artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-08-28 06:43:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into pr_echo360

Browse Source
This commit is contained in:
Daniel Vogt
2024-04-18 19:05:57 +02:00
committed by GitHub
parent 333e92b1e5 315b354429
commit cad8b67755
821 changed files with 48564 additions and 27794 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yt_dlp/extractor/_extractors.py
+308 -239
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/abc.py
+116 -8
View File
@@ -12,9 +12,11 @@ from ..utils import (
int_or_none,
parse_iso8601,
str_or_none,
traverse_obj,
try_get,
unescapeHTML,
update_url_query,
url_or_none,
)
@@ -85,6 +87,15 @@ class ABCIE(InfoExtractor):
'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': {
'id': '102520540',
'title': 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus',
'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):
@@ -107,7 +118,7 @@ class ABCIE(InfoExtractor):
video = True
if mobj is None:
mobj = re.search(r'(?P<type>)"sources": (?P<json_data>\[[^\]]+\]),', webpage)
mobj = re.search(r'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])', webpage)
if mobj is None:
mobj = re.search(
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
@@ -121,7 +132,8 @@ class ABCIE(InfoExtractor):
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
youtube = mobj.group('type') == 'YouTube'
video = mobj.group('type') == 'Video' or urls_info[0]['contentType'] == 'video/mp4'
video = mobj.group('type') == 'Video' or traverse_obj(
urls_info, (0, ('contentType', 'MIMEType')), get_all=False) == 'video/mp4'
if not isinstance(urls_info, list):
urls_info = [urls_info]
@@ -169,20 +181,100 @@ class ABCIViewIE(InfoExtractor):
_VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU']
# ABC iview programs are normally available for 14 days only.
_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,
},
@@ -244,6 +336,8 @@ 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*(.*)$', title, 'episode', default='') or None,
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
@@ -283,6 +377,18 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'noplaylist': True,
'skip_download': 'm3u8',
},
}, {
# 'videoEpisodes' is a dict with `items` key
'url': 'https://iview.abc.net.au/show/7-30-mark-humphries-satire',
'info_dict': {
'id': '178458-0',
'title': 'Episodes',
'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
'series': '7.30 Mark Humphries Satire',
'season': 'Episodes',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
},
'playlist_count': 15,
}]
def _real_extract(self, url):
@@ -302,12 +408,14 @@ 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),
}
yt_dlp/extractor/abematv.py
+69 -107
View File
@@ -12,7 +12,7 @@ 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 ..utils import (
@@ -22,80 +22,26 @@ from ..utils import (
int_or_none,
intlist_to_bytes,
OnDemandPagedList,
request_to_url,
time_seconds,
traverse_obj,
update_url_query,
)
# NOTE: network handler related code is temporary thing until network stack overhaul PRs are merged (#2861/#2862)
def add_opener(ydl, handler):
''' Add a handler for opening URLs, like _download_webpage '''
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
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
ydl._opener.add_handler(handler)
def remove_opener(ydl, handler):
'''
Remove handler(s) for opening URLs
@param handler Either handler object itself or handler type.
Specifying handler type will remove all handler which isinstance returns True.
'''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
opener = ydl._opener
assert isinstance(ydl._opener, urllib.request.OpenerDirector)
if isinstance(handler, (type, tuple)):
find_cp = lambda x: isinstance(x, handler)
else:
find_cp = lambda x: x is handler
removed = []
for meth in dir(handler):
if meth in ["redirect_request", "do_open", "proxy_open"]:
# oops, coincidental match
continue
i = meth.find("_")
protocol = meth[:i]
condition = meth[i + 1:]
if condition.startswith("error"):
j = condition.find("_") + i + 1
kind = meth[j + 1:]
try:
kind = int(kind)
except ValueError:
pass
lookup = opener.handle_error.get(protocol, {})
opener.handle_error[protocol] = lookup
elif condition == "open":
kind = protocol
lookup = opener.handle_open
elif condition == "response":
kind = protocol
lookup = opener.process_response
elif condition == "request":
kind = protocol
lookup = opener.process_request
else:
continue
handlers = lookup.setdefault(kind, [])
if handlers:
handlers[:] = [x for x in handlers if not find_cp(x)]
removed.append(x for x in handlers if find_cp(x))
if removed:
for x in opener.handlers:
if find_cp(x):
x.add_parent(None)
opener.handlers[:] = [x for x in opener.handlers if not find_cp(x)]
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 AbemaLicenseHandler(urllib.request.BaseHandler):
@@ -107,7 +53,7 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
# 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'))
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
self.ie = ie
def _get_videokey_from_ticket(self, ticket):
@@ -137,15 +83,17 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = request_to_url(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': len(response_data),
'Content-Length': str(len(response_data)),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'abematv'
_USERTOKEN = None
_DEVICE_ID = None
_MEDIATOKEN = None
@@ -190,11 +138,15 @@ class AbemaTVBaseIE(InfoExtractor):
if self._USERTOKEN:
return self._USERTOKEN
add_opener(self._downloader, AbemaLicenseHandler(self))
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:
@@ -213,10 +165,6 @@ class AbemaTVBaseIE(InfoExtractor):
})
AbemaTVBaseIE._USERTOKEN = user_data['token']
# don't allow adding it 2 times or more, though it's guarded
remove_opener(self._downloader, AbemaLicenseHandler)
add_opener(self._downloader, AbemaLicenseHandler(self))
return self._USERTOKEN
def _get_media_token(self, invalidate=False, to_show=True):
@@ -238,6 +186,37 @@ class AbemaTVBaseIE(InfoExtractor):
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('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)
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 {},
@@ -261,14 +240,14 @@ 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,
},
@@ -280,7 +259,7 @@ 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',
},
@@ -309,33 +288,6 @@ 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.
@@ -404,12 +356,12 @@ 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
@@ -436,6 +388,16 @@ class AbemaTVIE(AbemaTVBaseIE):
if 3 not in ondemand_types:
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
info.update(traverse_obj(api_response, {
'series': ('series', 'title'),
'season': ('season', 'name'),
'season_number': ('season', 'sequence'),
'episode_number': ('episode', 'number'),
}))
if not title:
title = traverse_obj(api_response, ('episode', 'title'))
if not description:
description = traverse_obj(api_response, ('episode', 'content'))
m3u8_url = f'https://vod-abematv.akamaized.net/program/{video_id}/playlist.m3u8'
elif video_type == 'slots':
yt_dlp/extractor/acast.py
+28 -6
View File
@@ -40,28 +40,33 @@ class ACastBaseIE(InfoExtractor):
class ACastIE(ACastBaseIE):
IE_NAME = 'acast'
_VALID_URL = r'''(?x)
_VALID_URL = r'''(?x:
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
'''
(?P<channel>[^/]+)/(?P<id>[^/#?"]+)
)'''
_EMBED_REGEX = [rf'(?x)<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
'description': 'md5:013959207e05011ad14a222cf22278cc',
'timestamp': 1477346700,
'upload_date': '20161024',
'duration': 2766,
'creator': 'Anton Berg & Martin Johnson',
'creator': 'Third Ear Studio',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
'thumbnail': 'https://assets.pippa.io/shows/616ebe1886d7b1398620b943/616ebe33c7e6e70013cae7da.jpg',
'episode_number': 2,
'display_id': '2.raggarmordet-rosterurdetforflutna',
'season_number': 4,
'season': 'Season 4',
}
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
@@ -73,6 +78,23 @@ class ACastIE(ACastBaseIE):
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://ausi.anu.edu.au/news/democracy-sausage-episode-can-labor-be-long-form-government',
'info_dict': {
'id': '646c68fb21fbf20011e9c651',
'ext': 'mp3',
'creator': 'The Australian National University',
'display_id': 'can-labor-be-a-long-form-government',
'duration': 2618,
'thumbnail': 'https://assets.pippa.io/shows/6113e8578b4903809f16f7e5/1684821529295-515b9520db9ce53275b995eb302f941c.jpeg',
'title': 'Can Labor be a long-form government?',
'episode': 'Can Labor be a long-form government?',
'upload_date': '20230523',
'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()
yt_dlp/extractor/acfun.py
+4 -3
View File
@@ -3,6 +3,7 @@ from ..utils import (
float_or_none,
format_field,
int_or_none,
str_or_none,
traverse_obj,
parse_codecs,
parse_qs,
@@ -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,
yt_dlp/extractor/adn.py
+108 -32
View File
@@ -3,13 +3,12 @@ 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_HTTPError,
compat_b64decode,
)
from ..compat import compat_b64decode
from ..networking.exceptions import HTTPError
from ..utils import (
ass_subtitles_timecode,
bytes_to_intlist,
@@ -19,17 +18,38 @@ from ..utils import (
int_or_none,
intlist_to_bytes,
long_to_bytes,
parse_iso8601,
pkcs1pad,
strip_or_none,
str_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\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
@@ -46,29 +66,35 @@ 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.de/video/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
@@ -118,6 +144,8 @@ 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),
@@ -142,14 +170,14 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e:
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
e.cause.response.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
def _real_extract(self, url):
video_id = self._match_id(url)
lang, video_id = self._match_valid_url(url).group('lang', 'id')
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
player = self._download_json(
video_base_url + 'configuration', video_id,
@@ -159,12 +187,15 @@ 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')
@@ -186,7 +217,9 @@ 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,
'X-Target-Distribution': lang,
**self._HEADERS
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
@@ -195,14 +228,14 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
})
break
except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError):
if not isinstance(e.cause, HTTPError):
raise e
if e.cause.code == 401:
if e.cause.status == 401:
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
error = self._parse_json(e.cause.response.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)
@@ -234,8 +267,14 @@ 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 {}
@@ -257,3 +296,40 @@ 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\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/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')
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={
'X-Target-Distribution': lang,
**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(
f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
ADNIE, episode_id)
return self.playlist_result(entries(), show_id, show.get('title'))
yt_dlp/extractor/adobepass.py
+12 -12
View File
@@ -2,11 +2,11 @@ import getpass
import json
import re
import time
import urllib.error
import xml.etree.ElementTree as etree
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import (
NO_DEFAULT,
ExtractorError,
@@ -1394,7 +1394,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = compat_urlparse.urljoin(urlh.geturl(), post_url)
post_url = compat_urlparse.urljoin(urlh.url, post_url)
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
@@ -1473,7 +1473,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
elif 'automatically signed in with' in provider_redirect_page:
# Seems like comcast is rolling up new way of automatically signing customers
oauth_redirect_url = self._html_search_regex(
r'continue:\s*"(https://oauth.xfinity.com/oauth/authorize\?.+)"', provider_redirect_page,
r'continue:\s*"(https://oauth\.xfinity\.com/oauth/authorize\?.+)"', provider_redirect_page,
'oauth redirect (signed)')
# Just need to process the request. No useful data comes back
self._download_webpage(oauth_redirect_url, video_id, 'Confirming auto login')
@@ -1573,7 +1573,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
}), headers={
'Content-Type': 'application/x-www-form-urlencoded'
})
elif mso_id == 'Spectrum':
elif mso_id in ('Spectrum', 'Charter_Direct'):
# Spectrum's login for is dynamically loaded via JS so we need to hardcode the flow
# as a one-off implementation.
provider_redirect_page, urlh = provider_redirect_page_res
@@ -1619,7 +1619,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history'] = 1
provider_login_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending first bookend',
urlh.url, video_id, 'Sending first bookend',
query=hidden_data)
provider_association_redirect, urlh = post_form(
@@ -1629,7 +1629,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
})
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl())
provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@@ -1638,7 +1638,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history'] = 3
mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending final bookend',
urlh.url, video_id, 'Sending final bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1652,7 +1652,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history_val'] = 1
provider_login_redirect_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending First Bookend',
urlh.url, video_id, 'Sending First Bookend',
query=hidden_data)
provider_login_redirect_page, urlh = provider_login_redirect_page_res
@@ -1680,7 +1680,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
})
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl())
provider_association_redirect, url=urlh.url)
last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@@ -1690,7 +1690,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
hidden_data['history_val'] = 3
mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending Final Bookend',
urlh.url, video_id, 'Sending Final Bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
@@ -1699,7 +1699,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
# based redirect that should be followed.
provider_redirect_page, urlh = provider_redirect_page_res
provider_refresh_redirect_url = extract_redirect_url(
provider_redirect_page, url=urlh.geturl())
provider_redirect_page, url=urlh.url)
if provider_refresh_redirect_url:
provider_redirect_page_res = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
@@ -1724,7 +1724,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
'requestor_id': requestor_id,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 401:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise_mvpd_required()
raise
if '<pendingLogout' in session:
yt_dlp/extractor/adultswim.py
+4 -3
View File
@@ -107,7 +107,6 @@ class AdultSwimIE(TurnerBaseIE):
title
tvRating
}''' % episode_path
['getVideoBySlug']
else:
query = query % '''metaDescription
title
@@ -170,8 +169,10 @@ class AdultSwimIE(TurnerBaseIE):
continue
ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
if ext == 'm3u8':
info['formats'].extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
info['formats'].extend(fmts)
self._merge_subtitles(subs, target=info['subtitles'])
elif ext == 'f4m':
continue
# info['formats'].extend(self._extract_f4m_formats(
yt_dlp/extractor/aenetworks.py
+36 -5
View File
@@ -3,6 +3,8 @@ from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
remove_start,
traverse_obj,
update_url_query,
urlencode_postdata,
)
@@ -72,7 +74,14 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
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})['results'][0]
filter_value, query={'filter[%s]' % filter_key: filter_value})
result = traverse_obj(
result, ('results',
lambda k, v: k == 0 and v[filter_key] == filter_value),
get_all=False)
if not result:
raise ExtractorError('Show not found in A&E feed (too new?)', expected=True,
video_id=remove_start(filter_value, '/'))
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
@@ -84,7 +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))
@@ -112,18 +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$',
'chapters': 'count:5',
'tags': 'count:14',
'categories': ['Mountain Men'],
'episode_number': 1,
'episode': 'Episode 1',
'season': 'Season 1',
'season_number': 1,
'series': 'Mountain Men',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
'skip': 'Geo-restricted - This content is not available in your location.'
