mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-01-06 23:11:16 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into cineverse-extra_metadata

Browse Source
This commit is contained in:
shloop
2024-08-17 13:01:11 -07:00
committed by GitHub
parent 97b8f7f8cc d62fef7e07
commit b20719b7c6
1221 changed files with 41624 additions and 32055 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1436
yt_dlp/extractor/_extractors.py
View File

File diff suppressed because it is too large Load Diff

138
yt_dlp/extractor/abc.py
View File

@@ -4,18 +4,18 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
ExtractorError,
js_to_json,
dict_get,
int_or_none,
js_to_json,
parse_iso8601,
str_or_none,
traverse_obj,
try_get,
unescapeHTML,
update_url_query,
url_or_none,
)
@@ -66,7 +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': {
@@ -74,7 +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': {
@@ -85,7 +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': {
@@ -94,7 +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):
@@ -125,7 +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(
@@ -163,7 +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 {
@@ -181,18 +181,99 @@ class ABCIViewIE(InfoExtractor):
_GEO_COUNTRIES = ['AU']
_TESTS = [{
'url': 'https://iview.abc.net.au/show/utopia/series/1/video/CO1211V001S00',
'md5': '52a942bfd7a0b79a6bfe9b4ce6c9d0ed',
'info_dict': {
'id': 'CO1211V001S00',
'ext': 'mp4',
'title': 'Series 1 Ep 1 Wood For The Trees',
'series': 'Utopia',
'description': 'md5:0cfb2c183c1b952d1548fd65c8a95c00',
'upload_date': '20230726',
'uploader_id': 'abc1',
'series_id': 'CO1211V',
'episode_id': 'CO1211V001S00',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Wood For The Trees',
'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/co/CO1211V001S00_5ad8353f4df09_1280.jpg',
'timestamp': 1690403700,
},
'params': {
'skip_download': True,
},
}, {
'note': 'No episode name',
'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': {
'id': 'LE1927H001S00',
'ext': 'mp4',
'title': "Series 11 Ep 1",
'series': "Gruen",
'title': 'Series 11 Ep 1',
'series': 'Gruen',
'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
'upload_date': '20190925',
'uploader_id': 'abc1',
'series_id': 'LE1927H',
'episode_id': 'LE1927H001S00',
'season_number': 11,
'season': 'Season 11',
'episode_number': 1,
'episode': 'Episode 1',
'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/le/LE1927H001S00_5d954fbd79e25_1280.jpg',
'timestamp': 1569445289,
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'params': {
'skip_download': True,
},
}, {
'note': 'No episode number',
'url': 'https://iview.abc.net.au/show/four-corners/series/2022/video/NC2203H039S00',
'md5': '77cb7d8434440e3b28fbebe331c2456a',
'info_dict': {
'id': 'NC2203H039S00',
'ext': 'mp4',
'title': 'Series 2022 Locking Up Kids',
'series': 'Four Corners',
'description': 'md5:54829ca108846d1a70e1fcce2853e720',
'upload_date': '20221114',
'uploader_id': 'abc1',
'series_id': 'NC2203H',
'episode_id': 'NC2203H039S00',
'season_number': 2022,
'season': 'Season 2022',
'episode': 'Locking Up Kids',
'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/nc/NC2203H039S00_636d8a0944a22_1920.jpg',
'timestamp': 1668460497,
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'params': {
'skip_download': True,
},
}, {
'note': 'No episode name or number',
'url': 'https://iview.abc.net.au/show/landline/series/2021/video/RF2004Q043S00',
'md5': '2e17dec06b13cc81dc119d2565289396',
'info_dict': {
'id': 'RF2004Q043S00',
'ext': 'mp4',
'title': 'Series 2021',
'series': 'Landline',
'description': 'md5:c9f30d9c0c914a7fd23842f6240be014',
'upload_date': '20211205',
'uploader_id': 'abc1',
'series_id': 'RF2004Q',
'episode_id': 'RF2004Q043S00',
'season_number': 2021,
'season': 'Season 2021',
'thumbnail': 'https://cdn.iview.abc.net.au/thumbs/i/rf/RF2004Q043S00_61a950639dbc0_1920.jpg',
'timestamp': 1638710705,
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'params': {
'skip_download': True,
},
@@ -206,13 +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, {
@@ -221,7 +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(
@@ -254,6 +334,8 @@ class ABCIViewIE(InfoExtractor):
'episode_number': int_or_none(self._search_regex(
r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
'episode_id': house_number,
'episode': self._search_regex(
r'^(?:Series\s+\d+)?\s*(?:Ep\s+\d+)?\s*(.*)$', title, 'episode', default='') or None,
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
@@ -274,7 +356,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'description': 'md5:93119346c24a7c322d446d8eece430ff',
'series': 'Upper Middle Bogan',
'season': 'Series 1',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 8,
}, {
@@ -293,6 +375,18 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'noplaylist': True,
'skip_download': 'm3u8',
},
}, {
# 'videoEpisodes' is a dict with `items` key
'url': 'https://iview.abc.net.au/show/7-30-mark-humphries-satire',
'info_dict': {
'id': '178458-0',
'title': 'Episodes',
'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
'series': '7.30 Mark Humphries Satire',
'season': 'Episodes',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 15,
}]
def _real_extract(self, url):
@@ -302,7 +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'])
@@ -312,12 +406,14 @@ class ABCIViewShowSeriesIE(InfoExtractor):
series = video_data['selectedSeries']
return {
'_type': 'playlist',
'entries': [self.url_result(episode['shareUrl'])
for episode in series['_embedded']['videoEpisodes']],
'entries': [self.url_result(episode_url, ABCIViewIE)
for episode_url in traverse_obj(series, (
'_embedded', 'videoEpisodes', (None, 'items'), ..., 'shareUrl', {url_or_none}))],
'id': series.get('id'),
'title': dict_get(series, ('title', 'displaySubtitle')),
'description': series.get('description'),
'series': dict_get(series, ('showTitle', 'displayTitle')),
'season': dict_get(series, ('title', 'displaySubtitle')),
'thumbnail': series.get('thumbnail'),
'thumbnail': traverse_obj(
series, 'thumbnail', ('images', lambda _, v: v['name'] == 'seriesThumbnail', 'url'), get_all=False),
}

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 = []

172
yt_dlp/extractor/abematv.py
View File

@@ -9,53 +9,53 @@ import re
import struct
import time
import urllib.parse
import urllib.request
import urllib.response
import uuid
from ..utils.networking import clean_proxies
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,
bytes_to_intlist,
decode_base_n,
int_or_none,
intlist_to_bytes,
OnDemandPagedList,
time_seconds,
traverse_obj,
update_url_query,
)
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'))
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)
@@ -65,33 +65,27 @@ 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'
_USERTOKEN = None
_DEVICE_ID = None
_MEDIATOKEN = None
@@ -100,11 +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
@@ -116,7 +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):
@@ -136,11 +130,15 @@ class AbemaTVBaseIE(InfoExtractor):
if self._USERTOKEN:
return self._USERTOKEN
self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
username, _ = self._get_login_info()
AbemaTVBaseIE._USERTOKEN = username and self.cache.load(self._NETRC_MACHINE, username)
auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
AbemaTVBaseIE._USERTOKEN = auth_cache and auth_cache.get('usertoken')
if AbemaTVBaseIE._USERTOKEN:
# try authentication with locally stored token
try:
AbemaTVBaseIE._DEVICE_ID = auth_cache.get('device_id')
self._get_media_token(True)
return
except ExtractorError as e:
@@ -153,13 +151,12 @@ class AbemaTVBaseIE(InfoExtractor):
data=json.dumps({
'deviceId': self._DEVICE_ID,
'applicationKeySecret': aks,
}).encode('utf-8'),
}).encode(),
headers={
'Content-Type': 'application/json',
})
AbemaTVBaseIE._USERTOKEN = user_data['token']
add_opener(self._downloader, AbemaLicenseHandler(self))
return self._USERTOKEN
def _get_media_token(self, invalidate=False, to_show=True):
@@ -174,13 +171,44 @@ 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']
return self._MEDIATOKEN
def _perform_login(self, username, password):
self._get_device_token()
if self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19') and self._get_media_token():
self.write_debug('Skipping logging in')
return
if '@' in username: # don't strictly check if it's email address or not
ep, method = 'user/email', 'email'
else:
ep, method = 'oneTimePassword', 'userId'
login_response = self._download_json(
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password,
}).encode(), headers={
'Authorization': f'bearer {self._get_device_token()}',
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
'Content-Type': 'application/json',
})
AbemaTVBaseIE._USERTOKEN = login_response['token']
self._get_media_token(True)
auth_cache = {
'device_id': AbemaTVBaseIE._DEVICE_ID,
'usertoken': AbemaTVBaseIE._USERTOKEN,
}
self.cache.store(self._NETRC_MACHINE, username, auth_cache)
def _call_api(self, endpoint, video_id, query=None, note='Downloading JSON metadata'):
return self._download_json(
f'https://api.abema.io/{endpoint}', video_id, query=query or {},
@@ -204,14 +232,14 @@ class AbemaTVBaseIE(InfoExtractor):
class AbemaTVIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/(?P<type>now-on-air|video/episode|channels/.+?/slots)/(?P<id>[^?/]+)'
_NETRC_MACHINE = 'abematv'
_TESTS = [{
'url': 'https://abema.tv/video/episode/194-25_s2_p1',
'info_dict': {
'id': '194-25_s2_p1',
'title': '第1話 「チーズケーキ」　「モーニング再び」',
'series': '異世界食堂２',
'series_number': 2,
'season': 'シーズン2',
'season_number': 2,
'episode': '第1話 「チーズケーキ」　「モーニング再び」',
'episode_number': 1,
},
@@ -223,7 +251,7 @@ class AbemaTVIE(AbemaTVBaseIE):
'title': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】',
'series': 'ゆるキャン△ SEASON２',
'episode': 'ゆるキャン△ SEASON２ 全話一挙【無料ビデオ72時間】',
'series_number': 2,
'season_number': 2,
'episode_number': 1,
'description': 'md5:9c5a3172ae763278f9303922f0ea5b17',
},
@@ -252,33 +280,6 @@ class AbemaTVIE(AbemaTVBaseIE):
}]
_TIMETABLE = None
def _perform_login(self, username, password):
self._get_device_token()
if self.cache.load(self._NETRC_MACHINE, username) and self._get_media_token():
self.write_debug('Skipping logging in')
return
if '@' in username: # don't strictly check if it's email address or not
ep, method = 'user/email', 'email'
else:
ep, method = 'oneTimePassword', 'userId'
login_response = self._download_json(
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password
}).encode('utf-8'), headers={
'Authorization': f'bearer {self._get_device_token()}',
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
'Content-Type': 'application/json',
})
AbemaTVBaseIE._USERTOKEN = login_response['token']
self._get_media_token(True)
self.cache.store(self._NETRC_MACHINE, username, AbemaTVBaseIE._USERTOKEN)
def _real_extract(self, url):
# starting download using infojson from this extractor is undefined behavior,
# and never be fixed in the future; you must trigger downloads by directly specifying URL.
@@ -334,7 +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(
@@ -347,17 +348,18 @@ class AbemaTVIE(AbemaTVBaseIE):
)?
''', r'\1', og_desc)
# canonical URL may contain series and episode number
# canonical URL may contain season and episode number
mobj = re.search(r's(\d+)_p(\d+)$', canonical_url)
if mobj:
seri = int_or_none(mobj.group(1), default=float('inf'))
epis = int_or_none(mobj.group(2), default=float('inf'))
info['series_number'] = seri if seri < 100 else None
info['season_number'] = seri if seri < 100 else None
# some anime like Detective Conan (though not available in AbemaTV)
# has more than 1000 episodes (1026 as of 2021/11/15)
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'
@@ -375,13 +377,13 @@ class AbemaTVIE(AbemaTVBaseIE):
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
if 3 not in ondemand_types:
if not traverse_obj(api_response, ('label', 'free', {bool})):
# 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', 'title'),
'season': ('season', 'name'),
'season_number': ('season', 'sequence'),
'episode_number': ('episode', 'number'),
}))
@@ -398,6 +400,7 @@ 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:
@@ -415,6 +418,7 @@ 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)

13
yt_dlp/extractor/acfun.py
View File

@@ -3,9 +3,10 @@ from ..utils import (
float_or_none,
format_field,
int_or_none,
traverse_obj,
parse_codecs,
parse_qs,
str_or_none,
traverse_obj,
)
@@ -24,7 +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 {
@@ -76,7 +77,7 @@ class AcFunVideoIE(AcFunVideoBaseIE):
'comment_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
'description': 'md5:67583aaf3a0f933bd606bc8a2d3ebb17',
}
},
}]
def _real_extract(self, url):
@@ -129,7 +130,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
'title': '红孩儿之趴趴蛙寻石记 第5话 ',
'duration': 760.0,
'season': '红孩儿之趴趴蛙寻石记',
'season_id': 5023171,
'season_id': '5023171',
'season_number': 1, # series has only 1 season
'episode': 'Episode 5',
'episode_number': 5,
@@ -146,7 +147,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
'title': '叽歪老表（第二季） 第5话 坚不可摧',
'season': '叽歪老表（第二季）',
'season_number': 2,
'season_id': 6065485,
'season_id': '6065485',
'episode': '坚不可摧',
'episode_number': 5,
'upload_date': '20220324',
@@ -191,7 +192,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
'title': json_bangumi_data.get('showTitle'),
'thumbnail': json_bangumi_data.get('image'),
'season': json_bangumi_data.get('bangumiTitle'),
'season_id': season_id,
'season_id': str_or_none(season_id),
'season_number': season_number,
'episode': json_bangumi_data.get('title'),
'episode_number': episode_number,

148
yt_dlp/extractor/adn.py
View File

@@ -3,33 +3,55 @@ import binascii
import json
import os
import random
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,
ass_subtitles_timecode,
bytes_to_intlist,
bytes_to_long,
ExtractorError,
float_or_none,
int_or_none,
intlist_to_bytes,
join_nonempty,
long_to_bytes,
parse_iso8601,
pkcs1pad,
str_or_none,
strip_or_none,
try_get,
unified_strdate,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class ADNIE(InfoExtractor):
class ADNBaseIE(InfoExtractor):
IE_DESC = 'Animation Digital Network'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = f'https://gw.api.{_BASE}/'
_PLAYER_BASE_URL = f'{_API_BASE_URL}player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
_POS_ALIGN_MAP = {
'start': 1,
'end': 3,
}
_LINE_ALIGN_MAP = {
'middle': 8,
'end': 4,
}
class ADNIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.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/558-fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '9841',
@@ -44,29 +66,32 @@ class ADNIE(InfoExtractor):
'season_number': 1,
'episode': 'À ce soir !',
'episode_number': 1,
'thumbnail': str,
'season': 'Season 1',
},
'skip': 'Only available in region (FR, ...)',
'skip': 'Only available in French and German speaking Europe',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
'url': 'https://animationdigitalnetwork.com/de/video/973-the-eminence-in-shadow/23550-folge-1',
'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
'info_dict': {
'id': '23550',
'ext': 'mp4',
'episode_number': 1,
'duration': 1417,
'release_date': '20231004',
'series': 'The Eminence in Shadow',
'season_number': 2,
'episode': str,
'title': str,
'thumbnail': str,
'season': 'Season 2',
'comment_count': int,
'average_rating': float,
'description': str,
},
# 'skip': 'Only available in French and German speaking Europe',
}]
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.' + _BASE + '/'
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
_POS_ALIGN_MAP = {
'start': 1,
'end': 3,
}
_LINE_ALIGN_MAP = {
'middle': 8,
'end': 4,
}
def _get_subtitles(self, sub_url, video_id):
if not sub_url:
return None
@@ -83,9 +108,9 @@ class ADNIE(InfoExtractor):
# 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
@@ -108,7 +133,7 @@ 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 '',
@@ -116,6 +141,8 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
if sub_lang == 'vostf':
sub_lang = 'fr'
elif sub_lang == 'vostde':
sub_lang = 'de'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
@@ -137,7 +164,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
'username': username,
})) or {}).get('accessToken')
if access_token:
self._HEADERS = {'authorization': 'Bearer ' + access_token}
self._HEADERS['Authorization'] = f'Bearer {access_token}'
except ExtractorError as e:
message = None
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
@@ -147,8 +174,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
def _real_extract(self, url):
video_id = self._match_id(url)
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
lang, video_id = self._match_valid_url(url).group('lang', 'id')
self._HEADERS['X-Target-Distribution'] = lang or 'fr'
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',
@@ -157,12 +185,15 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
user = options['user']
if not user.get('hasAccess'):
self.raise_login_required()
start_date = traverse_obj(options, ('video', 'startDate', {str}))
if (parse_iso8601(start_date) or 0) > time.time():
raise ExtractorError(f'This video is not available yet. Release date: {start_date}', expected=True)
self.raise_login_required('This video requires a subscription', method='password')
token = self._download_json(
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
video_id, 'Downloading access token', headers={
'x-player-refresh-token': user['refreshToken']
'X-Player-Refresh-Token': user['refreshToken'],
}, data=b'')['token']
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
@@ -184,12 +215,13 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
try:
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization
'X-Player-Token': authorization,
**self._HEADERS,
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
'source': 'Web',
})
break
except ExtractorError as e:
@@ -221,7 +253,8 @@ 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',
headers=self._HEADERS,
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
@@ -232,11 +265,17 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
elif format_id == 'vde':
for f in m3u8_formats:
f['language'] = 'de'
formats.extend(m3u8_formats)
if not formats:
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,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
self._API_BASE_URL + f'video/{video_id}', video_id,
'Downloading additional video metadata', fatal=False, headers=self._HEADERS) or {}).get('video') or {}
show = video.get('show') or {}
return {
@@ -255,3 +294,38 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
'comment_count': int_or_none(video.get('commentsCount')),
}
class ADNSeasonIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?animationdigitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>\d+)[^/?#]*/?(?:$|[#?])'
_TESTS = [{
'url': 'https://animationdigitalnetwork.com/video/911-tokyo-mew-mew-new',
'playlist_count': 12,
'info_dict': {
'id': '911',
'title': 'Tokyo Mew Mew New',
},
# 'skip': 'Only available in French end German speaking Europe',
}]
def _real_extract(self, url):
lang, video_show_slug = self._match_valid_url(url).group('lang', 'id')
self._HEADERS['X-Target-Distribution'] = lang or 'fr'
show = self._download_json(
f'{self._API_BASE_URL}show/{video_show_slug}/', video_show_slug,
'Downloading show JSON metadata', headers=self._HEADERS)['show']
show_id = str(show['id'])
episodes = self._download_json(
f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
'Downloading episode list', headers=self._HEADERS, query={
'order': 'asc',
'limit': '-1',
})
def entries():
for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
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

9
yt_dlp/extractor/adobetv.py
View File

@@ -2,13 +2,12 @@ import functools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ISO639Utils,
OnDemandPagedList,
float_or_none,
int_or_none,
ISO639Utils,
join_nonempty,
OnDemandPagedList,
parse_duration,
str_or_none,
str_to_int,
@@ -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):

7
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") {
@@ -107,7 +107,6 @@ class AdultSwimIE(TurnerBaseIE):
title
tvRating
}''' % episode_path
['getVideoBySlug']
else:
query = query % '''metaDescription
title
@@ -129,7 +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,
@@ -192,7 +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'),

60
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),
@@ -93,7 +93,7 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
traverse_obj(theplatform_metadata, ('ratings', 0, 'rating')))
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._extract_aen_smil(media_url, video_id, auth))
@@ -121,18 +121,28 @@ class AENetworksIE(AENetworksBaseIE):
'info_dict': {
'id': '22253814',
'ext': 'mp4',
'title': 'Winter is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'title': 'Winter Is Coming',
'description': 'md5:a40e370925074260b1c8a633c632c63a',
'timestamp': 1338306241,
'upload_date': '20120529',
'uploader': 'AENE-NEW',
'duration': 2592.0,
'thumbnail': r're:^https?://.*\.jpe?g$',
'chapters': 'count:5',
'tags': 'count:14',
'categories': ['Mountain Men'],
'episode_number': 1,
'episode': 'Episode 1',
'season': 'Season 1',
'season_number': 1,
'series': 'Mountain Men',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'Geo-restricted - This content is not available in your location.'
'skip': 'Geo-restricted - This content is not available in your location.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
@@ -143,6 +153,15 @@ class AENetworksIE(AENetworksBaseIE):
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
'duration': 1277.695,
'thumbnail': r're:^https?://.*\.jpe?g$',
'chapters': 'count:4',
'tags': 'count:23',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 9',
'season_number': 9,
'series': 'Duck Dynasty',
},
'params': {
# m3u8 download
@@ -152,28 +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):
@@ -190,14 +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 []):
@@ -229,10 +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'
@@ -290,7 +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',
@@ -338,12 +357,13 @@ class BiographyIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': '404 Not Found',
}]
def _real_extract(self, url):
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',

