.get('description'),
'duration': track_data.get('duration'),
'track': track_data.get('title'),
'artist': try_get(track_data, lambda x: x['user']['name'], compat_str),
'artist': try_get(track_data, lambda x: x['user']['name'], str),
'genre': track_data.get('genre'),
'thumbnails': thumbnails,
'view_count': track_data.get('play_count'),
@@ -175,11 +175,11 @@ class AudiusTrackIE(AudiusIE): # XXX: Do not subclass from concrete IE
_TESTS = [
{
'url': 'audius:9RWlo',
'only_matching': True
'only_matching': True,
},
{
'url': 'audius:http://discoveryprovider.audius.prod-us-west-2.staked.cloud/v1/tracks/9RWlo',
'only_matching': True
'only_matching': True,
},
]
@@ -207,7 +207,7 @@ class AudiusPlaylistIE(AudiusBaseIE):
if not track_id:
raise ExtractorError('Unable to get track ID from playlist')
entries.append(self.url_result(
'audius:%s' % track_id,
f'audius:{track_id}',
ie=AudiusTrackIE.ie_key(), video_id=track_id))
return entries
@@ -231,7 +231,7 @@ class AudiusPlaylistIE(AudiusBaseIE):
raise ExtractorError('Unable to get playlist ID')
playlist_tracks = self._api_request(
'/playlists/%s/tracks' % playlist_id,
f'/playlists/{playlist_id}/tracks',
title, note='Downloading playlist tracks metadata',
errnote='Unable to download playlist tracks metadata')
if not isinstance(playlist_tracks, list):
@@ -267,5 +267,5 @@ class AudiusProfileIE(AudiusPlaylistIE): # XXX: Do not subclass from concrete I
profile_audius_id = _profile_data[0]['id']
profile_bio = _profile_data[0].get('bio')
api_call = self._api_request('/full/users/handle/%s/tracks' % profile_id, profile_id)
api_call = self._api_request(f'/full/users/handle/{profile_id}/tracks', profile_id)
return self.playlist_result(self._build_playlist(api_call), profile_audius_id, profile_id, profile_bio)

27
yt_dlp/extractor/awaan.py
View File

@@ -1,10 +1,7 @@
import base64
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
format_field,
int_or_none,
@@ -22,14 +19,14 @@ class AWAANIE(InfoExtractor):
show_id, video_id, season_id = self._match_valid_url(url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
f'http://awaan.ae/media/{video_id}', 'AWAANVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://awaan.ae/program/season/%s' % season_id,
f'http://awaan.ae/program/season/{season_id}',
{'show_id': show_id}), 'AWAANSeason')
else:
return self.url_result(
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
f'http://awaan.ae/program/{show_id}', 'AWAANSeason')
class AWAANBaseIE(InfoExtractor):
@@ -75,11 +72,11 @@ class AWAANVideoIE(AWAANBaseIE):
video_id = self._match_id(url)
video_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
f'http://admin.mangomolo.com/analytics/index.php/plus/video?id={video_id}',
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + urllib.parse.urlencode({
'id': video_data['id'],
'user_id': video_data['user_id'],
'signature': video_data['signature'],
@@ -117,11 +114,11 @@ class AWAANLiveIE(AWAANBaseIE):
channel_id = self._match_id(url)
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
f'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id={channel_id}',
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + urllib.parse.urlencode({
'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
'signature': channel_data['signature'],
@@ -159,7 +156,7 @@ class AWAANSeasonIE(InfoExtractor):
show_id = smuggled_data.get('show_id')
if show_id is None:
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
f'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id={season_id}',
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
@@ -167,7 +164,7 @@ class AWAANSeasonIE(InfoExtractor):
'http://admin.mangomolo.com/analytics/index.php/plus/show',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
'Content-Type': 'application/x-www-form-urlencoded',
})
if not season_id:
season_id = show['default_season']
@@ -177,8 +174,8 @@ class AWAANSeasonIE(InfoExtractor):
entries = []
for video in show['videos']:
video_id = compat_str(video['id'])
video_id = str(video['id'])
entries.append(self.url_result(
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
f'http://awaan.ae/media/{video_id}', 'AWAANVideo', video_id))
return self.playlist_result(entries, season_id, title)

24
yt_dlp/extractor/aws.py
View File

@@ -1,9 +1,9 @@
import datetime as dt
import hashlib
import hmac
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
@@ -18,20 +18,20 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
'Accept': 'application/json',
'Host': self._AWS_PROXY_HOST,
'X-Amz-Date': amz_date,
'X-Api-Key': self._AWS_API_KEY
'X-Api-Key': self._AWS_API_KEY,
}
session_token = aws_dict.get('session_token')
if session_token:
headers['X-Amz-Security-Token'] = session_token
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
return hashlib.sha256(s.encode()).hexdigest()
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
canonical_querystring = compat_urllib_parse_urlencode(query)
canonical_querystring = urllib.parse.urlencode(query)
canonical_headers = ''
for header_name, header_value in sorted(headers.items()):
canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
canonical_headers += f'{header_name.lower()}:{header_value}\n'
signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())])
canonical_request = '\n'.join([
'GET',
@@ -39,7 +39,7 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
canonical_querystring,
canonical_headers,
signed_headers,
aws_hash('')
aws_hash(''),
])
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
@@ -49,7 +49,7 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
return hmac.new(key, msg.encode(), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
@@ -57,7 +57,7 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
k_signing = ('AWS4' + aws_dict['secret_key']).encode()
for value in credential_scope_list:
k_signing = aws_hmac_digest(k_signing, value)
@@ -65,11 +65,11 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
# Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
headers['Authorization'] = ', '.join([
'%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
'SignedHeaders=%s' % signed_headers,
'Signature=%s' % signature,
'{} Credential={}/{}'.format(self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
f'SignedHeaders={signed_headers}',
f'Signature={signature}',
])
return self._download_json(
'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
'https://{}{}{}'.format(self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
video_id, headers=headers)

6
yt_dlp/extractor/azmedien.py
View File

@@ -38,14 +38,14 @@ class AZMedienIE(InfoExtractor):
'timestamp': 1538328802,
'view_count': int,
'thumbnail': 'http://cfvod.kaltura.com/p/1719221/sp/171922100/thumbnail/entry_id/1_anruz3wy/version/100031',
'duration': 1930
'duration': 1930,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
'only_matching': True
'only_matching': True,
}]
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
_PARTNER_ID = '1719221'
@@ -62,5 +62,5 @@ class AZMedienIE(InfoExtractor):
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
return self.url_result(
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
f'kaltura:{self._PARTNER_ID}:{entry_id}',
ie=KalturaIE.ie_key(), video_id=entry_id)

7
yt_dlp/extractor/baidu.py
View File

@@ -24,8 +24,9 @@ class BaiduVideoIE(InfoExtractor):
}]
def _call_api(self, path, category, playlist_id, note):
return self._download_json('http://app.video.baidu.com/%s/?worktype=adnative%s&id=%s' % (
path, category, playlist_id), playlist_id, note)
return self._download_json(
f'http://app.video.baidu.com/{path}/?worktype=adnative{category}&id={playlist_id}',
playlist_id, note)
def _real_extract(self, url):
category, playlist_id = self._match_valid_url(url).groups()
@@ -44,7 +45,7 @@ class BaiduVideoIE(InfoExtractor):
'xqsingle', category, playlist_id, 'Download episodes JSON metadata')
entries = [self.url_result(
episode['url'], video_title=episode['title']
episode['url'], video_title=episode['title'],
) for episode in episodes_detail['videos']]
return self.playlist_result(

80
yt_dlp/extractor/banbye.py
View File

@@ -1,15 +1,16 @@
import math
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
InAdvancePagedList,
determine_ext,
format_field,
int_or_none,
join_nonempty,
traverse_obj,
unified_timestamp,
url_or_none,
)
@@ -20,8 +21,8 @@ class BanByeBaseIE(InfoExtractor):
@staticmethod
def _extract_playlist_id(url, param='playlist'):
return compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get(param, [None])[0]
return urllib.parse.parse_qs(
urllib.parse.urlparse(url).query).get(param, [None])[0]
def _extract_playlist(self, playlist_id):
data = self._download_json(f'{self._API_BASE}/playlists/{playlist_id}', playlist_id)
@@ -33,6 +34,7 @@ class BanByeBaseIE(InfoExtractor):
class BanByeIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
_TESTS = [{
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
'info_dict': {
@@ -61,6 +63,7 @@ class BanByeIE(BanByeBaseIE):
},
'playlist_mincount': 9,
}, {
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_kb6_o1Kyq-CD',
'info_dict': {
'id': 'v_kb6_o1Kyq-CD',
@@ -80,6 +83,48 @@ class BanByeIE(BanByeBaseIE):
'view_count': int,
'comment_count': int,
},
}, {
# ['src']['hls']['levels'] variant m3u8 urls only; master m3u8 is 404
'url': 'https://banbye.com/watch/v_a_gPFuC9LoW5',
'info_dict': {
'id': 'v_a_gPFuC9LoW5',
'ext': 'mp4',
'title': 'md5:183524056bebdfa245fd6d214f63c0fe',
'description': 'md5:943ac87287ca98d28d8b8797719827c6',
'uploader': 'wRealu24',
'channel_id': 'ch_wrealu24',
'channel_url': 'https://banbye.com/channel/ch_wrealu24',
'upload_date': '20231113',
'timestamp': 1699874062,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_a_gPFuC9LoW5/96.webp',
'tags': ['jaszczur', 'sejm', 'lewica', 'polska', 'ukrainizacja', 'pierwszeposiedzeniesejmu'],
},
'expected_warnings': ['Failed to download m3u8'],
}, {
# ['src']['hls']['masterPlaylist'] m3u8 only
'url': 'https://banbye.com/watch/v_B0rsKWsr-aaa',
'info_dict': {
'id': 'v_B0rsKWsr-aaa',
'ext': 'mp4',
'title': 'md5:00b254164b82101b3f9e5326037447ed',
'description': 'md5:3fd8b48aa81954ba024bc60f5de6e167',
'uploader': 'PSTV Piotr Szlachtowicz ',
'channel_id': 'ch_KV9EVObkB9wB',
'channel_url': 'https://banbye.com/channel/ch_KV9EVObkB9wB',
'upload_date': '20240629',
'timestamp': 1719646816,
'duration': 2377,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_B0rsKWsr-aaa/96.webp',
'tags': ['Biden', 'Trump', 'Wybory', 'USA'],
},
}]
def _real_extract(self, url):
@@ -94,11 +139,24 @@ class BanByeIE(BanByeBaseIE):
'id': f'{quality}p',
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.webp',
} for quality in [48, 96, 144, 240, 512, 1080]]
formats = [{
'format_id': f'http-{quality}p',
'quality': quality,
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.mp4',
} for quality in data['quality']]
formats = []
url_data = self._download_json(f'{self._API_BASE}/videos/{video_id}/url', video_id, data=b'')
if master_url := traverse_obj(url_data, ('src', 'hls', 'masterPlaylist', {url_or_none})):
formats = self._extract_m3u8_formats(master_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
for format_id, format_url in traverse_obj(url_data, (
'src', ('mp4', 'hls'), 'levels', {dict.items}, lambda _, v: url_or_none(v[1]))):
ext = determine_ext(format_url)
is_hls = ext == 'm3u8'
formats.append({
'url': format_url,
'ext': 'mp4' if is_hls else ext,
'format_id': join_nonempty(is_hls and 'hls', format_id),
'protocol': 'm3u8_native' if is_hls else 'https',
'height': int_or_none(format_id),
})
self._remove_duplicate_formats(formats)
return {
'id': video_id,

31
yt_dlp/extractor/bandcamp.py
View File

@@ -3,7 +3,6 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
@@ -42,7 +41,7 @@ class BandcampIE(InfoExtractor):
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
'skip': 'There is a limit of 200 free downloads / month for the test song',
}, {
# free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
@@ -119,7 +118,7 @@ class BandcampIE(InfoExtractor):
def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
return self._parse_json(self._html_search_regex(
r'data-%s=(["\'])({.+?})\1' % attr, webpage,
rf'data-{attr}=(["\'])({{.+?}})\1', webpage,
attr + ' data', group=2), video_id, fatal=fatal)
def _real_extract(self, url):
@@ -167,7 +166,7 @@ class BandcampIE(InfoExtractor):
download_link = tralbum.get('freeDownloadPage')
if download_link:
track_id = compat_str(tralbum['id'])
track_id = str(tralbum['id'])
download_webpage = self._download_webpage(
download_link, track_id, 'Downloading free downloads page')
@@ -192,7 +191,7 @@ class BandcampIE(InfoExtractor):
if isinstance(download_formats_list, list):
for f in blob['download_formats']:
name, ext = f.get('name'), f.get('file_extension')
if all(isinstance(x, compat_str) for x in (name, ext)):
if all(isinstance(x, str) for x in (name, ext)):
download_formats[name] = ext.strip('.')
for format_id, f in downloads.items():
@@ -207,7 +206,7 @@ class BandcampIE(InfoExtractor):
})
format_id = f.get('encoding_name') or format_id
stat = self._download_json(
stat_url, track_id, 'Downloading %s JSON' % format_id,
stat_url, track_id, f'Downloading {format_id} JSON',
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
fatal=False)
if not stat:
@@ -225,7 +224,7 @@ class BandcampIE(InfoExtractor):
'acodec': format_id.split('-')[0],
})
title = '%s - %s' % (artist, track) if artist else track
title = f'{artist} - {track}' if artist else track
if not duration:
duration = float_or_none(self._html_search_meta(
@@ -267,7 +266,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
},
{
'md5': '1a2c32e2691474643e912cc6cd4bffaa',
@@ -278,7 +277,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
}
},
},
],
'info_dict': {
@@ -287,9 +286,9 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'uploader_id': 'blazo',
},
'params': {
'playlistend': 2
'playlistend': 2,
},
'skip': 'Bandcamp imposes download limits.'
'skip': 'Bandcamp imposes download limits.',
}, {
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
'info_dict': {
@@ -324,7 +323,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
def suitable(cls, url):
return (False
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
else super(BandcampAlbumIE, cls).suitable(url))
else super().suitable(url))
def _real_extract(self, url):
uploader_id, album_id = self._match_valid_url(url).groups()
@@ -376,7 +375,7 @@ class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
},
}, {
'url': 'https://bandcamp.com/?blah/blah@&show=228',
'only_matching': True
'only_matching': True,
}]
def _real_extract(self, url):
@@ -407,7 +406,7 @@ class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
if subtitle:
title += ' - %s' % subtitle
title += f' - {subtitle}'
return {
'id': show_id,
@@ -419,7 +418,7 @@ class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
'series': 'Bandcamp Weekly',
'episode': show.get('subtitle'),
'episode_id': show_id,
'formats': formats
'formats': formats,
}
@@ -440,7 +439,7 @@ class BandcampUserIE(InfoExtractor):
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'id': 'dotscale',
'title': 'Discography of dotscale'
'title': 'Discography of dotscale',
},
'playlist_count': 1,
}, {