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
@@ -134,12 +153,22 @@ class AENetworksIE(AENetworksBaseIE):
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
'duration': 1277.695,
'thumbnail': r're:^https?://.*\.jpe?g$',
'chapters': 'count:4',
'tags': 'count:23',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 9',
'season_number': 9,
'series': 'Duck Dynasty',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'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
@@ -303,6 +332,7 @@ class HistoryTopicIE(AENetworksBaseIE):
class HistoryPlayerIE(AENetworksBaseIE):
IE_NAME = 'history:player'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|biography)\.com)/player/(?P<id>\d+)'
_TESTS = []
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
@@ -327,6 +357,7 @@ class BiographyIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': '404 Not Found',
}]
def _real_extract(self, url):
yt_dlp/extractor/aeonco.py
+43 -9
View File
@@ -1,5 +1,6 @@
from .common import InfoExtractor
from .vimeo import VimeoIE
from ..utils import ExtractorError, traverse_obj, url_or_none
class AeonCoIE(InfoExtractor):
@@ -19,22 +20,55 @@ class AeonCoIE(InfoExtractor):
}
}, {
'url': 'https://aeon.co/videos/dazzling-timelapse-shows-how-microbes-spoil-our-food-and-sometimes-enrich-it',
'md5': '4e5f3dad9dbda0dbfa2da41a851e631e',
'md5': '03582d795382e49f2fd0b427b55de409',
'info_dict': {
'id': '728595228',
'id': '759576926',
'ext': 'mp4',
'title': 'Wrought',
'thumbnail': 'https://i.vimeocdn.com/video/1484618528-c91452611f9a4e4497735a533da60d45b2fe472deb0c880f0afaab0cd2efb22a-d_1280',
'uploader': 'Biofilm Productions',
'uploader_id': 'user140352216',
'uploader_url': 'https://vimeo.com/user140352216',
'thumbnail': 'https://i.vimeocdn.com/video/1525599692-84614af88e446612f49ca966cf8f80eab2c73376bedd80555741c521c26f9a3e-d_1280',
'uploader': 'Aeon Video',
'uploader_id': 'aeonvideo',
'uploader_url': 'https://vimeo.com/aeonvideo',
'duration': 1344
}
}, {
'url': 'https://aeon.co/videos/chew-over-the-prisoners-dilemma-and-see-if-you-can-find-the-rational-path-out',
'md5': '1cfda0bf3ae24df17d00f2c0cb6cc21b',
'info_dict': {
'id': 'emyi4z-O0ls',
'ext': 'mp4',
'title': 'How to outsmart the Prisoner’s Dilemma - Lucas Husted',
'thumbnail': 'https://i.ytimg.com/vi_webp/emyi4z-O0ls/maxresdefault.webp',
'uploader': 'TED-Ed',
'uploader_id': '@TEDEd',
'uploader_url': 'https://www.youtube.com/@TEDEd',
'duration': 344,
'upload_date': '20200827',
'channel_id': 'UCsooa4yRKGN_zEE8iknghZA',
'playable_in_embed': True,
'description': 'md5:c0959524f08cb60f96fd010f3dfb17f3',
'categories': ['Education'],
'like_count': int,
'channel': 'TED-Ed',
'chapters': 'count:7',
'channel_url': 'https://www.youtube.com/channel/UCsooa4yRKGN_zEE8iknghZA',
'tags': 'count:26',
'availability': 'public',
'channel_follower_count': int,
'view_count': int,
'age_limit': 0,
'live_status': 'not_live',
'comment_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vimeo_id = self._search_regex(r'hosterId":\s*"(?P<id>[0-9]+)', webpage, 'vimeo id')
vimeo_url = VimeoIE._smuggle_referrer(f'https://player.vimeo.com/video/{vimeo_id}', 'https://aeon.co')
return self.url_result(vimeo_url, VimeoIE)
embed_url = traverse_obj(self._yield_json_ld(webpage, video_id), (
lambda _, v: v['@type'] == 'VideoObject', 'embedUrl', {url_or_none}), get_all=False)
if not embed_url:
raise ExtractorError('No embed URL found in webpage')
if 'player.vimeo.com' in embed_url:
embed_url = VimeoIE._smuggle_referrer(embed_url, 'https://aeon.co/')
return self.url_result(embed_url)
yt_dlp/extractor/afreecatv.py
+205 -310
View File
@@ -1,25 +1,65 @@
import functools
import re
from .common import InfoExtractor
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(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
expected=True)
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
IE_DESC = 'afreecatv.com'
_VALID_URL = r'''(?x)
@@ -34,7 +74,6 @@ class AfreecaTVIE(InfoExtractor):
)
(?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',
@@ -76,59 +115,6 @@ class AfreecaTVIE(InfoExtractor):
},
}],
'skip': 'Video is gone',
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
'info_dict': {
'id': '18650793',
'ext': 'mp4',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '윈아디',
'uploader_id': 'badkids',
'duration': 107,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
'info_dict': {
'id': '10481652',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'duration': 6492,
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '20160502_c4c62b9d_174361386_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 3601,
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '20160502_39e739bb_174361386_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 2891,
},
}],
'params': {
'skip_download': True,
},
}, {
# non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
@@ -140,14 +126,15 @@ class AfreecaTVIE(InfoExtractor):
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
'timestamp': 1491929865,
'duration': 213,
},
'params': {
'skip_download': True,
},
}, {
# PARTIAL_ADULT
'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
# adult content
'url': 'https://vod.afreecatv.com/player/97267690',
'info_dict': {
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
@@ -161,227 +148,114 @@ class AfreecaTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
'expected_warnings': ['adult content'],
'skip': 'The VOD does not exist',
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/15055030',
'url': 'https://vod.afreecatv.com/player/96753363',
'info_dict': {
'id': '20230108_9FF5BEE1_244432674_1',
'ext': 'mp4',
'uploader_id': 'rlantnghks',
'uploader': '페이즈으',
'duration': 10840,
'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,
}, {
'url': 'http://vod.afreecatv.com/player/15055030',
# 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)
webpage = self._download_webpage(url, video_id)
if re.search(r'alert\(["\']This video has been deleted', webpage):
raise ExtractorError(
'Video %s has been deleted' % video_id, expected=True)
station_id = self._search_regex(
r'nStationNo\s*=\s*(\d+)', webpage, 'station')
bbs_id = self._search_regex(
r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
video_id = self._search_regex(
r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
partial_view = False
adult_view = False
for _ in range(2):
query = {
data = self._download_json(
'https://api.m.afreecatv.com/station/video/a/view', video_id,
headers={'Referer': url}, data=urlencode_postdata({
'nTitleNo': video_id,
'nStationNo': station_id,
'nBbsNo': bbs_id,
}
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 = []
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',
}]
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}),
})
entries.append(file_info)
entries_info = info.copy()
entries_info.update({
'_type': 'multi_video',
'entries': entries,
})
return entries_info
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
})
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 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',
@@ -396,77 +270,97 @@ 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,
@@ -476,6 +370,7 @@ 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},
}
yt_dlp/extractor/airmozilla.py
-63
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
yt_dlp/extractor/allstar.py
+253
View File
@@ -0,0 +1,253 @@
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: $id) {
%s %s
}
}''' % (_FIELDS, _EXTRA_FIELDS),
'montage': '''query ($id: String!) {
video: getMontage(clipIdentifier: $id) {
%s
}
}''' % _FIELDS,
'Clips': '''query ($page: Int!, $user: String!, $game: Int) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: false, game: $game) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
'Montages': '''query ($page: Int!, $user: String!) {
videos: montages(search: createdDate, page: $page, user: $user) {
data { %s }
}
}''' % _FIELDS,
'Mobile Clips': '''query ($page: Int!, $user: String!) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: true) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}
class AllstarBaseIE(InfoExtractor):
@staticmethod
def _parse_video_data(video_data):
def media_url_or_none(path):
return urljoin('https://media.allstar.gg/', path)
info = traverse_obj(video_data, {
'id': ('_id', {str}),
'display_id': ('shareId', {str}),
'title': ('clipTitle', {str}),
'url': ('clipLink', {media_url_or_none}),
'thumbnails': (('clipImageThumb', 'clipImageSource'), {'url': {media_url_or_none}}),
'duration': ('clipLength', {int_or_none}),
'filesize': ('clipSizeBytes', {int_or_none}),
'timestamp': ('createdDate', {functools.partial(int_or_none, scale=1000)}),
'uploader': ('username', {str}),
'uploader_id': ('user', '_id', {str}),
'view_count': ('views', {int_or_none}),
})
if info.get('id') and info.get('url'):
basename = 'clip' if '/clips/' in info['url'] else 'montage'
info['webpage_url'] = f'https://allstar.gg/{basename}?{basename}={info["id"]}'
info.update({
'extractor_key': AllstarIE.ie_key(),
'extractor': AllstarIE.IE_NAME,
'uploader_url': urljoin('https://allstar.gg/u/', info.get('uploader_id')),
})
return info
def _call_api(self, query, variables, path, video_id=None, note=None):
response = self._download_json(
'https://a1.allstar.gg/graphql', video_id, note=note,
headers={'content-type': 'application/json'},
data=json.dumps({'variables': variables, 'query': query}).encode())
errors = traverse_obj(response, ('errors', ..., 'message', {str}))
if errors:
raise ExtractorError('; '.join(errors))
return traverse_obj(response, path)
class AllstarIE(AllstarBaseIE):
_VALID_URL = r'https?://(?:www\.)?allstar\.gg/(?P<type>(?:clip|montage))\?(?P=type)=(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://allstar.gg/clip?clip=64482c2da9eec30008a67d1b',
'info_dict': {
'id': '64482c2da9eec30008a67d1b',
'title': '4K on Inferno',
'url': 'md5:66befb5381eef0c9456026386c25fa55',
'thumbnail': r're:https://media\.allstar\.gg/.+\.(?:png|jpg)$',
'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=' - '))
yt_dlp/extractor/altcensored.py
+104
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)
yt_dlp/extractor/amadeustv.py
+77
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),
}
yt_dlp/extractor/amazonminitv.py
+7 -4
View File
@@ -22,8 +22,11 @@ class AmazonMiniTVBaseIE(InfoExtractor):
resp = self._download_json(
f'https://www.amazon.in/minitv/api/web/{"graphql" if data else "prs"}',
asin, note=note, headers={'Content-Type': 'application/json'},
data=json.dumps(data).encode() if data else None,
asin, note=note, headers={
'Content-Type': 'application/json',
'currentpageurl': '/',
'currentplatform': 'dWeb'
}, data=json.dumps(data).encode() if data else None,
query=None if data else {
'deviceType': 'A1WMMUXPCUJL4N',
'contentId': asin,
@@ -46,7 +49,7 @@ class AmazonMiniTVIE(AmazonMiniTVBaseIE):
'ext': 'mp4',
'title': 'May I Kiss You?',
'language': 'Hindi',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'description': 'md5:a549bfc747973e04feb707833474e59d',
'release_timestamp': 1644710400,
'release_date': '20220213',
@@ -68,7 +71,7 @@ class AmazonMiniTVIE(AmazonMiniTVBaseIE):
'ext': 'mp4',
'title': 'Jahaan',
'language': 'Hindi',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'description': 'md5:05eb765a77bf703f322f120ec6867339',
'release_timestamp': 1647475200,
'release_date': '20220317',
yt_dlp/extractor/amcnetworks.py
+1
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,
yt_dlp/extractor/amp.py
+6 -3
View File
@@ -5,6 +5,7 @@ from ..utils import (
int_or_none,
mimetype2ext,
parse_iso8601,
strip_jsonp,
unified_timestamp,
url_or_none,
)
@@ -15,7 +16,7 @@ class AMPIE(InfoExtractor): # XXX: Conventionally, base classes should end with
def _extract_feed_info(self, url):
feed = self._download_json(
url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')
'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']))
@@ -73,8 +74,10 @@ class AMPIE(InfoExtractor): # XXX: Conventionally, base classes should end with
media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124',
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
yt_dlp/extractor/ant1newsgr.py → yt_dlp/extractor/antenna.py
+41 -26
View File
@@ -1,26 +1,30 @@
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
HEADRequest,
ExtractorError,
determine_ext,
make_archive_id,
scale_thumbnails_to_max_format_width,
)
class Ant1NewsGrBaseIE(InfoExtractor):
class AntennaBaseIE(InfoExtractor):
def _download_and_extract_api_data(self, video_id, netloc, cid=None):
url = f'{self.http_scheme()}//{netloc}{self._API_PATH}'
info = self._download_json(url, video_id, query={'cid': cid or video_id})
try:
source = info['url']
except KeyError:
raise ExtractorError('no source found for %s' % video_id)
formats, subs = (self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
if determine_ext(source) == 'm3u8' else ([{'url': source}], {}))
info = self._download_json(f'{self.http_scheme()}//{netloc}{self._API_PATH}',
video_id, query={'cid': cid or video_id})
if not info.get('url'):
raise ExtractorError(f'No source found for {video_id}')
ext = determine_ext(info['url'])
if ext == 'm3u8':
formats, subs = self._extract_m3u8_formats_and_subtitles(info['url'], video_id, 'mp4')
else:
formats, subs = [{'url': info['url'], 'format_id': ext}], {}
thumbnails = scale_thumbnails_to_max_format_width(
formats, [{'url': info['thumb']}], r'(?<=/imgHandler/)\d+')
formats, [{'url': info['thumb']}], r'(?<=/imgHandler/)\d+') if info.get('thumb') else []
return {
'id': video_id,
'title': info.get('title'),
@@ -30,21 +34,31 @@ class Ant1NewsGrBaseIE(InfoExtractor):
}
class Ant1NewsGrWatchIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:watch'
IE_DESC = 'ant1news.gr videos'
_VALID_URL = r'https?://(?P<netloc>(?:www\.)?ant1news\.gr)/watch/(?P<id>\d+)/'
class AntennaGrWatchIE(AntennaBaseIE):
IE_NAME = 'antenna:watch'
IE_DESC = 'antenna.gr and ant1news.gr videos'
_VALID_URL = r'https?://(?P<netloc>(?:www\.)?(?:antenna|ant1news)\.gr)/watch/(?P<id>\d+)/'
_API_PATH = '/templates/data/player'
_TESTS = [{
'url': 'https://www.ant1news.gr/watch/1506168/ant1-news-09112021-stis-18-45',
'md5': '95925e6b32106754235f2417e0d2dfab',
'md5': 'c472d9dd7cd233c63aff2ea42201cda6',
'info_dict': {
'id': '1506168',
'ext': 'mp4',
'title': 'md5:0ad00fa66ecf8aa233d26ab0dba7514a',
'description': 'md5:18665af715a6dcfeac1d6153a44f16b0',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/26d46bf6-8158-4f02-b197-7096c714b2de.jpg',
'thumbnail': r're:https://ant1media\.azureedge\.net/imgHandler/\d+/26d46bf6-8158-4f02-b197-7096c714b2de\.jpg',
},
}, {
'url': 'https://www.antenna.gr/watch/1643812/oi-prodotes-epeisodio-01',
'md5': '8f6f7dd3b1dba4d835ba990e25f31243',
'info_dict': {
'id': '1643812',
'ext': 'mp4',
'format_id': 'mp4',
'title': 'ΟΙ ΠΡΟΔΟΤΕΣ – ΕΠΕΙΣΟΔΙΟ 01',
'thumbnail': r're:https://ant1media\.azureedge\.net/imgHandler/\d+/b3d63096-e72d-43c4-87a0-00d4363d242f\.jpg',
},
}]
@@ -52,25 +66,26 @@ class Ant1NewsGrWatchIE(Ant1NewsGrBaseIE):
video_id, netloc = self._match_valid_url(url).group('id', 'netloc')
webpage = self._download_webpage(url, video_id)
info = self._download_and_extract_api_data(video_id, netloc)
info['description'] = self._og_search_description(webpage)
info['description'] = self._og_search_description(webpage, default=None)
info['_old_archive_ids'] = [make_archive_id('Ant1NewsGrWatch', video_id)]
return info
class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE):
class Ant1NewsGrArticleIE(AntennaBaseIE):
IE_NAME = 'ant1newsgr:article'
IE_DESC = 'ant1news.gr articles'
_VALID_URL = r'https?://(?:www\.)?ant1news\.gr/[^/]+/article/(?P<id>\d+)/'
_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',
@@ -96,13 +111,13 @@ class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE):
video_kwargs={'url_transparent': True, 'timestamp': info.get('timestamp')})
class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
class Ant1NewsGrEmbedIE(AntennaBaseIE):
IE_NAME = 'ant1newsgr:embed'
IE_DESC = 'ant1news.gr embedded videos'
_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',
@@ -121,7 +136,7 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
canonical_url = self._request_webpage(
HEADRequest(url), video_id,
note='Resolve canonical player URL',
errnote='Could not resolve canonical player URL').geturl()
errnote='Could not resolve canonical player URL').url
_, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
cid = urllib.parse.parse_qs(query)['cid'][0]
yt_dlp/extractor/anvato.py
+1 -9
View File
@@ -336,7 +336,7 @@ class AnvatoIE(InfoExtractor):
elif media_format == 'm3u8-variant' or ext == 'm3u8':
# For some videos the initial m3u8 URL returns JSON instead
manifest_json = self._download_json(
video_url, video_id, note='Downloading manifest JSON', errnote=False)
video_url, video_id, note='Downloading manifest JSON', fatal=False)
if manifest_json:
video_url = manifest_json.get('master_m3u8')
if not video_url:
@@ -392,14 +392,6 @@ class AnvatoIE(InfoExtractor):
url = smuggle_url(url, {'token': anvplayer_data['token']})
yield cls.url_result(url, AnvatoIE, video_id)
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(
self._html_search_regex(
self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
video_id)
return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video'], 'default') # cbslocal token = 'default'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
yt_dlp/extractor/aol.py
+1
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})'
yt_dlp/extractor/archiveorg.py
+13 -249
View File
@@ -1,16 +1,15 @@
import json
import re
import urllib.error
import urllib.parse
from .common import InfoExtractor
from .naver import NaverBaseIE
from .youtube import YoutubeBaseInfoExtractor, YoutubeIE
from ..compat import compat_HTTPError, compat_urllib_parse_unquote
from ..compat import compat_urllib_parse_unquote
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
HEADRequest,
bug_reports_message,
clean_html,
dict_get,
@@ -32,6 +31,7 @@ from ..utils import (
unified_timestamp,
url_or_none,
urlhandle_detect_ext,
variadic,
)
@@ -50,10 +50,9 @@ 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',
@@ -111,7 +110,7 @@ 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',
@@ -131,11 +130,10 @@ 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,
},
}, {
@@ -170,7 +168,7 @@ 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': [
@@ -260,7 +258,7 @@ 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'])),
@@ -275,7 +273,7 @@ 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'),
@@ -303,7 +301,7 @@ 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')),
@@ -899,7 +897,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
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.