485
yt_dlp/extractor/afreecatv.py
View File

@@ -1,25 +1,73 @@
import functools
import re
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
ExtractorError,
OnDemandPagedList,
date_from_str,
UserNotLive,
determine_ext,
filter_dict,
int_or_none,
qualities,
traverse_obj,
unified_strdate,
orderedSet,
unified_timestamp,
update_url_query,
url_or_none,
urlencode_postdata,
xpath_text,
urljoin,
)
from ..utils.traversal import traverse_obj
class AfreecaTVIE(InfoExtractor):
class AfreecaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'afreecatv'
def _perform_login(self, username, password):
login_form = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'false',
'szScriptVar': 'oLoginRet',
'szAction': '',
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
result = int_or_none(response.get('RESULT'))
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
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'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
@@ -32,9 +80,8 @@ class AfreecaTVIE(InfoExtractor):
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)
(?P<id>\d+)/?(?:$|[?#&])
'''
_NETRC_MACHINE = 'afreecatv'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
@@ -87,6 +134,7 @@ class AfreecaTVIE(InfoExtractor):
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
'timestamp': 1491929865,
'duration': 213,
},
'params': {
@@ -120,219 +168,139 @@ class AfreecaTVIE(InfoExtractor):
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'thumbnail': 'http://videoimg.afreecatv.com/php/SnapshotLoad.php?rowKey=20230108_9FF5BEE1_244432674_1_r',
'thumbnail': r're:https?://videoimg\.afreecatv\.com/.+',
'upload_date': '20230108',
'timestamp': 1673218805,
'title': '젠지 페이즈',
},
'params': {
'skip_download': True,
},
}, {
# adult content
'url': 'https://vod.afreecatv.com/player/70395877',
'only_matching': True,
}, {
# subscribers only
'url': 'https://vod.afreecatv.com/player/104647403',
'only_matching': True,
}, {
# private
'url': 'https://vod.afreecatv.com/player/81669846',
'only_matching': True,
}]
@staticmethod
def parse_video_key(key):
video_key = {}
m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
if m:
video_key['upload_date'] = m.group('upload_date')
video_key['part'] = int(m.group('part'))
return video_key
def _perform_login(self, username, password):
login_form = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'false',
'szScriptVar': 'oLoginRet',
'szAction': '',
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
result = int_or_none(response.get('RESULT'))
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),
expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
partial_view = False
adult_view = False
for _ in range(2):
data = self._download_json(
'https://api.m.afreecatv.com/station/video/a/view',
video_id, headers={'Referer': url}, data=urlencode_postdata({
'nTitleNo': video_id,
'nApiLevel': 10,
}))['data']
if traverse_obj(data, ('code', {int})) == -6221:
raise ExtractorError('The VOD does not exist', expected=True)
query = {
data = self._call_api(
'station/video/a/view', video_id, headers={'Referer': url},
data=urlencode_postdata({
'nTitleNo': video_id,
'nStationNo': data['station_no'],
'nBbsNo': data['bbs_no'],
}
if partial_view:
query['partialView'] = 'SKIP_ADULT'
if adult_view:
query['adultView'] = 'ADULT_VIEW'
video_xml = self._download_xml(
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, 'Downloading video info XML%s'
% (' (skipping adult)' if partial_view else ''),
video_id, headers={
'Referer': url,
}, query=query)
'nApiLevel': 10,
}))['data']
flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
if flag and flag == 'SUCCEED':
break
if flag == 'PARTIAL_ADULT':
self.report_warning(
'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
'Only content suitable for all ages will be downloaded. '
'Provide account credentials if you wish to download restricted content.')
partial_view = True
continue
elif flag == 'ADULT':
if not adult_view:
adult_view = True
continue
error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
else:
error = flag
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
else:
raise ExtractorError('Unable to download video info')
error_code = traverse_obj(data, ('code', {int}))
if error_code == -6221:
raise ExtractorError('The VOD does not exist', expected=True)
elif error_code == -6205:
raise ExtractorError('This VOD is private', expected=True)
video_element = video_xml.findall('./track/video')[-1]
if video_element is None or video_element.text is None:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
video_url = video_element.text.strip()
title = xpath_text(video_xml, './track/title', 'title', fatal=True)
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(
video_xml, './track/duration', 'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
common_entry = {
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
}
info = common_entry.copy()
info.update({
'id': video_id,
'title': title,
'duration': duration,
common_info = traverse_obj(data, {
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('bj_id', {str}),
'duration': ('total_file_duration', {functools.partial(int_or_none, scale=1000)}),
'thumbnail': ('thumb', {url_or_none}),
})
if not video_url:
entries = []
file_elements = video_element.findall('./file')
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = url_or_none(file_element.text)
if not file_url:
continue
key = file_element.get('key', '')
upload_date = unified_strdate(self._search_regex(
r'^(\d{8})_', key, 'upload date', default=None))
if upload_date is not None:
# sometimes the upload date isn't included in the file name
# instead, another random ID is, which may parse as a valid
# date but be wildly out of a reasonable range
parsed_date = date_from_str(upload_date)
if parsed_date.year < 2000 or parsed_date.year >= 2100:
upload_date = None
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
if not formats and not self.get_param('ignore_no_formats'):
continue
file_info = common_entry.copy()
file_info.update({
'id': format_id,
'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date,
'duration': file_duration,
'formats': formats,
})
entries.append(file_info)
entries_info = info.copy()
entries_info.update({
'_type': 'multi_video',
'entries': entries,
})
return entries_info
entries = []
for file_num, file_element in enumerate(
traverse_obj(data, ('files', lambda _, v: url_or_none(v['file']))), start=1):
file_url = file_element['file']
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', m3u8_id='hls',
note=f'Downloading part {file_num} m3u8 information')
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
info = {
'id': video_id,
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
'duration': duration,
'thumbnail': thumbnail,
}
if determine_ext(video_url) == 'm3u8':
info['formats'] = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
app, playpath = video_url.split('mp4:')
info.update({
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
entries.append({
**common_info,
'id': file_element.get('file_info_key') or f'{video_id}_{file_num}',
'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
'formats': formats,
**traverse_obj(file_element, {
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('file_start', {unified_timestamp}),
}),
})
return info
if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
if not entries:
self.raise_login_required(
'Only users older than 19 are able to watch this video', method='password')
self.report_warning(
'In accordance with local laws and regulations, underage users are '
'restricted from watching adult content. Only content suitable for all '
f'ages will be downloaded. {self._login_hint("password")}')
if not entries and traverse_obj(data, ('sub_upload_type', {str})):
self.raise_login_required('This VOD is for subscribers only', method='password')
if len(entries) == 1:
return {
**entries[0],
'title': common_info.get('title'),
}
common_info['timestamp'] = traverse_obj(entries, (..., 'timestamp'), get_all=False)
return self.playlist_result(entries, video_id, multi_video=True, **common_info)
class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
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'
_VALID_URL = r'https?://play\.afreeca(?:tv)?\.com/(?P<id>[^/]+)(?:/(?P<bno>\d+))?'
_TESTS = [{
'url': 'https://play.afreecatv.com/pyh3646/237852185',
@@ -347,77 +315,97 @@ class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
},
'skip': 'Livestream has ended',
}, {
'url': 'http://play.afreeca.com/pyh3646/237852185',
'url': 'https://play.afreecatv.com/pyh3646/237852185',
'only_matching': True,
}, {
'url': 'http://play.afreeca.com/pyh3646',
'url': 'https://play.afreecatv.com/pyh3646',
'only_matching': True,
}]
_LIVE_API_URL = 'https://live.afreecatv.com/afreeca/player_live_api.php'
_WORKING_CDNS = [
'gcp_cdn', # live-global-cdn-v02.afreecatv.com
'gs_cdn_pc_app', # pc-app.stream.afreecatv.com
'gs_cdn_mobile_web', # mobile-web.stream.afreecatv.com
'gs_cdn_pc_web', # pc-web.stream.afreecatv.com
]
_BAD_CDNS = [
'gs_cdn', # chromecast.afreeca.gscdn.com (cannot resolve)
'gs_cdn_chromecast', # chromecast.stream.afreecatv.com (HTTP Error 400)
'azure_cdn', # live-global-cdn-v01.afreecatv.com (cannot resolve)
'aws_cf', # live-global-cdn-v03.afreecatv.com (cannot resolve)
'kt_cdn', # kt.stream.afreecatv.com (HTTP Error 400)
]
_QUALITIES = ('sd', 'hd', 'hd2k', 'original')
def _extract_formats(self, channel_info, broadcast_no, aid):
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
# If user has not passed CDN IDs, try API-provided CDN ID followed by other working CDN IDs
default_cdn_ids = orderedSet([
*traverse_obj(channel_info, ('CDN', {str}, all, lambda _, v: v not in self._BAD_CDNS)),
*self._WORKING_CDNS,
])
cdn_ids = self._configuration_arg('cdn', default_cdn_ids)
for attempt, cdn_id in enumerate(cdn_ids, start=1):
m3u8_url = traverse_obj(self._download_json(
urljoin(stream_base_url, 'broad_stream_assign.html'), broadcast_no,
f'Downloading {cdn_id} stream info', f'Unable to download {cdn_id} stream info',
fatal=False, query={
'return_type': cdn_id,
'broad_key': f'{broadcast_no}-common-master-hls',
}), ('view_url', {url_or_none}))
try:
return self._extract_m3u8_formats(
m3u8_url, broadcast_no, 'mp4', m3u8_id='hls', query={'aid': aid},
headers={'Referer': 'https://play.afreecatv.com/'})
except ExtractorError as e:
if attempt == len(cdn_ids):
raise
self.report_warning(
f'{e.cause or e.msg}. Retrying... (attempt {attempt} of {len(cdn_ids)})')
def _real_extract(self, url):
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
password = self.get_param('videopassword')
channel_info = traverse_obj(self._download_json(
self._LIVE_API_URL, broadcaster_id, data=urlencode_postdata({'bid': broadcaster_id})),
('CHANNEL', {dict})) or {}
info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
data=urlencode_postdata({'bid': broadcaster_id})) or {}
channel_info = info.get('CHANNEL') or {}
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
password_protected = channel_info.get('BPWD')
if not broadcast_no:
raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
if password_protected == 'Y' and password is None:
raise UserNotLive(video_id=broadcaster_id)
password = self.get_param('videopassword')
if channel_info.get('BPWD') == 'Y' and password is None:
raise ExtractorError(
'This livestream is protected by a password, use the --video-password option',
expected=True)
formats = []
quality_key = qualities(self._QUALITIES)
for quality_str in self._QUALITIES:
params = {
token_info = traverse_obj(self._download_json(
self._LIVE_API_URL, broadcast_no, 'Downloading access token for stream',
'Unable to download access token for stream', data=urlencode_postdata(filter_dict({
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
'quality': quality_str,
}
if password is not None:
params['pwd'] = password
aid_response = self._download_json(
self._LIVE_API_URL, broadcast_no, fatal=False,
data=urlencode_postdata(params),
note=f'Downloading access token for {quality_str} stream',
errnote=f'Unable to download access token for {quality_str} stream')
aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
if not aid:
continue
'quality': 'master',
'pwd': password,
}))), ('CHANNEL', {dict})) or {}
aid = token_info.get('AID')
if not aid:
result = token_info.get('RESULT')
if result == 0:
raise ExtractorError('This livestream has ended', expected=True)
elif result == -6:
self.raise_login_required('This livestream is for subscribers only', method='password')
raise ExtractorError('Unable to extract access token')
stream_base_url = channel_info.get('RMD') or 'https://livestream-manager.afreecatv.com'
stream_info = self._download_json(
f'{stream_base_url}/broad_stream_assign.html', broadcast_no, fatal=False,
query={
'return_type': channel_info.get('CDN', 'gcp_cdn'),
'broad_key': f'{broadcast_no}-common-{quality_str}-hls',
},
note=f'Downloading metadata for {quality_str} stream',
errnote=f'Unable to download metadata for {quality_str} stream') or {}
formats = self._extract_formats(channel_info, broadcast_no, aid)
if stream_info.get('view_url'):
formats.append({
'format_id': quality_str,
'url': update_url_query(stream_info['view_url'], {'aid': aid}),
'ext': 'mp4',
'protocol': 'm3u8',
'quality': quality_key(quality_str),
})
station_info = self._download_json(
station_info = traverse_obj(self._download_json(
'https://st.afreecatv.com/api/get_station_status.php', broadcast_no,
query={'szBjId': broadcaster_id}, fatal=False,
note='Downloading channel metadata', errnote='Unable to download channel metadata') or {}
'Downloading channel metadata', 'Unable to download channel metadata',
query={'szBjId': broadcaster_id}, fatal=False), {dict}) or {}
return {
'id': broadcast_no,
@@ -427,6 +415,7 @@ class AfreecaTVLiveIE(AfreecaTVIE): # XXX: Do not subclass from concrete IE
'timestamp': unified_timestamp(station_info.get('broad_start')),
'formats': formats,
'is_live': True,
'http_headers': {'Referer': url},
}

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)

63
yt_dlp/extractor/airmozilla.py
View File

@@ -1,63 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '8d02f53ee39cf006009180e21df1f3ba',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': r're:https?://.*/poster\.jpg',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main', 'Privacy'],
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._parse_json(self._search_regex(
r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
info_dict = self._parse_jwplayer_data(jwconfig, video_id)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
timestamp = parse_iso8601(self._html_search_regex(
r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._search_regex(
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
info_dict.update({
'id': video_id,
'title': self._og_search_title(webpage),
'url': self._og_search_url(webpage),
'display_id': display_id,
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
})
return info_dict

6
yt_dlp/extractor/airtv.py
View File

@@ -5,7 +5,7 @@ from ..utils import (
int_or_none,
mimetype2ext,
parse_iso8601,
traverse_obj
traverse_obj,
)
@@ -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'):

252
yt_dlp/extractor/allstar.py Normal file
View File

@@ -0,0 +1,252 @@
import functools
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
int_or_none,
join_nonempty,
parse_qs,
urljoin,
)
from ..utils.traversal import traverse_obj
_FIELDS = '''
_id
clipImageSource
clipImageThumb
clipLink
clipTitle
createdDate
shareId
user { _id }
username
views'''
_EXTRA_FIELDS = '''
clipLength
clipSizeBytes'''
_QUERIES = {
'clip': '''query ($id: String!) {
video: getClip(clipIdentifier: $id) {
%s %s
}
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'montage': '''query ($id: String!) {
video: getMontage(clipIdentifier: $id) {
%s
}
}''' % _FIELDS, # noqa: UP031
'Clips': '''query ($page: Int!, $user: String!, $game: Int) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: false, game: $game) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'Montages': '''query ($page: Int!, $user: String!) {
videos: montages(search: createdDate, page: $page, user: $user) {
data { %s }
}
}''' % _FIELDS, # noqa: UP031
'Mobile Clips': '''query ($page: Int!, $user: String!) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: true) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
}
class AllstarBaseIE(InfoExtractor):
@staticmethod
def _parse_video_data(video_data):
def media_url_or_none(path):
return urljoin('https://media.allstar.gg/', path)
info = traverse_obj(video_data, {
'id': ('_id', {str}),
'display_id': ('shareId', {str}),
'title': ('clipTitle', {str}),
'url': ('clipLink', {media_url_or_none}),
'thumbnails': (('clipImageThumb', 'clipImageSource'), {'url': {media_url_or_none}}),
'duration': ('clipLength', {int_or_none}),
'filesize': ('clipSizeBytes', {int_or_none}),
'timestamp': ('createdDate', {functools.partial(int_or_none, scale=1000)}),
'uploader': ('username', {str}),
'uploader_id': ('user', '_id', {str}),
'view_count': ('views', {int_or_none}),
})
if info.get('id') and info.get('url'):
basename = 'clip' if '/clips/' in info['url'] else 'montage'
info['webpage_url'] = f'https://allstar.gg/{basename}?{basename}={info["id"]}'
info.update({
'extractor_key': AllstarIE.ie_key(),
'extractor': AllstarIE.IE_NAME,
'uploader_url': urljoin('https://allstar.gg/u/', info.get('uploader_id')),
})
return info
def _call_api(self, query, variables, path, video_id=None, note=None):
response = self._download_json(
'https://a1.allstar.gg/graphql', video_id, note=note,
headers={'content-type': 'application/json'},
data=json.dumps({'variables': variables, 'query': query}).encode())
errors = traverse_obj(response, ('errors', ..., 'message', {str}))
if errors:
raise ExtractorError('; '.join(errors))
return traverse_obj(response, path)
class AllstarIE(AllstarBaseIE):
_VALID_URL = r'https?://(?:www\.)?allstar\.gg/(?P<type>(?:clip|montage))\?(?P=type)=(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://allstar.gg/clip?clip=64482c2da9eec30008a67d1b',
'info_dict': {
'id': '64482c2da9eec30008a67d1b',
'title': '4K on Inferno',
'url': 'md5:66befb5381eef0c9456026386c25fa55',
'thumbnail': r're:https://media\.allstar\.gg/.+\.(?:png|jpg)$',
'uploader': 'chrk.',
'ext': 'mp4',
'duration': 20,
'filesize': 21199257,
'timestamp': 1682451501,
'uploader_id': '62b8bdfc9021052f7905882d',
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230425',
'view_count': int,
},
}, {
'url': 'https://allstar.gg/clip?clip=8LJLY4JKB',
'info_dict': {
'id': '64a1ec6b887f4c0008dc50b8',
'display_id': '8LJLY4JKB',
'title': 'AK-47 3K on Mirage',
'url': 'md5:dde224fd12f035c0e2529a4ae34c4283',
'ext': 'mp4',
'thumbnail': r're:https://media\.allstar\.gg/.+\.(?:png|jpg)$',
'duration': 16,
'filesize': 30175859,
'timestamp': 1688333419,
'uploader': 'cherokee',
'uploader_id': '62b8bdfc9021052f7905882d',
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230702',
'view_count': int,
},
}, {
'url': 'https://allstar.gg/montage?montage=643e64089da7e9363e1fa66c',
'info_dict': {
'id': '643e64089da7e9363e1fa66c',
'display_id': 'APQLGM2IMXW',
'title': 'cherokee Rapid Fire Snipers Montage',
'url': 'md5:a3ee356022115db2b27c81321d195945',
'thumbnail': r're:https://media\.allstar\.gg/.+\.(?:png|jpg)$',
'ext': 'mp4',
'timestamp': 1681810448,
'uploader': 'cherokee',
'uploader_id': '62b8bdfc9021052f7905882d',
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230418',
'view_count': int,
},
}, {
'url': 'https://allstar.gg/montage?montage=RILJMH6QOS',
'info_dict': {
'id': '64a2697372ce3703de29e868',
'display_id': 'RILJMH6QOS',
'title': 'cherokee Rapid Fire Snipers Montage',
'url': 'md5:d5672e6f88579730c2310a80fdbc4030',
'thumbnail': r're:https://media\.allstar\.gg/.+\.(?:png|jpg)$',
'ext': 'mp4',
'timestamp': 1688365434,
'uploader': 'cherokee',
'uploader_id': '62b8bdfc9021052f7905882d',
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230703',
'view_count': int,
},
}]
def _real_extract(self, url):
query_id, video_id = self._match_valid_url(url).group('type', 'id')
return self._parse_video_data(
self._call_api(
_QUERIES.get(query_id), {'id': video_id}, ('data', 'video'), video_id))
class AllstarProfileIE(AllstarBaseIE):
_VALID_URL = r'https?://(?:www\.)?allstar\.gg/(?:profile\?user=|u/)(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://allstar.gg/profile?user=62b8bdfc9021052f7905882d',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-clips',
'title': 'cherokee - Clips',
},
'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,
}, {
'url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d?view=Montages',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-montages',
'title': 'cherokee - Montages',
},
'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,
}]
_PAGE_SIZE = 10
def _get_page(self, user_id, display_id, game, query, page_num):
page_num += 1
for video_data in self._call_api(
query, {
'user': user_id,
'page': page_num,
'game': game,
}, ('data', 'videos', 'data'), display_id, f'Downloading page {page_num}'):
yield self._parse_video_data(video_data)
def _real_extract(self, url):
display_id = self._match_id(url)
profile_data = self._download_json(
urljoin('https://api.allstar.gg/v1/users/profile/', display_id), display_id)
user_id = traverse_obj(profile_data, ('data', ('_id'), {str}))
if not user_id:
raise ExtractorError('Unable to extract the user id')
username = traverse_obj(profile_data, ('data', 'profile', ('username'), {str}))
url_query = parse_qs(url)
game = traverse_obj(url_query, ('game', 0, {int_or_none}))
query_id = traverse_obj(url_query, ('view', 0), default='Clips')
if query_id not in ('Clips', 'Montages', 'Mobile Clips'):
raise ExtractorError(f'Unsupported playlist URL type {query_id!r}')
return self.playlist_result(
OnDemandPagedList(
functools.partial(
self._get_page, user_id, display_id, game, _QUERIES.get(query_id)), self._PAGE_SIZE),
playlist_id=join_nonempty(user_id, query_id.lower().split()[0], game),
playlist_title=join_nonempty((username or display_id), query_id, game, delim=' - '))

6
yt_dlp/extractor/alphaporno.py
View File

@@ -1,9 +1,9 @@
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
int_or_none,
parse_duration,
parse_filesize,
int_or_none,
parse_iso8601,
)
@@ -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,