12
yt_dlp/extractor/bannedvideo.py
View File

@@ -23,7 +23,7 @@ class BannedVideoIE(InfoExtractor):
'description': 'md5:560d96f02abbebe6c6b78b47465f6b28',
'upload_date': '20200324',
'timestamp': 1585087895,
}
},
}]
_GRAPHQL_GETMETADATA_QUERY = '''
@@ -84,15 +84,15 @@ query GetCommentReplies($id: String!) {
'GetCommentReplies': _GRAPHQL_GETCOMMENTSREPLIES_QUERY,
}
def _call_api(self, video_id, id, operation, note):
def _call_api(self, video_id, id_var, operation, note):
return self._download_json(
'https://api.infowarsmedia.com/graphql', video_id, note=note,
headers={
'Content-Type': 'application/json; charset=utf-8'
'Content-Type': 'application/json; charset=utf-8',
}, data=json.dumps({
'variables': {'id': id},
'variables': {'id': id_var},
'operationName': operation,
'query': self._GRAPHQL_QUERIES[operation]
'query': self._GRAPHQL_QUERIES[operation],
}).encode('utf8')).get('data')
def _get_comments(self, video_id, comments, comment_data):
@@ -151,5 +151,5 @@ query GetCommentReplies($id: String!) {
'tags': [tag.get('name') for tag in video_info.get('tags')],
'availability': self._availability(is_unlisted=video_info.get('unlisted')),
'comments': comments,
'__post_extractor': self.extract_comments(video_id, comments, video_json.get('getVideoComments'))
'__post_extractor': self.extract_comments(video_id, comments, video_json.get('getVideoComments')),
}

110
yt_dlp/extractor/bbc.py
View File

@@ -2,10 +2,10 @@ import functools
import itertools
import json
import re
import urllib.parse
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import compat_str, compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
@@ -35,7 +35,7 @@ class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_ID_REGEX = r'(?:[pbml][\da-z]{7}|w[\da-z]{7,14})'
_VALID_URL = r'''(?x)
_VALID_URL = rf'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
(?:
@@ -45,8 +45,8 @@ class BBCCoUkIE(InfoExtractor):
radio/player/|
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
(?P<id>{_ID_REGEX})(?!/(?:episodes|broadcasts|clips))
'''
_EMBED_REGEX = [r'setPlaylist\("(?P<url>https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)']
_LOGIN_URL = 'https://account.bbc.com/signin'
@@ -75,7 +75,7 @@ class BBCCoUkIE(InfoExtractor):
'params': {
# rtmp download
'skip_download': True,
}
},
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
@@ -148,7 +148,7 @@ class BBCCoUkIE(InfoExtractor):
'params': {
# rtmp download
'skip_download': True,
}
},
}, {
'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
'note': 'Video',
@@ -162,7 +162,7 @@ class BBCCoUkIE(InfoExtractor):
'params': {
# rtmp download
'skip_download': True,
}
},
}, {
'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
'info_dict': {
@@ -268,19 +268,19 @@ class BBCCoUkIE(InfoExtractor):
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
f'Unable to login: {error}', expected=True)
raise ExtractorError('Unable to log in')
class MediaSelectionError(Exception):
def __init__(self, id):
self.id = id
def __init__(self, error_id):
self.id = error_id
def _extract_asx_playlist(self, connection, programme_id):
asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
return [ref.get('href') for ref in asx.findall('./Entry/ref')]
def _extract_items(self, playlist):
return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
return playlist.findall(f'./{{{self._EMP_PLAYLIST_NS}}}item')
def _extract_medias(self, media_selection):
error = media_selection.get('result')
@@ -312,7 +312,7 @@ class BBCCoUkIE(InfoExtractor):
def _raise_extractor_error(self, media_selection_error):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
f'{self.IE_NAME} returned error: {media_selection_error.id}',
expected=True)
def _download_media_selector(self, programme_id):
@@ -372,7 +372,7 @@ class BBCCoUkIE(InfoExtractor):
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
formats.append({
'url': ref,
'format_id': 'ref%s_%s' % (i, format_id),
'format_id': f'ref{i}_{format_id}',
})
elif transfer_format == 'dash':
formats.extend(self._extract_mpd_formats(
@@ -394,7 +394,7 @@ class BBCCoUkIE(InfoExtractor):
href, programme_id, f4m_id=format_id, fatal=False))
else:
if not supplier and bitrate:
format_id += '-%d' % bitrate
format_id += f'-{bitrate}'
fmt = {
'format_id': format_id,
'filesize': file_size,
@@ -423,9 +423,9 @@ class BBCCoUkIE(InfoExtractor):
identifier = connection.get('identifier')
server = connection.get('server')
fmt.update({
'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
'url': f'{protocol}://{server}/{application}?{auth_string}',
'play_path': identifier,
'app': '%s?%s' % (application, auth_string),
'app': f'{application}?{auth_string}',
'page_url': 'http://www.bbc.co.uk',
'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
'rtmp_live': False,
@@ -441,7 +441,7 @@ class BBCCoUkIE(InfoExtractor):
def _download_playlist(self, playlist_id):
try:
playlist = self._download_json(
'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
f'http://www.bbc.co.uk/programmes/{playlist_id}/playlist.json',
playlist_id, 'Downloading playlist JSON')
formats = []
subtitles = {}
@@ -480,32 +480,32 @@ class BBCCoUkIE(InfoExtractor):
def _process_legacy_playlist(self, playlist_id):
return self._process_legacy_playlist_url(
'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
f'http://www.bbc.co.uk/iplayer/playlist/{playlist_id}', playlist_id)
def _download_legacy_playlist_url(self, url, playlist_id=None):
return self._download_xml(
url, playlist_id, 'Downloading legacy playlist XML')
def _extract_from_legacy_playlist(self, playlist, playlist_id):
no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
no_items = playlist.find(f'./{{{self._EMP_PLAYLIST_NS}}}noItems')
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
msg = 'Episode %s is not yet available' % playlist_id
msg = f'Episode {playlist_id} is not yet available'
elif reason == 'postAvailability':
msg = 'Episode %s is no longer available' % playlist_id
msg = f'Episode {playlist_id} is no longer available'
elif reason == 'noMedia':
msg = 'Episode %s is not currently available' % playlist_id
msg = f'Episode {playlist_id} is not currently available'
else:
msg = 'Episode %s is not available: %s' % (playlist_id, reason)
msg = f'Episode {playlist_id} is not available: {reason}'
raise ExtractorError(msg, expected=True)
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind not in ('programme', 'radioProgramme'):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
title = playlist.find(f'./{{{self._EMP_PLAYLIST_NS}}}title').text
description_el = playlist.find(f'./{{{self._EMP_PLAYLIST_NS}}}summary')
description = description_el.text if description_el is not None else None
def get_programme_id(item):
@@ -515,7 +515,7 @@ class BBCCoUkIE(InfoExtractor):
if value and re.match(r'^[pb][\da-z]{7}$', value):
return value
get_from_attributes(item)
mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
mediator = item.find(f'./{{{self._EMP_PLAYLIST_NS}}}mediator')
if mediator is not None:
return get_from_attributes(mediator)
@@ -555,7 +555,7 @@ class BBCCoUkIE(InfoExtractor):
if not programme_id:
programme_id = self._search_regex(
r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
rf'"vpid"\s*:\s*"({self._ID_REGEX})"', webpage, 'vpid', fatal=False, default=None)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
@@ -641,7 +641,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
},
'params': {
'skip_download': True,
}
},
}, {
# article with single video embedded with data-playable containing XML playlist
# with direct video links as progressiveDownloadUrl (for now these are extracted)
@@ -884,7 +884,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader_id': 'bbc_world_service',
'series': 'CrowdScience',
'chapters': [],
}
},
}, { # onion routes
'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
'only_matching': True,
@@ -897,7 +897,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
def suitable(cls, url):
EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerEpisodesIE, BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE)
return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
else super(BBCIE, cls).suitable(url))
else super().suitable(url))
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
@@ -1009,7 +1009,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
if playlist:
entry = None
for key in ('streaming', 'progressiveDownload'):
playlist_url = playlist.get('%sUrl' % key)
playlist_url = playlist.get(f'{key}Url')
if not playlist_url:
continue
try:
@@ -1035,7 +1035,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
# http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227
group_id = self._search_regex(
r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX,
rf'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\']({self._ID_REGEX})',
webpage, 'group id', default=None)
if group_id:
return self.url_result(
@@ -1043,9 +1043,9 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
[r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
[rf'data-(?:video-player|media)-vpid="({self._ID_REGEX})"',
rf'<param[^>]+name="externalIdentifier"[^>]+value="({self._ID_REGEX})"',
rf'videoId\s*:\s*["\']({self._ID_REGEX})["\']'],
webpage, 'vpid', default=None)
if programme_id:
@@ -1142,7 +1142,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
video_id, url_transparent=True)
entry.update({
'timestamp': traverse_obj(morph_payload, (
'body', 'content', 'article', 'dateTimeInfo', 'dateTime', {parse_iso8601})
'body', 'content', 'article', 'dateTimeInfo', 'dateTime', {parse_iso8601}),
),
**traverse_obj(video_data, {
'thumbnail': (('iChefImage', 'image'), {url_or_none}, any),
@@ -1189,7 +1189,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'primary', 'secondary', 'tertiary', delim=' - ', from_dict=x)}),
'start_time': ('offset', 'start', {float_or_none}),
'end_time': ('offset', 'end', {float_or_none}),
})
}),
),
}
@@ -1287,7 +1287,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'description': ('synopses', ('long', 'medium', 'short'), {str}, {lambda x: x or None}, any),
'duration': ('versions', 0, 'duration', {int}),
'timestamp': ('versions', 0, 'availableFrom', {functools.partial(int_or_none, scale=1000)}),
})
}),
}
def is_type(*types):
@@ -1331,7 +1331,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
if blocks:
summary = []
for block in blocks:
text = try_get(block, lambda x: x['model']['text'], compat_str)
text = try_get(block, lambda x: x['model']['text'], str)
if text:
summary.append(text)
if summary:
@@ -1411,9 +1411,9 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
entries, playlist_id, playlist_title, playlist_description)
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),
re.findall(pattern, webpage))))
return list(filter(None, (
self._parse_json(s, playlist_id, fatal=False)
for s in re.findall(pattern, webpage))))
# US accessed article with single embedded video (e.g.
# https://www.bbc.com/news/uk-68546268)
@@ -1435,14 +1435,14 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
# Multiple video article (e.g.
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
EMBED_URL = rf'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+{self._ID_REGEX}(?:\b[^"]+)?'
entries = []
for match in extract_all(r'new\s+SMP\(({.+?})\)'):
embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
if embed_url and re.match(EMBED_URL, embed_url):
entries.append(embed_url)
entries.extend(re.findall(
r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
rf'setPlaylist\("({EMBED_URL})"\)', webpage))
if entries:
return self.playlist_result(
[self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
@@ -1492,11 +1492,11 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
video_id = media_meta.get('externalId')
if not video_id:
video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
video_id = playlist_id if len(medias) == 1 else f'{playlist_id}-{num}'
title = media_meta.get('caption')
if not title:
title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
title = playlist_title if len(medias) == 1 else f'{playlist_title} - Video {num}'
duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
@@ -1557,8 +1557,8 @@ class BBCCoUkArticleIE(InfoExtractor):
class BBCCoUkPlaylistBaseIE(InfoExtractor):
def _entries(self, webpage, url, playlist_id):
single_page = 'page' in compat_urlparse.parse_qs(
compat_urlparse.urlparse(url).query)
single_page = 'page' in urllib.parse.parse_qs(
urllib.parse.urlparse(url).query)
for page_num in itertools.count(2):
for video_id in re.findall(
self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
@@ -1572,8 +1572,8 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
if not next_page:
break
webpage = self._download_webpage(
compat_urlparse.urljoin(url, next_page), playlist_id,
'Downloading page %d' % page_num, page_num)
urllib.parse.urljoin(url, next_page), playlist_id,
f'Downloading page {page_num}', page_num)
def _real_extract(self, url):
playlist_id = self._match_id(url)
@@ -1588,7 +1588,7 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
_VALID_URL_TMPL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/%%s/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
_VALID_URL_TMPL = rf'https?://(?:www\.)?bbc\.co\.uk/iplayer/%s/(?P<id>{BBCCoUkIE._ID_REGEX})'
@staticmethod
def _get_default(episode, key, default_key='default'):
@@ -1712,11 +1712,11 @@ class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
variables['sliceId'] = series_id
return self._download_json(
'https://graph.ibl.api.bbc.co.uk/', pid, headers={
'Content-Type': 'application/json'
'Content-Type': 'application/json',
}, data=json.dumps({
'id': '5692d93d5aac8d796a0305e895e61551',
'variables': variables,
}).encode('utf-8'))['data']['programme']
}).encode())['data']['programme']
@staticmethod
def _get_playlist_data(data):
@@ -1776,7 +1776,7 @@ class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
def _call_api(self, pid, per_page, page=1, series_id=None):
return self._download_json(
'http://ibl.api.bbc.co.uk/ibl/v1/groups/%s/episodes' % pid,
f'http://ibl.api.bbc.co.uk/ibl/v1/groups/{pid}/episodes',
pid, query={
'page': page,
'per_page': per_page,
@@ -1792,7 +1792,7 @@ class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
IE_NAME = 'bbc.co.uk:playlist'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
_VALID_URL = rf'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>{BBCCoUkIE._ID_REGEX})/(?:episodes|broadcasts|clips)'
_URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
_VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
_TESTS = [{