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
if isinstance(e.cause, HTTPError) and e.cause.status == 404:
self.raise_no_formats(
'The requested video is not archived, indexed, or there is an issue with web.archive.org (try again later)', expected=True)
else:
@@ -926,7 +924,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh:
url = compat_urllib_parse_unquote(urlh.geturl())
url = compat_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'))}
@@ -947,237 +945,3 @@ class YoutubeWebArchiveIE(InfoExtractor):
if not info.get('title'):
info['title'] = video_id
return info
class VLiveWebArchiveIE(InfoExtractor):
IE_NAME = 'web.archive:vlive'
IE_DESC = 'web.archive.org saved vlive videos'
_VALID_URL = r'''(?x)
(?:https?://)?web\.archive\.org/
(?:web/)?(?:(?P<date>[0-9]{14})?[0-9A-Za-z_*]*/)? # /web and the version index is optional
(?:https?(?::|%3[Aa])//)?(?:
(?:(?:www|m)\.)?vlive\.tv(?::(?:80|443))?/(?:video|embed)/(?P<id>[0-9]+) # VLive URL
)
'''
_TESTS = [{
'url': 'https://web.archive.org/web/20221221144331/http://www.vlive.tv/video/1326',
'md5': 'cc7314812855ce56de70a06a27314983',
'info_dict': {
'id': '1326',
'ext': 'mp4',
'title': "Girl's Day's Broadcast",
'creator': "Girl's Day",
'view_count': int,
'uploader_id': 'muploader_a',
'uploader_url': None,
'uploader': None,
'upload_date': '20150817',
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'timestamp': 1439816449,
'like_count': int,
'channel': 'Girl\'s Day',
'channel_id': 'FDF27',
'comment_count': int,
'release_timestamp': 1439818140,
'release_date': '20150817',
'duration': 1014,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://web.archive.org/web/20221221182103/http://www.vlive.tv/video/16937',
'info_dict': {
'id': '16937',
'ext': 'mp4',
'title': '첸백시 걍방',
'creator': 'EXO',
'view_count': int,
'subtitles': 'mincount:12',
'uploader_id': 'muploader_j',
'uploader_url': 'http://vlive.tv',
'uploader': None,
'upload_date': '20161112',
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'timestamp': 1478923074,
'like_count': int,
'channel': 'EXO',
'channel_id': 'F94BD',
'comment_count': int,
'release_timestamp': 1478924280,
'release_date': '20161112',
'duration': 906,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://web.archive.org/web/20221127190050/http://www.vlive.tv/video/101870',
'info_dict': {
'id': '101870',
'ext': 'mp4',
'title': '[ⓓ xV] “레벨이들 매력에 반해? 안 반해?” 움직이는 HD 포토 (레드벨벳:Red Velvet)',
'creator': 'Dispatch',
'view_count': int,
'subtitles': 'mincount:6',
'uploader_id': 'V__FRA08071',
'uploader_url': 'http://vlive.tv',
'uploader': None,
'upload_date': '20181130',
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
'timestamp': 1543601327,
'like_count': int,
'channel': 'Dispatch',
'channel_id': 'C796F3',
'comment_count': int,
'release_timestamp': 1543601040,
'release_date': '20181130',
'duration': 279,
},
'params': {
'skip_download': True,
},
}]
# The wayback machine has special timestamp and "mode" values:
# timestamp:
# 1 = the first capture
# 2 = the last capture
# mode:
# id_ = Identity - perform no alterations of the original resource, return it as it was archived.
_WAYBACK_BASE_URL = 'https://web.archive.org/web/2id_/'
def _download_archived_page(self, url, video_id, *, timestamp='2', **kwargs):
for retry in self.RetryManager():
try:
return self._download_webpage(f'https://web.archive.org/web/{timestamp}id_/{url}', video_id, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 404:
raise ExtractorError('Page was not archived', expected=True)
retry.error = e
continue
def _download_archived_json(self, url, video_id, **kwargs):
page = self._download_archived_page(url, video_id, **kwargs)
if not page:
raise ExtractorError('Page was not archived', expected=True)
else:
return self._parse_json(page, video_id)
def _extract_formats_from_m3u8(self, m3u8_url, params, video_id):
m3u8_doc = self._download_archived_page(m3u8_url, video_id, note='Downloading m3u8', query=params, fatal=False)
if not m3u8_doc:
return
# M3U8 document should be changed to archive domain
m3u8_doc = m3u8_doc.splitlines()
url_base = m3u8_url.rsplit('/', 1)[0]
first_segment = None
for i, line in enumerate(m3u8_doc):
if not line.startswith('#'):
m3u8_doc[i] = f'{self._WAYBACK_BASE_URL}{url_base}/{line}?{urllib.parse.urlencode(params)}'
first_segment = first_segment or m3u8_doc[i]
# Segments may not have been archived. See https://web.archive.org/web/20221127190050/http://www.vlive.tv/video/101870
urlh = self._request_webpage(HEADRequest(first_segment), video_id, errnote=False,
fatal=False, note='Check first segment availablity')
if urlh:
formats, subtitles = self._parse_m3u8_formats_and_subtitles('\n'.join(m3u8_doc), ext='mp4', video_id=video_id)
if subtitles:
self._report_ignoring_subs('m3u8')
return formats
# Closely follows the logic of the ArchiveTeam grab script
# See: https://github.com/ArchiveTeam/vlive-grab/blob/master/vlive.lua
def _real_extract(self, url):
video_id, url_date = self._match_valid_url(url).group('id', 'date')
webpage = self._download_archived_page(f'https://www.vlive.tv/video/{video_id}', video_id, timestamp=url_date)
player_info = self._search_json(r'__PRELOADED_STATE__\s*=', webpage, 'player info', video_id)
user_country = traverse_obj(player_info, ('common', 'userCountry'))
main_script_url = self._search_regex(r'<script\s+src="([^"]+/js/main\.[^"]+\.js)"', webpage, 'main script url')
main_script = self._download_archived_page(main_script_url, video_id, note='Downloading main script')
app_id = self._search_regex(r'appId\s*=\s*"([^"]+)"', main_script, 'app id')
inkey = self._download_archived_json(
f'https://www.vlive.tv/globalv-web/vam-web/video/v1.0/vod/{video_id}/inkey', video_id, note='Fetching inkey', query={
'appId': app_id,
'platformType': 'PC',
'gcc': user_country,
'locale': 'en_US',
}, fatal=False)
vod_id = traverse_obj(player_info, ('postDetail', 'post', 'officialVideo', 'vodId'))
vod_data = self._download_archived_json(
f'https://apis.naver.com/rmcnmv/rmcnmv/vod/play/v2.0/{vod_id}', video_id, note='Fetching vod data', query={
'key': inkey.get('inkey'),
'pid': 'rmcPlayer_16692457559726800', # partially unix time and partially random. Fixed value used by archiveteam project
'sid': '2024',
'ver': '2.0',
'devt': 'html5_pc',
'doct': 'json',
'ptc': 'https',
'sptc': 'https',
'cpt': 'vtt',
'ctls': '%7B%22visible%22%3A%7B%22fullscreen%22%3Atrue%2C%22logo%22%3Afalse%2C%22playbackRate%22%3Afalse%2C%22scrap%22%3Afalse%2C%22playCount%22%3Atrue%2C%22commentCount%22%3Atrue%2C%22title%22%3Atrue%2C%22writer%22%3Atrue%2C%22expand%22%3Afalse%2C%22subtitles%22%3Atrue%2C%22thumbnails%22%3Atrue%2C%22quality%22%3Atrue%2C%22setting%22%3Atrue%2C%22script%22%3Afalse%2C%22logoDimmed%22%3Atrue%2C%22badge%22%3Atrue%2C%22seekingTime%22%3Atrue%2C%22muted%22%3Atrue%2C%22muteButton%22%3Afalse%2C%22viewerNotice%22%3Afalse%2C%22linkCount%22%3Afalse%2C%22createTime%22%3Afalse%2C%22thumbnail%22%3Atrue%7D%2C%22clicked%22%3A%7B%22expand%22%3Afalse%2C%22subtitles%22%3Afalse%7D%7D',
'pv': '4.26.9',
'dr': '1920x1080',
'cpl': 'en_US',
'lc': 'en_US',
'adi': '%5B%7B%22type%22%3A%22pre%22%2C%22exposure%22%3Afalse%2C%22replayExposure%22%3Afalse%7D%5D',
'adu': '%2F',
'videoId': vod_id,
'cc': user_country,
})
formats = []
streams = traverse_obj(vod_data, ('streams', ...))
if len(streams) > 1:
self.report_warning('Multiple streams found. Only the first stream will be downloaded.')
stream = streams[0]
max_stream = max(
stream.get('videos') or [],
key=lambda v: traverse_obj(v, ('bitrate', 'video'), default=0), default=None)
if max_stream is not None:
params = {arg.get('name'): arg.get('value') for arg in stream.get('keys', []) if arg.get('type') == 'param'}
formats = self._extract_formats_from_m3u8(max_stream.get('source'), params, video_id) or []
# For parts of the project MP4 files were archived
max_video = max(
traverse_obj(vod_data, ('videos', 'list', ...)),
key=lambda v: traverse_obj(v, ('bitrate', 'video'), default=0), default=None)
if max_video is not None:
video_url = self._WAYBACK_BASE_URL + max_video.get('source')
urlh = self._request_webpage(HEADRequest(video_url), video_id, errnote=False,
fatal=False, note='Check video availablity')
if urlh:
formats.append({'url': video_url})
return {
'id': video_id,
'formats': formats,
**traverse_obj(player_info, ('postDetail', 'post', {
'title': ('officialVideo', 'title', {str}),
'creator': ('author', 'nickname', {str}),
'channel': ('channel', 'channelName', {str}),
'channel_id': ('channel', 'channelCode', {str}),
'duration': ('officialVideo', 'playTime', {int_or_none}),
'view_count': ('officialVideo', 'playCount', {int_or_none}),
'like_count': ('officialVideo', 'likeCount', {int_or_none}),
'comment_count': ('officialVideo', 'commentCount', {int_or_none}),
'timestamp': ('officialVideo', 'createdAt', {lambda x: int_or_none(x, scale=1000)}),
'release_timestamp': ('officialVideo', 'willStartAt', {lambda x: int_or_none(x, scale=1000)}),
})),
**traverse_obj(vod_data, ('meta', {
'uploader_id': ('user', 'id', {str}),
'uploader': ('user', 'name', {str}),
'uploader_url': ('user', 'url', {url_or_none}),
'thumbnail': ('cover', 'source', {url_or_none}),
}), expected_type=lambda x: x or None),
**NaverBaseIE.process_subtitles(vod_data, lambda x: [self._WAYBACK_BASE_URL + x]),
}
yt_dlp/extractor/ard.py
+298 -364
View File
@@ -1,23 +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_query,
url_or_none,
xpath_text,
)
from ..compat import compat_etree_fromstring
from ..utils.traversal import traverse_obj
class ARDMediathekBaseIE(InfoExtractor):
@@ -60,45 +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', [])
@@ -154,144 +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'.*\.([^.]+)\.[^.]+$', furl)
fid = fid_m.group(1) if fid_m else None
formats.append({
'quality': QUALITIES(fid),
'format_id': fid,
'url': furl,
})
info = {
'formats': formats,
}
else: # request JSON file
if not document_id:
video_id = self._search_regex(
(r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
webpage, 'media id', default=None)
info = self._extract_media_info(
'http://www.ardmediathek.de/play/media/%s' % video_id,
webpage, video_id)
info.update({
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
})
info.update(self._ARD_extract_episode_info(info['title']))
return info
class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/(?:[^/?#&]+/)+(?P<id>[^/?#&]+))\.html'
_TESTS = [{
# available till 7.12.2023
'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-video-424.html',
'md5': 'a438f671e87a7eba04000336a119ccc4',
'md5': '94812e6438488fb923c361a44469614b',
'info_dict': {
'id': 'maischberger-video-424',
'display_id': 'maischberger-video-424',
@@ -398,16 +229,38 @@ class ARDIE(InfoExtractor):
}
class ARDBetaMediathekIE(ARDMediathekBaseIE):
class ARDBetaMediathekIE(InfoExtractor):
IE_NAME = 'ARDMediathek'
_VALID_URL = r'''(?x)https://
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:(?P<client>[^/]+)/)?
(?:player|live|video|(?P<playlist>sendung|sammlung))/
(?:(?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)
(?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
(?:[^/]+/)?
(?: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/liebe-auf-vier-pfoten/mdr-fernsehen/Y3JpZDovL21kci5kZS9zZW5kdW5nLzI4MjA0MC80MjIwOTEtNDAyNTM0',
'md5': 'b6e8ab03f2bcc6e1f9e6cef25fcc03c4',
'info_dict': {
'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',
'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/',
'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
'info_dict': {
@@ -424,7 +277,7 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
'skip': 'Error',
}, {
'url': 'https://www.ardmediathek.de/video/tagesschau-oder-tagesschau-20-00-uhr/das-erste/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'md5': 'f1837e563323b8a642a8ddeff0131f51',
'md5': '1e73ded21cb79bac065117e80c81dc88',
'info_dict': {
'id': '10049223',
'ext': 'mp4',
@@ -432,13 +285,31 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
'timestamp': 1636398000,
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
'display_id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhZ2Vzc2NoYXUvZmM4ZDUxMjgtOTE0ZC00Y2MzLTgzNzAtNDZkNGNiZWJkOTll',
'duration': 915,
'episode': 'tagesschau, 20:00 Uhr',
'series': 'tagesschau',
'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/sendung/beforeigners/beforeigners/staffel-1/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw/1',
'playlist_count': 6,
'url': 'https://www.ardmediathek.de/video/7-tage/7-tage-unter-harten-jungs/hr-fernsehen/N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'md5': 'c428b9effff18ff624d4f903bda26315',
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw',
'title': 'beforeigners/beforeigners/staffel-1',
'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',
@@ -455,191 +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
}
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']),
})
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}),
}))
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'))
yt_dlp/extractor/art19.py
+303
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})),
}
yt_dlp/extractor/arte.py
+44 -23
View File
@@ -48,17 +48,7 @@ class ArteTVIE(ArteTVBaseIE):
}, {
'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 +57,37 @@ class ArteTVIE(ArteTVBaseIE):
'only_matching': True,
}, {
'url': 'https://www.arte.tv/de/videos/110203-006-A/zaz/',
'only_matching': True,
}, {
'note': 'age-restricted',
'url': 'https://www.arte.tv/de/videos/006785-000-A/the-element-of-crime/',
'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': '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']
}, {
'url': 'https://www.arte.tv/de/videos/085374-003-A/im-hohen-norden-geboren/',
'info_dict': {
'id': '085374-003-A',
'ext': 'mp4',
'description': 'md5:ab79ec7cc472a93164415b4e4916abf9',
'timestamp': 1702872000,
'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/TnyHBfPxv3v2GEY3suXGZP/940x530',
'duration': 2594,
'title': 'Die kurze Zeit der Jugend',
'alt_title': 'Im hohen Norden geboren',
'upload_date': '20231218',
'subtitles': {
'fr': 'mincount:1',
'fr-acc': 'mincount:1',
},
},
}]
_GEO_BYPASS = True
@@ -130,13 +138,25 @@ class ArteTVIE(ArteTVBaseIE):
),
}
@staticmethod
def _fix_accessible_subs_locale(subs):
updated_subs = {}
for lang, sub_formats in subs.items():
for fmt in sub_formats:
if fmt.get('url', '').endswith('-MAL.m3u8'):
lang += '-acc'
updated_subs.setdefault(lang, []).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)
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'):
@@ -169,7 +189,7 @@ class ArteTVIE(ArteTVBaseIE):
)))
short_label = traverse_obj(stream_version, 'shortLabel', expected_type=str, default='?')