104
yt_dlp/extractor/altcensored.py Normal file
View File

@@ -0,0 +1,104 @@
import re
from .archiveorg import ArchiveOrgIE
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
clean_html,
int_or_none,
orderedSet,
str_to_int,
urljoin,
)
class AltCensoredIE(InfoExtractor):
IE_NAME = 'altcensored'
_VALID_URL = r'https?://(?:www\.)?altcensored\.com/(?:watch\?v=|embed/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.altcensored.com/watch?v=k0srjLSkga8',
'info_dict': {
'id': 'youtube-k0srjLSkga8',
'ext': 'webm',
'title': "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?",
'display_id': 'k0srjLSkga8.webm',
'release_date': '20180403',
'creators': ['Virginie Vota'],
'release_year': 2018,
'upload_date': '20230318',
'uploader': 'admin@altcensored.com',
'description': 'md5:0b38a8fc04103579d5c1db10a247dc30',
'timestamp': 1679161343,
'track': 'k0srjLSkga8',
'duration': 926.09,
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int,
'categories': ['News & Politics'],
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
category = clean_html(self._html_search_regex(
r'<a href="/category/\d+">([^<]+)</a>', webpage, 'category', default=None))
return {
'_type': 'url_transparent',
'url': f'https://archive.org/details/youtube-{video_id}',
'ie_key': ArchiveOrgIE.ie_key(),
'view_count': str_to_int(self._html_search_regex(
r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)),
'categories': [category] if category else None,
}
class AltCensoredChannelIE(InfoExtractor):
IE_NAME = 'altcensored:channel'
_VALID_URL = r'https?://(?:www\.)?altcensored\.com/channel/(?!page|table)(?P<id>[^/?#]+)'
_PAGE_SIZE = 24
_TESTS = [{
'url': 'https://www.altcensored.com/channel/UCFPTO55xxHqFqkzRZHu4kcw',
'info_dict': {
'title': 'Virginie Vota',
'id': 'UCFPTO55xxHqFqkzRZHu4kcw',
},
'playlist_count': 85,
}, {
'url': 'https://altcensored.com/channel/UC9CcJ96HKMWn0LZlcxlpFTw',
'info_dict': {
'title': 'yukikaze775',
'id': 'UC9CcJ96HKMWn0LZlcxlpFTw',
},
'playlist_count': 4,
}, {
'url': 'https://altcensored.com/channel/UCfYbb7nga6-icsFWWgS-kWw',
'info_dict': {
'title': 'Mister Metokur',
'id': 'UCfYbb7nga6-icsFWWgS-kWw',
},
'playlist_count': 121,
}]
def _real_extract(self, url):
channel_id = self._match_id(url)
webpage = self._download_webpage(
url, channel_id, 'Download channel webpage', 'Unable to get channel webpage')
title = self._html_search_meta('altcen_title', webpage, 'title', fatal=False)
page_count = int_or_none(self._html_search_regex(
r'<a[^>]+href="/channel/[\w-]+/page/(\d+)">(?:\1)</a>',
webpage, 'page count', default='1'))
def page_func(page_num):
page_num += 1
webpage = self._download_webpage(
f'https://altcensored.com/channel/{channel_id}/page/{page_num}',
channel_id, note=f'Downloading page {page_num}')
items = re.findall(r'<a[^>]+href="(/watch\?v=[^"]+)', webpage)
return [self.url_result(urljoin('https://www.altcensored.com', path), AltCensoredIE)
for path in orderedSet(items)]
return self.playlist_result(
InAdvancePagedList(page_func, page_count, self._PAGE_SIZE),
playlist_id=channel_id, playlist_title=title)

30
yt_dlp/extractor/alura.py
View File

@@ -1,17 +1,13 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
urlencode_postdata,
urljoin,
int_or_none,
clean_html,
ExtractorError
)
@@ -25,7 +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'},
{
@@ -34,12 +30,12 @@ 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):
course, video_id = self._match_valid_url(url)
course, video_id = self._match_valid_url(url).group('course_name', 'id')
video_url = self._VIDEO_URL % (course, video_id)
video_dict = self._download_json(video_url, video_id, 'Searching for videos')
@@ -52,7 +48,7 @@ class AluraIE(InfoExtractor):
formats = []
for video_obj in video_dict:
video_url_m3u8 = video_obj.get('link')
video_url_m3u8 = video_obj.get('mp4')
video_format = self._extract_m3u8_formats(
video_url_m3u8, None, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
@@ -66,7 +62,7 @@ class AluraIE(InfoExtractor):
return {
'id': video_id,
'title': video_title,
"formats": formats
'formats': formats,
}
def _perform_login(self, username, password):
@@ -95,7 +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',
@@ -107,7 +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')
@@ -123,7 +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):
@@ -161,7 +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)

77
yt_dlp/extractor/amadeustv.py Normal file
View File

@@ -0,0 +1,77 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
parse_iso8601,
url_or_none,
)
from ..utils.traversal import traverse_obj
class AmadeusTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?amadeus\.tv/library/(?P<id>[\da-f]+)'
_TESTS = [{
'url': 'http://www.amadeus.tv/library/65091a87ff85af59d9fc54c3',
'info_dict': {
'id': '5576678021301411311',
'ext': 'mp4',
'title': 'Jieon Park - 第五届珠海莫扎特国际青少年音乐周小提琴C组第三轮',
'thumbnail': 'http://1253584441.vod2.myqcloud.com/a0046a27vodtransbj1253584441/7db4af535576678021301411311/coverBySnapshot_10_0.jpg',
'duration': 1264.8,
'upload_date': '20230918',
'timestamp': 1695034800,
'display_id': '65091a87ff85af59d9fc54c3',
'view_count': int,
'description': 'md5:a0357b9c215489e2067cbae0b777bb95',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nuxt_data = self._search_nuxt_data(webpage, display_id, traverse=('fetch', '0'))
video_id = traverse_obj(nuxt_data, ('item', 'video', {str}))
if not video_id:
raise ExtractorError('Unable to extract actual video ID')
video_data = self._download_json(
f'http://playvideo.qcloud.com/getplayinfo/v2/1253584441/{video_id}',
video_id, headers={'Referer': 'http://www.amadeus.tv/'})
formats = []
for video in traverse_obj(video_data, ('videoInfo', ('sourceVideo', ('transcodeList', ...)), {dict})):
if not url_or_none(video.get('url')):
continue
formats.append({
**traverse_obj(video, {
'url': 'url',
'format_id': ('definition', {lambda x: f'http-{x or "0"}'}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
'filesize': (('totalSize', 'size'), {int_or_none}),
'vcodec': ('videoStreamList', 0, 'codec'),
'acodec': ('audioStreamList', 0, 'codec'),
'fps': ('videoStreamList', 0, 'fps', {float_or_none}),
}, get_all=False),
'http_headers': {'Referer': 'http://www.amadeus.tv/'},
})
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
**traverse_obj(video_data, {
'title': ('videoInfo', 'basicInfo', 'name', {str}),
'thumbnail': ('coverInfo', 'coverUrl', {url_or_none}),
'duration': ('videoInfo', 'sourceVideo', ('floatDuration', 'duration'), {float_or_none}),
}, get_all=False),
**traverse_obj(nuxt_data, ('item', {
'title': (('title', 'title_en', 'title_cn'), {str}),
'description': (('description', 'description_en', 'description_cn'), {str}),
'timestamp': ('date', {parse_iso8601}),
'view_count': ('view', {int_or_none}),
}), get_all=False),
}

12
yt_dlp/extractor/amara.py
View File

@@ -1,6 +1,6 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from .vimeo import VimeoIE
from .youtube import YoutubeIE
from ..utils import (
int_or_none,
parse_iso8601,
@@ -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',

13
yt_dlp/extractor/amcnetworks.py
View File

@@ -26,6 +26,7 @@ class AMCNetworksIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
@@ -63,8 +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',
@@ -75,15 +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.
@@ -130,7 +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(),
}

6
yt_dlp/extractor/amp.py
View File

@@ -1,7 +1,7 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
determine_ext,
int_or_none,
mimetype2ext,
parse_iso8601,
@@ -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)

8
yt_dlp/extractor/anchorfm.py
View File

@@ -5,7 +5,7 @@ from ..utils import (
int_or_none,
str_or_none,
traverse_obj,
unified_timestamp
unified_timestamp,
)
@@ -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):

12
yt_dlp/extractor/angel.py
View File

@@ -1,7 +1,7 @@
import re
from .common import InfoExtractor
from ..utils import url_or_none, merge_dicts
from ..utils import merge_dicts, url_or_none
class AngelIE(InfoExtractor):
@@ -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.

14
yt_dlp/extractor/antenna.py
View File

@@ -67,7 +67,7 @@ class AntennaGrWatchIE(AntennaBaseIE):
webpage = self._download_webpage(url, video_id)
info = self._download_and_extract_api_data(video_id, netloc)
info['description'] = self._og_search_description(webpage, default=None)
info['_old_archive_ids'] = [make_archive_id('Ant1NewsGrWatch', video_id)],
info['_old_archive_ids'] = [make_archive_id('Ant1NewsGrWatch', video_id)]
return info
@@ -78,14 +78,14 @@ class Ant1NewsGrArticleIE(AntennaBaseIE):
_TESTS = [{
'url': 'https://www.ant1news.gr/afieromata/article/549468/o-tzeims-mpont-sta-meteora-oi-apeiles-kai-o-xesikomos-ton-kalogeron',
'md5': '294f18331bb516539d72d85a82887dcc',
'md5': '57eb8d12181f0fa2b14b0b138e1de9b6',
'info_dict': {
'id': '_xvg/m_cmbatw=',
'ext': 'mp4',
'title': 'md5:a93e8ecf2e4073bfdffcb38f59945411',
'timestamp': 1603092840,
'upload_date': '20201019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
'timestamp': 1666166520,
'upload_date': '20221019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/1920/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
},
}, {
'url': 'https://ant1news.gr/Society/article/620286/symmoria-anilikon-dikigoros-thymaton-ithelan-na-toys-apoteleiosoyn',
@@ -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')})
@@ -117,7 +117,7 @@ class Ant1NewsGrEmbedIE(AntennaBaseIE):
_BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
_VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
_EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
_API_PATH = '/news/templates/data/jsonPlayer'
_API_PATH = '/templates/data/jsonPlayer'
_TESTS = [{
'url': 'https://www.antenna.gr/templates/pages/player?cid=3f_li_c_az_jw_y_u=&w=670&h=377',

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)

9
yt_dlp/extractor/aol.py
View File

@@ -10,6 +10,7 @@ from ..utils import (
class AolIE(YahooIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_NAME = 'aol.com'
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
@@ -29,7 +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/',
@@ -45,7 +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,
@@ -82,10 +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

5
yt_dlp/extractor/appleconnect.py
View File

@@ -1,8 +1,5 @@
from .common import InfoExtractor
from ..utils import (
str_to_int,
ExtractorError
)
from ..utils import ExtractorError, str_to_int
class AppleConnectIE(InfoExtractor):

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,

33
yt_dlp/extractor/appletrailers.py
View File

@@ -1,8 +1,8 @@
import re
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'])

122
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 (
@@ -31,6 +32,7 @@ from ..utils import (
unified_timestamp,
url_or_none,
urlhandle_detect_ext,
variadic,
)
@@ -49,10 +51,9 @@ class ArchiveOrgIE(InfoExtractor):
'release_date': '19681210',
'timestamp': 1268695290,
'upload_date': '20100315',
'creator': 'SRI International',
'creators': ['SRI International'],
'uploader': 'laura@archive.org',
'thumbnail': r're:https://archive\.org/download/.*\.jpg',
'release_year': 1968,
'display_id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.cdr',
'track': 'XD300-23 68HighlightsAResearchCntAugHumanIntellect',
@@ -110,7 +111,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': 'Turning',
'ext': 'flac',
'track': 'Turning',
'creator': 'Grateful Dead',
'creators': ['Grateful Dead'],
'display_id': 'gd1977-05-08d01t01.flac',
'track_number': 1,
'album': '1977-05-08 - Barton Hall - Cornell University',
@@ -130,11 +131,10 @@ class ArchiveOrgIE(InfoExtractor):
'location': 'Barton Hall - Cornell University',
'duration': 438.68,
'track': 'Deal',
'creator': 'Grateful Dead',
'creators': ['Grateful Dead'],
'album': '1977-05-08 - Barton Hall - Cornell University',
'release_date': '19770508',
'display_id': 'gd1977-05-08d01t07.flac',
'release_year': 1977,
'track_number': 7,
},
}, {
@@ -146,7 +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',
@@ -159,7 +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',
@@ -169,7 +169,7 @@ class ArchiveOrgIE(InfoExtractor):
'upload_date': '20160610',
'description': 'md5:f70956a156645a658a0dc9513d9e78b7',
'uploader': 'dimitrios@archive.org',
'creator': ['British Broadcasting Corporation', 'Time-Life Films'],
'creators': ['British Broadcasting Corporation', 'Time-Life Films'],
'timestamp': 1465594947,
},
'playlist': [
@@ -203,8 +203,8 @@ class ArchiveOrgIE(InfoExtractor):
'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
'display_id': 'irelandthemakingofarepublicreel2.mov',
},
}
]
},
],
}]
@staticmethod
@@ -221,7 +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.
@@ -247,7 +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)
@@ -259,7 +259,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': m['title'],
'description': clean_html(m.get('description')),
'uploader': dict_get(m, ['uploader', 'adder']),
'creator': m.get('creator'),
'creators': traverse_obj(m, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'license': m.get('licenseurl'),
'release_date': unified_strdate(m.get('date')),
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
@@ -274,7 +274,7 @@ class ArchiveOrgIE(InfoExtractor):
'title': f.get('title') or f['name'],
'display_id': f['name'],
'description': clean_html(f.get('description')),
'creator': f.get('creator'),
'creators': traverse_obj(f, ('creator', {variadic}, {lambda x: x[0] and list(x)})),
'duration': parse_duration(f.get('length')),
'track_number': int_or_none(f.get('track')),
'album': f.get('album'),
@@ -294,7 +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.
@@ -302,14 +304,14 @@ class ArchiveOrgIE(InfoExtractor):
is_logged_in = bool(self._get_cookies('https://archive.org').get('logged-in-sig'))
if extension in KNOWN_EXTENSIONS and (not f.get('private') or is_logged_in):
entry['formats'].append({
'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
'url': 'https://archive.org/download/' + identifier + '/' + urllib.parse.quote(f['name']),
'format': f.get('format'),
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'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():
@@ -372,7 +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',
@@ -389,7 +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
@@ -404,8 +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',
@@ -422,7 +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': {
@@ -438,7 +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',
@@ -455,7 +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',
@@ -474,15 +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': {
@@ -496,7 +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',
@@ -513,7 +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',
@@ -528,7 +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',
@@ -543,7 +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',
@@ -558,7 +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',
@@ -572,7 +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',
@@ -588,7 +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',
@@ -605,7 +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',
@@ -620,7 +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',
@@ -635,35 +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
@@ -674,13 +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,
@@ -689,14 +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())
@@ -853,7 +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
@@ -894,7 +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.
@@ -925,21 +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')),