7
yt_dlp/extractor/beatport.py
View File

@@ -1,7 +1,6 @@
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
@@ -33,7 +32,7 @@ class BeatportIE(InfoExtractor):
'display_id': 'birds-original-mix',
'ext': 'mp4',
'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
}
},
}]
def _real_extract(self, url):
@@ -51,7 +50,7 @@ class BeatportIE(InfoExtractor):
track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
title = ', '.join(a['name'] for a in track['artists']) + ' - ' + track['name']
if track['mix']:
title += ' (' + track['mix'] + ')'
@@ -89,7 +88,7 @@ class BeatportIE(InfoExtractor):
images.append(image)
return {
'id': compat_str(track.get('id')) or track_id,
'id': str(track.get('id')) or track_id,
'display_id': track.get('slug') or display_id,
'title': title,
'formats': formats,

8
yt_dlp/extractor/beeg.py
View File

@@ -23,7 +23,7 @@ class BeegIE(InfoExtractor):
'upload_date': '20220131',
'timestamp': 1643656455,
'display_id': '2540839',
}
},
}, {
'url': 'https://beeg.com/-0599050563103750?t=4-861',
'md5': 'bd8b5ea75134f7f07fad63008db2060e',
@@ -38,7 +38,7 @@ class BeegIE(InfoExtractor):
'timestamp': 1643623200,
'display_id': '2569965',
'upload_date': '20220131',
}
},
}, {
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
@@ -55,8 +55,8 @@ class BeegIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video = self._download_json(
'https://store.externulls.com/facts/file/%s' % video_id,
video_id, 'Downloading JSON for %s' % video_id)
f'https://store.externulls.com/facts/file/{video_id}',
video_id, f'Downloading JSON for {video_id}')
fc_facts = video.get('fc_facts')
first_fact = {}

2
yt_dlp/extractor/behindkink.py
View File

@@ -16,7 +16,7 @@ class BehindKinkIE(InfoExtractor):
'upload_date': '20141205',
'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
'age_limit': 18,
}
},
}
def _real_extract(self, url):

2
yt_dlp/extractor/bellmedia.py
View File

@@ -86,6 +86,6 @@ class BellMediaIE(InfoExtractor):
return {
'_type': 'url_transparent',
'id': video_id,
'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
'url': f'9c9media:{self._DOMAINS.get(domain, domain)}_web:{video_id}',
'ie_key': 'NineCNineMedia',
}

4
yt_dlp/extractor/berufetv.py
View File

@@ -16,7 +16,7 @@ class BerufeTVIE(InfoExtractor):
'tags': ['Studienfilm'],
'duration': 602.440,
'thumbnail': r're:^https://asset-out-cdn\.video-cdn\.net/private/videos/DvKC3DUpMKvUZ_6fEnfg3u/thumbnails/793063\?quality=thumbnail&__token__=[^\s]+$',
}
},
}]
def _real_extract(self, url):
@@ -54,7 +54,7 @@ class BerufeTVIE(InfoExtractor):
subtitles.setdefault(track['language'], []).append({
'url': track['source'],
'name': track.get('label'),
'ext': 'vtt'
'ext': 'vtt',
})
return {

8
yt_dlp/extractor/bet.py
View File

@@ -19,7 +19,7 @@ class BetIE(MTVServicesInfoExtractor):
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
}
},
},
'params': {
# rtmp download
@@ -39,16 +39,16 @@ class BetIE(MTVServicesInfoExtractor):
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
}
},
},
'params': {
# rtmp download
'skip_download': True,
},
}
},
]
_FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/bet-mrss-player'
def _get_feed_query(self, uri):
return {

4
yt_dlp/extractor/bfmtv.py
View File

@@ -98,8 +98,8 @@ class BFMTVArticleIE(BFMTVBaseIE):
'timestamp': 1673341692,
'duration': 109.269,
'tags': ['rmc', 'show', 'apolline de malherbe', 'info', 'talk', 'matinale', 'radio'],
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876630703001/5bef74b8-9d5e-4480-a21f-60c2e2480c46/96c88b74-f9db-45e1-8040-e199c5da216c/1920x1080/match/image.jpg'
}
'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876630703001/5bef74b8-9d5e-4480-a21f-60c2e2480c46/96c88b74-f9db-45e1-8040-e199c5da216c/1920x1080/match/image.jpg',
},
}]
def _real_extract(self, url):

14
yt_dlp/extractor/bigflix.py
View File

@@ -1,10 +1,8 @@
import base64
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
class BigflixIE(InfoExtractor):
@@ -21,7 +19,7 @@ class BigflixIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
}, {
# multiple formats
'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
@@ -38,7 +36,7 @@ class BigflixIE(InfoExtractor):
webpage, 'title')
def decode_url(quoted_b64_url):
return compat_b64decode(compat_urllib_parse_unquote(
return base64.b64decode(urllib.parse.unquote(
quoted_b64_url)).decode('utf-8')
formats = []
@@ -47,7 +45,7 @@ class BigflixIE(InfoExtractor):
video_url = decode_url(encoded_url)
f = {
'url': video_url,
'format_id': '%sp' % height,
'format_id': f'{height}p',
'height': int(height),
}
if video_url.startswith('rtmp'):
@@ -69,5 +67,5 @@ class BigflixIE(InfoExtractor):
'id': video_id,
'title': title,
'description': description,
'formats': formats
'formats': formats,
}

2
yt_dlp/extractor/bigo.py
View File

@@ -36,7 +36,7 @@ class BigoIE(InfoExtractor):
raise ExtractorError('Received invalid JSON data')
if info_raw.get('code'):
raise ExtractorError(
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
'Bigo says: {} (code {})'.format(info_raw.get('msg'), info_raw.get('code')), expected=True)
info = info_raw.get('data') or {}
if not info.get('alive'):

4
yt_dlp/extractor/bild.py
View File

@@ -20,7 +20,7 @@ class BildIE(InfoExtractor):
'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 196,
}
},
}, {
'note': 'static MP4 and HLS',
'url': 'https://www.bild.de/video/clip/news-ausland/deftiger-abgang-vom-10m-turm-bademeister-sorgt-fuer-skandal-85158620.bild.html',
@@ -32,7 +32,7 @@ class BildIE(InfoExtractor):
'description': 'md5:709b543c24dc31bbbffee73bccda34ad',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 69,
}
},
}]
def _real_extract(self, url):