if stream['protocol'].startswith('HLS'):
if 'HLS' in stream['protocol']:
fmts, subs = self._extract_m3u8_formats_and_subtitles(
stream['url'], video_id=video_id, ext='mp4', m3u8_id=stream_version_code, fatal=False)
for fmt in fmts:
@@ -181,6 +201,7 @@ 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'):
yt_dlp/extractor/asiancrush.py
-196
View File
@@ -1,196 +0,0 @@
import functools
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
int_or_none,
OnDemandPagedList,
parse_age_limit,
strip_or_none,
try_get,
)
class AsianCrushBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?(?P<host>(?:(?:asiancrush|yuyutv|midnightpulp)\.com|(?:cocoro|retrocrush)\.tv))'
_KALTURA_KEYS = [
'video_url', 'progressive_url', 'download_url', 'thumbnail_url',
'widescreen_thumbnail_url', 'screencap_widescreen',
]
_API_SUFFIX = {'retrocrush.tv': '-ott'}
def _call_api(self, host, endpoint, video_id, query, resource):
return self._download_json(
'https://api%s.%s/%s' % (self._API_SUFFIX.get(host, ''), host, endpoint), video_id,
'Downloading %s JSON metadata' % resource, query=query,
headers=self.geo_verification_headers())['objects']
def _download_object_data(self, host, object_id, resource):
return self._call_api(
host, 'search', object_id, {'id': object_id}, resource)[0]
def _get_object_description(self, obj):
return strip_or_none(obj.get('long_description') or obj.get('short_description'))
def _parse_video_data(self, video):
title = video['name']
entry_id, partner_id = [None] * 2
for k in self._KALTURA_KEYS:
k_url = video.get(k)
if k_url:
mobj = re.search(r'/p/(\d+)/.+?/entryId/([^/]+)/', k_url)
if mobj:
partner_id, entry_id = mobj.groups()
break
meta_categories = try_get(video, lambda x: x['meta']['categories'], list) or []
categories = list(filter(None, [c.get('name') for c in meta_categories]))
show_info = video.get('show_info') or {}
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, entry_id),
'ie_key': KalturaIE.ie_key(),
'id': entry_id,
'title': title,
'description': self._get_object_description(video),
'age_limit': parse_age_limit(video.get('mpaa_rating') or video.get('tv_rating')),
'categories': categories,
'series': show_info.get('show_name'),
'season_number': int_or_none(show_info.get('season_num')),
'season_id': show_info.get('season_id'),
'episode_number': int_or_none(show_info.get('episode_num')),
}
class AsianCrushIE(AsianCrushBaseIE):
_VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/video/004289v/women-who-flirt',
'md5': 'c3b740e48d0ba002a42c0b72857beae6',
'info_dict': {
'id': '1_y4tmjm5r',
'ext': 'mp4',
'title': 'Women Who Flirt',
'description': 'md5:b65c7e0ae03a85585476a62a186f924c',
'timestamp': 1496936429,
'upload_date': '20170608',
'uploader_id': 'craig@crifkin.com',
'age_limit': 13,
'categories': 'count:5',
'duration': 5812,
},
}, {
'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/video/true-tears/012328v-i...gave-away-my-tears',
'only_matching': True,
}]
def _real_extract(self, url):
host, video_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, video_id)
embed_vars = self._parse_json(self._search_regex(
r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
default='{}'), video_id, fatal=False) or {}
video_id = embed_vars.get('entry_id') or video_id
video = self._download_object_data(host, video_id, 'video')
return self._parse_video_data(video)
class AsianCrushPlaylistIE(AsianCrushBaseIE):
_VALID_URL = r'%s/series/0+(?P<id>\d+)s\b' % AsianCrushBaseIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/series/006447s/fruity-samurai',
'info_dict': {
'id': '6447',
'title': 'Fruity Samurai',
'description': 'md5:7535174487e4a202d3872a7fc8f2f154',
},
'playlist_count': 13,
}, {
'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/',
'only_matching': True,
}, {
'url': 'https://www.retrocrush.tv/series/012355s/true-tears',
'only_matching': True,
}]
_PAGE_SIZE = 1000000000
def _fetch_page(self, domain, parent_id, page):
videos = self._call_api(
domain, 'getreferencedobjects', parent_id, {
'max': self._PAGE_SIZE,
'object_type': 'video',
'parent_id': parent_id,
'start': page * self._PAGE_SIZE,
}, 'page %d' % (page + 1))
for video in videos:
yield self._parse_video_data(video)
def _real_extract(self, url):
host, playlist_id = self._match_valid_url(url).groups()
if host == 'cocoro.tv':
webpage = self._download_webpage(url, playlist_id)
entries = []
for mobj in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('class') == 'clearfix':
entries.append(self.url_result(
mobj.group('url'), ie=AsianCrushIE.ie_key()))
title = self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._html_extract_title(webpage)
if title:
title = re.sub(r'\s*\|\s*.+?$', '', title)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'twitter:description', webpage, 'description', fatal=False)
else:
show = self._download_object_data(host, playlist_id, 'show')
title = show.get('name')
description = self._get_object_description(show)
entries = OnDemandPagedList(
functools.partial(self._fetch_page, host, playlist_id),
self._PAGE_SIZE)
return self.playlist_result(entries, playlist_id, title, description)
yt_dlp/extractor/asobichannel.py
+168
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)
yt_dlp/extractor/asobistage.py
+154
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)
yt_dlp/extractor/atresplayer.py
+3 -3
View File
@@ -1,5 +1,5 @@
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
@@ -34,8 +34,8 @@ class AtresPlayerIE(InfoExtractor):
_API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
error = self._parse_json(e.cause.read(), None)
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)
yt_dlp/extractor/atttechchannel.py
-53
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,
}
yt_dlp/extractor/atvat.py
+4 -4
View File
@@ -1,4 +1,4 @@
import datetime
import datetime as dt
from .common import InfoExtractor
from ..utils import (
@@ -71,9 +71,9 @@ class ATVAtIE(InfoExtractor):
content_ids = [{'id': id, 'subclip_start': content['start'], 'subclip_end': content['end']}
for id, content in enumerate(contentResource)]
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,
yt_dlp/extractor/aws.py
+2 -2
View File
@@ -1,4 +1,4 @@
import datetime
import datetime as dt
import hashlib
import hmac
@@ -12,7 +12,7 @@ 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.utcnow().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',
yt_dlp/extractor/axs.py
+89
View File
@@ -0,0 +1,89 @@
from .common import InfoExtractor
from ..utils import (
float_or_none,
js_to_json,
parse_iso8601,
traverse_obj,
url_or_none,
)
class AxsIE(InfoExtractor):
IE_NAME = 'axs.tv'
_VALID_URL = r'https?://(?:www\.)?axs\.tv/(?:channel/(?:[^/?#]+/)+)?video/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.axs.tv/video/5f4dc776b70e4f1c194f22ef/',
'md5': '8d97736ae8e50c64df528e5e676778cf',
'info_dict': {
'id': '5f4dc776b70e4f1c194f22ef',
'title': 'Small Town',
'ext': 'mp4',
'description': 'md5:e314d28bfaa227a4d7ec965fae19997f',
'upload_date': '20230602',
'timestamp': 1685729564,
'duration': 1284.216,
'series': 'Rock & Roll Road Trip with Sammy Hagar',
'season': 'Season 2',
'season_number': 2,
'episode': '3',
'thumbnail': 'https://images.dotstudiopro.com/5f4e9d330a0c3b295a7e8394',
},
}, {
'url': 'https://www.axs.tv/channel/rock-star-interview/video/daryl-hall',
'md5': '300ae795cd8f9984652c0949734ffbdc',
'info_dict': {
'id': '5f488148b70e4f392572977c',
'display_id': 'daryl-hall',
'title': 'Daryl Hall',
'ext': 'mp4',
'description': 'md5:e54ecaa0f4b5683fc9259e9e4b196628',
'upload_date': '20230214',
'timestamp': 1676403615,
'duration': 2570.668,
'series': 'The Big Interview with Dan Rather',
'season': 'Season 3',
'season_number': 3,
'episode': '5',
'thumbnail': 'https://images.dotstudiopro.com/5f4d1901f340b50d937cec32',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage_json_data = self._search_json(
r'mountObj\s*=', webpage, 'video ID data', display_id,
transform_source=js_to_json)
video_id = webpage_json_data['video_id']
company_id = webpage_json_data['company_id']
meta = self._download_json(
f'https://api.myspotlight.tv/dotplayer/video/{company_id}/{video_id}',
video_id, query={'device_type': 'desktop_web'})['video']
formats = self._extract_m3u8_formats(
meta['video_m3u8'], video_id, 'mp4', m3u8_id='hls')
subtitles = {}
for cc in traverse_obj(meta, ('closeCaption', lambda _, v: url_or_none(v['srtPath']))):
subtitles.setdefault(cc.get('srtShortLang') or 'en', []).append(
{'ext': cc.get('srtExt'), 'url': cc['srtPath']})
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
**traverse_obj(meta, {
'title': ('title', {str}),
'description': ('description', {str}),
'series': ('seriestitle', {str}),
'season_number': ('season', {int}),
'episode': ('episode', {str}),
'duration': ('duration', {float_or_none}),
'timestamp': ('updated_at', {parse_iso8601}),
'thumbnail': ('thumb', {url_or_none}),
}),
'subtitles': subtitles,
}
yt_dlp/extractor/banbye.py
+24 -4
View File
@@ -31,7 +31,7 @@ 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 = [{
'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
@@ -59,7 +59,27 @@ class BanByeIE(BanByeBaseIE):
'title': 'Krzysztof Karoń',
'id': 'p_Ld82N6gBw_OJ',
},
'playlist_count': 9,
'playlist_mincount': 9,
}, {
'url': 'https://banbye.com/watch/v_kb6_o1Kyq-CD',
'info_dict': {
'id': 'v_kb6_o1Kyq-CD',
'ext': 'mp4',
'title': 'Co tak naprawdę dzieje się we Francji?! Czy Warszawa a potem cała Polska będzie drugim Paryżem?!🤔🇵🇱',
'description': 'md5:82be4c0e13eae8ea1ca8b9f2e07226a8',
'uploader': 'Marcin Rola - MOIM ZDANIEM!🇵🇱',
'channel_id': 'ch_QgWnHvDG2fo5',
'channel_url': 'https://banbye.com/channel/ch_QgWnHvDG2fo5',
'duration': 597,
'timestamp': 1688642656,
'upload_date': '20230706',
'thumbnail': 'https://cdn.banbye.com/video/v_kb6_o1Kyq-CD/96.webp',
'tags': ['Paryż', 'Francja', 'Polska', 'Imigranci', 'Morawiecki', 'Tusk'],
'like_count': int,
'dislike_count': int,
'view_count': int,
'comment_count': int,
},
}]
def _real_extract(self, url):
@@ -100,7 +120,7 @@ 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': {
@@ -132,7 +152,7 @@ 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']
yt_dlp/extractor/bbc.py
+42 -25
View File
@@ -2,11 +2,11 @@ import functools
import itertools
import json
import re
import urllib.error
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import compat_HTTPError, compat_str, compat_urlparse
from ..compat import compat_str, compat_urlparse
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@@ -15,11 +15,13 @@ from ..utils import (
float_or_none,
get_element_by_class,
int_or_none,
join_nonempty,
js_to_json,
parse_duration,
parse_iso8601,
parse_qs,
strip_or_none,
traverse_obj,
try_get,
unescapeHTML,
unified_timestamp,
@@ -41,7 +43,6 @@ class BBCCoUkIE(InfoExtractor):
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
music/(?:clips|audiovideo/popular)[/#]|
radio/player/|
sounds/play/|
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
@@ -218,20 +219,6 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
}, {
'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
'note': 'Audio',
'info_dict': {
'id': 'm0007jz9',
'ext': 'mp4',
'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra',
'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
'duration': 9840,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
@@ -277,7 +264,7 @@ class BBCCoUkIE(InfoExtractor):
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl():
if self._LOGIN_URL in urlh.url:
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
@@ -330,16 +317,25 @@ class BBCCoUkIE(InfoExtractor):
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(
@@ -388,8 +384,8 @@ class BBCCoUkIE(InfoExtractor):
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
if not (isinstance(e.exc_info[1], urllib.error.HTTPError)
and e.exc_info[1].code in (403, 404)):
if not (isinstance(e.exc_info[1], HTTPError)
and e.exc_info[1].status in (403, 404)):
raise
fmts = []
formats.extend(fmts)
@@ -472,7 +468,7 @@ class BBCCoUkIE(InfoExtractor):
return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee:
if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
if not (isinstance(ee.cause, HTTPError) and ee.cause.status == 404):
raise
# fallback to legacy playlist
@@ -844,6 +840,20 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'upload_date': '20190604',
'categories': ['Psychology'],
},
}, {
# BBC Sounds
'url': 'https://www.bbc.co.uk/sounds/play/m001q78b',
'info_dict': {
'id': 'm001q789',
'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',
},
}, { # onion routes
'url': 'https://www.bbcnewsd73hkzno2ini43t4gblxvycyac5aw4gnv7t2rccijh7745uqd.onion/news/av/world-europe-63208576',
'only_matching': True,
@@ -983,7 +993,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
# Some playlist URL may fail with 500, at the same time
# the other one may work fine (e.g.
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
if isinstance(e.cause, HTTPError) and e.cause.status == 500:
continue
raise
if entry:
@@ -1128,6 +1138,13 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'uploader_id': network.get('id'),
'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,
}
bbc3_config = self._parse_json(
@@ -1180,7 +1197,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
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)
yt_dlp/extractor/beatbump.py
+26 -16
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):
yt_dlp/extractor/beeg.py
+4 -3
View File
@@ -2,6 +2,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
str_or_none,
traverse_obj,
try_get,
unified_timestamp,
@@ -22,7 +23,7 @@ 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',
@@ -36,7 +37,7 @@ class BeegIE(InfoExtractor):
'age_limit': 18,
'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
'timestamp': 1643623200,
'display_id': 2569965,
'display_id': '2569965',
'upload_date': '20220131',
}
}, {
@@ -78,7 +79,7 @@ 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')),
yt_dlp/extractor/behindkink.py
+1
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/',
yt_dlp/extractor/bellmedia.py
+1 -1
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': [],
yt_dlp/extractor/bet.py
+1 -2
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 = [
{
yt_dlp/extractor/bfi.py
+1
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 = {
yt_dlp/extractor/bfmtv.py
+6 -4
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,
@@ -90,7 +93,6 @@ 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,
yt_dlp/extractor/bibeltv.py
+189 -19
View File
@@ -1,27 +1,197 @@
import functools
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
determine_ext,
format_field,
int_or_none,
js_to_json,
orderedSet,
parse_iso8601,
traverse_obj,
url_or_none,
)
class BibelTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?:crn/)?(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.bibeltv.de/mediathek/videos/329703-sprachkurs-in-malaiisch',
'md5': '252f908192d611de038b8504b08bf97f',
'info_dict': {
'id': 'ref:329703',
'ext': 'mp4',
'title': 'Sprachkurs in Malaiisch',
'description': 'md5:3e9f197d29ee164714e67351cf737dfe',
'timestamp': 1608316701,
'uploader_id': '5840105145001',
'upload_date': '20201218',
class BibelTVBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['AT', 'CH', 'DE']
_GEO_BYPASS = False
API_URL = 'https://www.bibeltv.de/mediathek/api'
AUTH_TOKEN = 'j88bRXY8DsEqJ9xmTdWhrByVi5Hm'
def _extract_formats_and_subtitles(self, data, crn_id, *, is_live=False):
formats = []
subtitles = {}
for media_url in traverse_obj(data, (..., 'src', {url_or_none})):
media_ext = determine_ext(media_url)
if media_ext == 'm3u8':
m3u8_formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
media_url, crn_id, live=is_live)
formats.extend(m3u8_formats)
subtitles.update(m3u8_subs)
elif media_ext == 'mpd':
mpd_formats, mpd_subs = self._extract_mpd_formats_and_subtitles(media_url, crn_id)
formats.extend(mpd_formats)
subtitles.update(mpd_subs)
elif media_ext == 'mp4':
formats.append({'url': media_url})
else:
self.report_warning(f'Unknown format {media_ext!r}')
return formats, subtitles
@staticmethod
def _extract_base_info(data):
return {
'id': data['crn'],
**traverse_obj(data, {
'title': 'title',
'description': 'description',
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('schedulingStart', {parse_iso8601}),
'season_number': 'seasonNumber',
'episode_number': 'episodeNumber',
'view_count': 'viewCount',
'like_count': 'likeCount',
}),
'thumbnails': orderedSet(traverse_obj(data, ('images', ..., {
'url': ('url', {url_or_none}),
}))),
}
}, {
'url': 'https://www.bibeltv.de/mediathek/videos/crn/326374',
'only_matching': True,
def _extract_url_info(self, data):
return {
'_type': 'url',
'url': format_field(data, 'slug', 'https://www.bibeltv.de/mediathek/videos/%s'),
**self._extract_base_info(data),
}
def _extract_video_info(self, data):
crn_id = data['crn']
if data.get('drm'):
self.report_drm(crn_id)
json_data = self._download_json(
format_field(data, 'id', f'{self.API_URL}/video/%s'), crn_id,
headers={'Authorization': self.AUTH_TOKEN}, fatal=False,
errnote='No formats available') or {}
formats, subtitles = self._extract_formats_and_subtitles(
traverse_obj(json_data, ('video', 'videoUrls', ...)), crn_id)
return {
'_type': 'video',
**self._extract_base_info(data),
'formats': formats,
'subtitles': subtitles,
}
class BibelTVVideoIE(BibelTVBaseIE):
IE_DESC = 'BibelTV single video'
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?P<id>\d+)[\w-]+'
IE_NAME = 'bibeltv:video'
_TESTS = [{
'url': 'https://www.bibeltv.de/mediathek/videos/344436-alte-wege',
'md5': 'ec1c07efe54353780512e8a4103b612e',
'info_dict': {
'id': '344436',
'ext': 'mp4',
'title': 'Alte Wege',
'description': 'md5:2f4eb7294c9797a47b8fd13cccca22e9',
'timestamp': 1677877071,
'duration': 150.0,
'upload_date': '20230303',
'thumbnail': r're:https://bibeltv\.imgix\.net/[\w-]+\.jpg',
'episode': 'Episode 1',
'episode_number': 1,
'view_count': int,
'like_count': int,
},
'params': {
'format': '6',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5840105145001/default_default/index.html?videoId=ref:%s'
def _real_extract(self, url):
crn_id = self._match_id(url)
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % crn_id, 'BrightcoveNew')
video_data = traverse_obj(
self._search_nextjs_data(self._download_webpage(url, crn_id), crn_id),
('props', 'pageProps', 'videoPageData', 'videos', 0, {dict}))
if not video_data:
raise ExtractorError('Missing video data.')