684
yt_dlp/extractor/ard.py
View File

@@ -1,24 +1,25 @@
import json
import functools
import re
from .common import InfoExtractor
from .generic import GenericIE
from ..utils import (
OnDemandPagedList,
bug_reports_message,
determine_ext,
ExtractorError,
int_or_none,
join_nonempty,
jwt_decode_hs256,
make_archive_id,
parse_duration,
qualities,
parse_iso8601,
remove_start,
str_or_none,
try_get,
unified_strdate,
unified_timestamp,
update_url,
update_url_query,
url_or_none,
xpath_text,
)
from ..compat import compat_etree_fromstring
from ..utils.traversal import traverse_obj
class ARDMediathekBaseIE(InfoExtractor):
@@ -61,45 +62,6 @@ class ARDMediathekBaseIE(InfoExtractor):
'subtitles': subtitles,
}
def _ARD_extract_episode_info(self, title):
"""Try to extract season/episode data from the title."""
res = {}
if not title:
return res
for pattern in [
# Pattern for title like "Homo sapiens (S06/E07) - Originalversion"
# from: https://www.ardmediathek.de/one/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw
r'.*(?P<ep_info> \(S(?P<season_number>\d+)/E(?P<episode_number>\d+)\)).*',
# E.g.: title="Fritjof aus Norwegen (2) (AD)"
# from: https://www.ardmediathek.de/ard/sammlung/der-krieg-und-ich/68cMkqJdllm639Skj4c7sS/
r'.*(?P<ep_info> \((?:Folge |Teil )?(?P<episode_number>\d+)(?:/\d+)?\)).*',
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:\:| -|) )\"(?P<episode>.+)\".*',
# E.g.: title="Folge 25/42: Symmetrie"
# from: https://www.ardmediathek.de/ard/video/grips-mathe/folge-25-42-symmetrie/ard-alpha/Y3JpZDovL2JyLmRlL3ZpZGVvLzMyYzI0ZjczLWQ1N2MtNDAxNC05ZmZhLTFjYzRkZDA5NDU5OQ/
# E.g.: title="Folge 1063 - Vertrauen"
# from: https://www.ardmediathek.de/ard/sendung/die-fallers/Y3JpZDovL3N3ci5kZS8yMzAyMDQ4/
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:/\d+)?(?:\:| -|) ).*',
]:
m = re.match(pattern, title)
if m:
groupdict = m.groupdict()
res['season_number'] = int_or_none(groupdict.get('season_number'))
res['episode_number'] = int_or_none(groupdict.get('episode_number'))
res['episode'] = str_or_none(groupdict.get('episode'))
# Build the episode title by removing numeric episode information:
if groupdict.get('ep_info') and not res['episode']:
res['episode'] = str_or_none(
title.replace(groupdict.get('ep_info'), ''))
if res['episode']:
res['episode'] = res['episode'].strip()
break
# As a fallback use the whole title as the episode name:
if not res.get('episode'):
res['episode'] = title.strip()
return res
def _extract_formats(self, media_info, video_id):
type_ = media_info.get('_type')
media_array = media_info.get('_mediaArray', [])
@@ -123,7 +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(
@@ -134,12 +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$',
@@ -155,144 +117,12 @@ class ARDMediathekBaseIE(InfoExtractor):
return formats
class ARDMediathekIE(ARDMediathekBaseIE):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
# available till 26.07.2022
'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822',
'info_dict': {
'id': '44726822',
'ext': 'mp4',
'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?',
'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5',
'duration': 1740,
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
'only_matching': True,
}, {
# audio
'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
'only_matching': True,
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'only_matching': True,
}, {
'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
def _real_extract(self, url):
# determine video id from url
m = self._match_valid_url(url)
document_id = None
numid = re.search(r'documentId=([0-9]+)', url)
if numid:
document_id = video_id = numid.group(1)
else:
video_id = m.group('video_id')
webpage = self._download_webpage(url, video_id)
ERRORS = (
('>Leider liegt eine Störung vor.', 'Video %s is unavailable'),
('>Der gewünschte Beitrag ist nicht mehr verfügbar.<',
'Video %s is no longer available'),
)
for pattern, message in ERRORS:
if pattern in webpage:
raise ExtractorError(message % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>',
r'<title[^>]*>(.*?)</title>'],
webpage, 'title')
description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'dcterms.abstract', webpage, 'description', default=None)
if description is None:
description = self._html_search_meta(
'description', webpage, 'meta description', default=None)
if description is None:
description = self._html_search_regex(
r'<p\s+class="teasertext">(.+?)</p>',
webpage, 'teaser text', default=None)
# Thumbnail is sometimes not present.
# It is in the mobile version, but that seems to use a different URL
# structure altogether.
thumbnail = self._og_search_thumbnail(webpage, default=None)
media_streams = re.findall(r'''(?x)
mediaCollection\.addMediaStream\([0-9]+,\s*[0-9]+,\s*"[^"]*",\s*
"([^"]+)"''', webpage)
if media_streams:
QUALITIES = qualities(['lo', 'hi', 'hq'])
formats = []
for furl in set(media_streams):
if furl.endswith('.f4m'):
fid = 'f4m'
else:
fid_m = re.match(r'.*\.([^.]+)\.[^.]+$', furl)
fid = fid_m.group(1) if fid_m else None
formats.append({
'quality': QUALITIES(fid),
'format_id': fid,
'url': furl,
})
info = {
'formats': formats,
}
else: # request JSON file
if not document_id:
video_id = self._search_regex(
(r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
webpage, 'media id', default=None)
info = self._extract_media_info(
'http://www.ardmediathek.de/play/media/%s' % video_id,
webpage, video_id)
info.update({
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
_TESTS = [{
# available till 7.12.2023
'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-video-424.html',
'md5': 'a438f671e87a7eba04000336a119ccc4',
'md5': '94812e6438488fb923c361a44469614b',
'info_dict': {
'id': 'maischberger-video-424',
'display_id': 'maischberger-video-424',
@@ -399,31 +229,36 @@ class ARDIE(InfoExtractor):
}
class ARDBetaMediathekIE(ARDMediathekBaseIE):
class ARDBetaMediathekIE(InfoExtractor):
IE_NAME = 'ARDMediathek'
_VALID_URL = r'''(?x)https://
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:(?P<client>[^/]+)/)?
(?:player|live|video|(?P<playlist>sendung|sammlung))/
(?:(?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)
(?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
(?:[^/]+/)?
(?:player|live|video)/
(?:[^?#]+/)?
(?P<id>[a-zA-Z0-9]+)
/?(?:[?#]|$)'''
_GEO_COUNTRIES = ['DE']
_TOKEN_URL = 'https://sso.ardmediathek.de/sso/token'
_TESTS = [{
'url': 'https://www.ardmediathek.de/video/filme-im-mdr/wolfsland-die-traurigen-schwestern/mdr-fernsehen/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy8xZGY0ZGJmZS00ZWQwLTRmMGItYjhhYy0wOGQ4ZmYxNjVhZDI',
'md5': '3fd5fead7a370a819341129c8d713136',
'url': 'https://www.ardmediathek.de/video/filme-im-mdr/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'md5': 'b6e8ab03f2bcc6e1f9e6cef25fcc03c4',
'info_dict': {
'display_id': 'filme-im-mdr/wolfsland-die-traurigen-schwestern/mdr-fernsehen',
'id': '12172961',
'title': 'Wolfsland - Die traurigen Schwestern',
'description': r're:^Als der Polizeiobermeister Raaben',
'duration': 5241,
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:efa186f7b0054957',
'timestamp': 1670710500,
'upload_date': '20221210',
'display_id': 'Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'id': '12939099',
'title': 'Liebe auf vier Pfoten',
'description': r're:^Claudia Schmitt, Anwältin in Salzburg',
'duration': 5222,
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:aee7cbf8f06de976?w=960&ch=ae4d0f2ee47d8b9b',
'timestamp': 1701343800,
'upload_date': '20231130',
'ext': 'mp4',
'age_limit': 12,
'episode': 'Wolfsland - Die traurigen Schwestern',
'series': 'Filme im MDR'
'episode': 'Liebe auf vier Pfoten',
'series': 'Filme im MDR',
'age_limit': 0,
'channel': 'MDR',
'_old_archive_ids': ['ardbetamediathek Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0'],
},
}, {
'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
@@ -450,11 +285,31 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
'timestamp': 1636398000,
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
'display_id': 'tagesschau-oder-tagesschau-20-00-uhr/das-erste',
'display_id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'duration': 915,
'episode': 'tagesschau, 20:00 Uhr',
'series': 'tagesschau',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:fbb21142783b0a49?w=960&ch=ee69108ae344f678',
'channel': 'ARD-Aktuell',
'_old_archive_ids': ['ardbetamediathek Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll'],
},
}, {
'url': 'https://www.ardmediathek.de/video/7-tage/7-tage-unter-harten-jungs/hr-fernsehen/N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'md5': 'c428b9effff18ff624d4f903bda26315',
'info_dict': {
'id': '94834686',
'ext': 'mp4',
'duration': 2700,
'episode': '7 Tage ... unter harten Jungs',
'description': 'md5:0f215470dcd2b02f59f4bd10c963f072',
'upload_date': '20231005',
'timestamp': 1696491171,
'display_id': 'N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'series': '7 Tage ...',
'channel': 'HR',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:f6e6d5ffac41925c?w=960&ch=fa32ba69bc87989a',
'title': '7 Tage ... unter harten Jungs',
'_old_archive_ids': ['ardbetamediathek N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3'],
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
@@ -471,203 +326,254 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
}, {
'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
'only_matching': True,
}]
def _extract_episode_info(self, title):
patterns = [
# Pattern for title like "Homo sapiens (S06/E07) - Originalversion"
# from: https://www.ardmediathek.de/one/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw
r'.*(?P<ep_info> \(S(?P<season_number>\d+)/E(?P<episode_number>\d+)\)).*',
# E.g.: title="Fritjof aus Norwegen (2) (AD)"
# from: https://www.ardmediathek.de/ard/sammlung/der-krieg-und-ich/68cMkqJdllm639Skj4c7sS/
r'.*(?P<ep_info> \((?:Folge |Teil )?(?P<episode_number>\d+)(?:/\d+)?\)).*',
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:\:| -|) )\"(?P<episode>.+)\".*',
# E.g.: title="Folge 25/42: Symmetrie"
# from: https://www.ardmediathek.de/ard/video/grips-mathe/folge-25-42-symmetrie/ard-alpha/Y3JpZDovL2JyLmRlL3ZpZGVvLzMyYzI0ZjczLWQ1N2MtNDAxNC05ZmZhLTFjYzRkZDA5NDU5OQ/
# E.g.: title="Folge 1063 - Vertrauen"
# from: https://www.ardmediathek.de/ard/sendung/die-fallers/Y3JpZDovL3N3ci5kZS8yMzAyMDQ4/
r'.*(?P<ep_info>Folge (?P<episode_number>\d+)(?:/\d+)?(?:\:| -|) ).*',
# As a fallback use the full title
r'(?P<title>.*)',
]
return traverse_obj(patterns, (..., {functools.partial(re.match, string=title)}, {
'season_number': ('season_number', {int_or_none}),
'episode_number': ('episode_number', {int_or_none}),
'episode': ((
('episode', {str_or_none}),
('ep_info', {lambda x: title.replace(x, '')}),
('title', {str}),
), {str.strip}),
}), get_all=False)
def _real_extract(self, url):
display_id = self._match_id(url)
query = {'embedded': 'false', 'mcV6': 'true'}
headers = {}
if self._get_cookies(self._TOKEN_URL).get('ams'):
token = self._download_json(
self._TOKEN_URL, display_id, 'Fetching token for age verification',
'Unable to fetch age verification token', fatal=False)
id_token = traverse_obj(token, ('idToken', {str}))
decoded_token = traverse_obj(id_token, ({jwt_decode_hs256}, {dict}))
user_id = traverse_obj(decoded_token, (('user_id', 'sub'), {str}), get_all=False)
if not user_id:
self.report_warning('Unable to extract token, continuing without authentication')
else:
headers['x-authorization'] = f'Bearer {id_token}'
query['userId'] = user_id
if decoded_token.get('age_rating') != 18:
self.report_warning('Account is not verified as 18+; video may be unavailable')
page_data = self._download_json(
f'https://api.ardmediathek.de/page-gateway/pages/ard/item/{display_id}',
display_id, query=query, headers=headers)
# For user convenience we use the old contentId instead of the longer crid
# Ref: https://github.com/yt-dlp/yt-dlp/issues/8731#issuecomment-1874398283
old_id = traverse_obj(page_data, ('tracking', 'atiCustomVars', 'contentId', {int}))
if old_id is not None:
video_id = str(old_id)
archive_ids = [make_archive_id(ARDBetaMediathekIE, display_id)]
else:
self.report_warning(f'Could not extract contentId{bug_reports_message()}')
video_id = display_id
archive_ids = None
player_data = traverse_obj(
page_data, ('widgets', lambda _, v: v['type'] in ('player_ondemand', 'player_live'), {dict}), get_all=False)
is_live = player_data.get('type') == 'player_live'
media_data = traverse_obj(player_data, ('mediaCollection', 'embedded', {dict}))
if player_data.get('blockedByFsk'):
self.raise_login_required('This video is only available for age verified users or after 22:00')
formats = []
subtitles = {}
for stream in traverse_obj(media_data, ('streams', ..., {dict})):
kind = stream.get('kind')
# Prioritize main stream over sign language and others
preference = 1 if kind == 'main' else None
for media in traverse_obj(stream, ('media', lambda _, v: url_or_none(v['url']))):
media_url = media['url']
audio_kind = traverse_obj(media, (
'audios', 0, 'kind', {str}), default='').replace('standard', '')
lang_code = traverse_obj(media, ('audios', 0, 'languageCode', {str})) or 'deu'
lang = join_nonempty(lang_code, audio_kind)
language_preference = 10 if lang == 'deu' else -10
if determine_ext(media_url) == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
media_url, video_id, m3u8_id=f'hls-{kind}', preference=preference, fatal=False, live=is_live)
for f in fmts:
f['language'] = lang
f['language_preference'] = language_preference
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.append({
'url': media_url,
'format_id': f'http-{kind}',
'preference': preference,
'language': lang,
'language_preference': language_preference,
**traverse_obj(media, {
'format_note': ('forcedLabel', {str}),
'width': ('maxHResolutionPx', {int_or_none}),
'height': ('maxVResolutionPx', {int_or_none}),
'vcodec': ('videoCodec', {str}),
}),
})
for sub in traverse_obj(media_data, ('subtitles', ..., {dict})):
for sources in traverse_obj(sub, ('sources', lambda _, v: url_or_none(v['url']))):
subtitles.setdefault(sub.get('languageCode') or 'deu', []).append({
'url': sources['url'],
'ext': {'webvtt': 'vtt', 'ebutt': 'ttml'}.get(sources.get('kind')),
})
age_limit = traverse_obj(page_data, ('fskRating', {lambda x: remove_start(x, 'FSK')}, {int_or_none}))
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
'age_limit': age_limit,
**traverse_obj(media_data, ('meta', {
'title': 'title',
'description': 'synopsis',
'timestamp': ('broadcastedOnDateTime', {parse_iso8601}),
'series': 'seriesTitle',
'thumbnail': ('images', 0, 'url', {url_or_none}),
'duration': ('durationSeconds', {int_or_none}),
'channel': 'clipSourceName',
})),
**self._extract_episode_info(page_data.get('title')),
'_old_archive_ids': archive_ids,
}
class ARDMediathekCollectionIE(InfoExtractor):
_VALID_URL = r'''(?x)https://
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:[^/?#]+/)?
(?P<playlist>sendung|serie|sammlung)/
(?:(?P<display_id>[^?#]+?)/)?
(?P<id>[a-zA-Z0-9]+)
(?:/(?P<season>\d+)(?:/(?P<version>OV|AD))?)?/?(?:[?#]|$)'''
_GEO_COUNTRIES = ['DE']
_TESTS = [{
'url': 'https://www.ardmediathek.de/serie/quiz/staffel-1-originalversion/Y3JpZDovL3dkci5kZS9vbmUvcXVpeg/1/OV',
'info_dict': {
'id': 'Y3JpZDovL3dkci5kZS9vbmUvcXVpeg_1_OV',
'display_id': 'quiz/staffel-1-originalversion',
'title': 'Staffel 1 Originalversion',
},
'playlist_count': 3,
}, {
'url': 'https://www.ardmediathek.de/serie/babylon-berlin/staffel-4-mit-audiodeskription/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu/4/AD',
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu_4_AD',
'display_id': 'babylon-berlin/staffel-4-mit-audiodeskription',
'title': 'Staffel 4 mit Audiodeskription',
},
'playlist_count': 12,
}, {
'url': 'https://www.ardmediathek.de/serie/babylon-berlin/staffel-1/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu/1/',
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JhYnlsb24tYmVybGlu_1',
'display_id': 'babylon-berlin/staffel-1',
'title': 'Staffel 1',
},
'playlist_count': 8,
}, {
'url': 'https://www.ardmediathek.de/sendung/tatort/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydA',
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydA',
'display_id': 'tatort',
'title': 'Tatort',
},
'playlist_mincount': 500,
}, {
'url': 'https://www.ardmediathek.de/sammlung/die-kirche-bleibt-im-dorf/5eOHzt8XB2sqeFXbIoJlg2',
'info_dict': {
'id': '5eOHzt8XB2sqeFXbIoJlg2',
'display_id': 'die-kirche-bleibt-im-dorf',
'title': 'Die Kirche bleibt im Dorf',
'description': 'Die Kirche bleibt im Dorf',
},
'playlist_count': 4,
}, {
# playlist of type 'sendung'
'url': 'https://www.ardmediathek.de/ard/sendung/doctor-who/Y3JpZDovL3dkci5kZS9vbmUvZG9jdG9yIHdobw/',
'only_matching': True,
}, {
# playlist of type 'serie'
'url': 'https://www.ardmediathek.de/serie/nachtstreife/staffel-1/Y3JpZDovL3N3ci5kZS9zZGIvc3RJZC8xMjQy/1',
'only_matching': True,
}, {
# playlist of type 'sammlung'
'url': 'https://www.ardmediathek.de/ard/sammlung/team-muenster/5JpTzLSbWUAK8184IOvEir/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
'only_matching': True,
}, {
'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3dkci5kZS9CZWl0cmFnLWQ2NDJjYWEzLTMwZWYtNGI4NS1iMTI2LTU1N2UxYTcxOGIzOQ/tatort-duo-koeln-leipzig-ihr-kinderlein-kommet',
'only_matching': True,
}]
def _ARD_load_playlist_snipped(self, playlist_id, display_id, client, mode, pageNumber):
""" Query the ARD server for playlist information
and returns the data in "raw" format """
if mode == 'sendung':
graphQL = json.dumps({
'query': '''{
showPage(
client: "%s"
showId: "%s"
pageNumber: %d
) {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
else: # mode == 'sammlung'
graphQL = json.dumps({
'query': '''{
morePage(
client: "%s"
compilationId: "%s"
pageNumber: %d
) {
widget {
pagination {
pageSize
totalElements
}
teasers { # Array
mediumTitle
links { target { id href title } }
type
}
}
}}''' % (client, playlist_id, pageNumber),
}).encode()
# Ressources for ARD graphQL debugging:
# https://api-test.ardmediathek.de/public-gateway
show_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
'[Playlist] %s' % display_id,
data=graphQL,
headers={'Content-Type': 'application/json'})['data']
# align the structure of the returned data:
if mode == 'sendung':
show_page = show_page['showPage']
else: # mode == 'sammlung'
show_page = show_page['morePage']['widget']
return show_page
def _ARD_extract_playlist(self, url, playlist_id, display_id, client, mode):
""" Collects all playlist entries and returns them as info dict.
Supports playlists of mode 'sendung' and 'sammlung', and also nested
playlists. """
entries = []
pageNumber = 0
while True: # iterate by pageNumber
show_page = self._ARD_load_playlist_snipped(
playlist_id, display_id, client, mode, pageNumber)
for teaser in show_page['teasers']: # process playlist items
if '/compilation/' in teaser['links']['target']['href']:
# alternativ cond.: teaser['type'] == "compilation"
# => This is an nested compilation, e.g. like:
# https://www.ardmediathek.de/ard/sammlung/die-kirche-bleibt-im-dorf/5eOHzt8XB2sqeFXbIoJlg2/
link_mode = 'sammlung'
else:
link_mode = 'video'
item_url = 'https://www.ardmediathek.de/%s/%s/%s/%s/%s' % (
client, link_mode, display_id,
# perform HTLM quoting of episode title similar to ARD:
re.sub('^-|-$', '', # remove '-' from begin/end
re.sub('[^a-zA-Z0-9]+', '-', # replace special chars by -
teaser['links']['target']['title'].lower()
.replace('ä', 'ae').replace('ö', 'oe')
.replace('ü', 'ue').replace('ß', 'ss'))),
teaser['links']['target']['id'])
entries.append(self.url_result(
item_url,
ie=ARDBetaMediathekIE.ie_key()))
if (show_page['pagination']['pageSize'] * (pageNumber + 1)
>= show_page['pagination']['totalElements']):
# we've processed enough pages to get all playlist entries
break
pageNumber = pageNumber + 1
return self.playlist_result(entries, playlist_id, playlist_title=display_id)
_PAGE_SIZE = 100
def _real_extract(self, url):
video_id, display_id, playlist_type, client, season_number = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'client', 'season')
display_id, client = display_id or video_id, client or 'ard'
playlist_id, display_id, playlist_type, season_number, version = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'season', 'version')
if playlist_type:
# TODO: Extract only specified season
return self._ARD_extract_playlist(url, video_id, display_id, client, playlist_type)
def call_api(page_num):
api_path = 'compilations/ard' if playlist_type == 'sammlung' else 'widgets/ard/asset'
return self._download_json(
f'https://api.ardmediathek.de/page-gateway/{api_path}/{playlist_id}', playlist_id,
f'Downloading playlist page {page_num}', query={
'pageNumber': page_num,
'pageSize': self._PAGE_SIZE,
**({
'seasoned': 'true',
'seasonNumber': season_number,
'withOriginalversion': 'true' if version == 'OV' else 'false',
'withAudiodescription': 'true' if version == 'AD' else 'false',
} if season_number else {}),
})
player_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
display_id, data=json.dumps({
'query': '''{
playerPage(client:"%s", clipId: "%s") {
blockedByFsk
broadcastedOn
maturityContentRating
mediaCollection {
_duration
_geoblocked
_isLive
_mediaArray {
_mediaStreamArray {
_quality
_server
_stream
}
}
_previewImage
_subtitleUrl
_type
}
show {
title
}
image {
src
}
synopsis
title
tracking {
atiCustomVars {
contentId
}
}
}
}''' % (client, video_id),
}).encode(), headers={
'Content-Type': 'application/json'
})['data']['playerPage']
title = player_page['title']
content_id = str_or_none(try_get(
player_page, lambda x: x['tracking']['atiCustomVars']['contentId']))
media_collection = player_page.get('mediaCollection') or {}
if not media_collection and content_id:
media_collection = self._download_json(
'https://www.ardmediathek.de/play/media/' + content_id,
content_id, fatal=False) or {}
info = self._parse_media_info(
media_collection, content_id or video_id,
player_page.get('blockedByFsk'))
age_limit = None
description = player_page.get('synopsis')
maturity_content_rating = player_page.get('maturityContentRating')
if maturity_content_rating:
age_limit = int_or_none(maturity_content_rating.lstrip('FSK'))
if not age_limit and description:
age_limit = int_or_none(self._search_regex(
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
info.update({
'age_limit': age_limit,
'display_id': display_id,
'title': title,
'description': description,
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
'series': try_get(player_page, lambda x: x['show']['title']),
'thumbnail': (media_collection.get('_previewImage')
or try_get(player_page, lambda x: update_url(x['image']['src'], query=None, fragment=None))
or self.get_thumbnail_from_html(display_id, url)),
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
def fetch_page(page_num):
for item in traverse_obj(call_api(page_num), ('teasers', ..., {dict})):
item_id = traverse_obj(item, ('links', 'target', ('urlId', 'id')), 'id', get_all=False)
if not item_id or item_id == playlist_id:
continue
item_mode = 'sammlung' if item.get('type') == 'compilation' else 'video'
yield self.url_result(
f'https://www.ardmediathek.de/{item_mode}/{item_id}',
ie=(ARDMediathekCollectionIE if item_mode == 'sammlung' else ARDBetaMediathekIE),
**traverse_obj(item, {
'id': ('id', {str}),
'title': ('longTitle', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': ('broadcastedOn', {parse_iso8601}),
}))
def get_thumbnail_from_html(self, display_id, url):
webpage = self._download_webpage(url, display_id, fatal=False) or ''
return (
self._og_search_thumbnail(webpage, default=None)
or self._html_search_meta('thumbnailUrl', webpage, default=None))
page_data = call_api(0)
full_id = join_nonempty(playlist_id, season_number, version, delim='_')
return self.playlist_result(
OnDemandPagedList(fetch_page, self._PAGE_SIZE), full_id, display_id=display_id,
title=page_data.get('title'), description=page_data.get('synopsis'))

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))

14
yt_dlp/extractor/arnes.py
View File

@@ -1,11 +1,9 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
format_field,
float_or_none,
format_field,
int_or_none,
parse_iso8601,
remove_start,
@@ -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]),
}