494
yt_dlp/extractor/bilibili.py
View File

@@ -31,12 +31,12 @@ from ..utils import (
mimetype2ext,
parse_count,
parse_qs,
parse_resolution,
qualities,
smuggle_url,
srt_subtitles_timecode,
str_or_none,
traverse_obj,
try_call,
unified_timestamp,
unsmuggle_url,
url_or_none,
@@ -47,6 +47,23 @@ from ..utils import (
class BilibiliBaseIE(InfoExtractor):
_FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?')
_WBI_KEY_CACHE_TIMEOUT = 30 # exact expire timeout is unclear, use 30s for one session
_wbi_key_cache = {}
@property
def is_logged_in(self):
return bool(self._get_cookies('https://api.bilibili.com').get('SESSDATA'))
def _check_missing_formats(self, play_info, formats):
parsed_qualities = set(traverse_obj(formats, (..., 'quality')))
missing_formats = join_nonempty(*[
traverse_obj(fmt, 'new_description', 'display_desc', 'quality')
for fmt in traverse_obj(play_info, (
'support_formats', lambda _, v: v['quality'] not in parsed_qualities))], delim=', ')
if missing_formats:
self.to_screen(
f'Format(s) {missing_formats} are missing; you have to login or '
f'become a premium member to download them. {self._login_hint()}')
def extract_formats(self, play_info):
format_names = {
@@ -86,18 +103,75 @@ class BilibiliBaseIE(InfoExtractor):
'format': format_names.get(video.get('id')),
} for video in traverse_obj(play_info, ('dash', 'video', ...)))
missing_formats = format_names.keys() - set(traverse_obj(formats, (..., 'quality')))
if missing_formats:
self.to_screen(f'Format(s) {", ".join(format_names[i] for i in missing_formats)} are missing; '
f'you have to login or become premium member to download them. {self._login_hint()}')
if formats:
self._check_missing_formats(play_info, formats)
fragments = traverse_obj(play_info, ('durl', lambda _, v: url_or_none(v['url']), {
'url': ('url', {url_or_none}),
'duration': ('length', {functools.partial(float_or_none, scale=1000)}),
'filesize': ('size', {int_or_none}),
}))
if fragments:
formats.append({
'url': fragments[0]['url'],
'filesize': sum(traverse_obj(fragments, (..., 'filesize'))),
**({
'fragments': fragments,
'protocol': 'http_dash_segments',
} if len(fragments) > 1 else {}),
**traverse_obj(play_info, {
'quality': ('quality', {int_or_none}),
'format_id': ('quality', {str_or_none}),
'format_note': ('quality', {lambda x: format_names.get(x)}),
'duration': ('timelength', {functools.partial(float_or_none, scale=1000)}),
}),
**parse_resolution(format_names.get(play_info.get('quality'))),
})
return formats
def _download_playinfo(self, video_id, cid, headers=None):
def _get_wbi_key(self, video_id):
if time.time() < self._wbi_key_cache.get('ts', 0) + self._WBI_KEY_CACHE_TIMEOUT:
return self._wbi_key_cache['key']
session_data = self._download_json(
'https://api.bilibili.com/x/web-interface/nav', video_id, note='Downloading wbi sign')
lookup = ''.join(traverse_obj(session_data, (
'data', 'wbi_img', ('img_url', 'sub_url'),
{lambda x: x.rpartition('/')[2].partition('.')[0]})))
# from getMixinKey() in the vendor js
mixin_key_enc_tab = [
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49,
33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40,
61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, 57, 62, 11,
36, 20, 34, 44, 52,
]
self._wbi_key_cache.update({
'key': ''.join(lookup[i] for i in mixin_key_enc_tab)[:32],
'ts': time.time(),
})
return self._wbi_key_cache['key']
def _sign_wbi(self, params, video_id):
params['wts'] = round(time.time())
params = {
k: ''.join(filter(lambda char: char not in "!'()*", str(v)))
for k, v in sorted(params.items())
}
query = urllib.parse.urlencode(params)
params['w_rid'] = hashlib.md5(f'{query}{self._get_wbi_key(video_id)}'.encode()).hexdigest()
return params
def _download_playinfo(self, bvid, cid, headers=None, qn=None):
params = {'bvid': bvid, 'cid': cid, 'fnval': 4048}
if qn:
params['qn'] = qn
return self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note=f'Downloading video formats for cid {cid}', headers=headers)['data']
'https://api.bilibili.com/x/player/wbi/playurl', bvid,
query=self._sign_wbi(params, bvid), headers=headers,
note=f'Downloading video formats for cid {cid} {qn or ""}')['data']
def json2srt(self, json_data):
srt_data = ''
@@ -112,21 +186,21 @@ class BilibiliBaseIE(InfoExtractor):
'danmaku': [{
'ext': 'xml',
'url': f'https://comment.bilibili.com/{cid}.xml',
}]
}],
}
subtitle_info = traverse_obj(self._download_json(
video_info = self._download_json(
'https://api.bilibili.com/x/player/v2', video_id,
query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid},
note=f'Extracting subtitle info {cid}'), ('data', 'subtitle'))
subs_list = traverse_obj(subtitle_info, ('subtitles', lambda _, v: v['subtitle_url'] and v['lan']))
if not subs_list and traverse_obj(subtitle_info, 'allow_submit'):
if not self._get_cookies('https://api.bilibili.com').get('SESSDATA'): # no login session cookie
self.report_warning(f'CC subtitles (if any) are only visible when logged in. {self._login_hint()}', only_once=True)
for s in subs_list:
note=f'Extracting subtitle info {cid}')
if traverse_obj(video_info, ('data', 'need_login_subtitle')):
self.report_warning(
f'Subtitles are only available when logged in. {self._login_hint()}', only_once=True)
for s in traverse_obj(video_info, (
'data', 'subtitle', 'subtitles', lambda _, v: v['subtitle_url'] and v['lan'])):
subtitles.setdefault(s['lan'], []).append({
'ext': 'srt',
'data': self.json2srt(self._download_json(s['subtitle_url'], video_id))
'data': self.json2srt(self._download_json(s['subtitle_url'], video_id)),
})
return subtitles
@@ -203,19 +277,19 @@ class BilibiliBaseIE(InfoExtractor):
self._get_divisions(video_id, graph_version, edges, choice['edge_id'], cid_edges=cid_edges)
return cid_edges
def _get_interactive_entries(self, video_id, cid, metainfo):
def _get_interactive_entries(self, video_id, cid, metainfo, headers=None):
graph_version = traverse_obj(
self._download_json(
'https://api.bilibili.com/x/player/wbi/v2', video_id,
'Extracting graph version', query={'bvid': video_id, 'cid': cid}),
'Extracting graph version', query={'bvid': video_id, 'cid': cid}, headers=headers),
('data', 'interaction', 'graph_version', {int_or_none}))
cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1)
for cid, edges in cid_edges.items():
play_info = self._download_playinfo(video_id, cid)
play_info = self._download_playinfo(video_id, cid, headers=headers)
yield {
**metainfo,
'id': f'{video_id}_{cid}',
'title': f'{metainfo.get("title")} - {list(edges.values())[0].get("title")}',
'title': f'{metainfo.get("title")} - {next(iter(edges.values())).get("title")}',
'formats': self.extract_formats(play_info),
'description': f'{json.dumps(edges, ensure_ascii=False)}\n{metainfo.get("description", "")}',
'duration': float_or_none(play_info.get('timelength'), scale=1000),
@@ -243,17 +317,17 @@ class BiliBiliIE(BilibiliBaseIE):
'timestamp': 1488353834,
'like_count': int,
'view_count': int,
'_old_archive_ids': ['bilibili 8903802_part1'],
},
}, {
'note': 'old av URL version',
'url': 'http://www.bilibili.com/video/av1074402/',
'info_dict': {
'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
'id': 'BV11x411K7CN',
'ext': 'mp4',
'title': '【金坷垃】金泡沫',
'uploader': '菊子桑',
'uploader_id': '156160',
'id': 'BV11x411K7CN',
'title': '【金坷垃】金泡沫',
'duration': 308.36,
'upload_date': '20140420',
'timestamp': 1397983878,
@@ -262,6 +336,8 @@ class BiliBiliIE(BilibiliBaseIE):
'comment_count': int,
'view_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
'_old_archive_ids': ['bilibili 1074402_part1'],
},
'params': {'skip_download': True},
}, {
@@ -269,7 +345,7 @@ class BiliBiliIE(BilibiliBaseIE):
'url': 'https://www.bilibili.com/video/BV1bK411W797',
'info_dict': {
'id': 'BV1bK411W797',
'title': '物语中的人物是如何吐槽自己的OP的'
'title': '物语中的人物是如何吐槽自己的OP的',
},
'playlist_count': 18,
'playlist': [{
@@ -288,8 +364,9 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
'duration': 90.314,
}
}]
'_old_archive_ids': ['bilibili 498159642_part1'],
},
}],
}, {
'note': 'Specific page of Anthology',
'url': 'https://www.bilibili.com/video/BV1bK411W797?p=1',
@@ -308,28 +385,8 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
'duration': 90.314,
}
}, {
'note': 'video has subtitles',
'url': 'https://www.bilibili.com/video/BV12N4y1M7rh',
'info_dict': {
'id': 'BV12N4y1M7rh',
'ext': 'mp4',
'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1',
'tags': list,
'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4',
'duration': 313.557,
'upload_date': '20220709',
'uploader': '小夫太渴',
'timestamp': 1657347907,
'uploader_id': '1326814124',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'subtitles': 'count:2'
'_old_archive_ids': ['bilibili 498159642_part1'],
},
'params': {'listsubtitles': True},
}, {
'url': 'https://www.bilibili.com/video/av8903802/',
'info_dict': {
@@ -347,6 +404,7 @@ class BiliBiliIE(BilibiliBaseIE):
'comment_count': int,
'view_count': int,
'like_count': int,
'_old_archive_ids': ['bilibili 8903802_part1'],
},
'params': {
'skip_download': True,
@@ -370,6 +428,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 463665680_part1'],
},
'params': {'skip_download': True},
}, {
@@ -388,8 +447,8 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 893839363_part1'],
},
'params': {'skip_download': True},
}, {
'note': 'newer festival video',
'url': 'https://www.bilibili.com/festival/2023honkaiimpact3gala?bvid=BV1ay4y1d77f',
@@ -406,8 +465,57 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 778246196_part1'],
},
}, {
'note': 'legacy flv/mp4 video',
'url': 'https://www.bilibili.com/video/BV1ms411Q7vw/?p=4',
'info_dict': {
'id': 'BV1ms411Q7vw_p4',
'title': '[搞笑]【动画】云南方言快乐生产线出品 p04 新烧包谷之漫游桃花岛',
'timestamp': 1458222815,
'upload_date': '20160317',
'description': '云南方言快乐生产线出品',
'duration': float,
'uploader': '一笑颠天',
'uploader_id': '3916081',
'view_count': int,
'comment_count': int,
'like_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 4120229_part4'],
},
'params': {'extractor_args': {'bilibili': {'prefer_multi_flv': ['32']}}},
'playlist_count': 19,
'playlist': [{
'info_dict': {
'id': 'BV1ms411Q7vw_p4_0',
'ext': 'flv',
'title': '[搞笑]【动画】云南方言快乐生产线出品 p04 新烧包谷之漫游桃花岛',
'duration': 399.102,
},
}],
}, {
'note': 'legacy mp4-only video',
'url': 'https://www.bilibili.com/video/BV1nx411u79K',
'info_dict': {
'id': 'BV1nx411u79K',
'ext': 'mp4',
'title': '【练习室】201603声乐练习《No Air》with VigoVan',
'timestamp': 1508893551,
'upload_date': '20171025',
'description': '@ZERO-G伯远\n声乐练习 《No Air》with Vigo Van',
'duration': 80.384,
'uploader': '伯远',
'uploader_id': '10584494',
'comment_count': int,
'view_count': int,
'like_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 15700301_part1'],
},
'params': {'skip_download': True},
}, {
'note': 'interactive/split-path video',
'url': 'https://www.bilibili.com/video/BV1af4y1H7ga/',
@@ -425,6 +533,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 292734508_part1'],
},
'playlist_count': 33,
'playlist': [{
@@ -443,6 +552,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 292734508_part1'],
},
}],
}, {
@@ -465,6 +575,29 @@ class BiliBiliIE(BilibiliBaseIE):
'upload_date': '20191021',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'video has subtitles, which requires login',
'url': 'https://www.bilibili.com/video/BV12N4y1M7rh',
'info_dict': {
'id': 'BV12N4y1M7rh',
'ext': 'mp4',
'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1',
'tags': list,
'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4',
'duration': 313.557,
'upload_date': '20220709',
'uploader': '小夫太渴',
'timestamp': 1657347907,
'uploader_id': '1326814124',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'subtitles': 'count:2', # login required for CC subtitle
'_old_archive_ids': ['bilibili 898179753_part1'],
},
'params': {'listsubtitles': True},
'skip': 'login required for subtitle',
}, {
'url': 'https://www.bilibili.com/video/BV1jL41167ZG/',
'info_dict': {
@@ -498,8 +631,9 @@ class BiliBiliIE(BilibiliBaseIE):
if not self._match_valid_url(urlh.url):
return self.url_result(urlh.url)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
headers['Referer'] = url
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
is_festival = 'videoData' not in initial_state
if is_festival:
video_data = initial_state['videoInfo']
@@ -548,7 +682,6 @@ class BiliBiliIE(BilibiliBaseIE):
aid = video_data.get('aid')
old_video_id = format_field(aid, None, f'%s_part{part_id or 1}')
cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid')
festival_info = {}
@@ -586,19 +719,65 @@ class BiliBiliIE(BilibiliBaseIE):
is_interactive = traverse_obj(video_data, ('rights', 'is_stein_gate'))
if is_interactive:
return self.playlist_result(
self._get_interactive_entries(video_id, cid, metainfo), **metainfo, **{
'duration': traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})),
'__post_extractor': self.extract_comments(aid),
})
self._get_interactive_entries(video_id, cid, metainfo, headers=headers), **metainfo,
duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})),
__post_extractor=self.extract_comments(aid))
else:
return {
**metainfo,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'chapters': self._get_chapters(aid, cid),
'subtitles': self.extract_subtitles(video_id, cid),
'formats': self.extract_formats(play_info),
'__post_extractor': self.extract_comments(aid),
}
formats = self.extract_formats(play_info)
if not traverse_obj(play_info, ('dash')):
# we only have legacy formats and need additional work
has_qn = lambda x: x in traverse_obj(formats, (..., 'quality'))
for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})):
formats.extend(traverse_obj(
self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, qn=qn)),
lambda _, v: not has_qn(v['quality'])))
self._check_missing_formats(play_info, formats)
flv_formats = traverse_obj(formats, lambda _, v: v['fragments'])
if flv_formats and len(flv_formats) < len(formats):
# Flv and mp4 are incompatible due to `multi_video` workaround, so drop one
if not self._configuration_arg('prefer_multi_flv'):
dropped_fmts = ', '.join(
f'{f.get("format_note")} ({f.get("format_id")})' for f in flv_formats)
formats = traverse_obj(formats, lambda _, v: not v.get('fragments'))
if dropped_fmts:
self.to_screen(
f'Dropping incompatible flv format(s) {dropped_fmts} since mp4 is available. '
'To extract flv, pass --extractor-args "bilibili:prefer_multi_flv"')
else:
formats = traverse_obj(
# XXX: Filtering by extractor-arg is for testing purposes
formats, lambda _, v: v['quality'] == int(self._configuration_arg('prefer_multi_flv')[0]),
) or [max(flv_formats, key=lambda x: x['quality'])]
if traverse_obj(formats, (0, 'fragments')):
# We have flv formats, which are individual short videos with their own timestamps and metainfo
# Binary concatenation corrupts their timestamps, so we need a `multi_video` workaround
return {
**metainfo,
'_type': 'multi_video',
'entries': [{
'id': f'{metainfo["id"]}_{idx}',
'title': metainfo['title'],
'http_headers': metainfo['http_headers'],
'formats': [{
**fragment,
'format_id': formats[0].get('format_id'),
}],
'subtitles': self.extract_subtitles(video_id, cid) if idx == 0 else None,
'__post_extractor': self.extract_comments(aid) if idx == 0 else None,
} for idx, fragment in enumerate(formats[0]['fragments'])],
'duration': float_or_none(play_info.get('timelength'), scale=1000),
}
else:
return {
**metainfo,
'formats': formats,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'chapters': self._get_chapters(aid, cid),
'subtitles': self.extract_subtitles(video_id, cid),
'__post_extractor': self.extract_comments(aid),
}
class BiliBiliBangumiIE(BilibiliBaseIE):
@@ -640,7 +819,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'duration': 1425.256,
'timestamp': 1554566400,
'upload_date': '20190406',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
'skip': 'Geo-restricted',
}, {
@@ -661,7 +840,7 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'duration': 1922.129,
'timestamp': 1602853860,
'upload_date': '20201016',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}]
@@ -764,7 +943,7 @@ class BiliBiliBangumiMediaIE(BilibiliBaseIE):
'duration': 1525.777,
'timestamp': 1425074413,
'upload_date': '20150227',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
}]
@@ -794,7 +973,7 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
'title': '鬼灭之刃',
'description': 'md5:e2cc9848b6f69be6db79fc2a82d9661b',
},
'playlist_mincount': 26
'playlist_mincount': 26,
}, {
'url': 'https://www.bilibili.com/bangumi/play/ss2251',
'info_dict': {
@@ -819,7 +998,7 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE):
'duration': 1436.992,
'timestamp': 1343185080,