return self._extract_video_info(video_data)
class BibelTVSeriesIE(BibelTVBaseIE):
IE_DESC = 'BibelTV series playlist'
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/serien/(?P<id>\d+)[\w-]+'
IE_NAME = 'bibeltv:series'
_TESTS = [{
'url': 'https://www.bibeltv.de/mediathek/serien/333485-ein-wunder-fuer-jeden-tag',
'playlist_mincount': 400,
'info_dict': {
'id': '333485',
'title': 'Ein Wunder für jeden Tag',
'description': 'Tägliche Kurzandacht mit Déborah Rosenkranz.',
},
}]
def _real_extract(self, url):
crn_id = self._match_id(url)
webpage = self._download_webpage(url, crn_id)
nextjs_data = self._search_nextjs_data(webpage, crn_id)
series_data = traverse_obj(nextjs_data, ('props', 'pageProps', 'seriePageData', {dict}))
if not series_data:
raise ExtractorError('Missing series data.')
return self.playlist_result(
traverse_obj(series_data, ('videos', ..., {dict}, {self._extract_url_info})),
crn_id, series_data.get('title'), clean_html(series_data.get('description')))
class BibelTVLiveIE(BibelTVBaseIE):
IE_DESC = 'BibelTV live program'
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/livestreams/(?P<id>[\w-]+)'
IE_NAME = 'bibeltv:live'
_TESTS = [{
'url': 'https://www.bibeltv.de/livestreams/bibeltv/',
'info_dict': {
'id': 'bibeltv',
'ext': 'mp4',
'title': 're:Bibel TV',
'live_status': 'is_live',
'thumbnail': 'https://streampreview.bibeltv.de/bibeltv.webp',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bibeltv.de/livestreams/impuls/',
'only_matching': True,
}]
def _real_extract(self, url):
stream_id = self._match_id(url)
webpage = self._download_webpage(url, stream_id)
stream_data = self._search_json(
r'\\"video\\":', webpage, 'bibeltvData', stream_id,
transform_source=lambda jstring: js_to_json(jstring.replace('\\"', '"')))
formats, subtitles = self._extract_formats_and_subtitles(
traverse_obj(stream_data, ('src', ...)), stream_id, is_live=True)
return {
'id': stream_id,
'title': stream_data.get('title'),
'thumbnail': stream_data.get('poster'),
'is_live': True,
'formats': formats,
'subtitles': subtitles,
}
yt_dlp/extractor/bigo.py
+2 -1
View File
@@ -29,7 +29,8 @@ 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')
yt_dlp/extractor/bild.py
+29 -3
View File
@@ -1,6 +1,7 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
unescapeHTML,
)
@@ -8,7 +9,8 @@ from ..utils import (
class BildIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
IE_DESC = 'Bild.de'
_TEST = {
_TESTS = [{
'note': 'static MP4 only',
'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
'md5': 'dd495cbd99f2413502a1713a1156ac8a',
'info_dict': {
@@ -19,7 +21,19 @@ class BildIE(InfoExtractor):
'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',
'md5': 'fb0ed4f09c495d4ba7ce2eee0bb90de1',
'info_dict': {
'id': '85158620',
'ext': 'mp4',
'title': 'Der Sprungturm-Skandal',
'description': 'md5:709b543c24dc31bbbffee73bccda34ad',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 69,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -27,11 +41,23 @@ class BildIE(InfoExtractor):
video_data = self._download_json(
url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
formats = []
for src in traverse_obj(video_data, ('clipList', 0, 'srces', lambda _, v: v['src'])):
src_type = src.get('type')
if src_type == 'application/x-mpegURL':
formats.extend(
self._extract_m3u8_formats(
src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False))
elif src_type == 'video/mp4':
formats.append({'url': src['src'], 'format_id': 'http-mp4'})
else:
self.report_warning(f'Skipping unsupported format type: "{src_type}"')
return {
'id': video_id,
'title': unescapeHTML(video_data['title']).strip(),
'description': unescapeHTML(video_data.get('description')),
'url': video_data['clipList'][0]['srces'][0]['src'],
'formats': formats,
'thumbnail': video_data.get('poster'),
'duration': int_or_none(video_data.get('durationSec')),
}
yt_dlp/extractor/bilibili.py
+1122 -122
View File
File diff suppressed because it is too large Load Diff
yt_dlp/extractor/biqle.py
-110
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')),
}
yt_dlp/extractor/bitchute.py
+47 -5
View File
@@ -2,13 +2,15 @@ import functools
import re
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
HEADRequest,
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,
@@ -17,6 +19,7 @@ from ..utils import (
traverse_obj,
unified_strdate,
urlencode_postdata,
urljoin,
)
@@ -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},
}, {
@@ -77,7 +102,10 @@ class BitChuteIE(InfoExtractor):
def _check_format(self, video_url, video_id):
urls = orderedSet(
re.sub(r'(^https?://)(seed\d+)(?=\.bitchute\.com)', fr'\g<1>{host}', video_url)
for host in (r'\g<2>', 'seed150', 'seed151', 'seed152', 'seed153'))
for host in (r'\g<2>', 'seed122', 'seed125', 'seed126', 'seed128',
'seed132', 'seed150', 'seed151', 'seed152', 'seed153',
'seed167', 'seed171', 'seed177', 'seed305', 'seed307',
'seedp29xb', 'zb10-7gsop1v78'))
for url in urls:
try:
response = self._request_webpage(
@@ -96,6 +124,11 @@ 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(
@@ -118,12 +151,19 @@ 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,
@@ -145,12 +185,14 @@ 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$',
'uploader': 'BitChute',
'upload_date': '20170103',
'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
'channel': 'BitChute',
'channel_url': 'https://www.bitchute.com/channel/bitchute/',
'duration': 16,
'view_count': int,
},
@@ -166,7 +208,7 @@ class BitChuteChannelIE(InfoExtractor):
'info_dict': {
'id': 'wV9Imujxasw9',
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
'description': 'md5:747724ef404eebdfc04277714f81863e',
}
}]
yt_dlp/extractor/bitwave.py
-58
View File
@@ -1,58 +0,0 @@
from .common import InfoExtractor
class BitwaveReplayIE(InfoExtractor):
IE_NAME = 'bitwave:replay'
_VALID_URL = r'https?://(?:www\.)?bitwave\.tv/(?P<user>\w+)/replay/(?P<id>\w+)/?$'
_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']
}
yt_dlp/extractor/bleacherreport.py
+7 -6
View File
@@ -4,10 +4,12 @@ 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'],
@@ -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')),
@@ -70,8 +72,6 @@ class BleacherReportIE(InfoExtractor):
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']
elif video_type == 'youtube.com':
info['url'] = video['id']
elif video_type == 'vine.co':
@@ -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',
yt_dlp/extractor/boosty.py
+209
View File
@@ -0,0 +1,209 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
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')
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')
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:
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)
yt_dlp/extractor/booyah.py
-86
View File
@@ -1,86 +0,0 @@
from .common import InfoExtractor
from ..utils import int_or_none, str_or_none, traverse_obj
class BooyahBaseIE(InfoExtractor):
_BOOYAH_SESSION_KEY = None
def _real_initialize(self):
BooyahBaseIE._BOOYAH_SESSION_KEY = self._request_webpage(
'https://booyah.live/api/v3/auths/sessions', None, data=b'').getheader('booyah-session-key')
def _get_comments(self, video_id):
comment_json = self._download_json(
f'https://booyah.live/api/v3/playbacks/{video_id}/comments/tops', video_id,
headers={'Booyah-Session-Key': self._BOOYAH_SESSION_KEY}, fatal=False) or {}
return [{
'id': comment.get('comment_id'),
'author': comment.get('from_nickname'),
'author_id': comment.get('from_uid'),
'author_thumbnail': comment.get('from_thumbnail'),
'text': comment.get('content'),
'timestamp': comment.get('create_time'),
'like_count': comment.get('like_cnt'),
} for comment in comment_json.get('comment_list') or ()]
class BooyahClipsIE(BooyahBaseIE):
_VALID_URL = r'https?://booyah.live/clips/(?P<id>\d+)'
_TESTS = [{
'url': 'https://booyah.live/clips/13887261322952306617',
'info_dict': {
'id': '13887261322952306617',
'ext': 'mp4',
'view_count': int,
'duration': 30,
'channel_id': 90565760,
'like_count': int,
'title': 'Cayendo con estilo 😎',
'uploader': '♡LɪꜱGΛ​MER​',
'comment_count': int,
'uploader_id': '90565760',
'thumbnail': 'https://resmambet-a.akamaihd.net/mambet-storage/Clip/90565760/90565760-27204374-fba0-409d-9d7b-63a48b5c0e75.jpg',
'upload_date': '20220617',
'timestamp': 1655490556,
'modified_timestamp': 1655490556,
'modified_date': '20220617',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(
f'https://booyah.live/api/v3/playbacks/{video_id}', video_id,
headers={'Booyah-Session-key': self._BOOYAH_SESSION_KEY})
formats = []
for video_data in json_data['playback']['endpoint_list']:
formats.extend(({
'url': video_data.get('stream_url'),
'ext': 'mp4',
'height': video_data.get('resolution'),
}, {
'url': video_data.get('download_url'),
'ext': 'mp4',
'format_note': 'Watermarked',
'height': video_data.get('resolution'),
'preference': -10,
}))
return {
'id': video_id,
'title': traverse_obj(json_data, ('playback', 'name')),
'thumbnail': traverse_obj(json_data, ('playback', 'thumbnail_url')),
'formats': formats,
'view_count': traverse_obj(json_data, ('playback', 'views')),
'like_count': traverse_obj(json_data, ('playback', 'likes')),
'duration': traverse_obj(json_data, ('playback', 'duration')),
'comment_count': traverse_obj(json_data, ('playback', 'comment_cnt')),
'channel_id': traverse_obj(json_data, ('playback', 'channel_id')),
'uploader': traverse_obj(json_data, ('user', 'nickname')),
'uploader_id': str_or_none(traverse_obj(json_data, ('user', 'uid'))),
'modified_timestamp': int_or_none(traverse_obj(json_data, ('playback', 'update_time_ms')), 1000),
'timestamp': int_or_none(traverse_obj(json_data, ('playback', 'create_time_ms')), 1000),
'__post_extractor': self.extract_comments(video_id, self._get_comments(video_id)),
}
yt_dlp/extractor/box.py
+45 -31
View File
@@ -1,36 +1,61 @@
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?://(?:[^.]+\.)?app\.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'},
}]
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']
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,
'Downloading token JSON metadata',
@@ -58,26 +83,15 @@ class BoxIE(InfoExtractor):
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 {}
yt_dlp/extractor/bpb.py
+144 -30
View File
@@ -1,56 +1,170 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_text_and_html_by_tag,
get_elements_by_class,
join_nonempty,
js_to_json,
determine_ext,
mimetype2ext,
unified_strdate,
url_or_none,
urljoin,
variadic,
)
from ..utils.traversal import traverse_obj
def html_get_element(tag=None, cls=None):
assert tag or cls, 'One of tag or class is required'
if cls:
func = functools.partial(get_elements_by_class, cls, tag=tag)
else:
func = functools.partial(get_element_text_and_html_by_tag, tag)
def html_get_element_wrapper(html):
return variadic(func(html))[0]
return html_get_element_wrapper
class BpbIE(InfoExtractor):
IE_DESC = 'Bundeszentrale für politische Bildung'
_VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
_VALID_URL = r'https?://(?:www\.|m\.)?bpb\.de/(?:[^/?#]+/)*(?P<id>\d+)(?:[/?#]|$)'
_TEST = {
_TESTS = [{
'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
'md5': 'c4f84c8a8044ca9ff68bb8441d300b3f',
'info_dict': {
'id': '297',
'ext': 'mp4',
'creator': 'Kooperative Berlin',
'description': 'md5:f4f75885ba009d3e2b156247a8941ce6',
'release_date': '20160115',
'series': 'Interview auf dem Geschichtsforum 1989 | 2009',
'tags': ['Friedliche Revolution', 'Erinnerungskultur', 'Vergangenheitspolitik', 'DDR 1949 - 1990', 'Freiheitsrecht', 'BStU', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/7/297_teaser_16x9_1240.jpg?8839D',
'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.'
'uploader': 'Bundeszentrale für politische Bildung',
},
}, {
'url': 'https://www.bpb.de/mediathek/video/522184/krieg-flucht-und-falschmeldungen-wirstattdesinformation-2/',
'info_dict': {
'id': '522184',
'ext': 'mp4',
'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
'description': 'md5:f83c795ff8f825a69456a9e51fc15903',
'release_date': '20230621',
'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
'thumbnail': 'https://www.bpb.de/cache/images/4/522184_teaser_16x9_1240.png?EABFB',
'title': 'md5:9b01ccdbf58dbf9e5c9f6e771a803b1c',
'uploader': 'Bundeszentrale für politische Bildung',
},
}, {
'url': 'https://www.bpb.de/lernen/bewegtbild-und-politische-bildung/webvideo/518789/krieg-flucht-und-falschmeldungen-wirstattdesinformation-1/',
'info_dict': {
'id': '518789',
'ext': 'mp4',
'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
'description': 'md5:85228aed433e84ff0ff9bc582abd4ea8',
'release_date': '20230302',
'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
'thumbnail': 'https://www.bpb.de/cache/images/9/518789_teaser_16x9_1240.jpeg?56D0D',
'title': 'md5:3e956f264bb501f6383f10495a401da4',
'uploader': 'Bundeszentrale für politische Bildung',
},
}, {
'url': 'https://www.bpb.de/mediathek/podcasts/apuz-podcast/539727/apuz-20-china/',
'only_matching': True,
}, {
'url': 'https://www.bpb.de/mediathek/audio/315813/folge-1-eine-einfuehrung/',
'info_dict': {
'id': '315813',
'ext': 'mp3',
'creator': 'Axel Schröder',
'description': 'md5:eda9d1af34e5912efef5baf54fba4427',
'release_date': '20200921',
'series': 'Auf Endlagersuche. Der deutsche Weg zu einem sicheren Atommülllager',
'tags': ['Atomenergie', 'Endlager', 'hoch-radioaktiver Abfall', 'Endlagersuche', 'Atommüll', 'Atomendlager', 'Gorleben', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/3/315813_teaser_16x9_1240.png?92A94',
'title': 'Folge 1: Eine Einführung',
'uploader': 'Bundeszentrale für politische Bildung',
},
}, {
'url': 'https://www.bpb.de/517806/die-weltanschauung-der-neuen-rechten/',
'info_dict': {
'id': '517806',
'ext': 'mp3',
'creator': 'Bundeszentrale für politische Bildung',
'description': 'md5:594689600e919912aade0b2871cc3fed',
'release_date': '20230127',
'series': 'Vorträge des Fachtags "Modernisierer. Grenzgänger. Anstifter. Sechs Jahrzehnte \'Neue Rechte\'"',
'tags': ['Rechtsextremismus', 'Konservatismus', 'Konservativismus', 'neue Rechte', 'Rechtspopulismus', 'Schnellroda', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/6/517806_teaser_16x9_1240.png?7A7A0',
'title': 'Die Weltanschauung der "Neuen Rechten"',
'uploader': 'Bundeszentrale für politische Bildung',
},
}, {
'url': 'https://www.bpb.de/mediathek/reihen/zahlen-und-fakten-soziale-situation-filme/520153/zahlen-und-fakten-die-soziale-situation-in-deutschland-migration/',
'only_matching': True,
}]
_TITLE_RE = re.compile('(?P<title>[^<]*)<[^>]+>(?P<series>[^<]*)')
def _parse_vue_attributes(self, name, string, video_id):
attributes = extract_attributes(self._search_regex(rf'(<{name}(?:"[^"]*?"|[^>])*>)', string, name))
for key, value in attributes.items():
if key.startswith(':'):
attributes[key] = self._parse_json(value, video_id, transform_source=js_to_json, fatal=False)
return attributes
@staticmethod
def _process_source(source):
url = url_or_none(source['src'])
if not url:
return None
source_type = source.get('type', '')
extension = mimetype2ext(source_type)
is_video = source_type.startswith('video')
note = url.rpartition('.')[0].rpartition('_')[2] if is_video else None
return {
'url': url,
'ext': extension,
'vcodec': None if is_video else 'none',
'quality': 10 if note == 'high' else 0,
'format_note': note,
'format_id': join_nonempty(extension, note),
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h2 class="white">(.*?)</h2>', webpage, 'title')
video_info_dicts = re.findall(
r"({\s*src\s*:\s*'https?://film\.bpb\.de/[^}]+})", webpage)
formats = []
for video_info in video_info_dicts:
video_info = self._parse_json(
video_info, video_id, transform_source=js_to_json, fatal=False)
if not video_info:
continue
video_url = video_info.get('src')
if not video_url:
continue
quality = 'high' if '_high' in video_url else 'low'
formats.append({
'url': video_url,
'quality': 10 if quality == 'high' else 0,
'format_note': quality,
'format_id': '%s-%s' % (quality, determine_ext(video_url)),
})
title_result = traverse_obj(webpage, ({html_get_element(cls='opening-header__title')}, {self._TITLE_RE.match}))
json_lds = list(self._yield_json_ld(webpage, video_id, fatal=False))
return {
'id': video_id,
'formats': formats,
'title': title,
'description': self._og_search_description(webpage),
'title': traverse_obj(title_result, ('title', {str.strip})) or None,
# This metadata could be interpreted otherwise, but it fits "series" the most
'series': traverse_obj(title_result, ('series', {str.strip})) or None,
'description': join_nonempty(*traverse_obj(webpage, [(
{html_get_element(cls='opening-intro')},
[{html_get_element(tag='bpb-accordion-item')}, {html_get_element(cls='text-content')}],
), {clean_html}]), delim='\n\n') or None,
'creator': self._html_search_meta('author', webpage),
'uploader': self._html_search_meta('publisher', webpage),
'release_date': unified_strdate(self._html_search_meta('date', webpage)),
'tags': traverse_obj(json_lds, (..., 'keywords', {lambda x: x.split(',')}, ...)),
**traverse_obj(self._parse_vue_attributes('bpb-player', webpage, video_id), {
'formats': (':sources', ..., {self._process_source}),
'thumbnail': ('poster', {lambda x: urljoin(url, x)}),
}),
}
yt_dlp/extractor/br.py
+1 -143
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'
@@ -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,
}
yt_dlp/extractor/brainpop.py
+318
View File
@@ -0,0 +1,318 @@
import json
import re
from .common import InfoExtractor
from ..utils import (
classproperty,
int_or_none,
traverse_obj,
urljoin
)
class BrainPOPBaseIE(InfoExtractor):
_NETRC_MACHINE = 'brainpop'
_ORIGIN = '' # So that _VALID_URL doesn't crash
_LOGIN_ERRORS = {
1502: 'The username and password you entered did not match.', # LOGIN_FAILED
1503: 'Payment method is expired.', # LOGIN_FAILED_ACCOUNT_NOT_ACTIVE
1506: 'Your BrainPOP plan has expired.', # LOGIN_FAILED_ACCOUNT_EXPIRED
1507: 'Terms not accepted.', # LOGIN_FAILED_TERMS_NOT_ACCEPTED
1508: 'Account not activated.', # LOGIN_FAILED_SUBSCRIPTION_NOT_ACTIVE
1512: 'The maximum number of devices permitted are logged in with your account right now.', # LOGIN_FAILED_LOGIN_LIMIT_REACHED
1513: 'You are trying to access your account from outside of its allowed IP range.', # LOGIN_FAILED_INVALID_IP
1514: 'Individual accounts are not included in your plan. Try again with your shared username and password.', # LOGIN_FAILED_MBP_DISABLED
1515: 'Account not activated.', # LOGIN_FAILED_TEACHER_NOT_ACTIVE
1523: 'That username and password won\'t work on this BrainPOP site.', # LOGIN_FAILED_NO_ACCESS
1524: 'You\'ll need to join a class before you can login.', # LOGIN_FAILED_STUDENT_NO_PERIOD
1526: 'Your account is locked. Reset your password, or ask a teacher or administrator for help.', # LOGIN_FAILED_ACCOUNT_LOCKED
}
@classproperty
def _VALID_URL(cls):
root = re.escape(cls._ORIGIN).replace(r'https:', r'https?:').replace(r'www\.', r'(?:www\.)?')