303
yt_dlp/extractor/art19.py Normal file
View File

@@ -0,0 +1,303 @@
import re
from .common import InfoExtractor
from ..utils import float_or_none, int_or_none, parse_iso8601, url_or_none
from ..utils.traversal import traverse_obj
class Art19IE(InfoExtractor):
_UUID_REGEX = r'[\da-f]{8}-?[\da-f]{4}-?[\da-f]{4}-?[\da-f]{4}-?[\da-f]{12}'
_VALID_URL = [
rf'https?://(?:www\.)?art19\.com/shows/[^/#?]+/episodes/(?P<id>{_UUID_REGEX})',
rf'https?://rss\.art19\.com/episodes/(?P<id>{_UUID_REGEX})\.mp3',
]
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL[0]})']
_TESTS = [{
'url': 'https://rss.art19.com/episodes/5ba1413c-48b8-472b-9cc3-cfd952340bdb.mp3',
'info_dict': {
'id': '5ba1413c-48b8-472b-9cc3-cfd952340bdb',
'ext': 'mp3',
'title': 'Why Did DeSantis Drop Out?',
'series': 'The Daily Briefing',
'release_timestamp': 1705941275,
'description': 'md5:da38961da4a3f7e419471365e3c6b49f',
'episode': 'Episode 582',
'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
'series_id': 'ed52a0ab-08b1-4def-8afc-549e4d93296d',
'upload_date': '20240122',
'timestamp': 1705940815,
'episode_number': 582,
'modified_date': '20240122',
'episode_id': '5ba1413c-48b8-472b-9cc3-cfd952340bdb',
'modified_timestamp': 1705941275,
'release_date': '20240122',
'duration': 527.4,
},
}, {
'url': 'https://art19.com/shows/scamfluencers/episodes/8319b776-4153-4d22-8630-631f204a03dd',
'info_dict': {
'id': '8319b776-4153-4d22-8630-631f204a03dd',
'ext': 'mp3',
'title': 'Martha Stewart: The Homemaker Hustler Part 2',
'modified_date': '20240116',
'upload_date': '20240105',
'modified_timestamp': 1705435802,
'episode_id': '8319b776-4153-4d22-8630-631f204a03dd',
'series_id': 'd3c9b8ca-26b3-42f4-9bd8-21d1a9031e75',
'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
'description': 'md5:4aa7cfd1358dc57e729835bc208d7893',
'release_timestamp': 1705305660,
'release_date': '20240115',
'timestamp': 1704481536,
'episode_number': 88,
'series': 'Scamfluencers',
'duration': 2588.37501,
'episode': 'Episode 88',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.nu.nl/formule-1/6291456/verstappen-wordt-een-synoniem-voor-formule-1.html',
'info_dict': {
'id': '7d42626a-7301-47db-bb8a-3b6f054d77d7',
'ext': 'mp3',
'title': "'Verstappen wordt een synoniem voor Formule 1'",
'season': 'Seizoen 6',
'description': 'md5:39a7159a31c4cda312b2e893bdd5c071',
'episode_id': '7d42626a-7301-47db-bb8a-3b6f054d77d7',
'duration': 3061.82111,
'series_id': '93f4e113-2a60-4609-a564-755058fa40d8',
'release_date': '20231126',
'modified_timestamp': 1701156004,
'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
'season_number': 6,
'episode_number': 52,
'modified_date': '20231128',
'upload_date': '20231126',
'timestamp': 1701025981,
'season_id': '36097c1e-7455-490d-a2fe-e2f10b4d5f26',
'series': 'De Boordradio',
'release_timestamp': 1701026308,
'episode': 'Episode 52',
},
}, {
'url': 'https://www.wishtv.com/podcast-episode/larry-bucshon-announces-retirement-from-congress/',
'info_dict': {
'id': '8da368bd-08d1-46d0-afaa-c134a4af7dc0',
'ext': 'mp3',
'title': 'Larry Bucshon announces retirement from congress',
'upload_date': '20240115',
'episode_number': 148,
'episode': 'Episode 148',
'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
'release_date': '20240115',
'timestamp': 1705328205,
'release_timestamp': 1705329275,
'series': 'All INdiana Politics',
'modified_date': '20240117',
'modified_timestamp': 1705458901,
'series_id': 'c4af6c27-b10f-4ff2-9f84-0f407df86ff1',
'episode_id': '8da368bd-08d1-46d0-afaa-c134a4af7dc0',
'description': 'md5:53b5239e4d14973a87125c217c255b2a',
'duration': 1256.18848,
},
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
yield from super()._extract_embed_urls(url, webpage)
for episode_id in re.findall(
rf'<div[^>]+\bclass=[\'"][^\'"]*art19-web-player[^\'"]*[\'"][^>]+\bdata-episode-id=[\'"]({cls._UUID_REGEX})[\'"]', webpage):
yield f'https://rss.art19.com/episodes/{episode_id}.mp3'
def _real_extract(self, url):
episode_id = self._match_id(url)
player_metadata = self._download_json(
f'https://art19.com/episodes/{episode_id}', episode_id,
note='Downloading player metadata', fatal=False,
headers={'Accept': 'application/vnd.art19.v0+json'})
rss_metadata = self._download_json(
f'https://rss.art19.com/episodes/{episode_id}.json', episode_id, fatal=False,
note='Downloading RSS metadata')
formats = [{
'format_id': 'direct',
'url': f'https://rss.art19.com/episodes/{episode_id}.mp3',
'vcodec': 'none',
'acodec': 'mp3',
}]
for fmt_id, fmt_data in traverse_obj(rss_metadata, ('content', 'media', {dict.items}, ...)):
if fmt_id == 'waveform_bin':
continue
fmt_url = traverse_obj(fmt_data, ('url', {url_or_none}))
if not fmt_url:
continue
formats.append({
'format_id': fmt_id,
'url': fmt_url,
'vcodec': 'none',
'acodec': fmt_id,
'quality': -2 if fmt_id == 'ogg' else -1,
})
return {
'id': episode_id,
'formats': formats,
**traverse_obj(player_metadata, ('episode', {
'title': ('title', {str}),
'description': ('description_plain', {str}),
'episode_id': ('id', {str}),
'episode_number': ('episode_number', {int_or_none}),
'season_id': ('season_id', {str}),
'series_id': ('series_id', {str}),
'timestamp': ('created_at', {parse_iso8601}),
'release_timestamp': ('released_at', {parse_iso8601}),
'modified_timestamp': ('updated_at', {parse_iso8601}),
})),
**traverse_obj(rss_metadata, ('content', {
'title': ('episode_title', {str}),
'description': ('episode_description_plain', {str}),
'episode_id': ('episode_id', {str}),
'episode_number': ('episode_number', {int_or_none}),
'season': ('season_title', {str}),
'season_id': ('season_id', {str}),
'season_number': ('season_number', {int_or_none}),
'series': ('series_title', {str}),
'series_id': ('series_id', {str}),
'thumbnail': ('cover_image', {url_or_none}),
'duration': ('duration', {float_or_none}),
})),
}
class Art19ShowIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?art19\.com/shows/(?P<id>[\w-]+)(?:/embed)?/?'
_VALID_URL = [
rf'{_VALID_URL_BASE}(?:$|[#?])',
r'https?://rss\.art19\.com/(?P<id>[\w-]+)/?(?:$|[#?])',
]
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL_BASE}[^\'"])']
_TESTS = [{
'url': 'https://www.art19.com/shows/5898c087-a14f-48dc-b6fc-a2280a1ff6e0/',
'info_dict': {
'_type': 'playlist',
'id': '5898c087-a14f-48dc-b6fc-a2280a1ff6e0',
'display_id': 'echt-gebeurd',
'title': 'Echt Gebeurd',
'description': 'md5:5fd11dc80b76e51ffd34b6067fd5e560',
'timestamp': 1492642167,
'upload_date': '20170419',
'modified_timestamp': int,
'modified_date': str,
'tags': 'count:7',
},
'playlist_mincount': 425,
}, {
'url': 'https://www.art19.com/shows/echt-gebeurd',
'info_dict': {
'_type': 'playlist',
'id': '5898c087-a14f-48dc-b6fc-a2280a1ff6e0',
'display_id': 'echt-gebeurd',
'title': 'Echt Gebeurd',
'description': 'md5:5fd11dc80b76e51ffd34b6067fd5e560',
'timestamp': 1492642167,
'upload_date': '20170419',
'modified_timestamp': int,
'modified_date': str,
'tags': 'count:7',
},
'playlist_mincount': 425,
}, {
'url': 'https://rss.art19.com/scamfluencers',
'info_dict': {
'_type': 'playlist',
'id': 'd3c9b8ca-26b3-42f4-9bd8-21d1a9031e75',
'display_id': 'scamfluencers',
'title': 'Scamfluencers',
'description': 'md5:7d239d670c0ced6dadbf71c4caf764b7',
'timestamp': 1647368573,
'upload_date': '20220315',
'modified_timestamp': int,
'modified_date': str,
'tags': [],
},
'playlist_mincount': 90,
}, {
'url': 'https://art19.com/shows/enthuellt/embed',
'info_dict': {
'_type': 'playlist',
'id': 'e2cacf57-bb8a-4263-aa81-719bcdd4f80c',
'display_id': 'enthuellt',
'title': 'Enthüllt',
'description': 'md5:17752246643414a2fd51744fc9a1c08e',
'timestamp': 1601645860,
'upload_date': '20201002',
'modified_timestamp': int,
'modified_date': str,
'tags': 'count:10',
},
'playlist_mincount': 10,
}]
_WEBPAGE_TESTS = [{
'url': 'https://deconstructingyourself.com/deconstructing-yourself-podcast',
'info_dict': {
'_type': 'playlist',
'id': 'cfbb9b01-c295-4adb-8726-adde7c03cf21',
'display_id': 'deconstructing-yourself',
'title': 'Deconstructing Yourself',
'description': 'md5:dab5082b28b248a35476abf64768854d',
'timestamp': 1570581181,
'upload_date': '20191009',
'modified_timestamp': int,
'modified_date': str,
'tags': 'count:5',
},
'playlist_mincount': 80,
}, {
'url': 'https://chicagoreader.com/columns-opinion/podcasts/ben-joravsky-show-podcast-episodes/',
'info_dict': {
'_type': 'playlist',
'id': '9dfa2c37-ab87-4c13-8388-4897914313ec',
'display_id': 'the-ben-joravsky-show',
'title': 'The Ben Joravsky Show',
'description': 'md5:c0f3ec0ee0dbea764390e521adc8780a',
'timestamp': 1550875095,
'upload_date': '20190222',
'modified_timestamp': int,
'modified_date': str,
'tags': ['Chicago Politics', 'chicago', 'Ben Joravsky'],
},
'playlist_mincount': 1900,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
yield from super()._extract_embed_urls(url, webpage)
for series_id in re.findall(
r'<div[^>]+\bclass=[\'"][^\'"]*art19-web-player[^\'"]*[\'"][^>]+\bdata-series-id=[\'"]([\w-]+)[\'"]', webpage):
yield f'https://art19.com/shows/{series_id}'
def _real_extract(self, url):
series_id = self._match_id(url)
series_metadata = self._download_json(
f'https://art19.com/series/{series_id}', series_id, note='Downloading series metadata',
headers={'Accept': 'application/vnd.art19.v0+json'})
return {
'_type': 'playlist',
'entries': [
self.url_result(f'https://rss.art19.com/episodes/{episode_id}.mp3', Art19IE)
for episode_id in traverse_obj(series_metadata, ('series', 'episode_ids', ..., {str}))
],
**traverse_obj(series_metadata, ('series', {
'id': ('id', {str}),
'display_id': ('slug', {str}),
'title': ('title', {str}),
'description': ('description_plain', {str}),
'timestamp': ('created_at', {parse_iso8601}),
'modified_timestamp': ('updated_at', {parse_iso8601}),
})),
'tags': traverse_obj(series_metadata, ('tags', ..., 'name', {str})),
}

111
yt_dlp/extractor/arte.py
View File

@@ -5,6 +5,7 @@ from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
join_nonempty,
parse_iso8601,
parse_qs,
strip_or_none,
@@ -19,46 +20,22 @@ 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,
}, {
'url': 'https://www.arte.tv/pl/videos/100103-000-A/usa-dyskryminacja-na-porodowce/',
'info_dict': {
'id': '100103-000-A',
'title': 'USA: Dyskryminacja na porodówce',
'description': 'md5:242017b7cce59ffae340a54baefcafb1',
'alt_title': 'ARTE Reportage',
'upload_date': '20201103',
'duration': 554,
'thumbnail': r're:https://api-cdn\.arte\.tv/.+940x530',
'timestamp': 1604417980,
'ext': 'mp4',
},
'params': {'skip_download': 'm3u8'}
}, {
'note': 'No alt_title',
'url': 'https://www.arte.tv/fr/videos/110371-000-A/la-chaleur-supplice-des-arbres-de-rue/',
'info_dict': {
'id': '110371-000-A',
'ext': 'mp4',
'upload_date': '20220718',
'duration': 154,
'timestamp': 1658162460,
'description': 'md5:5890f36fe7dccfadb8b7c0891de54786',
'title': 'La chaleur, supplice des arbres de rue',
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/CPE2sQDtD8GLQgt8DuYHLf/940x530',
},
'params': {'skip_download': 'm3u8'}
'only_matching': True,
}, {
'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A',
'only_matching': True,
@@ -67,19 +44,38 @@ class ArteTVIE(ArteTVBaseIE):
'only_matching': True,
}, {
'url': 'https://www.arte.tv/de/videos/110203-006-A/zaz/',
'only_matching': True,
}, {
'url': 'https://www.arte.tv/fr/videos/109067-000-A/la-loi-de-teheran/',
'info_dict': {
'id': '110203-006-A',
'chapters': 'count:16',
'description': 'md5:cf592f1df52fe52007e3f8eac813c084',
'alt_title': 'Zaz',
'title': 'Baloise Session 2022',
'timestamp': 1668445200,
'duration': 4054,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/ubQjmVCGyRx3hmBuZEK9QZ/940x530',
'upload_date': '20221114',
'id': '109067-000-A',
'ext': 'mp4',
'description': 'md5:d2ca367b8ecee028dddaa8bd1aebc739',
'timestamp': 1713927600,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/3rR6PLzfbigSkkeHtkCZNF/940x530',
'duration': 7599,
'title': 'La loi de Téhéran',
'upload_date': '20240424',
'subtitles': {
'fr': 'mincount:1',
'fr-acc': 'mincount:1',
'fr-forced': 'mincount:1',
},
},
}, {
'note': 'age-restricted',
'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
'info_dict': {
'id': '006785-000-A',
'description': 'md5:c2f94fdfefc8a280e4dab68ab96ab0ba',
'title': 'The Element of Crime',
'timestamp': 1696111200,
'duration': 5849,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/q82dTTfyuCXupPsGxXsd7B/940x530',
'upload_date': '20230930',
'ext': 'mp4',
},
'expected_warnings': ['geo restricted']
'skip': '404 Not Found',
}]
_GEO_BYPASS = True
@@ -130,13 +126,27 @@ class ArteTVIE(ArteTVBaseIE):
),
}
@staticmethod
def _fix_accessible_subs_locale(subs):
updated_subs = {}
for lang, sub_formats in subs.items():
for fmt in sub_formats:
url = fmt.get('url') or ''
suffix = ('acc' if url.endswith('-MAL.m3u8')
else 'forced' if '_VO' not in url
else None)
updated_subs.setdefault(join_nonempty(lang, suffix), []).append(fmt)
return updated_subs
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
lang = mobj.group('lang') or mobj.group('lang_2')
langauge_code = self._LANG_MAP.get(lang)
language_code = self._LANG_MAP.get(lang)
config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id)
config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id, headers={
'x-validated-age': '18',
})
geoblocking = traverse_obj(config, ('data', 'attributes', 'restriction', 'geoblocking')) or {}
if geoblocking.get('restrictedArea'):
@@ -160,10 +170,10 @@ class ArteTVIE(ArteTVBaseIE):
m = self._VERSION_CODE_RE.match(stream_version_code)
if m:
lang_pref = int(''.join('01'[x] for x in (
m.group('vlang') == langauge_code, # we prefer voice in the requested language
m.group('vlang') == language_code, # we prefer voice in the requested language
not m.group('audio_desc'), # and not the audio description version
bool(m.group('original_voice')), # but if voice is not in the requested language, at least choose the original voice
m.group('sub_lang') == langauge_code, # if subtitles are present, we prefer them in the requested language
m.group('sub_lang') == language_code, # if subtitles are present, we prefer them in the requested language
not m.group('has_sub'), # but we prefer no subtitles otherwise
not m.group('sdh_sub'), # and we prefer not the hard-of-hearing subtitles if there are subtitles
)))
@@ -181,6 +191,7 @@ class ArteTVIE(ArteTVBaseIE):
secondary_formats.extend(fmts)
else:
formats.extend(fmts)
subs = self._fix_accessible_subs_locale(subs)
self._merge_subtitles(subs, target=subtitles)
elif stream['protocol'] in ('HTTPS', 'RTMP'):
@@ -236,7 +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,
@@ -251,7 +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,
@@ -287,7 +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': {
@@ -301,7 +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):
@@ -310,12 +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

168
yt_dlp/extractor/asobichannel.py Normal file
View File

@@ -0,0 +1,168 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
merge_dicts,
parse_iso8601,
url_or_none,
)
from ..utils.traversal import traverse_obj
class AsobiChannelBaseIE(InfoExtractor):
_MICROCMS_HEADER = {'X-MICROCMS-API-KEY': 'qRaKehul9AHU8KtL0dnq1OCLKnFec6yrbcz3'}
def _extract_info(self, metadata):
return traverse_obj(metadata, {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('body', {clean_html}),
'thumbnail': ('contents', 'video_thumb', 'url', {url_or_none}),
'timestamp': ('publishedAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
'channel': ('channel', 'name', {str}),
'channel_id': ('channel', 'id', {str}),
})
class AsobiChannelIE(AsobiChannelBaseIE):
IE_NAME = 'asobichannel'
IE_DESC = 'ASOBI CHANNEL'
_VALID_URL = r'https?://asobichannel\.asobistore\.jp/watch/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://asobichannel.asobistore.jp/watch/1ypp48qd32p',
'md5': '39df74e872afe032c4eb27b89144fc92',
'info_dict': {
'id': '1ypp48qd32p',
'ext': 'mp4',
'title': 'アイドルマスター ミリオンライブ！ 765プロch 原っぱ通信 #1',
'description': 'md5:b930bd2199c9b2fd75951ce4aaa7efd2',
'thumbnail': 'https://images.microcms-assets.io/assets/d2420de4b9194e11beb164f99edb1f95/a8e6f84119f54eb9ab4ce16729239905/%E3%82%B5%E3%83%A0%E3%83%8D%20(1).png',
'timestamp': 1697098247,
'upload_date': '20231012',
'modified_timestamp': 1698381162,
'modified_date': '20231027',
'channel': 'アイドルマスター',
'channel_id': 'idolmaster',
},
}, {
'url': 'https://asobichannel.asobistore.jp/watch/redigiwnjzqj',
'md5': '229fa8fb5c591c75ce8c37a497f113f6',
'info_dict': {
'id': 'redigiwnjzqj',
'ext': 'mp4',
'title': '【おまけ放送】アイドルマスター ミリオンライブ！ 765プロch 原っぱ通信 #1',
'description': 'md5:7d9cd35fb54425a6967822bd564ea2d9',
'thumbnail': 'https://images.microcms-assets.io/assets/d2420de4b9194e11beb164f99edb1f95/20e5c1d6184242eebc2512a5dec59bf0/P1_%E5%8E%9F%E3%81%A3%E3%81%B1%E3%82%B5%E3%83%A0%E3%83%8D.png',
'modified_timestamp': 1697797125,
'modified_date': '20231020',
'timestamp': 1697261769,
'upload_date': '20231014',
'channel': 'アイドルマスター',
'channel_id': 'idolmaster',
},
}]
_survapi_header = None
def _real_initialize(self):
token = self._download_json(
'https://asobichannel-api.asobistore.jp/api/v1/vspf/token', None,
note='Retrieving API token')
self._survapi_header = {'Authorization': f'Bearer {token}'}
def _process_vod(self, video_id, metadata):
content_id = metadata['contents']['video_id']
vod_data = self._download_json(
f'https://survapi.channel.or.jp/proxy/v1/contents/{content_id}/get_by_cuid', video_id,
headers=self._survapi_header, note='Downloading vod data')
return {
'formats': self._extract_m3u8_formats(vod_data['ex_content']['streaming_url'], video_id),
}
def _process_live(self, video_id, metadata):
content_id = metadata['contents']['video_id']
event_data = self._download_json(
f'https://survapi.channel.or.jp/ex/events/{content_id}?embed=channel', video_id,
headers=self._survapi_header, note='Downloading event data')
player_type = traverse_obj(event_data, ('data', 'Player_type', {str}))
if player_type == 'poster':
self.raise_no_formats('Live event has not yet started', expected=True)
live_status = 'is_upcoming'
formats = []
elif player_type == 'player':
live_status = 'is_live'
formats = self._extract_m3u8_formats(
event_data['data']['Channel']['Custom_live_url'], video_id, live=True)
else:
raise ExtractorError('Unsupported player type {player_type!r}')
return {
'release_timestamp': traverse_obj(metadata, ('period', 'start', {parse_iso8601})),
'live_status': live_status,
'formats': formats,
}
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._download_json(
f'https://channel.microcms.io/api/v1/media/{video_id}', video_id,
headers=self._MICROCMS_HEADER)
info = self._extract_info(metadata)
video_type = traverse_obj(metadata, ('contents', 'video_type', 0, {str}))
if video_type == 'VOD':
return merge_dicts(info, self._process_vod(video_id, metadata))
if video_type == 'LIVE':
return merge_dicts(info, self._process_live(video_id, metadata))
raise ExtractorError(f'Unexpected video type {video_type!r}')
class AsobiChannelTagURLIE(AsobiChannelBaseIE):
IE_NAME = 'asobichannel:tag'
IE_DESC = 'ASOBI CHANNEL'
_VALID_URL = r'https?://asobichannel\.asobistore\.jp/tag/(?P<id>[a-z0-9-_]+)'
_TESTS = [{
'url': 'https://asobichannel.asobistore.jp/tag/bjhh-nbcja',
'info_dict': {
'id': 'bjhh-nbcja',
'title': 'アイドルマスター ミリオンライブ！ 765プロch 原っぱ通信',
},
'playlist_mincount': 16,
}, {
'url': 'https://asobichannel.asobistore.jp/tag/hvm5qw3c6od',
'info_dict': {
'id': 'hvm5qw3c6od',
'title': 'アイマスMOIW2023ラジオ',
},
'playlist_mincount': 13,
}]
def _real_extract(self, url):
tag_id = self._match_id(url)
webpage = self._download_webpage(url, tag_id)
title = traverse_obj(self._search_nextjs_data(
webpage, tag_id, fatal=False), ('props', 'pageProps', 'data', 'name', {str}))
media = self._download_json(
f'https://channel.microcms.io/api/v1/media?limit=999&filters=(tag[contains]{tag_id})',
tag_id, headers=self._MICROCMS_HEADER)
def entries():
for metadata in traverse_obj(media, ('contents', lambda _, v: v['id'])):
yield {
'_type': 'url',
'url': f'https://asobichannel.asobistore.jp/watch/{metadata["id"]}',
'ie_key': AsobiChannelIE.ie_key(),
**self._extract_info(metadata),
}
return self.playlist_result(entries(), tag_id, title)