'upload_date': '20120725',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$'
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}],
}]
@@ -906,7 +1085,7 @@ class BilibiliCheeseIE(BilibiliCheeseBaseIE):
'upload_date': '20230924',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'view_count': int,
}
},
}]
def _real_extract(self, url):
@@ -939,7 +1118,7 @@ class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE):
'upload_date': '20230924',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'view_count': int,
}
},
}],
'params': {'playlist_items': '1'},
}, {
@@ -969,7 +1148,7 @@ class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE):
}))
class BilibiliSpaceBaseIE(InfoExtractor):
class BilibiliSpaceBaseIE(BilibiliBaseIE):
def _extract_playlist(self, fetch_page, get_metadata, get_entries):
first_page = fetch_page(0)
metadata = get_metadata(first_page)
@@ -989,73 +1168,53 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
'id': '3985676',
},
'playlist_mincount': 178,
'skip': 'login required',
}, {
'url': 'https://space.bilibili.com/313580179/video',
'info_dict': {
'id': '313580179',
},
'playlist_mincount': 92,
'skip': 'login required',
}]
def _extract_signature(self, playlist_id):
session_data = self._download_json('https://api.bilibili.com/x/web-interface/nav', playlist_id, fatal=False)
key_from_url = lambda x: x[x.rfind('/') + 1:].split('.')[0]
img_key = traverse_obj(
session_data, ('data', 'wbi_img', 'img_url', {key_from_url})) or '34478ba821254d9d93542680e3b86100'
sub_key = traverse_obj(
session_data, ('data', 'wbi_img', 'sub_url', {key_from_url})) or '7e16a90d190a4355a78fd00b32a38de6'
session_key = img_key + sub_key
signature_values = []
for position in (
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49, 33, 9, 42, 19, 29, 28, 14, 39,
12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40, 61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63,
57, 62, 11, 36, 20, 34, 44, 52
):
char_at_position = try_call(lambda: session_key[position])
if char_at_position:
signature_values.append(char_at_position)
return ''.join(signature_values)[:32]
def _real_extract(self, url):
playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video')
if not is_video_url:
self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. '
'To download audios, add a "/audio" to the URL')
signature = self._extract_signature(playlist_id)
def fetch_page(page_idx):
query = {
'keyword': '',
'mid': playlist_id,
'order': 'pubdate',
'order': traverse_obj(parse_qs(url), ('order', 0)) or 'pubdate',
'order_avoided': 'true',
'platform': 'web',
'pn': page_idx + 1,
'ps': 30,
'tid': 0,
'web_location': 1550101,
'wts': int(time.time()),
}
query['w_rid'] = hashlib.md5(f'{urllib.parse.urlencode(query)}{signature}'.encode()).hexdigest()
try:
response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search',
playlist_id, note=f'Downloading page {page_idx}', query=query,
headers={'referer': url})
response = self._download_json(
'https://api.bilibili.com/x/space/wbi/arc/search', playlist_id,
query=self._sign_wbi(query, playlist_id),
note=f'Downloading space page {page_idx}', headers={'Referer': url})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
raise
if response['code'] in (-352, -401):
status_code = response['code']
if status_code == -401:
raise ExtractorError(
f'Request is blocked by server ({-response["code"]}), '
'please add cookies, wait and try later.', expected=True)
'Request is blocked by server (401), please add cookies, wait and try later.', expected=True)
elif status_code == -352 and not self.is_logged_in:
self.raise_login_required('Request is rejected, you need to login to access playlist')
elif status_code != 0:
raise ExtractorError(f'Request failed ({status_code}): {response.get("message") or "Unknown error"}')
return response['data']
def get_metadata(page_data):
@@ -1163,7 +1322,7 @@ class BilibiliCollectionListIE(BilibiliSpaceListBaseIE):
'uploader_id': ('meta', 'mid', {str_or_none}),
'timestamp': ('meta', 'ptime', {int_or_none}),
'thumbnail': ('meta', 'cover', {url_or_none}),
})
}),
}
def get_entries(page_data):
@@ -1195,7 +1354,7 @@ class BilibiliSeriesListIE(BilibiliSpaceListBaseIE):
mid, sid = self._match_valid_url(url).group('mid', 'sid')
playlist_id = f'{mid}_{sid}'
playlist_meta = traverse_obj(self._download_json(
f'https://api.bilibili.com/x/series/series?series_id={sid}', playlist_id, fatal=False
f'https://api.bilibili.com/x/series/series?series_id={sid}', playlist_id, fatal=False,
), {
'title': ('data', 'meta', 'name', {str}),
'description': ('data', 'meta', 'description', {str}),
@@ -1217,7 +1376,7 @@ class BilibiliSeriesListIE(BilibiliSpaceListBaseIE):
'page_count': math.ceil(entry_count / page_size),
'page_size': page_size,
'uploader': self._get_uploader(mid, playlist_id),
**playlist_meta
**playlist_meta,
}
def get_entries(page_data):
@@ -1241,7 +1400,7 @@ class BilibiliFavoritesListIE(BilibiliSpaceListBaseIE):
'upload_date': '20201109',
'modified_timestamp': int,
'modified_date': str,
'thumbnail': r"re:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg",
'thumbnail': r're:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg',
'view_count': int,
'like_count': int,
},
@@ -1281,7 +1440,10 @@ class BilibiliWatchlaterIE(BilibiliSpaceListBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/watchlater/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.bilibili.com/watchlater/#/list',
'info_dict': {'id': 'watchlater'},
'info_dict': {
'id': r're:\d+',
'title': '稍后再看',
},
'playlist_mincount': 0,
'skip': 'login required',
}]
@@ -1345,7 +1507,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'uploader_id': '84912',
'timestamp': 1604905176,
'upload_date': '20201109',
'thumbnail': r"re:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg",
'thumbnail': r're:http://i\d\.hdslb\.com/bfs/archive/14b83c62aa8871b79083df1e9ab4fbc699ad16fe\.jpg',
},
'playlist_mincount': 22,
}, {
@@ -1357,21 +1519,26 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'skip': 'redirect url',
}, {
'url': 'https://www.bilibili.com/list/watchlater',
'info_dict': {'id': 'watchlater'},
'info_dict': {
'id': r're:2_\d+',
'title': '稍后再看',
'uploader': str,
'uploader_id': str,
},
'playlist_mincount': 0,
'skip': 'login required',
}, {
'url': 'https://www.bilibili.com/medialist/play/watchlater',
'info_dict': {'id': 'watchlater'},
'playlist_mincount': 0,
'skip': 'login required',
'skip': 'redirect url & login required',
}]
def _extract_medialist(self, query, list_id):
for page_num in itertools.count(1):
page_data = self._download_json(
'https://api.bilibili.com/x/v2/medialist/resource/list',
list_id, query=query, note=f'getting playlist {query["biz_id"]} page {page_num}'
list_id, query=query, note=f'getting playlist {query["biz_id"]} page {page_num}',
)['data']
yield from self._get_entries(page_data, 'media_list', ending_key='bv_id')
query['oid'] = traverse_obj(page_data, ('media_list', -1, 'id'))
@@ -1407,7 +1574,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'tid': ('tid', {int_or_none}),
'sort_field': ('sortFiled', {int_or_none}),
'desc': ('desc', {bool_or_none}, {str_or_none}, {str.lower}),
})
}),
}
metadata = {
'id': f'{query["type"]}_{query["biz_id"]}',
@@ -1415,7 +1582,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'title': ('title', {str}),
'uploader': ('upper', 'name', {str}),
'uploader_id': ('upper', 'mid', {str_or_none}),
'timestamp': ('ctime', {int_or_none}),
'timestamp': ('ctime', {int_or_none}, {lambda x: x or None}),
'thumbnail': ('cover', {url_or_none}),
})),
}
@@ -1430,26 +1597,26 @@ class BilibiliCategoryIE(InfoExtractor):
'url': 'https://www.bilibili.com/v/kichiku/mad',
'info_dict': {
'id': 'kichiku: mad',
'title': 'kichiku: mad'
'title': 'kichiku: mad',
},
'playlist_mincount': 45,
'params': {
'playlistend': 45
}
'playlistend': 45,
},
}]
def _fetch_page(self, api_url, num_pages, query, page_num):
parsed_json = self._download_json(
api_url, query, query={'Search_key': query, 'pn': page_num},
note='Extracting results from page %s of %s' % (page_num, num_pages))
note=f'Extracting results from page {page_num} of {num_pages}')
video_list = traverse_obj(parsed_json, ('data', 'archives'), expected_type=list)
if not video_list:
raise ExtractorError('Failed to retrieve video list for page %d' % page_num)
raise ExtractorError(f'Failed to retrieve video list for page {page_num}')
for video in video_list:
yield self.url_result(
'https://www.bilibili.com/video/%s' % video['bvid'], 'BiliBili', video['bvid'])
'https://www.bilibili.com/video/{}'.format(video['bvid']), 'BiliBili', video['bvid'])
def _entries(self, category, subcategory, query):
# map of categories : subcategories : RIDs
@@ -1459,7 +1626,7 @@ class BilibiliCategoryIE(InfoExtractor):
'manual_vocaloid': 126,
'guide': 22,
'theatre': 216,
'course': 127
'course': 127,
},
}
@@ -1485,7 +1652,7 @@ class BilibiliCategoryIE(InfoExtractor):
def _real_extract(self, url):
category, subcategory = urllib.parse.urlparse(url).path.split('/')[2:4]
query = '%s: %s' % (category, subcategory)
query = f'{category}: {subcategory}'
return self.playlist_result(self._entries(category, subcategory, query), query, query)
@@ -1588,7 +1755,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
formats = [{
'url': play_data['cdns'][0],
'filesize': int_or_none(play_data.get('size')),
'vcodec': 'none'
'vcodec': 'none',
}]
for a_format in formats:
@@ -1606,7 +1773,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
subtitles = {
'origin': [{
'url': lyric,
}]
}],
}
return {
@@ -1674,7 +1841,7 @@ class BiliBiliPlayerIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'http://www.bilibili.tv/video/av%s/' % video_id,
f'http://www.bilibili.tv/video/av{video_id}/',
ie=BiliBiliIE.ie_key(), video_id=video_id)
@@ -1702,11 +1869,10 @@ class BiliIntlBaseIE(InfoExtractor):
return json.get('data')
def json2srt(self, json):
data = '\n\n'.join(
return '\n\n'.join(
f'{i + 1}\n{srt_subtitles_timecode(line["from"])} --> {srt_subtitles_timecode(line["to"])}\n{line["content"]}'
for i, line in enumerate(traverse_obj(json, (
'body', lambda _, l: l['content'] and l['from'] and l['to']))))
return data
def _get_subtitles(self, *, ep_id=None, aid=None):
sub_json = self._call_api(
@@ -1808,14 +1974,15 @@ class BiliIntlBaseIE(InfoExtractor):
note='Downloading login key', errnote='Unable to download login key')['data']
public_key = Cryptodome.RSA.importKey(key_data['key'])
password_hash = Cryptodome.PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode('utf-8'))
password_hash = Cryptodome.PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode())
login_post = self._download_json(
'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None, data=urlencode_postdata({
'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None,
data=urlencode_postdata({
'username': username,
'password': base64.b64encode(password_hash).decode('ascii'),
'keep_me': 'true',
's_locale': 'en_US',
'isTrusted': 'true'
'isTrusted': 'true',
}), note='Logging in', errnote='Unable to log in')
if login_post.get('code'):
if login_post.get('message'):
@@ -1842,17 +2009,17 @@ class BiliIntlIE(BiliIntlBaseIE):
'chapters': [{
'start_time': 0,
'end_time': 76.242,
'title': '<Untitled Chapter 1>'
'title': '<Untitled Chapter 1>',
}, {
'start_time': 76.242,
'end_time': 161.161,
'title': 'Intro'
'title': 'Intro',
}, {
'start_time': 1325.742,
'end_time': 1403.903,
'title': 'Outro'
'title': 'Outro',
}],
}
},
}, {
# Non-Bstation page
'url': 'https://www.bilibili.tv/en/play/1033760/11005006',
@@ -1869,17 +2036,17 @@ class BiliIntlIE(BiliIntlBaseIE):
'chapters': [{
'start_time': 0,
'end_time': 88.0,
'title': '<Untitled Chapter 1>'
'title': '<Untitled Chapter 1>',
}, {
'start_time': 88.0,
'end_time': 156.0,
'title': 'Intro'
'title': 'Intro',
}, {
'start_time': 1173.0,
'end_time': 1259.535,
'title': 'Outro'
'title': 'Outro',
}],
}
},
}, {
# Subtitle with empty content
'url': 'https://www.bilibili.tv/en/play/1005144/10131790',
@@ -1890,7 +2057,7 @@ class BiliIntlIE(BiliIntlBaseIE):
'thumbnail': r're:^https://pic\.bstarstatic\.com/ogv/.+\.png$',
'episode_number': 140,
},
'skip': 'According to the copyright owner\'s request, you may only watch the video after you log in.'
'skip': 'According to the copyright owner\'s request, you may only watch the video after you log in.',
}, {
# episode comment extraction
'url': 'https://www.bilibili.tv/en/play/34580/340317',
@@ -1908,20 +2075,20 @@ class BiliIntlIE(BiliIntlBaseIE):
'chapters': [{
'start_time': 0,
'end_time': 61.0,
'title': '<Untitled Chapter 1>'
'title': '<Untitled Chapter 1>',
}, {
'start_time': 61.0,
'end_time': 134.0,
'title': 'Intro'
'title': 'Intro',
}, {
'start_time': 1290.0,
'end_time': 1379.0,
'title': 'Outro'
'title': 'Outro',
}],
},
'params': {
'getcomments': True
}
'getcomments': True,
},
}, {
# user generated content comment extraction
'url': 'https://www.bilibili.tv/en/video/2045730385',
@@ -1936,8 +2103,8 @@ class BiliIntlIE(BiliIntlBaseIE):
'thumbnail': r're:https://pic\.bstarstatic\.(?:com|net)/ugc/f6c363659efd2eabe5683fbb906b1582\.jpg',
},
'params': {
'getcomments': True
}
'getcomments': True,
},
}, {
# episode id without intro and outro
'url': 'https://www.bilibili.tv/en/play/1048837/11246489',
@@ -1992,7 +2159,7 @@ class BiliIntlIE(BiliIntlBaseIE):
# Non-Bstation layout, read through episode list
season_json = self._call_api(f'/web/v2/ogv/play/episodes?season_id={season_id}&platform=web', video_id)
video_data = traverse_obj(season_json, (
'sections', ..., 'episodes', lambda _, v: str(v['episode_id']) == video_id
'sections', ..., 'episodes', lambda _, v: str(v['episode_id']) == video_id,
), expected_type=dict, get_all=False)
# XXX: webpage metadata may not accurate, it just used to not crash when video_data not found
@@ -2024,7 +2191,7 @@ class BiliIntlIE(BiliIntlBaseIE):
'id': replies.get('rpid'),
'like_count': int_or_none(replies.get('like_count')),
'parent': replies.get('parent'),
'timestamp': unified_timestamp(replies.get('ctime_text'))
'timestamp': unified_timestamp(replies.get('ctime_text')),
}
if not traverse_obj(comment_api_raw_data, ('data', 'cursor', 'is_end')):
@@ -2077,11 +2244,11 @@ class BiliIntlIE(BiliIntlBaseIE):
chapters = [{
'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_start_time')), 1000),
'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'opening_end_time')), 1000),
'title': 'Intro'
'title': 'Intro',
}, {
'start_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_start_time')), 1000),
'end_time': float_or_none(traverse_obj(intro_ending_json, ('skip', 'ending_end_time')), 1000),
'title': 'Outro'
'title': 'Outro',
}]
return {
@@ -2137,12 +2304,13 @@ class BiliIntlSeriesIE(BiliIntlBaseIE):
episode_id = str(episode['episode_id'])
yield self.url_result(smuggle_url(
BiliIntlIE._make_url(episode_id, series_id),
self._parse_video_metadata(episode)
self._parse_video_metadata(episode),
), BiliIntlIE, episode_id)
def _real_extract(self, url):
series_id = self._match_id(url)
series_info = self._call_api(f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {}
series_info = self._call_api(
f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {}
return self.playlist_result(
self._entries(series_id), series_id, series_info.get('title'), series_info.get('description'),
categories=traverse_obj(series_info, ('styles', ..., 'title'), expected_type=str_or_none),
@@ -2156,19 +2324,19 @@ class BiliLiveIE(InfoExtractor):
'url': 'https://live.bilibili.com/196',
'info_dict': {
'id': '33989',
'description': "周六杂谈回，其他时候随机游戏。 | \n录播：@下播型泛式录播组。 | \n直播通知群（全员禁言）：666906670，902092584，59971⑧481 （功能一样，别多加）",
'description': '周六杂谈回，其他时候随机游戏。 | \n录播：@下播型泛式录播组。 | \n直播通知群（全员禁言）：666906670，902092584，59971⑧481 （功能一样，别多加）',
'ext': 'flv',
'title': "太空狼人杀联动，不被爆杀就算赢",
'thumbnail': "https://i0.hdslb.com/bfs/live/new_room_cover/e607bc1529057ef4b332e1026e62cf46984c314d.jpg",
'title': '太空狼人杀联动，不被爆杀就算赢',
'thumbnail': 'https://i0.hdslb.com/bfs/live/new_room_cover/e607bc1529057ef4b332e1026e62cf46984c314d.jpg',
'timestamp': 1650802769,
},
'skip': 'not live'
'skip': 'not live',
}, {
'url': 'https://live.bilibili.com/196?broadcast_type=0&is_room_feed=1?spm_id_from=333.999.space_home.strengthen_live_card.click',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://live.bilibili.com/blanc/196',
'only_matching': True
'only_matching': True,
}]
_FORMATS = {
@@ -2209,7 +2377,7 @@ class BiliLiveIE(InfoExtractor):
raise ExtractorError('Streamer is not live', expected=True)
formats = []
for qn in self._FORMATS.keys():
for qn in self._FORMATS:
stream_data = self._call_api('xlive/web-room/v2/index/getRoomPlayInfo', room_id, {
'room_id': room_id,
'qn': qn,