return rf'{root}/(?P<slug>[^/]+/[^/]+/(?P<id>[^/?#&]+))'
def _assemble_formats(self, slug, format_id, display_id, token='', extra_fields={}):
formats = []
formats = self._extract_m3u8_formats(
f'{urljoin(self._HLS_URL, slug)}.m3u8?{token}',
display_id, 'mp4', m3u8_id=f'{format_id}-hls', fatal=False)
formats.append({
'format_id': format_id,
'url': f'{urljoin(self._VIDEO_URL, slug)}?{token}',
})
for f in formats:
f.update(extra_fields)
return formats
def _extract_adaptive_formats(self, data, token, display_id, key_format='%s', extra_fields={}):
formats = []
additional_key_formats = {
'%s': {},
'ad_%s': {
'format_note': 'Audio description',
'source_preference': -2
}
}
for additional_key_format, additional_key_fields in additional_key_formats.items():
for key_quality, key_index in enumerate(('high', 'low')):
full_key_index = additional_key_format % (key_format % key_index)
if data.get(full_key_index):
formats.extend(self._assemble_formats(data[full_key_index], full_key_index, display_id, token, {
'quality': -1 - key_quality,
**additional_key_fields,
**extra_fields
}))
return formats
def _perform_login(self, username, password):
login_res = self._download_json(
'https://api.brainpop.com/api/login', None,
data=json.dumps({'username': username, 'password': password}).encode(),
headers={
'Content-Type': 'application/json',
'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:
self.report_warning(
f'Unable to login: {self._LOGIN_ERRORS.get(status_code) or login_res.get("message")}'
or f'Got status code {status_code}')
class BrainPOPIE(BrainPOPBaseIE):
_ORIGIN = 'https://www.brainpop.com'
_VIDEO_URL = 'https://svideos.brainpop.com'
_HLS_URL = 'https://hls.brainpop.com'
_CDN_URL = 'https://cdn.brainpop.com'
_TESTS = [{
'url': 'https://www.brainpop.com/health/conflictresolution/martinlutherkingjr/movie?ref=null',
'md5': '3ead374233ae74c7f1b0029a01c972f0',
'info_dict': {
'id': '1f3259fa457292b4',
'ext': 'mp4',
'title': 'Martin Luther King, Jr.',
'display_id': 'martinlutherkingjr',
'description': 'md5:f403dbb2bf3ccc7cf4c59d9e43e3c349',
},
}, {
'url': 'https://www.brainpop.com/science/space/bigbang/',
'md5': '9a1ff0e77444dd9e437354eb669c87ec',
'info_dict': {
'id': 'acae52cd48c99acf',
'ext': 'mp4',
'title': 'Big Bang',
'display_id': 'bigbang',
'description': 'md5:3e53b766b0f116f631b13f4cae185d38',
},
'skip': 'Requires login',
}]
def _real_extract(self, url):
slug, display_id = self._match_valid_url(url).group('slug', 'id')
movie_data = self._download_json(
f'https://api.brainpop.com/api/content/published/bp/en/{slug}/movie?full=1', display_id,
'Downloading movie data JSON', 'Unable to download movie data')['data']
topic_data = traverse_obj(self._download_json(
f'https://api.brainpop.com/api/content/published/bp/en/{slug}?full=1', display_id,
'Downloading topic data JSON', 'Unable to download topic data', fatal=False),
('data', 'topic'), expected_type=dict) or movie_data['topic']
if not traverse_obj(movie_data, ('access', 'allow')):
reason = traverse_obj(movie_data, ('access', 'reason'))
if 'logged' in reason:
self.raise_login_required(reason, metadata_available=True)
else:
self.raise_no_formats(reason, video_id=display_id)
movie_feature = movie_data['feature']
movie_feature_data = movie_feature['data']
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
}))
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
}))
# TODO: Do localization fields also have subtitles?
for name, url in movie_feature_data.items():
lang = self._search_regex(
r'^subtitles_(?P<lang>\w+)$', name, 'subtitle metadata', default=None)
if lang and url:
subtitles.setdefault(lang, []).append({
'url': urljoin(self._CDN_URL, url)
})
return {
'id': topic_data['topic_id'],
'display_id': display_id,
'title': topic_data.get('name'),
'description': topic_data.get('synopsis'),
'formats': formats,
'subtitles': subtitles,
}
class BrainPOPLegacyBaseIE(BrainPOPBaseIE):
def _parse_js_topic_data(self, topic_data, display_id, token):
movie_data = topic_data['movies']
# TODO: Are there non-burned subtitles?
formats = self._extract_adaptive_formats(movie_data, token, display_id)
return {
'id': topic_data['EntryID'],
'display_id': display_id,
'title': topic_data.get('name'),
'alt_title': topic_data.get('title'),
'description': topic_data.get('synopsis'),
'formats': formats,
}
def _real_extract(self, url):
slug, display_id = self._match_valid_url(url).group('slug', 'id')
webpage = self._download_webpage(url, display_id)
topic_data = self._search_json(
r'var\s+content\s*=\s*', webpage, 'content data',
display_id, end_pattern=';')['category']['unit']['topic']
token = self._search_regex(r'ec_token\s*:\s*[\'"]([^\'"]+)', webpage, 'video token')
return self._parse_js_topic_data(topic_data, display_id, token)
class BrainPOPJrIE(BrainPOPLegacyBaseIE):
_ORIGIN = 'https://jr.brainpop.com'
_VIDEO_URL = 'https://svideos-jr.brainpop.com'
_HLS_URL = 'https://hls-jr.brainpop.com'
_CDN_URL = 'https://cdn-jr.brainpop.com'
_TESTS = [{
'url': 'https://jr.brainpop.com/health/feelingsandsel/emotions/',
'md5': '04e0561bb21770f305a0ce6cf0d869ab',
'info_dict': {
'id': '347',
'ext': 'mp4',
'title': 'Emotions',
'display_id': 'emotions',
},
}, {
'url': 'https://jr.brainpop.com/science/habitats/arctichabitats/',
'md5': 'b0ed063bbd1910df00220ee29340f5d6',
'info_dict': {
'id': '29',
'ext': 'mp4',
'title': 'Arctic Habitats',
'display_id': 'arctichabitats',
},
'skip': 'Requires login',
}]
class BrainPOPELLIE(BrainPOPLegacyBaseIE):
_ORIGIN = 'https://ell.brainpop.com'
_VIDEO_URL = 'https://svideos-esl.brainpop.com'
_HLS_URL = 'https://hls-esl.brainpop.com'
_CDN_URL = 'https://cdn-esl.brainpop.com'
_TESTS = [{
'url': 'https://ell.brainpop.com/level1/unit1/lesson1/',
'md5': 'a2012700cfb774acb7ad2e8834eed0d0',
'info_dict': {
'id': '1',
'ext': 'mp4',
'title': 'Lesson 1',
'display_id': 'lesson1',
'alt_title': 'Personal Pronouns',
},
}, {
'url': 'https://ell.brainpop.com/level3/unit6/lesson5/',
'md5': 'be19c8292c87b24aacfb5fda2f3f8363',
'info_dict': {
'id': '101',
'ext': 'mp4',
'title': 'Lesson 5',
'display_id': 'lesson5',
'alt_title': 'Review: Unit 6',
},
'skip': 'Requires login',
}]
class BrainPOPEspIE(BrainPOPLegacyBaseIE):
IE_DESC = 'BrainPOP Español'
_ORIGIN = 'https://esp.brainpop.com'
_VIDEO_URL = 'https://svideos.brainpop.com'
_HLS_URL = 'https://hls.brainpop.com'
_CDN_URL = 'https://cdn.brainpop.com/mx'
_TESTS = [{
'url': 'https://esp.brainpop.com/ciencia/la_diversidad_de_la_vida/ecosistemas/',
'md5': 'cb3f062db2b3c5240ddfcfde7108f8c9',
'info_dict': {
'id': '3893',
'ext': 'mp4',
'title': 'Ecosistemas',
'display_id': 'ecosistemas',
'description': 'md5:80fc55b07e241f8c8f2aa8d74deaf3c3',
},
}, {
'url': 'https://esp.brainpop.com/espanol/la_escritura/emily_dickinson/',
'md5': '98c1b9559e0e33777209c425cda7dac4',
'info_dict': {
'id': '7146',
'ext': 'mp4',
'title': 'Emily Dickinson',
'display_id': 'emily_dickinson',
'description': 'md5:2795ad87b1d239c9711c1e92ab5a978b',
},
'skip': 'Requires login',
}]
class BrainPOPFrIE(BrainPOPLegacyBaseIE):
IE_DESC = 'BrainPOP Français'
_ORIGIN = 'https://fr.brainpop.com'
_VIDEO_URL = 'https://svideos.brainpop.com'
_HLS_URL = 'https://hls.brainpop.com'
_CDN_URL = 'https://cdn.brainpop.com/fr'
_TESTS = [{
'url': 'https://fr.brainpop.com/sciencesdelaterre/energie/sourcesdenergie/',
'md5': '97e7f48af8af93f8a2be11709f239371',
'info_dict': {
'id': '1651',
'ext': 'mp4',
'title': 'Sources d\'énergie',
'display_id': 'sourcesdenergie',
'description': 'md5:7eece350f019a21ef9f64d4088b2d857',
},
}, {
'url': 'https://fr.brainpop.com/francais/ecrire/plagiat/',
'md5': '0cf2b4f89804d0dd4a360a51310d445a',
'info_dict': {
'id': '5803',
'ext': 'mp4',
'title': 'Plagiat',
'display_id': 'plagiat',
'description': 'md5:4496d87127ace28e8b1eda116e77cd2b',
},
'skip': 'Requires login',
}]
class BrainPOPIlIE(BrainPOPLegacyBaseIE):
IE_DESC = 'BrainPOP Hebrew'
_ORIGIN = 'https://il.brainpop.com'
_VIDEO_URL = 'https://svideos.brainpop.com'
_HLS_URL = 'https://hls.brainpop.com'
_CDN_URL = 'https://cdn.brainpop.com/he'
_TESTS = [{
'url': 'https://il.brainpop.com/category_9/subcategory_150/subjects_3782/',
'md5': '9e4ea9dc60ecd385a6e5ca12ccf31641',
'info_dict': {
'id': '3782',
'ext': 'mp4',
'title': 'md5:e993632fcda0545d9205602ec314ad67',
'display_id': 'subjects_3782',
'description': 'md5:4cc084a8012beb01f037724423a4d4ed',
},
}]
yt_dlp/extractor/bravotv.py
+154 -82
View File
@@ -1,117 +1,189 @@
import re
from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import (
smuggle_url,
update_url_query,
int_or_none,
extract_attributes,
float_or_none,
try_get,
dict_get,
get_element_html_by_class,
int_or_none,
merge_dicts,
parse_age_limit,
remove_end,
str_or_none,
traverse_obj,
unescapeHTML,
unified_timestamp,
update_url_query,
url_or_none,
)
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?P<req_id>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<site>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
'info_dict': {
'id': 'epL0pmK1kQlT',
'id': '3923059',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'description': 'Find out who takes the title of Top Chef!',
'uploader': 'NBCU-BRAV',
'upload_date': '20190314',
'timestamp': 1552591860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'The Top Chef Season 16 Winner Is...',
'duration': 190.0,
}
'duration': 190.357,
'season': 'Season 16',
'thumbnail': r're:^https://.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
'info_dict': {
'id': '9000234570',
'ext': 'mp4',
'title': 'London Calling',
'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
'upload_date': '20230310',
'timestamp': 1678410000,
'season_number': 20,
'episode_number': 1,
'series': 'Top Chef',
'episode': 'London Calling',
'duration': 3266.03,
'season': 'Season 20',
'chapters': 'count:7',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
'info_dict': {
'id': '3692045',
'ext': 'mp4',
'title': 'Closing Night',
'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
'upload_date': '20180401',
'timestamp': 1522623600,
'season_number': 1,
'episode_number': 1,
'series': 'In Ice Cold Blood',
'episode': 'Closing Night',
'duration': 2629.051,
'season': 'Season 1',
'chapters': 'count:6',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'info_dict': {
'id': '3974019',
'ext': 'mp4',
'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
'upload_date': '20190617',
'timestamp': 1560790800,
'season_number': 2,
'episode_number': 16,
'series': 'In Ice Cold Blood',
'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'duration': 68.235,
'season': 'Season 2',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
settings = self._parse_json(self._search_regex(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
display_id)
info = {}
settings = self._search_json(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
query = {
'mbr': 'true',
'manifest': 'm3u',
'formats': 'm3u,mpeg4',
}
account_pid, release_pid = [None] * 2
tve = settings.get('ls_tve')
if tve:
query['manifest'] = 'm3u'
mobj = re.search(r'<[^>]+id="pdk-player"[^>]+data-url=["\']?(?:https?:)?//player\.theplatform\.com/p/([^/]+)/(?:[^/]+/)*select/([^?#&"\']+)', webpage)
if mobj:
account_pid, tp_path = mobj.groups()
release_pid = tp_path.strip('/').split('/')[-1]
else:
account_pid = 'HNK2IC'
tp_path = release_pid = tve['release_pid']
if tve.get('entitlement') == 'auth':
adobe_pass = settings.get('tve_adobe_auth', {})
if site == 'bravotv':
site = 'bravo'
account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
account_id = tve['data-mpx-media-account-id']
metadata = self._parse_json(
tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
video_id = tve.get('data-guid') or metadata['guid']
if tve.get('data-entitlement') == 'auth':
auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
site = remove_end(site, 'tv')
release_pid = tve['data-release-pid']
resource = self._get_mvpd_resource(
adobe_pass.get('adobePassResourceId') or site,
tve['title'], release_pid, tve.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, release_pid,
adobe_pass.get('adobePassRequestorId') or site, resource)
tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
tve['data-title'], release_pid, tve.get('data-rating'))
query.update({
'switch': 'HLSServiceSecure',
'auth': self._extract_mvpd_auth(
url, release_pid, auth.get('adobePassRequestorId') or site, resource),
})
else:
shared_playlist = settings['ls_playlist']
account_pid = shared_playlist['account_pid']
metadata = shared_playlist['video_metadata'][shared_playlist['default_clip']]
tp_path = release_pid = metadata.get('release_pid')
if not release_pid:
release_pid = metadata['guid']
tp_path = 'media/guid/2140479951/' + release_pid
info.update({
'title': metadata['title'],
'description': metadata.get('description'),
'season_number': int_or_none(metadata.get('season_num')),
'episode_number': int_or_none(metadata.get('episode_num')),
})
query['switch'] = 'progressive'
tp_url = 'http://link.theplatform.com/s/%s/%s' % (account_pid, tp_path)
ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
account_id = ls_playlist['mpxMediaAccountId']
video_id = ls_playlist['defaultGuid']
metadata = traverse_obj(
ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}),
display_id, fatal=False)
if tp_metadata:
info.update({
'title': tp_metadata.get('title'),
'description': tp_metadata.get('description'),
'duration': float_or_none(tp_metadata.get('duration'), 1000),
'season_number': int_or_none(
dict_get(tp_metadata, ('pl1$seasonNumber', 'nbcu$seasonNumber'))),
'episode_number': int_or_none(
dict_get(tp_metadata, ('pl1$episodeNumber', 'nbcu$episodeNumber'))),
# For some reason the series is sometimes wrapped into a single element array.
'series': try_get(
dict_get(tp_metadata, ('pl1$show', 'nbcu$show')),
lambda x: x[0] if isinstance(x, list) else x,
expected_type=str),
'episode': dict_get(
tp_metadata, ('pl1$episodeName', 'nbcu$episodeName', 'title')),
})
update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
info.update({
'_type': 'url_transparent',
'id': release_pid,
'url': smuggle_url(update_url_query(tp_url, query), {'force_smil_url': True}),
'ie_key': 'ThePlatform',
})
return info
seconds_or_none = lambda x: float_or_none(x, 1000)
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {seconds_or_none}),
'end_time': ('endTime', {seconds_or_none}),
}))
# prune pointless single chapters that span the entire duration from short videos
if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
chapters = None
m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
**merge_dicts(traverse_obj(tp_metadata, {
'title': 'title',
'description': 'description',
'duration': ('duration', {seconds_or_none}),
'timestamp': ('pubDate', {seconds_or_none}),
'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
}, get_all=False), traverse_obj(metadata, {
'title': 'title',
'description': 'description',
'duration': ('durationInSeconds', {int_or_none}),
'timestamp': ('airDate', {unified_timestamp}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode': 'episodeTitle',
'series': 'show',
}))
}
yt_dlp/extractor/breakcom.py
-86
View File
@@ -1,86 +0,0 @@
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
int_or_none,
url_or_none,
)
class BreakIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?break\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'info_dict': {
'id': '2468056',
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
'age_limit': 13,
},
}, {
# youtube embed
'url': 'http://www.break.com/video/someone-forgot-boat-brakes-work',
'info_dict': {
'id': 'RrrDLdeL2HQ',
'ext': 'mp4',
'title': 'Whale Watching Boat Crashing Into San Diego Dock',
'description': 'md5:afc1b2772f0a8468be51dd80eb021069',
'upload_date': '20160331',
'uploader': 'Steve Holden',
'uploader_id': 'sdholden07',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
'only_matching': True,
}]
def _real_extract(self, url):
display_id, video_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
youtube_url = YoutubeIE._extract_url(webpage)
if youtube_url:
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
content = self._parse_json(
self._search_regex(
r'(?s)content["\']\s*:\s*(\[.+?\])\s*[,\n]', webpage,
'content'),
display_id)
formats = []
for video in content:
video_url = url_or_none(video.get('url'))
if not video_url:
continue
bitrate = int_or_none(self._search_regex(
r'(\d+)_kbps', video_url, 'tbr', default=None))
formats.append({
'url': video_url,
'format_id': 'http-%d' % bitrate if bitrate else 'http',
'tbr': bitrate,
})
title = self._search_regex(
(r'title["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
r'<h1[^>]*>(?P<value>[^<]+)'), webpage, 'title', group='value')
def get(key, name):
return int_or_none(self._search_regex(
r'%s["\']\s*:\s*["\'](\d+)' % key, webpage, name,
default=None))
age_limit = get('ratings', 'age limit')
video_id = video_id or get('pid', 'video id') or display_id
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'age_limit': age_limit,
'formats': formats,
}
yt_dlp/extractor/breitbart.py
+1 -1
View File
@@ -2,7 +2,7 @@ from .common import InfoExtractor
class BreitBartIE(InfoExtractor):
_VALID_URL = r'https?:\/\/(?:www\.)breitbart.com/videos/v/(?P<id>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?breitbart\.com/videos/v/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.breitbart.com/videos/v/5cOz1yup/?pl=Ij6NDOji',
'md5': '0aa6d1d6e183ac5ca09207fe49f17ade',
yt_dlp/extractor/brightcove.py
+7 -5
View File
@@ -7,10 +7,10 @@ from .adobepass import AdobePassIE
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_parse_qs,
compat_urlparse,
)
from ..networking.exceptions import HTTPError
from ..utils import (
clean_html,
dict_get,
@@ -575,6 +575,7 @@ class BrightcoveNewBaseIE(AdobePassIE):
self.raise_no_formats(
error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
headers.pop('Authorization', None) # or else http formats will give error 400
for f in formats:
f.setdefault('http_headers', {}).update(headers)
@@ -895,8 +896,9 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
store_pk(policy_key)
return policy_key
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id)
headers = {}
token = smuggled_data.get('token')
api_url = f'https://{"edge-auth" if token else "edge"}.api.brightcove.com/playback/v1/accounts/{account_id}/{content_type}s/{video_id}'
headers = {'Authorization': f'Bearer {token}'} if token else {}
referrer = smuggled_data.get('referrer') # XXX: notice the spelling/case of the key
if referrer:
headers.update({
@@ -913,8 +915,8 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
json_data = self._download_json(api_url, video_id, headers=headers)
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
if isinstance(e.cause, HTTPError) and e.cause.status in (401, 403):
json_data = self._parse_json(e.cause.response.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)
yt_dlp/extractor/brilliantpala.py
+127
View File
@@ -0,0 +1,127 @@
import hashlib
from .common import InfoExtractor
from ..utils import (
ExtractorError,
traverse_obj,
urlencode_postdata,
)
class BrilliantpalaBaseIE(InfoExtractor):
_NETRC_MACHINE = 'brilliantpala'
_DOMAIN = '{subdomain}.brilliantpala.org'
def _initialize_pre_login(self):
self._HOMEPAGE = f'https://{self._DOMAIN}'
self._LOGIN_API = f'{self._HOMEPAGE}/login/'
self._LOGOUT_DEVICES_API = f'{self._HOMEPAGE}/logout_devices/?next=/'
self._CONTENT_API = f'{self._HOMEPAGE}/api/v2.4/contents/{{content_id}}/'
self._HLS_AES_URI = f'{self._HOMEPAGE}/api/v2.5/video_contents/{{content_id}}/key/'
def _get_logged_in_username(self, url, video_id):
webpage, urlh = self._download_webpage_handle(url, video_id)
if urlh.url.startswith(self._LOGIN_API):
self.raise_login_required()
return self._html_search_regex(
r'"username"\s*:\s*"(?P<username>[^"]+)"', webpage, 'logged-in username')
def _perform_login(self, username, password):
login_form = self._hidden_inputs(self._download_webpage(
self._LOGIN_API, None, 'Downloading login page'))
login_form.update({
'username': username,
'password': password,
})
self._set_cookie(self._DOMAIN, 'csrftoken', login_form['csrfmiddlewaretoken'])
logged_page = self._download_webpage(
self._LOGIN_API, None, note='Logging in', headers={'Referer': self._LOGIN_API},
data=urlencode_postdata(login_form))
if self._html_search_regex(
r'(Your username / email and password)', logged_page, 'auth fail', default=None):
raise ExtractorError('wrong username or password', expected=True)
# the maximum number of logins is one
if self._html_search_regex(
r'(Logout Other Devices)', logged_page, 'logout devices button', default=None):
logout_device_form = self._hidden_inputs(logged_page)
self._download_webpage(
self._LOGOUT_DEVICES_API, None, headers={'Referer': self._LOGIN_API},
note='Logging out other devices', data=urlencode_postdata(logout_device_form))
def _real_extract(self, url):
course_id, content_id = self._match_valid_url(url).group('course_id', 'content_id')
video_id = f'{course_id}-{content_id}'
username = self._get_logged_in_username(url, video_id)
content_json = self._download_json(
self._CONTENT_API.format(content_id=content_id), video_id,
note='Fetching content info', errnote='Unable to fetch content info')
entries = []
for stream in traverse_obj(content_json, ('video', 'streams', lambda _, v: v['id'] and v['url'])):
formats = self._extract_m3u8_formats(stream['url'], video_id, fatal=False)
if not formats:
continue
entries.append({
'id': str(stream['id']),
'title': content_json.get('title'),
'formats': formats,
'hls_aes': {'uri': self._HLS_AES_URI.format(content_id=content_id)},
'http_headers': {'X-Key': hashlib.sha256(username.encode('ascii')).hexdigest()},
'thumbnail': content_json.get('cover_image'),
})
return self.playlist_result(
entries, playlist_id=video_id, playlist_title=content_json.get('title'))
class BrilliantpalaElearnIE(BrilliantpalaBaseIE):
IE_NAME = 'Brilliantpala:Elearn'
IE_DESC = 'VoD on elearn.brilliantpala.org'
_VALID_URL = r'https?://elearn\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
_TESTS = [{
'url': 'https://elearn.brilliantpala.org/courses/42/contents/12345/',
'only_matching': True,
}, {
'url': 'https://elearn.brilliantpala.org/courses/98/contents/36683/',
'info_dict': {
'id': '23577',
'ext': 'mp4',
'title': 'Physical World, Units and Measurements - 1',
'thumbnail': 'https://d1j3vi2u94ebt0.cloudfront.net/institute/brilliantpalalms/chapter_contents/26237/e657f81b90874be19795c7ea081f8d5c.png',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
},
}]
_DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='elearn')
class BrilliantpalaClassesIE(BrilliantpalaBaseIE):
IE_NAME = 'Brilliantpala:Classes'
IE_DESC = 'VoD on classes.brilliantpala.org'
_VALID_URL = r'https?://classes\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
_TESTS = [{
'url': 'https://classes.brilliantpala.org/courses/42/contents/12345/',
'only_matching': True,
}, {
'url': 'https://classes.brilliantpala.org/courses/416/contents/25445/',
'info_dict': {
'id': '9128',
'ext': 'mp4',
'title': 'Motion in a Straight Line - Class 1',
'thumbnail': 'https://d3e4y8hquds3ek.cloudfront.net/institute/brilliantpalaelearn/chapter_contents/ff5ba838d0ec43419f67387fe1a01fa8.png',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
},
}]
_DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='classes')
yt_dlp/extractor/bundestag.py
+123
View File
@@ -0,0 +1,123 @@
import functools
import re
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
bug_reports_message,
clean_html,
format_field,
get_element_text_and_html_by_tag,
int_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BundestagIE(InfoExtractor):
_VALID_URL = [
r'https?://dbtg\.tv/[cf]vid/(?P<id>\d+)',
r'https?://www\.bundestag\.de/mediathek/?\?(?:[^#]+&)?videoid=(?P<id>\d+)',
]
_TESTS = [{
'url': 'https://dbtg.tv/cvid/7605304',
'info_dict': {
'id': '7605304',
'ext': 'mp4',
'title': '145. Sitzung vom 15.12.2023, TOP 24 Barrierefreiheit',
'description': 'md5:321a9dc6bdad201264c0045efc371561',
},
}, {
'url': 'https://www.bundestag.de/mediathek?videoid=7602120&url=L21lZGlhdGhla292ZXJsYXk=&mod=mediathek',
'info_dict': {
'id': '7602120',
'ext': 'mp4',
'title': '130. Sitzung vom 18.10.2023, TOP 1 Befragung der Bundesregierung',
'description': 'Befragung der Bundesregierung',
},
}, {
'url': 'https://www.bundestag.de/mediathek?videoid=7604941#url=L21lZGlhdGhla292ZXJsYXk/dmlkZW9pZD03NjA0OTQx&mod=mediathek',
'only_matching': True,
}, {
'url': 'http://dbtg.tv/fvid/3594346',
'only_matching': True,
}]
_OVERLAY_URL = 'https://www.bundestag.de/mediathekoverlay'
_INSTANCE_FORMAT = 'https://cldf-wzw-od.r53.cdn.tv1.eu/13014bundestagod/_definst_/13014bundestag/ondemand/3777parlamentsfernsehen/archiv/app144277506/145293313/{0}/{0}_playlist.smil/playlist.m3u8'
_SHARE_URL = 'https://webtv.bundestag.de/player/macros/_x_s-144277506/shareData.json?contentId='
_SHARE_AUDIO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<bitrate>\d+)kb_(?P<channels>\w+)_\w+_\d+\.(?P<ext>\w+)'
_SHARE_VIDEO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<width>\w+)_(?P<height>\w+)_(?P<bitrate>\d+)kb_\w+_\w+_\d+\.(?P<ext>\w+)'
def _bt_extract_share_formats(self, video_id):
share_data = self._download_json(
f'{self._SHARE_URL}{video_id}', video_id, note='Downloading share format JSON')
if traverse_obj(share_data, ('status', 'code', {int})) != 1:
self.report_warning(format_field(
share_data, [('status', 'message', {str})],
'Share API response: %s', default='Unknown Share API Error')
+ bug_reports_message())
return
for name, url in share_data.items():
if not isinstance(name, str) or not url_or_none(url):
continue
elif name.startswith('audio'):
match = re.search(self._SHARE_AUDIO_REGEX, url)
yield {
'format_id': name,
'url': url,
'vcodec': 'none',
**traverse_obj(match, {
'acodec': 'codec',
'audio_channels': ('channels', {{'mono': 1, 'stereo': 2}.get}),
'abr': ('bitrate', {int_or_none}),
'ext': 'ext',
}),
}
elif name.startswith('download'):
match = re.search(self._SHARE_VIDEO_REGEX, url)
yield {
'format_id': name,
'url': url,
**traverse_obj(match, {
'vcodec': 'codec',
'tbr': ('bitrate', {int_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
'ext': 'ext',
}),
}
def _real_extract(self, url):
video_id = self._match_id(url)
formats = []
result = {'id': video_id, 'formats': formats}
try:
formats.extend(self._extract_m3u8_formats(
self._INSTANCE_FORMAT.format(video_id), video_id, m3u8_id='instance'))
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 404:
raise ExtractorError('Could not find video id', expected=True)
self.report_warning(f'Error extracting hls formats: {error}', video_id)
formats.extend(self._bt_extract_share_formats(video_id))
if not formats:
self.raise_no_formats('Could not find suitable formats', video_id=video_id)
result.update(traverse_obj(self._download_webpage(
self._OVERLAY_URL, video_id,
query={'videoid': video_id, 'view': 'main'},
note='Downloading metadata overlay', fatal=False,
), {
'title': (
{functools.partial(get_element_text_and_html_by_tag, 'h3')}, 0,
{functools.partial(re.sub, r'<span[^>]*>[^<]+</span>', '')}, {clean_html}),
'description': ({functools.partial(get_element_text_and_html_by_tag, 'p')}, 0, {clean_html}),
}))
return result
yt_dlp/extractor/byutv.py
+1 -15
View File
@@ -8,9 +8,9 @@ from ..utils import (
class BYUtvIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_TESTS = [{
# ooyalaVOD
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
'info_dict': {
'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH',
@@ -24,7 +24,6 @@ class BYUtvIE(InfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
}, {
# dvr
'url': 'https://www.byutv.org/player/8f1dab9b-b243-47c8-b525-3e2d021a3451/byu-softball-pacific-vs-byu-41219---game-2',
@@ -63,19 +62,6 @@ class BYUtvIE(InfoExtractor):
'x-byutv-platformkey': 'xsaaw9c7y5',
})
ep = video.get('ooyalaVOD')
if ep:
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'display_id': display_id,
'title': ep.get('title'),
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
info = {}
formats = []
subtitles = {}
yt_dlp/extractor/cableav.py
+1 -1
View File
@@ -2,7 +2,7 @@ from .common import InfoExtractor
class CableAVIE(InfoExtractor):
_VALID_URL = r'https://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://cableav.tv/lS4iR9lWjN8/',
'md5': '7e3fe5e49d61c4233b7f5b0f69b15e18',
yt_dlp/extractor/camfm.py
+85
View File
@@ -0,0 +1,85 @@
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
get_elements_by_class,
join_nonempty,
traverse_obj,
unified_timestamp,
urljoin,
)
class CamFMShowIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?camfm\.co\.uk/shows/(?P<id>[^/]+)'
_TESTS = [{
'playlist_mincount': 5,
'url': 'https://camfm.co.uk/shows/soul-mining/',
'info_dict': {
'id': 'soul-mining',
'thumbnail': 'md5:6a873091f92c936f23bdcce80f75e66a',
'title': 'Soul Mining',
'description': 'Telling the stories of jazz, funk and soul from all corners of the world.',
},
}]
def _real_extract(self, url):
show_id = self._match_id(url)
page = self._download_webpage(url, show_id)
return {
'_type': 'playlist',
'id': show_id,
'entries': [self.url_result(urljoin('https://camfm.co.uk', i), CamFMEpisodeIE)