154
yt_dlp/extractor/asobistage.py Normal file
View File

@@ -0,0 +1,154 @@
import functools
from .common import InfoExtractor
from ..utils import str_or_none, url_or_none
from ..utils.traversal import traverse_obj
class AsobiStageIE(InfoExtractor):
IE_DESC = 'ASOBISTAGE (アソビステージ)'
_VALID_URL = r'https?://asobistage\.asobistore\.jp/event/(?P<id>(?P<event>\w+)/(?P<type>archive|player)/(?P<slug>\w+))(?:[?#]|$)'
_TESTS = [{
'url': 'https://asobistage.asobistore.jp/event/315passionhour_2022summer/archive/frame',
'info_dict': {
'id': '315passionhour_2022summer/archive/frame',
'title': '315プロダクションプレゼンツ 315パッションアワー!!!',
'thumbnail': r're:^https?://[\w.-]+/\w+/\w+',
},
'playlist_count': 1,
'playlist': [{
'info_dict': {
'id': 'edff52f2',
'ext': 'mp4',
'title': '315passion_FRAME_only',
'thumbnail': r're:^https?://[\w.-]+/\w+/\w+',
},
}],
}, {
'url': 'https://asobistage.asobistore.jp/event/idolmaster_idolworld2023_goods/archive/live',
'info_dict': {
'id': 'idolmaster_idolworld2023_goods/archive/live',
'title': 'md5:378510b6e830129d505885908bd6c576',
'thumbnail': r're:^https?://[\w.-]+/\w+/\w+',
},
'playlist_count': 1,
'playlist': [{
'info_dict': {
'id': '3aef7110',
'ext': 'mp4',
'title': 'asobistore_station_1020_serverREC',
'thumbnail': r're:^https?://[\w.-]+/\w+/\w+',
},
}],
}, {
'url': 'https://asobistage.asobistore.jp/event/sidem_fclive_bpct/archive/premium_hc',
'playlist_count': 4,
'info_dict': {
'id': 'sidem_fclive_bpct/archive/premium_hc',
'title': '315 Production presents F＠NTASTIC COMBINATION LIVE ～BRAINPOWER!!～/～CONNECTIME!!!!～',
'thumbnail': r're:^https?://[\w.-]+/\w+/\w+',
},
}, {
'url': 'https://asobistage.asobistore.jp/event/ijigenfes_utagassen/player/day1',
'only_matching': True,
}]
_API_HOST = 'https://asobistage-api.asobistore.jp'
_HEADERS = {}
_is_logged_in = False
@functools.cached_property
def _owned_tickets(self):
owned_tickets = set()
if not self._is_logged_in:
return owned_tickets
for path, name in [
('api/v1/purchase_history/list', 'ticket purchase history'),
('api/v1/serialcode/list', 'redemption history'),
]:
response = self._download_json(
f'{self._API_HOST}/{path}', None, f'Downloading {name}',
f'Unable to download {name}', expected_status=400)
if traverse_obj(response, ('payload', 'error_message'), 'error') == 'notlogin':
self._is_logged_in = False
break
owned_tickets.update(
traverse_obj(response, ('payload', 'value', ..., 'digital_product_id', {str_or_none})))
return owned_tickets
def _get_available_channel_id(self, channel):
channel_id = traverse_obj(channel, ('chennel_vspf_id', {str}))
if not channel_id:
return None
# if rights_type_id == 6, then 'No conditions (no login required - non-members are OK)'
if traverse_obj(channel, ('viewrights', lambda _, v: v['rights_type_id'] == 6)):
return channel_id
available_tickets = traverse_obj(channel, (
'viewrights', ..., ('tickets', 'serialcodes'), ..., 'digital_product_id', {str_or_none}))
if not self._owned_tickets.intersection(available_tickets):
self.report_warning(
f'You are not a ticketholder for "{channel.get("channel_name") or channel_id}"')
return None
return channel_id
def _real_initialize(self):
if self._get_cookies(self._API_HOST):
self._is_logged_in = True
token = self._download_json(
f'{self._API_HOST}/api/v1/vspf/token', None, 'Getting token', 'Unable to get token')
self._HEADERS['Authorization'] = f'Bearer {token}'
def _real_extract(self, url):
video_id, event, type_, slug = self._match_valid_url(url).group('id', 'event', 'type', 'slug')
video_type = {'archive': 'archives', 'player': 'broadcasts'}[type_]
webpage = self._download_webpage(url, video_id)
event_data = traverse_obj(
self._search_nextjs_data(webpage, video_id, default={}),
('props', 'pageProps', 'eventCMSData', {
'title': ('event_name', {str}),
'thumbnail': ('event_thumbnail_image', {url_or_none}),
}))
available_channels = traverse_obj(self._download_json(
f'https://asobistage.asobistore.jp/cdn/v101/events/{event}/{video_type}.json',
video_id, 'Getting channel list', 'Unable to get channel list'), (
video_type, lambda _, v: v['broadcast_slug'] == slug,
'channels', lambda _, v: v['chennel_vspf_id'] != '00000'))
entries = []
for channel_id in traverse_obj(available_channels, (..., {self._get_available_channel_id})):
if video_type == 'archives':
channel_json = self._download_json(
f'https://survapi.channel.or.jp/proxy/v1/contents/{channel_id}/get_by_cuid', channel_id,
'Getting archive channel info', 'Unable to get archive channel info', fatal=False,
headers=self._HEADERS)
channel_data = traverse_obj(channel_json, ('ex_content', {
'm3u8_url': 'streaming_url',
'title': 'title',
'thumbnail': ('thumbnail', 'url'),
}))
else: # video_type == 'broadcasts'
channel_json = self._download_json(
f'https://survapi.channel.or.jp/ex/events/{channel_id}', channel_id,
'Getting live channel info', 'Unable to get live channel info', fatal=False,
headers=self._HEADERS, query={'embed': 'channel'})
channel_data = traverse_obj(channel_json, ('data', {
'm3u8_url': ('Channel', 'Custom_live_url'),
'title': 'Name',
'thumbnail': 'Poster_url',
}))
entries.append({
'id': channel_id,
'title': channel_data.get('title'),
'formats': self._extract_m3u8_formats(channel_data.get('m3u8_url'), channel_id, fatal=False),
'is_live': video_type == 'broadcasts',
'thumbnail': url_or_none(channel_data.get('thumbnail')),
})
if not self._is_logged_in and not entries:
self.raise_login_required()
return self.playlist_result(entries, video_id, **event_data)

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))

53
yt_dlp/extractor/atttechchannel.py
View File

@@ -1,53 +0,0 @@
from .common import InfoExtractor
from ..utils import unified_strdate
class ATTTechChannelIE(InfoExtractor):
_VALID_URL = r'https?://techchannel\.att\.com/play-video\.cfm/([^/]+/)*(?P<id>.+)'
_TEST = {
'url': 'http://techchannel.att.com/play-video.cfm/2014/1/27/ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'info_dict': {
'id': '11316',
'display_id': 'ATT-Archives-The-UNIX-System-Making-Computers-Easier-to-Use',
'ext': 'flv',
'title': 'AT&T Archives : The UNIX System: Making Computers Easier to Use',
'description': 'A 1982 film about UNIX is the foundation for software in use around Bell Labs and AT&T.',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140127',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r"url\s*:\s*'(rtmp://[^']+)'",
webpage, 'video URL')
video_id = self._search_regex(
r'mediaid\s*=\s*(\d+)',
webpage, 'video id', fatal=False)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'[Rr]elease\s+date:\s*(\d{1,2}/\d{1,2}/\d{4})',
webpage, 'upload date', fatal=False), False)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
}

26
yt_dlp/extractor/atvat.py
View File

@@ -1,11 +1,11 @@
import datetime
import datetime as dt
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
jwt_encode_hs256,
try_get,
ExtractorError,
)
@@ -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,
@@ -66,14 +66,14 @@ 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 = datetime.datetime.now()
not_before = time_of_request - datetime.timedelta(minutes=5)
expire = time_of_request + datetime.timedelta(minutes=5)
time_of_request = dt.datetime.now()
not_before = time_of_request - dt.timedelta(minutes=5)
expire = time_of_request + dt.timedelta(minutes=5)
payload = {
'content_ids': {
content_id: content_ids,
@@ -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_urllib_parse_urlencode,
compat_str,
)
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)

28
yt_dlp/extractor/aws.py
View File

@@ -1,9 +1,9 @@
import datetime
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
@@ -12,26 +12,26 @@ class AWSIE(InfoExtractor): # XXX: Conventionally, base classes should end with
def _aws_execute_api(self, aws_dict, video_id, query=None):
query = query or {}
amz_date = datetime.datetime.now(datetime.timezone.utc).strftime('%Y%m%dT%H%M%SZ')
amz_date = dt.datetime.now(dt.timezone.utc).strftime('%Y%m%dT%H%M%SZ')
date = amz_date[:8]
headers = {
'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)

8
yt_dlp/extractor/axs.py
View File

@@ -24,7 +24,8 @@ class AxsIE(InfoExtractor):
'timestamp': 1685729564,
'duration': 1284.216,
'series': 'Rock & Roll Road Trip with Sammy Hagar',
'season': 2,
'season': 'Season 2',
'season_number': 2,
'episode': '3',
'thumbnail': 'https://images.dotstudiopro.com/5f4e9d330a0c3b295a7e8394',
},
@@ -41,7 +42,8 @@ class AxsIE(InfoExtractor):
'timestamp': 1676403615,
'duration': 2570.668,
'series': 'The Big Interview with Dan Rather',
'season': 3,
'season': 'Season 3',
'season_number': 3,
'episode': '5',
'thumbnail': 'https://images.dotstudiopro.com/5f4d1901f340b50d937cec32',
},
@@ -77,7 +79,7 @@ class AxsIE(InfoExtractor):
'title': ('title', {str}),
'description': ('description', {str}),
'series': ('seriestitle', {str}),
'season': ('season', {int}),
'season_number': ('season', {int}),
'episode': ('episode', {str}),
'duration': ('duration', {float_or_none}),
'timestamp': ('updated_at', {parse_iso8601}),

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(

88
yt_dlp/extractor/banbye.py
View File

@@ -1,15 +1,16 @@
import math
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_parse_qs,
)
from ..utils import (
format_field,
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)
@@ -31,8 +32,9 @@ class BanByeBaseIE(InfoExtractor):
class BanByeIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?watch/(?P<id>[\w-]+)'
_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,
@@ -120,7 +178,7 @@ class BanByeIE(BanByeBaseIE):
class BanByeChannelIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?channel/(?P<id>\w+)'
_VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?channel/(?P<id>\w+)'
_TESTS = [{
'url': 'https://banbye.com/channel/ch_wrealu24',
'info_dict': {
@@ -152,7 +210,7 @@ class BanByeChannelIE(BanByeBaseIE):
'sort': 'new',
'limit': self._PAGE_SIZE,
'offset': page_num * self._PAGE_SIZE,
}, note=f'Downloading page {page_num+1}')
}, note=f'Downloading page {page_num + 1}')
return [
self.url_result(f"{self._VIDEO_BASE}/{video['_id']}", BanByeIE)
for video in data['items']

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,
}, {

18
yt_dlp/extractor/bannedvideo.py
View File

@@ -2,11 +2,11 @@ import json
from .common import InfoExtractor
from ..utils import (
try_get,
int_or_none,
url_or_none,
float_or_none,
int_or_none,
try_get,
unified_timestamp,
url_or_none,
)
@@ -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')),
}