30
yt_dlp/extractor/bitchute.py
View File

@@ -24,7 +24,7 @@ from ..utils import (
class BitChuteIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -39,7 +39,7 @@ class BitChuteIE(InfoExtractor):
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/'
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
},
}, {
# test case: video with different channel and uploader
@@ -55,7 +55,7 @@ class BitChuteIE(InfoExtractor):
'upload_date': '20231106',
'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
'channel': 'Full Measure with Sharyl Attkisson',
'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/'
'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
},
}, {
# video not downloadable in browser, but we can recover it
@@ -72,7 +72,7 @@ class BitChuteIE(InfoExtractor):
'upload_date': '20181113',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/'
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
},
'params': {'check_formats': None},
}, {
@@ -91,6 +91,9 @@ class BitChuteIE(InfoExtractor):
}, {
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
'only_matching': True,
}, {
'url': 'https://old.bitchute.com/video/UGlrF9o9b-Q/',
'only_matching': True,
}]
_GEO_BYPASS = False
@@ -115,7 +118,7 @@ class BitChuteIE(InfoExtractor):
continue
return {
'url': url,
'filesize': int_or_none(response.headers.get('Content-Length'))
'filesize': int_or_none(response.headers.get('Content-Length')),
}
def _raise_if_restricted(self, webpage):
@@ -132,7 +135,7 @@ class BitChuteIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
self._raise_if_restricted(webpage)
publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
@@ -171,13 +174,13 @@ class BitChuteIE(InfoExtractor):
class BitChuteChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bitchute.com/channel/bitchute/',
'info_dict': {
'id': 'bitchute',
'title': 'BitChute',
'description': 'md5:5329fb3866125afa9446835594a9b138',
'description': 'md5:2134c37d64fc3a4846787c402956adac',
},
'playlist': [
{
@@ -196,7 +199,7 @@ class BitChuteChannelIE(InfoExtractor):
'duration': 16,
'view_count': int,
},
}
},
],
'params': {
'skip_download': True,
@@ -209,7 +212,10 @@ class BitChuteChannelIE(InfoExtractor):
'id': 'wV9Imujxasw9',
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:747724ef404eebdfc04277714f81863e',
}
},
}, {
'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
'only_matching': True,
}]
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
@@ -224,13 +230,13 @@ class BitChuteChannelIE(InfoExtractor):
'container': 'playlist-video',
'title': 'title',
'description': 'description',
}
},
}
@staticmethod
def _make_url(playlist_id, playlist_type):
return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
return f'https://old.bitchute.com/{playlist_type}/{playlist_id}/'
def _fetch_page(self, playlist_id, playlist_type, page_num):
playlist_url = self._make_url(playlist_id, playlist_type)

2
yt_dlp/extractor/blackboardcollaborate.py
View File

@@ -47,7 +47,7 @@ class BlackboardCollaborateIE(InfoExtractor):
region = mobj.group('region')
video_id = mobj.group('id')
info = self._download_json(
'https://{}.bbcollab.com/collab/api/csa/recordings/{}/data'.format(region, video_id), video_id)
f'https://{region}.bbcollab.com/collab/api/csa/recordings/{video_id}/data', video_id)
duration = info.get('duration')
title = info['name']
upload_date = info.get('created')

12
yt_dlp/extractor/bleacherreport.py
View File

@@ -44,7 +44,7 @@ class BleacherReportIE(InfoExtractor):
def _real_extract(self, url):
article_id = self._match_id(url)
article_data = self._download_json('http://api.bleacherreport.com/api/v1/articles/%s' % article_id, article_id)['article']
article_data = self._download_json(f'http://api.bleacherreport.com/api/v1/articles/{article_id}', article_id)['article']
thumbnails = []
primary_photo = article_data.get('primaryPhoto')
@@ -71,11 +71,11 @@ class BleacherReportIE(InfoExtractor):
if video:
video_type = video['type']
if video_type in ('cms.bleacherreport.com', 'vid.bleacherreport.com'):
info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
info['url'] = 'http://bleacherreport.com/video_embed?id={}'.format(video['id'])
elif video_type == 'youtube.com':
info['url'] = video['id']
elif video_type == 'vine.co':
info['url'] = 'https://vine.co/v/%s' % video['id']
info['url'] = 'https://vine.co/v/{}'.format(video['id'])
else:
info['url'] = video_type + video['id']
return info
@@ -99,12 +99,12 @@ class BleacherReportCMSIE(AMPIE):
},
'expected_warnings': [
'Unable to download f4m manifest'
]
'Unable to download f4m manifest',
],
}]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._extract_feed_info('http://vid.bleacherreport.com/videos/%s.akamai' % video_id)
info = self._extract_feed_info(f'http://vid.bleacherreport.com/videos/{video_id}.akamai')
info['id'] = video_id
return info

25
yt_dlp/extractor/blerp.py
View File

@@ -16,7 +16,7 @@ class BlerpIE(InfoExtractor):
'uploader_id': '5fb81e51aa66ae000c395478',
'ext': 'mp3',
'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
}
},
}, {
'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
'info_dict': {
@@ -25,11 +25,11 @@ class BlerpIE(InfoExtractor):
'uploader': '179617322678353920',
'uploader_id': '5ba99cf71386730004552c42',
'ext': 'mp3',
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
}
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee'],
},
}]
_GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
_GRAPHQL_OPERATIONNAME = 'webBitePageGetBite'
_GRAPHQL_QUERY = (
'''query webBitePageGetBite($_id: MongoID!) {
web {
@@ -141,27 +141,26 @@ class BlerpIE(InfoExtractor):
'operationName': self._GRAPHQL_OPERATIONNAME,
'query': self._GRAPHQL_QUERY,
'variables': {
'_id': audio_id
}
'_id': audio_id,
},
}
headers = {
'Content-Type': 'application/json'
'Content-Type': 'application/json',
}
json_result = self._download_json('https://api.blerp.com/graphql',
audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
json_result = self._download_json(
'https://api.blerp.com/graphql', audio_id,
data=json.dumps(data).encode(), headers=headers)
bite_json = json_result['data']['web']['biteById']
info_dict = {
return {
'id': bite_json['_id'],
'url': bite_json['audio']['mp3']['url'],
'title': bite_json['title'],
'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
'ext': 'mp3',
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None),
}
return info_dict

4
yt_dlp/extractor/blogger.py
View File

@@ -21,14 +21,14 @@ class BloggerIE(InfoExtractor):
'ext': 'mp4',
'thumbnail': r're:^https?://.*',
'duration': 76.068,
}
},
}]
def _real_extract(self, url):
token_id = self._match_id(url)
webpage = self._download_webpage(url, token_id)
data_json = self._search_regex(r'var\s+VIDEO_CONFIG\s*=\s*(\{.*)', webpage, 'JSON data')
data = self._parse_json(data_json.encode('utf-8').decode('unicode_escape'), token_id)
data = self._parse_json(data_json.encode().decode('unicode_escape'), token_id)
streams = data['streams']
formats = [{
'ext': mimetype2ext(traverse_obj(parse_qs(stream['play_url']), ('mime', 0))),

2
yt_dlp/extractor/bloomberg.py
View File

@@ -55,7 +55,7 @@ class BloombergIE(InfoExtractor):
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(
'http://www.bloomberg.com/multimedia/api/embed?id=%s' % video_id, video_id)
f'http://www.bloomberg.com/multimedia/api/embed?id={video_id}', video_id)
formats = []
for stream in embed_info['streams']:
stream_url = stream.get('url')

15
yt_dlp/extractor/bokecc.py
View File

@@ -1,5 +1,6 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_parse_qs
from ..utils import ExtractorError
@@ -9,20 +10,18 @@ class BokeCCBaseIE(InfoExtractor):
r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
webpage, 'player params', group='query')
player_params = compat_parse_qs(player_params_str)
player_params = urllib.parse.parse_qs(player_params_str)
info_xml = self._download_xml(
'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
'http://p.bokecc.com/servlet/playinfo?uid={}&vid={}&m=1'.format(
player_params['siteid'][0], player_params['vid'][0]), video_id)
formats = [{
return [{
'format_id': format_id,
'url': quality.find('./copy').attrib['playurl'],
'quality': int(quality.attrib['value']),
} for quality in info_xml.findall('./video/quality')]
return formats
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
@@ -38,11 +37,11 @@ class BokeCCIE(BokeCCBaseIE):
}]
def _real_extract(self, url):
qs = compat_parse_qs(self._match_valid_url(url).group('query'))
qs = urllib.parse.parse_qs(self._match_valid_url(url).group('query'))
if not qs.get('vid') or not qs.get('uid'):
raise ExtractorError('Invalid URL', expected=True)
video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0])
video_id = '{}_{}'.format(qs['uid'][0], qs['vid'][0])
webpage = self._download_webpage(url, video_id)

9
yt_dlp/extractor/bongacams.py
View File

@@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
try_get,
@@ -38,7 +37,7 @@ class BongaCamsIE(InfoExtractor):
channel_id = mobj.group('id')
amf = self._download_json(
'https://%s/tools/amf.php' % host, channel_id,
f'https://{host}/tools/amf.php', channel_id,
data=urlencode_postdata((
('method', 'getRoomData'),
('args[]', channel_id),
@@ -48,14 +47,14 @@ class BongaCamsIE(InfoExtractor):
server_url = amf['localData']['videoServerUrl']
uploader_id = try_get(
amf, lambda x: x['performerData']['username'], compat_str) or channel_id
amf, lambda x: x['performerData']['username'], str) or channel_id
uploader = try_get(
amf, lambda x: x['performerData']['displayName'], compat_str)
amf, lambda x: x['performerData']['displayName'], str)
like_count = int_or_none(try_get(
amf, lambda x: x['performerData']['loversCount']))
formats = self._extract_m3u8_formats(
'%s/hls/stream_%s/playlist.m3u8' % (server_url, uploader_id),
f'{server_url}/hls/stream_{uploader_id}/playlist.m3u8',
channel_id, 'mp4', m3u8_id='hls', live=True)
return {