553
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')
@@ -312,21 +312,30 @@ 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):
last_exception = None
formats, subtitles = [], {}
for media_set in self._MEDIA_SETS:
try:
return self._download_media_selector_url(
fmts, subs = self._download_media_selector_url(
self._MEDIA_SELECTOR_URL_TEMPL % (media_set, programme_id), programme_id)
formats.extend(fmts)
if subs:
self._merge_subtitles(subs, target=subtitles)
except BBCCoUkIE.MediaSelectionError as e:
if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
last_exception = e
continue
self._raise_extractor_error(e)
self._raise_extractor_error(last_exception)
if last_exception:
if formats or subtitles:
self.report_warning(f'{self.IE_NAME} returned error: {last_exception.id}')
else:
self._raise_extractor_error(last_exception)
return formats, subtitles
def _download_media_selector_url(self, url, programme_id=None):
media_selection = self._download_json(
@@ -363,7 +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(
@@ -385,7 +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,
@@ -414,9 +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,
@@ -432,7 +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 = {}
@@ -471,32 +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):
@@ -506,7 +515,7 @@ class BBCCoUkIE(InfoExtractor):
if value and re.match(r'^[pb][\da-z]{7}$', value):
return value
get_from_attributes(item)
mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
mediator = item.find(f'./{{{self._EMP_PLAYLIST_NS}}}mediator')
if mediator is not None:
return get_from_attributes(mediator)
@@ -546,7 +555,7 @@ class BBCCoUkIE(InfoExtractor):
if not programme_id:
programme_id = self._search_regex(
r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
rf'"vpid"\s*:\s*"({self._ID_REGEX})"', webpage, 'vpid', fatal=False, default=None)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
@@ -593,7 +602,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
'title': 'Russia stages massive WW2 parade',
'title': 'Russia stages massive WW2 parade despite Western boycott',
'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
},
'playlist_count': 2,
@@ -614,6 +623,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': '3662a707-0af9-3149-963f-47bea720b460',
'title': 'BUGGER',
'description': r're:BUGGER The recent revelations by the whistleblower Edward Snowden were fascinating. .{211}\.{3}$',
},
'playlist_count': 18,
}, {
@@ -622,16 +632,16 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': 'p02mprgb',
'ext': 'mp4',
'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'description': 'md5:2868290467291b37feda7863f7a83f54',
'title': 'Germanwings crash site aerial video',
'description': r're:(?s)Aerial video showed the site where the Germanwings flight 4U 9525, .{156} BFM TV\.$',
'duration': 47,
'timestamp': 1427219242,
'upload_date': '20150324',
'thumbnail': 'https://ichef.bbci.co.uk/news/1024/media/images/81879000/jpg/_81879090_81879089.jpg',
},
'params': {
# rtmp download
'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)
@@ -647,21 +657,24 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
},
'params': {
'skip_download': True,
}
},
'skip': 'now SIMORGH_DATA with no video',
}, {
# single video embedded with data-playable containing XML playlists (regional section)
'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
'info_dict': {
'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'id': '39275083',
'display_id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'ext': 'mp4',
'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
'description': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'timestamp': 1434713142,
'upload_date': '20150619',
'thumbnail': 'https://a.files.bbci.co.uk/worldservice/live/assets/images/2015/06/19/150619132146_honduras_hsopitales_militares_640x360_aptn_nocredit.jpg',
},
'params': {
'skip_download': True,
}
},
}, {
# single video from video playlist embedded with vxp-playlist-data JSON
'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
@@ -674,22 +687,21 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
},
'params': {
'skip_download': True,
}
},
'skip': '404 Not Found',
}, {
# single video story with digitalData
# single video story with __PWA_PRELOADED_STATE__
'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
'info_dict': {
'id': 'p02q6gc4',
'ext': 'flv',
'title': 'Sri Lanka’s spicy secret',
'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
'timestamp': 1437674293,
'upload_date': '20150723',
'ext': 'mp4',
'title': 'Tasting the spice of life in Jaffna',
'description': r're:(?s)BBC Travel Show’s Henry Golding explores the city of Jaffna .{151} aftertaste\.$',
'timestamp': 1646058397,
'upload_date': '20220228',
'duration': 255,
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/1920xn/p02vxvkn.jpg',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# single video story without digitalData
'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
@@ -701,12 +713,10 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'timestamp': 1415867444,
'upload_date': '20141113',
},
'params': {
# rtmp download
'skip_download': True,
}
'skip': 'redirects to TopGear home page',
}, {
# single video embedded with Morph
# TODO: replacement test page
'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
'info_dict': {
'id': 'p041vhd0',
@@ -717,27 +727,22 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader': 'BBC Sport',
'uploader_id': 'bbc_sport',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Georestricted to UK',
'skip': 'Video no longer in page',
}, {
# single video with playlist.sxml URL in playlist param
# single video in __INITIAL_DATA__
'url': 'http://www.bbc.com/sport/0/football/33653409',
'info_dict': {
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'title': 'Ronaldo to Man Utd, Arsenal to spend?',
'description': r're:(?s)BBC Sport\'s David Ornstein rounds up the latest transfer reports, .{359} here\.$',
'timestamp': 1437750175,
'upload_date': '20150724',
'thumbnail': r're:https?://.+/.+media/images/69320000/png/_69320754_mmgossipcolumnextraaugust18.png',
'duration': 140,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# article with multiple videos embedded with playlist.sxml in playlist param
# article with multiple videos embedded with Morph.setPayload
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': '34475836',
@@ -745,6 +750,21 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
},
'playlist_count': 3,
}, {
# Testing noplaylist
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': 'p034ppnv',
'ext': 'mp4',
'title': 'All you need to know about Jurgen Klopp',
'timestamp': 1444335081,
'upload_date': '20151008',
'duration': 122.0,
'thumbnail': 'https://ichef.bbci.co.uk/onesport/cps/976/cpsprodpb/7542/production/_85981003_klopp.jpg',
},
'params': {
'noplaylist': True,
},
}, {
# school report article with single video
'url': 'http://www.bbc.co.uk/schoolreport/35744779',
@@ -753,6 +773,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'title': 'School which breaks down barriers in Jerusalem',
},
'playlist_count': 1,
'skip': 'redirects to Young Reporter home page https://www.bbc.co.uk/news/topics/cg41ylwv43pt',
}, {
# single video with playlist URL from weather section
'url': 'http://www.bbc.com/weather/features/33601775',
@@ -769,18 +790,33 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1437785037,
'upload_date': '20150725',
'duration': 105,
},
}, {
# video with window.__INITIAL_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/av/world-europe-59468682',
'info_dict': {
'id': 'p0b71qth',
'id': 'p0b779gc',
'ext': 'mp4',
'title': 'Why France is making this woman a national hero',
'description': 'md5:7affdfab80e9c3a1f976230a1ff4d5e4',
'description': r're:(?s)France is honouring the US-born 20th Century singer and activist Josephine .{208} Second World War.',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1638230731,
'upload_date': '20211130',
'timestamp': 1638215626,
'upload_date': '20211129',
'duration': 125,
},
}, {
# video with script id __NEXT_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/uk-68546268',
'info_dict': {
'id': 'p0hj0lq7',
'ext': 'mp4',
'title': 'Nasser Hospital doctor describes his treatment by IDF',
'description': r're:(?s)Doctor Abu Sabha said he was detained by Israeli forces after .{276} hostages\."$',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1710188248,
'upload_date': '20240311',
'duration': 104,
},
}, {
# single video article embedded with data-media-vpid
@@ -808,6 +844,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader': 'Radio 3',
'uploader_id': 'bbc_radio_three',
},
'skip': '404 Not Found',
}, {
'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
'info_dict': {
@@ -815,6 +852,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'ext': 'mp4',
'title': 'md5:2fabf12a726603193a2879a055f72514',
'description': 'Learn English words and phrases from this story',
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/1200x675/p06pq9gk.jpg',
},
'add_ie': [BBCCoUkIE.ie_key()],
}, {
@@ -823,27 +861,29 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'info_dict': {
'id': 'p07c6sb9',
'ext': 'mp4',
'title': 'How positive thinking is harming your happiness',
'alt_title': 'The downsides of positive thinking',
'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
'title': 'The downsides of positive thinking',
'description': 'The downsides of positive thinking',
'duration': 235,
'thumbnail': r're:https?://.+/p07c9dsr.jpg',
'upload_date': '20190604',
'categories': ['Psychology'],
'thumbnail': r're:https?://.+/p07c9dsr\.(?:jpg|webp|png)',
'upload_date': '20220223',
'timestamp': 1645632746,
},
}, {
# BBC Sounds
'url': 'https://www.bbc.co.uk/sounds/play/m001q78b',
'url': 'https://www.bbc.co.uk/sounds/play/w3ct5rgx',
'info_dict': {
'id': 'm001q789',
'id': 'p0hrw4nr',
'ext': 'mp4',
'title': 'The Night Tracks Mix - Music for the darkling hour',
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/raw/p0c00hym.jpg',
'chapters': 'count:8',
'description': 'md5:815fb51cbdaa270040aab8145b3f1d67',
'uploader': 'Radio 3',
'duration': 1800,
'uploader_id': 'bbc_radio_three',
'title': 'Are our coastlines being washed away?',
'description': r're:(?s)Around the world, coastlines are constantly changing .{2000,} Images\)$',
'timestamp': 1713556800,
'upload_date': '20240419',
'duration': 1588,
'thumbnail': 'https://ichef.bbci.co.uk/images/ic/raw/p0hrnxbl.jpg',
'uploader': 'World Service',
'uploader_id': 'bbc_world_service',
'series': 'CrowdScience',
'chapters': [],
},
}, { # onion routes
'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
@@ -857,7 +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.
@@ -969,7 +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:
@@ -995,18 +1035,17 @@ 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(
'https://www.bbc.co.uk/programmes/%s' % group_id,
ie=BBCCoUkIE.ie_key())
f'https://www.bbc.co.uk/programmes/{group_id}', BBCCoUkIE)
# 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:
@@ -1060,83 +1099,133 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
}
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video
# seems to be always related to the first one
morph_payload = self._parse_json(
self._search_regex(
r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
webpage, 'morph payload', default='{}'),
playlist_id, fatal=False)
# Several setPayload calls may be present but the video(s)
# should be in one that mentions leadMedia or videoData
morph_payload = self._search_json(
r'\bMorph\s*\.\s*setPayload\s*\([^,]+,', webpage, 'morph payload', playlist_id,
contains_pattern=r'{(?s:(?:(?!</script>).)+(?:"leadMedia"|\\"videoData\\")\s*:.+)}',
default={})
if morph_payload:
components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
for component in components:
if not isinstance(component, dict):
continue
lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
if not lead_media:
continue
identifiers = lead_media.get('identifiers')
if not identifiers or not isinstance(identifiers, dict):
continue
programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
for lead_media in traverse_obj(morph_payload, (
'body', 'components', ..., 'props', 'leadMedia', {dict})):
programme_id = traverse_obj(lead_media, ('identifiers', ('vpid', 'playablePid'), {str}, any))
if not programme_id:
continue
title = lead_media.get('title') or self._og_search_title(webpage)
formats, subtitles = self._download_media_selector(programme_id)
description = lead_media.get('summary')
uploader = lead_media.get('masterBrand')
uploader_id = lead_media.get('mid')
duration = None
duration_d = lead_media.get('duration')
if isinstance(duration_d, dict):
duration = parse_duration(dict_get(
duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'title': lead_media.get('title') or self._og_search_title(webpage),
**traverse_obj(lead_media, {
'description': ('summary', {str}),
'duration': ('duration', ('rawDuration', 'formattedDuration', 'spokenDuration'), {parse_duration}),
'uploader': ('masterBrand', {str}),
'uploader_id': ('mid', {str}),
}),
'formats': formats,
'subtitles': subtitles,
}
body = self._parse_json(traverse_obj(morph_payload, (
'body', 'content', 'article', 'body')), playlist_id, fatal=False)
for video_data in traverse_obj(body, (lambda _, v: v['videoData']['pid'], 'videoData')):
if video_data.get('vpid'):
video_id = video_data['vpid']
formats, subtitles = self._download_media_selector(video_id)
entry = {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
}
else:
video_id = video_data['pid']
entry = self.url_result(
f'https://www.bbc.co.uk/programmes/{video_id}', BBCCoUkIE,
video_id, url_transparent=True)
entry.update({
'timestamp': traverse_obj(morph_payload, (
'body', 'content', 'article', 'dateTimeInfo', 'dateTime', {parse_iso8601}),
),
**traverse_obj(video_data, {
'thumbnail': (('iChefImage', 'image'), {url_or_none}, any),
'title': (('title', 'caption'), {str}, any),
'duration': ('duration', {parse_duration}),
}),
})
if video_data.get('isLead') and not self._yes_playlist(playlist_id, video_id):
return entry
entries.append(entry)
if entries:
playlist_title = traverse_obj(morph_payload, (
'body', 'content', 'article', 'headline', {str})) or playlist_title
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
preload_state = self._parse_json(self._search_regex(
r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
if preload_state:
current_programme = preload_state.get('programmes', {}).get('current') or {}
programme_id = current_programme.get('id')
if current_programme and programme_id and current_programme.get('type') == 'playable_item':
title = current_programme.get('titles', {}).get('tertiary') or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
synopses = current_programme.get('synopses') or {}
network = current_programme.get('network') or {}
duration = int_or_none(
current_programme.get('duration', {}).get('value'))
thumbnail = None
image_url = current_programme.get('image_url')
if image_url:
thumbnail = image_url.replace('{recipe}', 'raw')
# various PRELOADED_STATE JSON
preload_state = self._search_json(
r'window\.__(?:PWA_)?PRELOADED_STATE__\s*=', webpage,
'preload state', playlist_id, transform_source=js_to_json, default={})
# PRELOADED_STATE with current programmme
current_programme = traverse_obj(preload_state, ('programmes', 'current', {dict}))
programme_id = traverse_obj(current_programme, ('id', {str}))
if programme_id and current_programme.get('type') == 'playable_item':
title = traverse_obj(current_programme, ('titles', ('tertiary', 'secondary'), {str}, any)) or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
return {
'id': programme_id,
'title': title,
'formats': formats,
**traverse_obj(current_programme, {
'description': ('synopses', ('long', 'medium', 'short'), {str}, any),
'thumbnail': ('image_url', {lambda u: url_or_none(u.replace('{recipe}', 'raw'))}),
'duration': ('duration', 'value', {int_or_none}),
'uploader': ('network', 'short_title', {str}),
'uploader_id': ('network', 'id', {str}),
'timestamp': ((('availability', 'from'), ('release', 'date')), {parse_iso8601}, any),
'series': ('titles', 'primary', {str}),
}),
'subtitles': subtitles,
'chapters': traverse_obj(preload_state, (
'tracklist', 'tracks', lambda _, v: float(v['offset']['start']), {
'title': ('titles', {lambda x: join_nonempty(
'primary', 'secondary', 'tertiary', delim=' - ', from_dict=x)}),
'start_time': ('offset', 'start', {float_or_none}),
'end_time': ('offset', 'end', {float_or_none}),
}),
),
}
# PWA_PRELOADED_STATE with article video asset
asset_id = traverse_obj(preload_state, (
'entities', 'articles', lambda k, _: k.rsplit('/', 1)[-1] == playlist_id,
'assetVideo', 0, {str}, any))
if asset_id:
video_id = traverse_obj(preload_state, ('entities', 'videos', asset_id, 'vpid', {str}))
if video_id:
article = traverse_obj(preload_state, (
'entities', 'articles', lambda _, v: v['assetVideo'][0] == asset_id, any))
def image_url(image_id):
return traverse_obj(preload_state, (
'entities', 'images', image_id, 'url',
{lambda u: url_or_none(u.replace('$recipe', 'raw'))}))
formats, subtitles = self._download_media_selector(video_id)
return {
'id': programme_id,
'title': title,
'description': dict_get(synopses, ('long', 'medium', 'short')),
'thumbnail': thumbnail,
'duration': duration,
'uploader': network.get('short_title'),
'uploader_id': network.get('id'),
'id': video_id,
**traverse_obj(preload_state, ('entities', 'videos', asset_id, {
'title': ('title', {str}),
'description': (('synopsisLong', 'synopsisMedium', 'synopsisShort'), {str}, any),
'thumbnail': (0, {image_url}),
'duration': ('duration', {int_or_none}),
})),
'formats': formats,
'subtitles': subtitles,
'chapters': traverse_obj(preload_state, (
'tracklist', 'tracks', lambda _, v: float_or_none(v['offset']['start']), {
'title': ('titles', {lambda x: join_nonempty(
'primary', 'secondary', 'tertiary', delim=' - ', from_dict=x)}),
'start_time': ('offset', 'start', {float_or_none}),
'end_time': ('offset', 'end', {float_or_none}),
})) or None,
'timestamp': traverse_obj(article, ('displayDate', {parse_iso8601})),
}
else:
return self.url_result(
f'https://www.bbc.co.uk/programmes/{asset_id}', BBCCoUkIE,
asset_id, playlist_title, display_id=playlist_id,
description=playlist_description)
bbc3_config = self._parse_json(
self._search_regex(
@@ -1182,17 +1271,52 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def parse_model(model):
"""Extract single video from model structure"""
item_id = traverse_obj(model, ('versions', 0, 'versionId', {str}))
if not item_id:
return
formats, subtitles = self._download_media_selector(item_id)
return {
'id': item_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(model, {
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'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):
return lambda _, v: v['type'] in types
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*("{.+?}")\s*;', webpage,
'quoted preload state', default=None)
if initial_data is None:
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*({.+?})\s*;', webpage,
'preload state', default={})
'preload state', default='{}')
else:
initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
initial_data = self._parse_json(initial_data, playlist_id, fatal=False)
if initial_data:
for video_data in traverse_obj(initial_data, (
'stores', 'article', 'articleBodyContent', is_type('video'))):
model = traverse_obj(video_data, (
'model', 'blocks', is_type('aresMedia'),
'model', 'blocks', is_type('aresMediaMetadata'),
'model', {dict}, any))
entry = parse_model(model)
if entry:
entries.append(entry)
if entries:
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def parse_media(media):
if not media:
return
@@ -1207,7 +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:
@@ -1225,37 +1349,100 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'subtitles': subtitles,
'timestamp': item_time,
'description': strip_or_none(item_desc),
'duration': int_or_none(item.get('duration')),
})
for resp in (initial_data.get('data') or {}).values():
name = resp.get('name')
for resp in traverse_obj(initial_data, ('data', lambda _, v: v['name'])):
name = resp['name']
if name == 'media-experience':
parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
elif name == 'article':
for block in (try_get(resp,
(lambda x: x['data']['blocks'],
lambda x: x['data']['content']['model']['blocks'],),
list) or []):
if block.get('type') not in ['media', 'video']:
continue
parse_media(block.get('model'))
for block in traverse_obj(resp, (
'data', (None, ('content', 'model')), 'blocks',
is_type('media', 'video'), 'model', {dict})):
parse_media(block)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
# extract from SIMORGH_DATA hydration JSON
simorgh_data = self._search_json(
r'window\s*\.\s*SIMORGH_DATA\s*=', webpage,
'simorgh data', playlist_id, default={})
if simorgh_data:
done = False
for video_data in traverse_obj(simorgh_data, (
'pageData', 'content', 'model', 'blocks', is_type('video', 'legacyMedia'))):
model = traverse_obj(video_data, (
'model', 'blocks', is_type('aresMedia'),
'model', 'blocks', is_type('aresMediaMetadata'),
'model', {dict}, any))
if video_data['type'] == 'video':
entry = parse_model(model)
else: # legacyMedia: no duration, subtitles
block_id, entry = traverse_obj(model, ('blockId', {str})), None
media_data = traverse_obj(simorgh_data, (
'pageData', 'promo', 'media',
{lambda x: x if x['id'] == block_id else None}))
formats = traverse_obj(media_data, ('playlist', lambda _, v: url_or_none(v['url']), {
'url': ('url', {url_or_none}),
'ext': ('format', {str}),
'tbr': ('bitrate', {functools.partial(int_or_none, scale=1000)}),
}))
if formats:
entry = {
'id': block_id,
'display_id': playlist_id,
'formats': formats,
'description': traverse_obj(simorgh_data, ('pageData', 'promo', 'summary', {str})),
**traverse_obj(model, {
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'description': ('synopses', ('long', 'medium', 'short'), {str}, any),
'timestamp': ('firstPublished', {functools.partial(int_or_none, scale=1000)}),
}),
}
done = True
if entry:
entries.append(entry)
if done:
break
if entries:
return self.playlist_result(
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)
next_data = traverse_obj(self._search_nextjs_data(webpage, playlist_id, default={}),
('props', 'pageProps', 'page'))
model = traverse_obj(next_data, (
..., 'contents', is_type('video'),
'model', 'blocks', is_type('media'),
'model', 'blocks', is_type('mediaMetadata'),
'model', {dict}, any))
if model and (entry := parse_model(model)):
if not entry.get('timestamp'):
entry['timestamp'] = traverse_obj(next_data, (
..., 'contents', is_type('timestamp'), 'model',
'timestamp', {functools.partial(int_or_none, scale=1000)}, any))
entries.append(entry)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
# 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],
@@ -1305,11 +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'))
@@ -1370,8 +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):
@@ -1385,8 +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)
@@ -1401,7 +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'):
@@ -1525,11 +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):
@@ -1589,7 +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,
@@ -1605,7 +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 = [{

42
yt_dlp/extractor/beatbump.py
View File

@@ -3,14 +3,13 @@ from .youtube import YoutubeIE, YoutubeTabIE
class BeatBumpVideoIE(InfoExtractor):
_VALID_URL = r'https://beatbump\.ml/listen\?id=(?P<id>[\w-]+)'
_VALID_URL = r'https?://beatbump\.(?:ml|io)/listen\?id=(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://beatbump.ml/listen?id=MgNrAu2pzNs',
'md5': '5ff3fff41d3935b9810a9731e485fe66',
'info_dict': {
'id': 'MgNrAu2pzNs',
'ext': 'mp4',
'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
'artist': 'Stephen',
'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
@@ -22,10 +21,9 @@ class BeatBumpVideoIE(InfoExtractor):
'alt_title': 'Voyeur Girl',
'view_count': int,
'track': 'Voyeur Girl',
'uploader': 'Stephen - Topic',
'uploader': 'Stephen',
'title': 'Voyeur Girl',
'channel_follower_count': int,
'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
'age_limit': 0,
'availability': 'public',
'live_status': 'not_live',
@@ -36,7 +34,12 @@ class BeatBumpVideoIE(InfoExtractor):
'tags': 'count:11',
'creator': 'Stephen',
'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
}
'channel_is_verified': True,
'heatmap': 'count:100',
},
}, {
'url': 'https://beatbump.io/listen?id=LDGZAprNGWo',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -45,7 +48,7 @@ class BeatBumpVideoIE(InfoExtractor):
class BeatBumpPlaylistIE(InfoExtractor):
_VALID_URL = r'https://beatbump\.ml/(?:release\?id=|artist/|playlist/)(?P<id>[\w-]+)'
_VALID_URL = r'https?://beatbump\.(?:ml|io)/(?:release\?id=|artist/|playlist/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://beatbump.ml/release?id=MPREb_gTAcphH99wE',
'playlist_count': 50,
@@ -56,25 +59,28 @@ class BeatBumpPlaylistIE(InfoExtractor):
'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
'description': '',
'tags': [],
'modified_date': '20221223',
}
'modified_date': '20231110',
},
'expected_warnings': ['YouTube Music is not directly supported'],
}, {
'url': 'https://beatbump.ml/artist/UC_aEa8K-EOJ3D6gOs7HcyNg',
'playlist_mincount': 1,
'params': {'flatplaylist': True},
'info_dict': {
'id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_id': '@NoCopyrightSounds',
'channel_follower_count': int,
'title': 'NoCopyrightSounds - Videos',
'title': 'NoCopyrightSounds',
'uploader': 'NoCopyrightSounds',
'description': 'md5:cd4fd53d81d363d05eee6c1b478b491a',
'channel': 'NoCopyrightSounds',
'tags': 'count:12',
'tags': 'count:65',
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'channel_is_verified': True,
},
'expected_warnings': ['YouTube Music is not directly supported'],
}, {
'url': 'https://beatbump.ml/playlist/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
'playlist_mincount': 1,
@@ -84,16 +90,20 @@ class BeatBumpPlaylistIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
'view_count': int,
'channel_url': 'https://www.youtube.com/@NoCopyrightSounds',
'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
'uploader_id': '@NoCopyrightSounds',
'title': 'NCS : All Releases 💿',
'uploader': 'NoCopyrightSounds',
'availability': 'public',
'channel': 'NoCopyrightSounds',
'tags': [],
'modified_date': '20221225',
'modified_date': '20231112',
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
}
},
'expected_warnings': ['YouTube Music is not directly supported'],
}, {
'url': 'https://beatbump.io/playlist/VLPLFCHGavqRG-q_2ZhmgU2XB2--ZY6irT1c',
'only_matching': True,
}]
def _real_extract(self, url):

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,

16
yt_dlp/extractor/beeg.py
View File

@@ -1,7 +1,7 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
str_or_none,
traverse_obj,
try_get,
unified_timestamp,
@@ -22,8 +22,8 @@ class BeegIE(InfoExtractor):
'age_limit': 18,
'upload_date': '20220131',
'timestamp': 1643656455,
'display_id': 2540839,
}
'display_id': '2540839',
},
}, {
'url': 'https://beeg.com/-0599050563103750?t=4-861',
'md5': 'bd8b5ea75134f7f07fad63008db2060e',
@@ -36,9 +36,9 @@ class BeegIE(InfoExtractor):
'age_limit': 18,
'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
'timestamp': 1643623200,
'display_id': 2569965,
'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 = {}
@@ -78,7 +78,7 @@ class BeegIE(InfoExtractor):
return {
'id': video_id,
'display_id': first_fact.get('id'),
'display_id': str_or_none(first_fact.get('id')),
'title': traverse_obj(video, ('file', 'stuff', 'sf_name')),
'description': traverse_obj(video, ('file', 'stuff', 'sf_story')),
'timestamp': unified_timestamp(first_fact.get('fc_created')),

3
yt_dlp/extractor/behindkink.py
View File

@@ -3,6 +3,7 @@ from ..utils import url_basename
class BehindKinkIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
@@ -15,7 +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):

4
yt_dlp/extractor/bellmedia.py
View File

@@ -32,7 +32,7 @@ class BellMediaIE(InfoExtractor):
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
'upload_date': '20180525',
'timestamp': 1527288600,
'season_id': 73997,
'season_id': '73997',
'season': '2018',
'thumbnail': 'http://images2.9c9media.com/image_asset/2018_5_25_baf30cbd-b28d-4a18-9903-4bb8713b00f5_PNG_956x536.jpg',
'tags': [],
@@ -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 {

11
yt_dlp/extractor/bet.py
View File

@@ -1,10 +1,9 @@
from .mtv import MTVServicesInfoExtractor
from ..utils import unified_strdate
# TODO Remove - Reason: Outdated Site
class BetIE(MTVServicesInfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
_TESTS = [
{
@@ -20,7 +19,7 @@ class BetIE(MTVServicesInfoExtractor):
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'subtitles': {
'en': 'mincount:2',
}
},
},
'params': {
# rtmp download
@@ -40,16 +39,16 @@ class BetIE(MTVServicesInfoExtractor):
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'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 {

1
yt_dlp/extractor/bfi.py
View File

@@ -5,6 +5,7 @@ from ..utils import extract_attributes
class BFIPlayerIE(InfoExtractor):
_WORKING = False
IE_NAME = 'bfi:player'
_VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P<id>[\w-]+)-online'
_TEST = {

14
yt_dlp/extractor/bfmtv.py
View File

@@ -7,7 +7,7 @@ from ..utils import extract_attributes
class BFMTVBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.|rmc\.)?bfmtv\.com/'
_VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block"[^>]*>)'
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>)'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _brightcove_url_result(self, video_id, video_block):
@@ -55,8 +55,11 @@ class BFMTVLiveIE(BFMTVIE): # XXX: Do not subclass from concrete IE
'ext': 'mp4',
'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'uploader_id': '876450610001',
'upload_date': '20171018',
'timestamp': 1508329950,
'upload_date': '20220926',
'timestamp': 1664207191,
'live_status': 'is_live',
'thumbnail': r're:https://.+/image\.jpg',
'tags': [],
},
'params': {
'skip_download': True,
@@ -90,14 +93,13 @@ class BFMTVArticleIE(BFMTVBaseIE):
'id': '6318445464112',
'ext': 'mp4',
'title': 'Le plein de bioéthanol fait de plus en plus mal à la pompe',
'description': None,
'uploader_id': '876630703001',
'upload_date': '20230110',
'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):

4
yt_dlp/extractor/bibeltv.py
View File

@@ -1,4 +1,4 @@
from functools import partial
import functools
from .common import InfoExtractor
from ..utils import (
@@ -50,7 +50,7 @@ class BibelTVBaseIE(InfoExtractor):
**traverse_obj(data, {
'title': 'title',
'description': 'description',
'duration': ('duration', {partial(int_or_none, scale=1000)}),
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('schedulingStart', {parse_iso8601}),
'season_number': 'seasonNumber',
'episode_number': 'episodeNumber',

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,
}

5
yt_dlp/extractor/bigo.py
View File

@@ -29,13 +29,14 @@ class BigoIE(InfoExtractor):
info_raw = self._download_json(
'https://ta.bigo.tv/official_website/studio/getInternalStudioInfo',
user_id, data=urlencode_postdata({'siteId': user_id}))
user_id, data=urlencode_postdata({'siteId': user_id}),
headers={'Accept': 'application/json'})
if not isinstance(info_raw, dict):
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):

1072
yt_dlp/extractor/bilibili.py
View File

File diff suppressed because it is too large Load Diff

110
yt_dlp/extractor/biqle.py
View File

@@ -1,110 +0,0 @@
from .common import InfoExtractor
from .vk import VKIE
from ..compat import compat_b64decode
from ..utils import (
int_or_none,
js_to_json,
traverse_obj,
unified_timestamp,
)
class BIQLEIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
_TESTS = [{
'url': 'https://biqle.ru/watch/-2000421746_85421746',
'md5': 'ae6ef4f04d19ac84e4658046d02c151c',
'info_dict': {
'id': '-2000421746_85421746',
'ext': 'mp4',
'title': 'Forsaken By Hope Studio Clip',
'description': 'Forsaken By Hope Studio Clip — Смотреть онлайн',
'upload_date': '19700101',
'thumbnail': r're:https://[^/]+/impf/7vN3ACwSTgChP96OdOfzFjUCzFR6ZglDQgWsIw/KPaACiVJJxM\.jpg\?size=800x450&quality=96&keep_aspect_ratio=1&background=000000&sign=b48ea459c4d33dbcba5e26d63574b1cb&type=video_thumb',
'timestamp': 0,
},
}, {
'url': 'http://biqle.org/watch/-44781847_168547604',
'md5': '7f24e72af1db0edf7c1aaba513174f97',
'info_dict': {
'id': '-44781847_168547604',
'ext': 'mp4',
'title': 'Ребенок в шоке от автоматической мойки',
'description': 'Ребенок в шоке от автоматической мойки — Смотреть онлайн',
'timestamp': 1396633454,
'upload_date': '20140404',
'thumbnail': r're:https://[^/]+/c535507/u190034692/video/l_b84df002\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('name', webpage, 'Title', fatal=False)
timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
description = self._html_search_meta('description', webpage, 'Description', default=None)
global_embed_url = self._search_regex(
r'<script[^<]+?window.globEmbedUrl\s*=\s*\'((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^\']+)\'',
webpage, 'global Embed url')
hash = self._search_regex(
r'<script id="data-embed-video[^<]+?hash: "([^"]+)"[^<]*</script>', webpage, 'Hash')
embed_url = global_embed_url + hash
if VKIE.suitable(embed_url):
return self.url_result(embed_url, VKIE.ie_key(), video_id)
embed_page = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage', headers={'Referer': url})
glob_params = self._parse_json(self._search_regex(
r'<script id="globParams">[^<]*window.globParams = ([^;]+);[^<]+</script>',
embed_page, 'Global Parameters'), video_id, transform_source=js_to_json)
host_name = compat_b64decode(glob_params['server'][::-1]).decode()
item = self._download_json(
f'https://{host_name}/method/video.get/{video_id}', video_id,
headers={'Referer': url}, query={
'token': glob_params['video']['access_token'],
'videos': video_id,
'ckey': glob_params['c_key'],
'credentials': glob_params['video']['credentials'],
})['response']['items'][0]
formats = []
for f_id, f_url in item.get('files', {}).items():
if f_id == 'external':
return self.url_result(f_url)
ext, height = f_id.split('_')
height_extra_key = traverse_obj(glob_params, ('video', 'partial', 'quality', height))
if height_extra_key:
formats.append({
'format_id': f'{height}p',
'url': f'https://{host_name}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
'height': int_or_none(height),
'ext': ext,
})
thumbnails = []
for k, v in item.items():
if k.startswith('photo_') and v:
width = k.replace('photo_', '')
thumbnails.append({
'id': width,
'url': v,
'width': int_or_none(width),
})
return {
'id': video_id,
'title': title,
'formats': formats,
'comment_count': int_or_none(item.get('comments')),
'description': description,
'duration': int_or_none(item.get('duration')),
'thumbnails': thumbnails,
'timestamp': timestamp,
'view_count': int_or_none(item.get('views')),
}