3
yt_dlp/extractor/bostonglobe.py
View File

@@ -57,8 +57,7 @@ class BostonGlobeIE(InfoExtractor):
if video_id and account_id and player_id and embed:
entries.append(
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
% (account_id, player_id, embed, video_id))
f'http://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}')
if len(entries) == 0:
return self.url_result(url, 'Generic')

26
yt_dlp/extractor/box.py
View File

@@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
class BoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<service>app|ent)\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_TESTS = [{
'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@@ -38,10 +38,22 @@ class BoxIE(InfoExtractor):
'uploader_id': '239068974',
},
'params': {'skip_download': 'dash fragment too small'},
}, {
'url': 'https://thejacksonlaboratory.ent.box.com/s/2x09dm6vcg6y28o0oox1so4l0t8wzt6l/file/1536173056065',
'info_dict': {
'id': '1536173056065',
'ext': 'mp4',
'uploader_id': '18523128264',
'uploader': 'Lexi Hennigan',
'title': 'iPSC Symposium recording part 1.mp4',
'timestamp': 1716228343,
'upload_date': '20240520',
},
'params': {'skip_download': 'dash fragment too small'},
}]
def _real_extract(self, url):
shared_name, file_id = self._match_valid_url(url).groups()
shared_name, file_id, service = self._match_valid_url(url).group('shared_name', 'id', 'service')
webpage = self._download_webpage(url, file_id or shared_name)
if not file_id:
@@ -57,14 +69,14 @@ class BoxIE(InfoExtractor):
request_token = self._search_json(
r'Box\.config\s*=', webpage, 'Box config', file_id)['requestToken']
access_token = self._download_json(
'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
f'https://{service}.box.com/app-api/enduserapp/elements/tokens', file_id,
'Downloading token JSON metadata',
data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
'Content-Type': 'application/json',
'X-Request-Token': request_token,
'X-Box-EndUser-API': 'sharedName=' + shared_name,
})[file_id]['read']
shared_link = 'https://app.box.com/s/' + shared_name
shared_link = f'https://{service}.box.com/s/{shared_name}'
f = self._download_json(
'https://api.box.com/2.0/files/' + file_id, file_id,
'Downloading file JSON metadata', headers={
@@ -72,20 +84,20 @@ class BoxIE(InfoExtractor):
'BoxApi': 'shared_link=' + shared_link,
'X-Rep-Hints': '[dash]', # TODO: extract `hls` formats
}, query={
'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size',
})
title = f['name']
query = {
'access_token': access_token,
'shared_link': shared_link
'shared_link': shared_link,
}
formats = []
for url_tmpl in traverse_obj(f, (
'representations', 'entries', lambda _, v: v['representation'] == 'dash',
'content', 'url_template', {url_or_none}
'content', 'url_template', {url_or_none},
)):
manifest_url = update_url_query(url_tmpl.replace('{+asset_path}', 'manifest.mpd'), query)
fmts = self._extract_mpd_formats(manifest_url, file_id)

10
yt_dlp/extractor/boxcast.py
View File

@@ -21,7 +21,7 @@ class BoxCastVideoIE(InfoExtractor):
'release_date': '20221210',
'uploader_id': 're8w0v8hohhvpqtbskpe',
'uploader': 'Children\'s Health Defense',
}
},
}, {
'url': 'https://boxcast.tv/video-portal/vctwevwntun3o0ikq7af/rvyblnn0fxbfjx5nwxhl/otbpltj2kzkveo2qz3ad',
'info_dict': {
@@ -30,8 +30,8 @@ class BoxCastVideoIE(InfoExtractor):
'uploader_id': 'vctwevwntun3o0ikq7af',
'uploader': 'Legacy Christian Church',
'title': 'The Quest | 1: Beginner\'s Bay | Jamie Schools',
'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg'
}
'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg',
},
}, {
'url': 'https://boxcast.tv/channel/z03fqwaeaby5lnaawox2?b=ssihlw5gvfij2by8tkev',
'info_dict': {
@@ -44,7 +44,7 @@ class BoxCastVideoIE(InfoExtractor):
'uploader': 'Lighthouse Ministries International - Beltsville, Maryland',
'description': 'md5:ac23e3d01b0b0be592e8f7fe0ec3a340',
'title': 'New Year\'s Eve CROSSOVER Service at LHMI | December 31, 2022',
}
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://childrenshealthdefense.eu/live-stream/',
@@ -57,7 +57,7 @@ class BoxCastVideoIE(InfoExtractor):
'release_date': '20221210',
'uploader_id': 're8w0v8hohhvpqtbskpe',
'uploader': 'Children\'s Health Defense',
}
},
}]
def _real_extract(self, url):

8
yt_dlp/extractor/br.py
View File

@@ -61,7 +61,7 @@ class BRIE(InfoExtractor):
'title': 'Umweltbewusster Häuslebauer',
'description': 'md5:d52dae9792d00226348c1dbb13c9bae2',
'duration': 116,
}
},
},
{
'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
@@ -74,7 +74,7 @@ class BRIE(InfoExtractor):
'duration': 893,
'uploader': 'Eva Maria Steimle',
'upload_date': '20170208',
}
},
},
]
@@ -142,7 +142,7 @@ class BRIE(InfoExtractor):
http_format_info = format_info.copy()
http_format_info.update({
'url': format_url,
'format_id': 'http-%s' % asset_type,
'format_id': f'http-{asset_type}',
})
formats.append(http_format_info)
server_prefix = xpath_text(asset, 'serverPrefix')
@@ -151,7 +151,7 @@ class BRIE(InfoExtractor):
rtmp_format_info.update({
'url': server_prefix,
'play_path': xpath_text(asset, 'fileName'),
'format_id': 'rtmp-%s' % asset_type,
'format_id': f'rtmp-{asset_type}',
})
formats.append(rtmp_format_info)
return formats

14
yt_dlp/extractor/brainpop.py
View File

@@ -52,8 +52,8 @@ class BrainPOPBaseIE(InfoExtractor):
'%s': {},
'ad_%s': {
'format_note': 'Audio description',
'source_preference': -2
}
'source_preference': -2,
},
}
for additional_key_format, additional_key_fields in additional_key_formats.items():
for key_quality, key_index in enumerate(('high', 'low')):
@@ -62,7 +62,7 @@ class BrainPOPBaseIE(InfoExtractor):
formats.extend(self._assemble_formats(data[full_key_index], full_key_index, display_id, token, {
'quality': -1 - key_quality,
**additional_key_fields,
**extra_fields
**extra_fields,
}))
return formats
@@ -72,7 +72,7 @@ class BrainPOPBaseIE(InfoExtractor):
data=json.dumps({'username': username, 'password': password}).encode(),
headers={
'Content-Type': 'application/json',
'Referer': self._ORIGIN
'Referer': self._ORIGIN,
}, note='Logging in', errnote='Unable to log in', expected_status=400)
status_code = int_or_none(login_res['status_code'])
if status_code != 1505:
@@ -131,12 +131,12 @@ class BrainPOPIE(BrainPOPBaseIE):
formats, subtitles = [], {}
formats.extend(self._extract_adaptive_formats(movie_feature_data, movie_feature_data.get('token', ''), display_id, '%s_v2', {
'language': movie_feature.get('language') or 'en',
'language_preference': 10
'language_preference': 10,
}))
for lang, localized_feature in traverse_obj(movie_feature, 'localization', default={}, expected_type=dict).items():
formats.extend(self._extract_adaptive_formats(localized_feature, localized_feature.get('token', ''), display_id, '%s_v2', {
'language': lang,
'language_preference': -10
'language_preference': -10,
}))
# TODO: Do localization fields also have subtitles?
@@ -145,7 +145,7 @@ class BrainPOPIE(BrainPOPBaseIE):
r'^subtitles_(?P<lang>\w+)$', name, 'subtitle metadata', default=None)
if lang and url:
subtitles.setdefault(lang, []).append({
'url': urljoin(self._CDN_URL, url)
'url': urljoin(self._CDN_URL, url),
})
return {

2
yt_dlp/extractor/bravotv.py
View File

@@ -185,5 +185,5 @@ class BravoTVIE(AdobePassIE):
'episode_number': ('episodeNumber', {int_or_none}),
'episode': 'episodeTitle',
'series': 'show',
}))
})),
}

4
yt_dlp/extractor/breitbart.py
View File

@@ -13,7 +13,7 @@ class BreitBartIE(InfoExtractor):
'description': 'md5:bac35eb0256d1cb17f517f54c79404d5',
'thumbnail': 'https://cdn.jwplayer.com/thumbs/5cOz1yup-1920.jpg',
'age_limit': 0,
}
},
}, {
'url': 'https://www.breitbart.com/videos/v/eaiZjVOn/',
'only_matching': True,
@@ -30,5 +30,5 @@ class BreitBartIE(InfoExtractor):
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'age_limit': self._rta_search(webpage),
'formats': formats
'formats': formats,
}

84
yt_dlp/extractor/brightcove.py
View File

@@ -1,15 +1,12 @@
import base64
import re
import struct
import urllib.parse
import xml.etree.ElementTree
from .adobepass import AdobePassIE
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
compat_urlparse,
)
from ..compat import compat_etree_fromstring
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
@@ -21,6 +18,7 @@ from ..utils import (
fix_xml_ampersands,
float_or_none,
int_or_none,
join_nonempty,
js_to_json,
mimetype2ext,
parse_iso8601,
@@ -142,7 +140,7 @@ class BrightcoveLegacyIE(InfoExtractor):
# from http://www.un.org/chinese/News/story.asp?NewsID=27724
'url': 'https://link.brightcove.com/services/player/bcpid1722935254001/?bctid=5360463607001&autoStart=false&secureConnections=true&width=650&height=350',
'only_matching': True, # Tested in GenericIE
}
},
]
_WEBPAGE_TESTS = [{
@@ -315,7 +313,7 @@ class BrightcoveLegacyIE(InfoExtractor):
object_str = fix_xml_ampersands(object_str)
try:
object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
object_doc = compat_etree_fromstring(object_str.encode())
except xml.etree.ElementTree.ParseError:
return
@@ -323,7 +321,7 @@ class BrightcoveLegacyIE(InfoExtractor):
if fv_el is not None:
flashvars = dict(
(k, v[0])
for k, v in compat_parse_qs(fv_el.attrib['value']).items())
for k, v in urllib.parse.parse_qs(fv_el.attrib['value']).items())
else:
flashvars = {}
@@ -340,32 +338,32 @@ class BrightcoveLegacyIE(InfoExtractor):
params = {}
playerID = find_param('playerID') or find_param('playerId')
if playerID is None:
player_id = find_param('playerID') or find_param('playerId')
if player_id is None:
raise ExtractorError('Cannot find player ID')
params['playerID'] = playerID
params['playerID'] = player_id
playerKey = find_param('playerKey')
player_key = find_param('playerKey')
# Not all pages define this value
if playerKey is not None:
params['playerKey'] = playerKey
if player_key is not None:
params['playerKey'] = player_key
# These fields hold the id of the video
videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
if videoPlayer is not None:
if isinstance(videoPlayer, list):
videoPlayer = videoPlayer[0]
videoPlayer = videoPlayer.strip()
video_player = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
if video_player is not None:
if isinstance(video_player, list):
video_player = video_player[0]
video_player = video_player.strip()
# UUID is also possible for videoPlayer (e.g.
# http://www.popcornflix.com/hoodies-vs-hooligans/7f2d2b87-bbf2-4623-acfb-ea942b4f01dd
# or http://www8.hp.com/cn/zh/home.html)
if not (re.match(
r'^(?:\d+|[\da-fA-F]{8}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{12})$',
videoPlayer) or videoPlayer.startswith('ref:')):
video_player) or video_player.startswith('ref:')):
return None
params['@videoPlayer'] = videoPlayer
linkBase = find_param('linkBaseURL')
if linkBase is not None:
params['linkBaseURL'] = linkBase
params['@videoPlayer'] = video_player
link_base = find_param('linkBaseURL')
if link_base is not None:
params['linkBaseURL'] = link_base
return cls._make_brightcove_url(params)
@classmethod
@@ -389,7 +387,7 @@ class BrightcoveLegacyIE(InfoExtractor):
@classmethod
def _make_brightcove_url(cls, params):
return update_url_query(
'http://c.brightcove.com/services/viewer/htmlFederated', params)
'https://c.brightcove.com/services/viewer/htmlFederated', params)
@classmethod
def _extract_brightcove_url(cls, webpage):
@@ -448,13 +446,13 @@ class BrightcoveLegacyIE(InfoExtractor):
url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
mobj = self._match_valid_url(url)
query_str = mobj.group('query')
query = compat_urlparse.parse_qs(query_str)
query = urllib.parse.parse_qs(query_str)
videoPlayer = query.get('@videoPlayer')
if videoPlayer:
video_player = query.get('@videoPlayer')
if video_player:
# We set the original url as the default 'Referer' header
referer = query.get('linkBaseURL', [None])[0] or smuggled_data.get('Referer', url)
video_id = videoPlayer[0]
video_id = video_player[0]
if 'playerID' not in query:
mobj = re.search(r'/bcpid(\d+)', url)
if mobj is not None:
@@ -473,7 +471,7 @@ class BrightcoveLegacyIE(InfoExtractor):
if referer:
headers['Referer'] = referer
player_page = self._download_webpage(
'http://link.brightcove.com/services/player/bcpid' + player_id[0],
'https://link.brightcove.com/services/player/bcpid' + player_id[0],
video_id, headers=headers, fatal=False)
if player_page:
player_key = self._search_regex(
@@ -483,7 +481,7 @@ class BrightcoveLegacyIE(InfoExtractor):
enc_pub_id = player_key.split(',')[1].replace('~', '=')
publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0]
if publisher_id:
brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
brightcove_new_url = f'https://players.brightcove.net/{publisher_id}/default_default/index.html?videoId={video_id}'
if referer:
brightcove_new_url = smuggle_url(brightcove_new_url, {'referrer': referer})
return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
@@ -541,12 +539,7 @@ class BrightcoveNewBaseIE(AdobePassIE):
})
def build_format_id(kind):
format_id = kind
if tbr:
format_id += '-%dk' % int(tbr)
if height:
format_id += '-%dp' % height
return format_id
return join_nonempty(kind, tbr and f'{int(tbr)}k', height and f'{height}p')
if src or streaming_src:
f.update({
@@ -654,7 +647,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'params': {
# m3u8 download
'skip_download': True,
}
},
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
@@ -666,7 +659,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'params': {
# m3u8 download
'skip_download': True,
}
},
}, {
'url': 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=5743160747001',
'only_matching': True,
@@ -804,7 +797,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
# Look for iframe embeds [1]
for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
entries.append(url if url.startswith('http') else 'http:' + url)
entries.append(url if url.startswith(('http:', 'https:')) else 'https:' + url)
# Look for <video> tags [2] and embed_in_page embeds [3]
# [2] looks like:
@@ -833,8 +826,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
player_id = player_id or attrs.get('data-player') or 'default'
embed = embed or attrs.get('data-embed') or 'default'
bc_url = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' % (
account_id, player_id, embed, video_id)
bc_url = f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}'
# Some brightcove videos may be embedded with video tag only and
# without script tag or any mentioning of brightcove at all. Such
@@ -865,13 +857,13 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
account_id, player_id, embed, content_type, video_id = self._match_valid_url(url).groups()
policy_key_id = '%s_%s' % (account_id, player_id)
policy_key_id = f'{account_id}_{player_id}'
policy_key = self.cache.load('brightcove', policy_key_id)
policy_key_extracted = False
store_pk = lambda x: self.cache.store('brightcove', policy_key_id, x)
def extract_policy_key():
base_url = 'http://players.brightcove.net/%s/%s_%s/' % (account_id, player_id, embed)
base_url = f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/'
config = self._download_json(
base_url + 'config.json', video_id, fatal=False) or {}
policy_key = try_get(
@@ -910,7 +902,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
if not policy_key:
policy_key = extract_policy_key()
policy_key_extracted = True
headers['Accept'] = 'application/json;pk=%s' % policy_key
headers['Accept'] = f'application/json;pk={policy_key}'
try:
json_data = self._download_json(api_url, video_id, headers=headers)
break
@@ -936,7 +928,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
custom_fields['bcadobepassresourceid'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
'Accept': f'application/json;pk={policy_key}',
}, query={
'tveToken': tve_token,
})