69
yt_dlp/extractor/bitchute.py
View File

@@ -7,8 +7,10 @@ from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
extract_attributes,
get_element_by_class,
get_element_by_id,
get_element_html_by_class,
get_elements_html_by_class,
int_or_none,
orderedSet,
@@ -17,11 +19,12 @@ from ..utils import (
traverse_obj,
unified_strdate,
urlencode_postdata,
urljoin,
)
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/',
@@ -34,6 +37,25 @@ class BitChuteIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
},
}, {
# test case: video with different channel and uploader
'url': 'https://www.bitchute.com/video/Yti_j9A-UZ4/',
'md5': 'f10e6a8e787766235946d0868703f1d0',
'info_dict': {
'id': 'Yti_j9A-UZ4',
'ext': 'mp4',
'title': 'Israel at War | Full Measure',
'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'sharylattkisson',
'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/',
},
}, {
# video not downloadable in browser, but we can recover it
@@ -48,6 +70,9 @@ class BitChuteIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20181113',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
},
'params': {'check_formats': None},
}, {
@@ -66,6 +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
@@ -90,7 +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):
@@ -99,10 +127,15 @@ class BitChuteIE(InfoExtractor):
reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
self.raise_geo_restricted(reason)
@staticmethod
def _make_url(html):
path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
return urljoin('https://www.bitchute.com', path)
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))
@@ -121,12 +154,19 @@ class BitChuteIE(InfoExtractor):
'Video is unavailable. Please make sure this video is playable in the browser '
'before reporting this issue.', expected=True, video_id=video_id)
details = get_element_by_class('details', webpage) or ''
uploader_html = get_element_html_by_class('creator', details) or ''
channel_html = get_element_html_by_class('name', details) or ''
return {
'id': video_id,
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'uploader': clean_html(get_element_by_class('owner', webpage)),
'uploader': clean_html(uploader_html),
'uploader_url': self._make_url(uploader_html),
'channel': clean_html(channel_html),
'channel_url': self._make_url(channel_html),
'upload_date': unified_strdate(self._search_regex(
r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
'formats': formats,
@@ -134,13 +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': [
{
@@ -148,16 +188,18 @@ class BitChuteChannelIE(InfoExtractor):
'info_dict': {
'id': 'UGlrF9o9b-Q',
'ext': 'mp4',
'filesize': None,
'title': 'This is the first video on #BitChute !',
'description': 'md5:a0337e7b1fe39e32336974af8173a034',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'BitChute',
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
'duration': 16,
'view_count': int,
},
}
},
],
'params': {
'skip_download': True,
@@ -169,8 +211,11 @@ class BitChuteChannelIE(InfoExtractor):
'info_dict': {
'id': 'wV9Imujxasw9',
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
}
'description': 'md5:747724ef404eebdfc04277714f81863e',
},
}, {
'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
'only_matching': True,
}]
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
@@ -185,13 +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)

58
yt_dlp/extractor/bitwave.py
View File

@@ -1,58 +0,0 @@
from .common import InfoExtractor
class BitwaveReplayIE(InfoExtractor):
IE_NAME = 'bitwave:replay'
_VALID_URL = r'https?://(?:www\.)?bitwave\.tv/(?P<user>\w+)/replay/(?P<id>\w+)/?$'
_TEST = {
'url': 'https://bitwave.tv/RhythmicCarnage/replay/z4P6eq5L7WDrM85UCrVr',
'only_matching': True
}
def _real_extract(self, url):
replay_id = self._match_id(url)
replay = self._download_json(
'https://api.bitwave.tv/v1/replays/' + replay_id,
replay_id
)
return {
'id': replay_id,
'title': replay['data']['title'],
'uploader': replay['data']['name'],
'uploader_id': replay['data']['name'],
'url': replay['data']['url'],
'thumbnails': [
{'url': x} for x in replay['data']['thumbnails']
],
}
class BitwaveStreamIE(InfoExtractor):
IE_NAME = 'bitwave:stream'
_VALID_URL = r'https?://(?:www\.)?bitwave\.tv/(?P<id>\w+)/?$'
_TEST = {
'url': 'https://bitwave.tv/doomtube',
'only_matching': True
}
def _real_extract(self, url):
username = self._match_id(url)
channel = self._download_json(
'https://api.bitwave.tv/v1/channels/' + username,
username)
formats = self._extract_m3u8_formats(
channel['data']['url'], username,
'mp4')
return {
'id': username,
'title': channel['data']['title'],
'uploader': username,
'uploader_id': username,
'formats': formats,
'thumbnail': channel['data']['thumbnail'],
'is_live': True,
'view_count': channel['data']['viewCount']
}

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')

27
yt_dlp/extractor/bleacherreport.py
View File

@@ -1,13 +1,15 @@
from .common import InfoExtractor
from .amp import AMPIE
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
str_or_none,
)
class BleacherReportIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/articles/(?P<id>\d+)'
_TESTS = [{
'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football',
@@ -16,13 +18,13 @@ class BleacherReportIE(InfoExtractor):
'id': '2496438',
'ext': 'mp4',
'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?',
'uploader_id': 3992341,
'uploader_id': '3992341',
'description': 'CFB, ACC, Florida State',
'timestamp': 1434380212,
'upload_date': '20150615',
'uploader': 'Team Stream Now ',
},
'add_ie': ['Ooyala'],
'skip': 'Video removed',
}, {
'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo',
'md5': '6a5cd403418c7b01719248ca97fb0692',
@@ -33,7 +35,7 @@ class BleacherReportIE(InfoExtractor):
'timestamp': 1446839961,
'uploader': 'Sean Fay',
'description': 'md5:b1601e2314c4d8eec23b6eafe086a757',
'uploader_id': 6466954,
'uploader_id': '6466954',
'upload_date': '20151011',
},
'add_ie': ['Youtube'],
@@ -42,7 +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')
@@ -58,7 +60,7 @@ class BleacherReportIE(InfoExtractor):
'id': article_id,
'title': article_data['title'],
'uploader': article_data.get('author', {}).get('name'),
'uploader_id': article_data.get('authorId'),
'uploader_id': str_or_none(article_data.get('authorId')),
'timestamp': parse_iso8601(article_data.get('createdAt')),
'thumbnails': thumbnails,
'comment_count': int_or_none(article_data.get('commentsCount')),
@@ -69,13 +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']
elif video_type == 'ooyala.com':
info['url'] = 'ooyala:%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
@@ -84,6 +84,7 @@ class BleacherReportIE(InfoExtractor):
class BleacherReportCMSIE(AMPIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
_TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
@@ -98,12 +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

6
yt_dlp/extractor/blogger.py
View File

@@ -1,3 +1,4 @@
from .common import InfoExtractor
from ..utils import (
mimetype2ext,
parse_duration,
@@ -5,7 +6,6 @@ from ..utils import (
str_or_none,
traverse_obj,
)
from .common import InfoExtractor
class BloggerIE(InfoExtractor):
@@ -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 {

225
yt_dlp/extractor/boosty.py Normal file
View File

@@ -0,0 +1,225 @@
import json
import urllib.parse
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
bug_reports_message,
int_or_none,
qualities,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BoostyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?boosty\.to/(?P<user>[^/#?]+)/posts/(?P<post_id>[^/#?]+)'
_TESTS = [{
# single ok_video
'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
'info_dict': {
'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
'title': 'phasma_3',
'channel': 'Kuplinov',
'channel_id': '7958701',
'timestamp': 1655031975,
'upload_date': '20220612',
'release_timestamp': 1655049000,
'release_date': '20220612',
'modified_timestamp': 1668680993,
'modified_date': '20221117',
'tags': ['куплинов', 'phasmophobia'],
'like_count': int,
'ext': 'mp4',
'duration': 105,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
# multiple ok_video
'url': 'https://boosty.to/maddyson/posts/0c652798-3b35-471f-8b48-a76a0b28736f',
'info_dict': {
'id': '0c652798-3b35-471f-8b48-a76a0b28736f',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
},
'playlist_count': 3,
'playlist': [{
'info_dict': {
'id': 'cc325a9f-a563-41c6-bf47-516c1b506c9a',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 31204,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
'info_dict': {
'id': 'd07b0a72-9493-4512-b54e-55ce468fd4b7',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 25704,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}, {
'info_dict': {
'id': '4a3bba32-78c8-422a-9432-2791aff60b42',
'title': 'то что не пропустил юта6',
'channel': 'Илья Давыдов',
'channel_id': '6808257',
'timestamp': 1694017040,
'upload_date': '20230906',
'release_timestamp': 1694017040,
'release_date': '20230906',
'modified_timestamp': 1694071178,
'modified_date': '20230907',
'like_count': int,
'ext': 'mp4',
'duration': 31867,
'view_count': int,
'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
},
}],
}, {
# single external video (youtube)
'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
'info_dict': {
'id': 'EXelTnve5lY',
'title': 'Послание Президента Федеральному Собранию | Класс народа',
'upload_date': '20210425',
'channel': 'Денис Чужой',
'tags': 'count:10',
'like_count': int,
'ext': 'mp4',
'duration': 816,
'view_count': int,
'thumbnail': r're:^https://i\.ytimg\.com/',
'age_limit': 0,
'availability': 'public',
'categories': list,
'channel_follower_count': int,
'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
'channel_is_verified': bool,
'channel_url': r're:^https://www\.youtube\.com/',
'comment_count': int,
'description': str,
'heatmap': 'count:100',
'live_status': str,
'playable_in_embed': bool,
'uploader': str,
'uploader_id': str,
'uploader_url': r're:^https://www\.youtube\.com/',
},
}]
_MP4_TYPES = ('tiny', 'lowest', 'low', 'medium', 'high', 'full_hd', 'quad_hd', 'ultra_hd')
def _extract_formats(self, player_urls, video_id):
formats = []
quality = qualities(self._MP4_TYPES)
for player_url in traverse_obj(player_urls, lambda _, v: url_or_none(v['url'])):
url = player_url['url']
format_type = player_url.get('type')
if format_type in ('hls', 'hls_live', 'live_ondemand_hls', 'live_playback_hls'):
formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id='hls', fatal=False))
elif format_type in ('dash', 'dash_live', 'live_playback_dash'):
formats.extend(self._extract_mpd_formats(url, video_id, mpd_id='dash', fatal=False))
elif format_type in self._MP4_TYPES:
formats.append({
'url': url,
'ext': 'mp4',
'format_id': format_type,
'quality': quality(format_type),
})
else:
self.report_warning(f'Unknown format type: {format_type!r}')
return formats
def _real_extract(self, url):
user, post_id = self._match_valid_url(url).group('user', 'post_id')
auth_headers = {}
auth_cookie = self._get_cookies('https://boosty.to/').get('auth')
if auth_cookie is not None:
try:
auth_data = json.loads(urllib.parse.unquote(auth_cookie.value))
auth_headers['Authorization'] = f'Bearer {auth_data["accessToken"]}'
except (json.JSONDecodeError, KeyError):
self.report_warning(f'Failed to extract token from auth cookie{bug_reports_message()}')
post = self._download_json(
f'https://api.boosty.to/v1/blog/{user}/post/{post_id}', post_id,
note='Downloading post data', errnote='Unable to download post data', headers=auth_headers)
post_title = post.get('title')
if not post_title:
self.report_warning('Unable to extract post title. Falling back to parsing html page')
webpage = self._download_webpage(url, video_id=post_id)
post_title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
common_metadata = {
'title': post_title,
**traverse_obj(post, {
'channel': ('user', 'name', {str}),
'channel_id': ('user', 'id', {str_or_none}),
'timestamp': ('createdAt', {int_or_none}),
'release_timestamp': ('publishTime', {int_or_none}),
'modified_timestamp': ('updatedAt', {int_or_none}),
'tags': ('tags', ..., 'title', {str}),
'like_count': ('count', 'likes', {int_or_none}),
}),
}
entries = []
for item in traverse_obj(post, ('data', ..., {dict})):
item_type = item.get('type')
if item_type == 'video' and url_or_none(item.get('url')):
entries.append(self.url_result(item['url'], YoutubeIE))
elif item_type == 'ok_video':
video_id = item.get('id') or post_id
entries.append({
'id': video_id,
'formats': self._extract_formats(item.get('playerUrls'), video_id),
**common_metadata,
**traverse_obj(item, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'view_count': ('viewsCounter', {int_or_none}),
'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
}, get_all=False)})
if not entries and not post.get('hasAccess'):
self.raise_login_required('This post requires a subscription', metadata_available=True)
elif not entries:
raise ExtractorError('No videos found', expected=True)
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, post_id, post_title, **common_metadata)

4
yt_dlp/extractor/bostonglobe.py
View File

@@ -1,7 +1,6 @@
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
)
@@ -58,8 +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')

98
yt_dlp/extractor/box.py
View File

@@ -1,45 +1,82 @@
import json
import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
parse_iso8601,
# try_get,
update_url_query,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/]+)/file/(?P<id>\d+)'
_TEST = {
_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',
'info_dict': {
'id': '510727257538',
'ext': 'mp4',
'title': 'Garber St. Louis will be 28th MLS team +scarving.mp4',
'uploader': 'MLS Video',
'uploader': '',
'timestamp': 1566320259,
'upload_date': '20190820',
'uploader_id': '235196876',
}
}
},
'params': {'skip_download': 'dash fragment too small'},
}, {
'url': 'https://utexas.app.box.com/s/2x6vanv85fdl8j2eqlcxmv0gp1wvps6e',
'info_dict': {
'id': '787379022466',
'ext': 'mp4',
'title': 'Webinar recording: Take the Leap!.mp4',
'uploader': 'Patricia Mosele',
'timestamp': 1615824864,
'upload_date': '20210315',
'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()
webpage = self._download_webpage(url, file_id)
request_token = self._parse_json(self._search_regex(
r'Box\.config\s*=\s*({.+?});', webpage,
'Box config'), file_id)['requestToken']
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:
post_stream_data = self._search_json(
r'Box\.postStreamData\s*=', webpage, 'Box post-stream data', shared_name)
shared_item = traverse_obj(
post_stream_data, ('/app-api/enduserapp/shared-item', {dict})) or {}
if shared_item.get('itemType') != 'file':
raise ExtractorError('The requested resource is not a file', expected=True)
file_id = str(shared_item['itemID'])
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={
@@ -47,37 +84,26 @@ 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 entry in (try_get(f, lambda x: x['representations']['entries'], list) or []):
# entry_url_template = try_get(
# entry, lambda x: x['content']['url_template'])
# if not entry_url_template:
# continue
# representation = entry.get('representation')
# if representation == 'dash':
# TODO: append query to every fragment URL
# formats.extend(self._extract_mpd_formats(
# entry_url_template.replace('{+asset_path}', 'manifest.mpd'),
# file_id, query=query))
authenticated_download_url = f.get('authenticated_download_url')
if authenticated_download_url and f.get('is_download_available'):
formats.append({
'ext': f.get('extension') or determine_ext(title),
'filesize': f.get('size'),
'format_id': 'download',
'url': update_url_query(authenticated_download_url, query),
})
for url_tmpl in traverse_obj(f, (
'representations', 'entries', lambda _, v: v['representation'] == 'dash',
'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)
for fmt in fmts:
fmt['extra_param_to_segment_url'] = urllib.parse.urlparse(manifest_url).query
formats.extend(fmts)
creator = f.get('created_by') or {}

16
yt_dlp/extractor/boxcast.py
View File

@@ -1,9 +1,5 @@
from .common import InfoExtractor
from ..utils import (
js_to_json,
traverse_obj,
unified_timestamp
)
from ..utils import js_to_json, traverse_obj, unified_timestamp
class BoxCastVideoIE(InfoExtractor):
@@ -25,7 +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': {
@@ -34,8 +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': {
@@ -48,7 +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/',
@@ -61,7 +57,7 @@ class BoxCastVideoIE(InfoExtractor):
'release_date': '20221210',
'uploader_id': 're8w0v8hohhvpqtbskpe',
'uploader': 'Children\'s Health Defense',
}
},
}]
def _real_extract(self, url):

152
yt_dlp/extractor/br.py
View File

@@ -1,18 +1,15 @@
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
xpath_element,
xpath_text,
)
class BRIE(InfoExtractor):
_WORKING = False
IE_DESC = 'Bayerischer Rundfunk'
_VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
@@ -64,7 +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',
@@ -77,7 +74,7 @@ class BRIE(InfoExtractor):
'duration': 893,
'uploader': 'Eva Maria Steimle',
'upload_date': '20170208',
}
},
},
]
@@ -145,7 +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')
@@ -154,7 +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
@@ -167,142 +164,3 @@ class BRIE(InfoExtractor):
} for variant in variants.findall('variant') if xpath_text(variant, 'url')]
thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
return thumbnails
class BRMediathekIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
_VALID_URL = r'https?://(?:www\.)?br\.de/mediathek//?video/(?:[^/?&#]+?-)?(?P<id>av:[0-9a-f]{24})'
_TESTS = [{
'url': 'https://www.br.de/mediathek/video/gesundheit-die-sendung-vom-28112017-av:5a1e6a6e8fce6d001871cc8e',
'md5': 'fdc3d485835966d1622587d08ba632ec',
'info_dict': {
'id': 'av:5a1e6a6e8fce6d001871cc8e',
'ext': 'mp4',
'title': 'Die Sendung vom 28.11.2017',
'description': 'md5:6000cdca5912ab2277e5b7339f201ccc',
'timestamp': 1511942766,
'upload_date': '20171129',
}
}, {
'url': 'https://www.br.de/mediathek//video/av:61b0db581aed360007558c12',
'only_matching': True,
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._download_json(
'https://proxy-base.master.mango.express/graphql',
clip_id, data=json.dumps({
"query": """{
viewer {
clip(id: "%s") {
title
description
duration
createdAt
ageRestriction
videoFiles {
edges {
node {
publicLocation
fileSize
videoProfile {
width
height
bitrate
encoding
}
}
}
}
captionFiles {
edges {
node {
publicLocation
}
}
}
teaserImages {
edges {
node {
imageFiles {
edges {
node {
publicLocation
width
height
}
}
}
}
}
}
}
}
}""" % clip_id}).encode(), headers={
'Content-Type': 'application/json',
})['data']['viewer']['clip']
title = clip['title']
formats = []
for edge in clip.get('videoFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
ext = determine_ext(n_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
n_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
video_profile = node.get('videoProfile', {})
tbr = int_or_none(video_profile.get('bitrate'))
format_id = 'http'
if tbr:
format_id += '-%d' % tbr
formats.append({
'format_id': format_id,
'url': n_url,
'width': int_or_none(video_profile.get('width')),
'height': int_or_none(video_profile.get('height')),
'tbr': tbr,
'filesize': int_or_none(node.get('fileSize')),
})
subtitles = {}
for edge in clip.get('captionFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
subtitles.setdefault('de', []).append({
'url': n_url,
})
thumbnails = []
for edge in clip.get('teaserImages', {}).get('edges', []):
for image_edge in edge.get('node', {}).get('imageFiles', {}).get('edges', []):
node = image_edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
thumbnails.append({
'url': n_url,
'width': int_or_none(node.get('width')),
'height': int_or_none(node.get('height')),
})
return {
'id': clip_id,
'title': title,
'description': clip.get('description'),
'duration': int_or_none(clip.get('duration')),
'timestamp': parse_iso8601(clip.get('createdAt')),
'age_limit': int_or_none(clip.get('ageRestriction')),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
}

16
yt_dlp/extractor/brainpop.py
View File

@@ -6,7 +6,7 @@ from ..utils import (
classproperty,
int_or_none,
traverse_obj,
urljoin
urljoin,
)
@@ -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 {

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