10
yt_dlp/extractor/bundesliga.py
View File

@@ -16,17 +16,17 @@ class BundesligaIE(InfoExtractor):
'upload_date': '20220928',
'duration': 146,
'timestamp': 1664366511,
'description': 'md5:803d4411bd134140c774021dd4b7598b'
}
'description': 'md5:803d4411bd134140c774021dd4b7598b',
},
},
{
'url': 'https://www.bundesliga.com/en/bundesliga/videos/latest-features/T8IKc8TX?vid=ROHjs06G',
'only_matching': True
'only_matching': True,
},
{
'url': 'https://www.bundesliga.com/en/bundesliga/videos/goals?vid=mOG56vWA',
'only_matching': True
}
'only_matching': True,
},
]
def _real_extract(self, url):

4
yt_dlp/extractor/businessinsider.py
View File

@@ -10,7 +10,7 @@ class BusinessInsiderIE(InfoExtractor):
'info_dict': {
'id': 'cjGDb0X9',
'ext': 'mp4',
'title': "Bananas give you more radiation exposure than living next to a nuclear power plant",
'title': 'Bananas give you more radiation exposure than living next to a nuclear power plant',
'description': 'md5:0175a3baf200dd8fa658f94cade841b3',
'upload_date': '20160611',
'timestamp': 1465675620,
@@ -41,5 +41,5 @@ class BusinessInsiderIE(InfoExtractor):
r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'),
webpage, 'jwplatform id')
return self.url_result(
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
f'jwplatform:{jwplatform_id}', ie=JWPlatformIE.ie_key(),
video_id=video_id)

6
yt_dlp/extractor/buzzfeed.py
View File

@@ -23,8 +23,8 @@ class BuzzFeedIE(InfoExtractor):
'upload_date': '20141024',
'uploader_id': 'Buddhanz1',
'uploader': 'Angry Ram',
}
}]
},
}],
}, {
'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
'params': {
@@ -45,7 +45,7 @@ class BuzzFeedIE(InfoExtractor):
'uploader_id': 'CindysMunchkin',
'uploader': 're:^Munchkin the',
},
}]
}],
}, {
'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK',
'info_dict': {

2
yt_dlp/extractor/byutv.py
View File

@@ -36,7 +36,7 @@ class BYUtvIE(InfoExtractor):
'duration': 11645,
},
'params': {
'skip_download': True
'skip_download': True,
},
}, {
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',

4
yt_dlp/extractor/c56.py
View File

@@ -38,7 +38,7 @@ class C56IE(InfoExtractor):
return self.url_result(sohu_video_info['url'], 'Sohu')
page = self._download_json(
'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
f'http://vxml.56.com/json/{text_id}/', text_id, 'Downloading video info')
info = page['info']
@@ -46,7 +46,7 @@ class C56IE(InfoExtractor):
{
'format_id': f['type'],
'filesize': int(f['filesize']),
'url': f['url']
'url': f['url'],
} for f in info['rfiles']
]

16
yt_dlp/extractor/callin.py
View File

@@ -29,8 +29,8 @@ class CallinIE(InfoExtractor):
'series_id': '436d1f82ddeb30cd2306ea9156044d8d2cfdc3f1f1552d245117a42173e78553',
'episode': 'The Title IX Regime and the Long March Through and Beyond the Institutions',
'episode_number': 1,
'episode_id': '218b979630a35ead12c6fd096f2996c56c37e4d0dc1f6dc0feada32dcf7b31cd'
}
'episode_id': '218b979630a35ead12c6fd096f2996c56c37e4d0dc1f6dc0feada32dcf7b31cd',
},
}, {
'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW',
'md5': '14ede27ee2c957b7e4db93140fc0745c',
@@ -54,7 +54,7 @@ class CallinIE(InfoExtractor):
'thumbnail': 'https://d1z76fhpoqkd01.cloudfront.net/shows/legacy/1ade9142625344045dc17cf523469ced1d93610762f4c886d06aa190a2f979e8.png',
'episode_id': 'c3dab47f237bf953d180d3f243477a84302798be0e0b29bc9ade6d60a69f04f5',
'timestamp': 1662100688.005,
}
},
}, {
'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA',
'md5': '16f704ddbf82a27e3930533b12062f07',
@@ -78,7 +78,7 @@ class CallinIE(InfoExtractor):
'thumbnail': 'https://d1z76fhpoqkd01.cloudfront.net/shows/legacy/461ea0d86172cb6aff7d6c80fd49259cf5e64bdf737a4650f8bc24cf392ca218.png',
'episode_id': '8d06f869798f93a7814e380bceabea72d501417e620180416ff6bd510596e83c',
'timestamp': 1661476708.282,
}
},
}]
def try_get_user_name(self, d):
@@ -94,7 +94,7 @@ class CallinIE(InfoExtractor):
next_data = self._search_nextjs_data(webpage, display_id)
episode = next_data['props']['pageProps']['episode']
id = episode['id']
video_id = episode['id']
title = episode.get('title') or self._generic_title('', webpage)
url = episode['m3u8']
formats = self._extract_m3u8_formats(url, display_id, ext='ts')
@@ -125,11 +125,11 @@ class CallinIE(InfoExtractor):
episode_list = traverse_obj(show_json, ('pageProps', 'show', 'episodes')) or []
episode_number = next(
(len(episode_list) - i for (i, e) in enumerate(episode_list) if e.get('id') == id),
(len(episode_list) - i for i, e in enumerate(episode_list) if e.get('id') == video_id),
None)
return {
'id': id,
'id': video_id,
'_old_archive_ids': [make_archive_id(self, display_id.rsplit('-', 1)[-1])],
'display_id': display_id,
'title': title,
@@ -151,5 +151,5 @@ class CallinIE(InfoExtractor):
'series_id': show_id,
'episode': title,
'episode_number': episode_number,
'episode_id': id
'episode_id': video_id,
}

2
yt_dlp/extractor/caltrans.py
View File

@@ -11,7 +11,7 @@ class CaltransIE(InfoExtractor):
'title': 'US-50 : Sacramento : Hwy 50 at 24th',
'live_status': 'is_live',
'thumbnail': 'https://cwwp2.dot.ca.gov/data/d3/cctv/image/hwy50at24th/hwy50at24th.jpg',
}
},
}
def _real_extract(self, url):

4
yt_dlp/extractor/cam4.py
View File

@@ -12,12 +12,12 @@ class CAM4IE(InfoExtractor):
'age_limit': 18,
'live_status': 'is_live',
'thumbnail': 'https://snapshots.xcdnpro.com/thumbnails/foxynesss',
}
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
m3u8_playlist = self._download_json('https://www.cam4.com/rest/v1.0/profile/{}/streamInfo'.format(channel_id), channel_id).get('cdnURL')
m3u8_playlist = self._download_json(f'https://www.cam4.com/rest/v1.0/profile/{channel_id}/streamInfo', channel_id).get('cdnURL')
formats = self._extract_m3u8_formats(m3u8_playlist, channel_id, 'mp4', m3u8_id='hls', live=True)

33
yt_dlp/extractor/camdemy.py
View File

@@ -1,10 +1,7 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
clean_html,
parse_duration,
@@ -28,7 +25,7 @@ class CamdemyIE(InfoExtractor):
'duration': 1591,
'upload_date': '20130114',
'view_count': int,
}
},
}, {
# With non-empty description
# webpage returns "No permission or not login"
@@ -42,7 +39,7 @@ class CamdemyIE(InfoExtractor):
'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
'creator': 'evercam',
'duration': 318,
}
},
}, {
# External source (YouTube)
'url': 'http://www.camdemy.com/media/14842',
@@ -76,12 +73,12 @@ class CamdemyIE(InfoExtractor):
title = oembed_obj['title']
thumb_url = oembed_obj['thumbnail_url']
video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
video_folder = urllib.parse.urljoin(thumb_url, 'video/')
file_list_doc = self._download_xml(
compat_urlparse.urljoin(video_folder, 'fileList.xml'),
urllib.parse.urljoin(video_folder, 'fileList.xml'),
video_id, 'Downloading filelist XML')
file_name = file_list_doc.find('./video/item/fileName').text
video_url = compat_urlparse.urljoin(video_folder, file_name)
video_url = urllib.parse.urljoin(video_folder, file_name)
# Some URLs return "No permission or not login" in a webpage despite being
# freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885)
@@ -117,35 +114,35 @@ class CamdemyFolderIE(InfoExtractor):
'id': '450',
'title': '信號與系統 2012 & 2011 (Signals and Systems)',
},
'playlist_mincount': 145
'playlist_mincount': 145,
}, {
# links without trailing slash
# and multi-page
'url': 'http://www.camdemy.com/folder/853',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
'title': '科學計算 - 使用 Matlab',
},
'playlist_mincount': 20
'playlist_mincount': 20,
}, {
# with displayMode parameter. For testing the codes to add parameters
'url': 'http://www.camdemy.com/folder/853/?displayMode=defaultOrderByOrg',
'info_dict': {
'id': '853',
'title': '科學計算 - 使用 Matlab'
'title': '科學計算 - 使用 Matlab',
},
'playlist_mincount': 20
'playlist_mincount': 20,
}]
def _real_extract(self, url):
folder_id = self._match_id(url)
# Add displayMode=list so that all links are displayed in a single page
parsed_url = list(compat_urlparse.urlparse(url))
query = dict(compat_urlparse.parse_qsl(parsed_url[4]))
parsed_url = list(urllib.parse.urlparse(url))
query = dict(urllib.parse.parse_qsl(parsed_url[4]))
query.update({'displayMode': 'list'})
parsed_url[4] = compat_urllib_parse_urlencode(query)
final_url = compat_urlparse.urlunparse(parsed_url)
parsed_url[4] = urllib.parse.urlencode(query)
final_url = urllib.parse.urlunparse(parsed_url)
page = self._download_webpage(final_url, folder_id)
matches = re.findall(r"href='(/media/\d+/?)'", page)

Some files were not shown because too many files have changed in this diff Show More