for i in re.findall(r"javascript:popup\('(/player/[^']+)', 'listen'", page)],
'thumbnail': urljoin('https://camfm.co.uk', self._search_regex(
r'<img[^>]+class="thumb-expand"[^>]+src="([^"]+)"', page, 'thumbnail', fatal=False)),
'title': self._html_search_regex('<h1>([^<]+)</h1>', page, 'title', fatal=False),
'description': clean_html(get_element_by_class('small-12 medium-8 cell', page))
}
class CamFMEpisodeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?camfm\.co\.uk/player/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://camfm.co.uk/player/43336',
'skip': 'Episode will expire - don\'t actually know when, but it will go eventually',
'info_dict': {
'id': '43336',
'title': 'AITAA: Am I the Agony Aunt? - 19:00 Tue 16/05/2023',
'ext': 'mp3',
'upload_date': '20230516',
'description': 'md5:f165144f94927c0f1bfa2ee6e6ab7bbf',
'timestamp': 1684263600,
'series': 'AITAA: Am I the Agony Aunt?',
'thumbnail': 'md5:5980a831360d0744c3764551be3d09c1',
'categories': ['Entertainment'],
}
}]
def _real_extract(self, url):
episode_id = self._match_id(url)
page = self._download_webpage(url, episode_id)
audios = self._parse_html5_media_entries('https://audio.camfm.co.uk', page, episode_id)
caption = get_element_by_class('caption', page)
series = clean_html(re.sub(r'<span[^<]+<[^<]+>', '', caption))
card_section = get_element_by_class('card-section', page)
date = self._html_search_regex('>Aired at ([^<]+)<', card_section, 'air date', fatal=False)
return {
'id': episode_id,
'title': join_nonempty(series, date, delim=' - '),
'formats': traverse_obj(audios, (..., 'formats', ...)),
'timestamp': unified_timestamp(date), # XXX: Does not account for UK's daylight savings
'series': series,
'description': clean_html(re.sub(r'<b>[^<]+</b><br[^>]+/>', '', card_section)),
'thumbnail': urljoin('https://camfm.co.uk', self._search_regex(
r'<div[^>]+class="cover-art"[^>]+style="[^"]+url\(\'([^\']+)',
page, 'thumbnail', fatal=False)),
'categories': get_elements_by_class('label', caption),
'was_live': True,
}
yt_dlp/extractor/camwithher.py
-87
View File
@@ -1,87 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
unified_strdate,
)
class CamWithHerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P<id>\w+)'
_TESTS = [{
'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=',
'info_dict': {
'id': '5644',
'ext': 'flv',
'title': 'Periscope Tease',
'description': 'In the clouds teasing on periscope to my favorite song',
'duration': 240,
'view_count': int,
'comment_count': int,
'uploader': 'MileenaK',
'upload_date': '20160322',
'age_limit': 18,
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937',
'only_matching': True,
}, {
'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=',
'only_matching': True,
}, {
'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
flv_id = self._html_search_regex(
r'<a[^>]+href=["\']/download/\?v=(\d+)', webpage, 'video id')
# Video URL construction algorithm is reverse-engineered from cwhplayer.swf
rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % (
('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id)
title = self._html_search_regex(
r'<div[^>]+style="float:left"[^>]*>\s*<h2>(.+?)</h2>', webpage, 'title')
description = self._html_search_regex(
r'>Description:</span>(.+?)</div>', webpage, 'description', default=None)
runtime = self._search_regex(
r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None)
if runtime:
runtime = re.sub(r'[\s-]', '', runtime)
duration = parse_duration(runtime)
view_count = int_or_none(self._search_regex(
r'Views\s*:\s*(\d+)', webpage, 'view count', default=None))
comment_count = int_or_none(self._search_regex(
r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None))
uploader = self._search_regex(
r'Added by\s*:\s*<a[^>]+>([^<]+)</a>', webpage, 'uploader', default=None)
upload_date = unified_strdate(self._search_regex(
r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None))
return {
'id': flv_id,
'url': rtmp_url,
'ext': 'flv',
'no_resume': True,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
'uploader': uploader,
'upload_date': upload_date,
'age_limit': 18
}
yt_dlp/extractor/canal1.py
+39
View File
@@ -0,0 +1,39 @@
from .common import InfoExtractor
class Canal1IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|noticias\.)?canal1\.com\.co/(?:[^?#&])+/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://canal1.com.co/noticias/napa-i-una-cadena-de-produccion-de-arroz-que-se-quedo-en-veremos-y-abandonada-en-el-departamento-del-choco/',
'info_dict': {
'id': '63b39f6b354977084b85ab54',
'display_id': 'napa-i-una-cadena-de-produccion-de-arroz-que-se-quedo-en-veremos-y-abandonada-en-el-departamento-del-choco',
'title': 'Ñapa I Una cadena de producción de arroz que se quedó en veremos y abandonada en el departamento del Chocó',
'description': 'md5:bc49c6d64d20610ea1e7daf079a0d013',
'thumbnail': r're:^https?://[^?#]+63b39f6b354977084b85ab54',
'ext': 'mp4',
},
}, {
'url': 'https://noticias.canal1.com.co/noticias/tres-i-el-triste-record-que-impuso-elon-musk-el-dueno-de-tesla-y-de-twitter/',
'info_dict': {
'id': '63b39e93f5fd223aa32250fb',
'display_id': 'tres-i-el-triste-record-que-impuso-elon-musk-el-dueno-de-tesla-y-de-twitter',
'title': 'Tres I El triste récord que impuso Elon Musk, el dueño de Tesla y de Twitter',
'description': 'md5:d9f691f131a21ce6767ca6c05d17d791',
'thumbnail': r're:^https?://[^?#]+63b39e93f5fd223aa32250fb',
'ext': 'mp4',
},
}, {
# Geo-restricted to Colombia
'url': 'https://canal1.com.co/programas/guerreros-canal-1/video-inedito-guerreros-despedida-kewin-zarate/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
return self.url_result(
self._search_regex(r'"embedUrl"\s*:\s*"([^"]+)', webpage, 'embed url'),
display_id=display_id, url_transparent=True)
yt_dlp/extractor/canalplus.py
+1 -1
View File
@@ -64,7 +64,7 @@ class CanalplusIE(InfoExtractor):
# response = self._request_webpage(
# HEADRequest(fmt_url), video_id,
# 'Checking if the video is georestricted')
# if '/blocage' in response.geturl():
# if '/blocage' in response.url:
# raise ExtractorError(
# 'The video is not available in your country',
# expected=True)
yt_dlp/extractor/canvas.py
-383
View File
@@ -1,383 +0,0 @@
import json
from .common import InfoExtractor
from .gigya import GigyaBaseIE
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
float_or_none,
get_element_by_class,
int_or_none,
merge_dicts,
str_or_none,
strip_or_none,
url_or_none,
urlencode_postdata
)
class CanvasIE(InfoExtractor):
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
'info_dict': {
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'ext': 'mp4',
'title': 'Nachtwacht: De Greystook',
'description': 'Nachtwacht: De Greystook',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1468.02,
},
'expected_warnings': ['is not a supported codec'],
}, {
'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'only_matching': True,
}]
_GEO_BYPASS = False
_HLS_ENTRY_PROTOCOLS_MAP = {
'HLS': 'm3u8_native',
'HLS_AES': 'm3u8_native',
}
_REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v2'
def _real_extract(self, url):
mobj = self._match_valid_url(url)
site_id, video_id = mobj.group('site_id'), mobj.group('id')
data = None
if site_id != 'vrtvideo':
# Old API endpoint, serves more formats but may fail for some videos
data = self._download_json(
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
% (site_id, video_id), video_id, 'Downloading asset JSON',
'Unable to download asset JSON', fatal=False)
# New API endpoint
if not data:
vrtnutoken = self._download_json('https://token.vrt.be/refreshtoken',
video_id, note='refreshtoken: Retrieve vrtnutoken',
errnote='refreshtoken failed')['vrtnutoken']
headers = self.geo_verification_headers()
headers.update({'Content-Type': 'application/json; charset=utf-8'})
vrtPlayerToken = self._download_json(
'%s/tokens' % self._REST_API_BASE, video_id,
'Downloading token', headers=headers, data=json.dumps({
'identityToken': vrtnutoken
}).encode('utf-8'))['vrtPlayerToken']
data = self._download_json(
'%s/videos/%s' % (self._REST_API_BASE, video_id),
video_id, 'Downloading video JSON', query={
'vrtPlayerToken': vrtPlayerToken,
'client': 'null',
}, expected_status=400)
if 'title' not in data:
code = data.get('code')
if code == 'AUTHENTICATION_REQUIRED':
self.raise_login_required()
elif code == 'INVALID_LOCATION':
self.raise_geo_restricted(countries=['BE'])
raise ExtractorError(data.get('message') or code, expected=True)
# Note: The title may be an empty string
title = data['title'] or f'{site_id} {video_id}'
description = data.get('description')
formats = []
subtitles = {}
for target in data['targetUrls']:
format_url, format_type = url_or_none(target.get('url')), str_or_none(target.get('type'))
if not format_url or not format_type:
continue
format_type = format_type.upper()
if format_type in self._HLS_ENTRY_PROTOCOLS_MAP:
fmts, subs = self._extract_m3u8_formats_and_subtitles(
format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type],
m3u8_id=format_type, fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
elif format_type == 'HDS':
formats.extend(self._extract_f4m_formats(
format_url, video_id, f4m_id=format_type, fatal=False))
elif format_type == 'MPEG_DASH':
fmts, subs = self._extract_mpd_formats_and_subtitles(
format_url, video_id, mpd_id=format_type, fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
elif format_type == 'HSS':
fmts, subs = self._extract_ism_formats_and_subtitles(
format_url, video_id, ism_id='mss', fatal=False)
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
else:
formats.append({
'format_id': format_type,
'url': format_url,
})
subtitle_urls = data.get('subtitleUrls')
if isinstance(subtitle_urls, list):
for subtitle in subtitle_urls:
subtitle_url = subtitle.get('url')
if subtitle_url and subtitle.get('type') == 'CLOSED':
subtitles.setdefault('nl', []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': video_id,
'title': title,
'description': description,
'formats': formats,
'duration': float_or_none(data.get('duration'), 1000),
'thumbnail': data.get('posterImageUrl'),
'subtitles': subtitles,
}
class CanvasEenIE(InfoExtractor):
IE_DESC = 'canvas.be and een.be'
_VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
'md5': 'ed66976748d12350b118455979cca293',
'info_dict': {
'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'display_id': 'de-afspraak-veilt-voor-de-warmste-week',
'ext': 'flv',
'title': 'De afspraak veilt voor de Warmste Week',
'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 49.02,
},
'expected_warnings': ['is not a supported codec'],
}, {
# with subtitles
'url': 'http://www.canvas.be/video/panorama/2016/pieter-0167',
'info_dict': {
'id': 'mz-ast-5240ff21-2d30-4101-bba6-92b5ec67c625',
'display_id': 'pieter-0167',
'ext': 'mp4',
'title': 'Pieter 0167',
'description': 'md5:943cd30f48a5d29ba02c3a104dc4ec4e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2553.08,
'subtitles': {
'nl': [{
'ext': 'vtt',
}],
},
},
'params': {
'skip_download': True,
},
'skip': 'Pagina niet gevonden',
}, {
'url': 'https://www.een.be/thuis/emma-pakt-thilly-aan',
'info_dict': {
'id': 'md-ast-3a24ced2-64d7-44fb-b4ed-ed1aafbf90b8',
'display_id': 'emma-pakt-thilly-aan',
'ext': 'mp4',
'title': 'Emma pakt Thilly aan',
'description': 'md5:c5c9b572388a99b2690030afa3f3bad7',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 118.24,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['is not a supported codec'],
}, {
'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
site_id, display_id = mobj.group('site_id'), mobj.group('id')
webpage = self._download_webpage(url, display_id)
title = strip_or_none(self._search_regex(
r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None))
video_id = self._html_search_regex(
r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
group='id')
return {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/%s/assets/%s' % (site_id, video_id),
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
}
class VrtNUIE(GigyaBaseIE):
IE_DESC = 'VrtNU.be'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
_TESTS = [{
# Available via old API endpoint
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/',
'info_dict': {
'id': 'pbs-pub-e8713dac-899e-41de-9313-81269f4c04ac$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
'ext': 'mp4',
'title': 'Postbus X - Aflevering 1 (Seizoen 1989)',
'description': 'md5:b704f669eb9262da4c55b33d7c6ed4b7',
'duration': 1457.04,
'thumbnail': r're:^https?://.*\.jpg$',
'series': 'Postbus X',
'season': 'Seizoen 1989',
'season_number': 1989,
'episode': 'De zwarte weduwe',
'episode_number': 1,
'timestamp': 1595822400,
'upload_date': '20200727',
},
'skip': 'This video is only available for registered users',
'expected_warnings': ['is not a supported codec'],
}, {
# Only available via new API endpoint
'url': 'https://www.vrt.be/vrtnu/a-z/kamp-waes/1/kamp-waes-s1a5/',
'info_dict': {
'id': 'pbs-pub-0763b56c-64fb-4d38-b95b-af60bf433c71$vid-ad36a73c-4735-4f1f-b2c0-a38e6e6aa7e1',
'ext': 'mp4',
'title': 'Aflevering 5',
'description': 'Wie valt door de mand tijdens een missie?',
'duration': 2967.06,
'season': 'Season 1',
'season_number': 1,
'episode_number': 5,
},
'skip': 'This video is only available for registered users',
'expected_warnings': ['Unable to download asset JSON', 'is not a supported codec', 'Unknown MIME type'],
}]
_NETRC_MACHINE = 'vrtnu'
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
_CONTEXT_ID = 'R3595707040'
def _perform_login(self, username, password):
auth_info = self._gigya_login({
'APIKey': self._APIKEY,
'targetEnv': 'jssdk',
'loginID': username,
'password': password,
'authMode': 'cookie',
})
if auth_info.get('errorDetails'):
raise ExtractorError('Unable to login: VrtNU said: ' + auth_info.get('errorDetails'), expected=True)
# Sometimes authentication fails for no good reason, retry
login_attempt = 1
while login_attempt <= 3:
try:
self._request_webpage('https://token.vrt.be/vrtnuinitlogin',
None, note='Requesting XSRF Token', errnote='Could not get XSRF Token',
query={'provider': 'site', 'destination': 'https://www.vrt.be/vrtnu/'})
post_data = {
'UID': auth_info['UID'],
'UIDSignature': auth_info['UIDSignature'],
'signatureTimestamp': auth_info['signatureTimestamp'],
'_csrf': self._get_cookies('https://login.vrt.be').get('OIDCXSRF').value,
}
self._request_webpage(
'https://login.vrt.be/perform_login',
None, note='Performing login', errnote='perform login failed',
headers={}, query={
'client_id': 'vrtnu-site'
}, data=urlencode_postdata(post_data))
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
login_attempt += 1
self.report_warning('Authentication failed')
self._sleep(1, None, msg_template='Waiting for %(timeout)s seconds before trying again')
else:
raise e
else:
break
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
attrs = extract_attributes(self._search_regex(
r'(<nui-media[^>]+>)', webpage, 'media element'))
video_id = attrs['videoid']
publication_id = attrs.get('publicationid')
if publication_id:
video_id = publication_id + '$' + video_id
page = (self._parse_json(self._search_regex(
r'digitalData\s*=\s*({.+?});', webpage, 'digial data',
default='{}'), video_id, fatal=False) or {}).get('page') or {}
info = self._search_json_ld(webpage, display_id, default={})
return merge_dicts(info, {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'season_number': int_or_none(page.get('episode_season')),
})
class DagelijkseKostIE(InfoExtractor):
IE_DESC = 'dagelijksekost.een.be'
_VALID_URL = r'https?://dagelijksekost\.een\.be/gerechten/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://dagelijksekost.een.be/gerechten/hachis-parmentier-met-witloof',
'md5': '30bfffc323009a3e5f689bef6efa2365',
'info_dict': {
'id': 'md-ast-27a4d1ff-7d7b-425e-b84f-a4d227f592fa',
'display_id': 'hachis-parmentier-met-witloof',
'ext': 'mp4',
'title': 'Hachis parmentier met witloof',
'description': 'md5:9960478392d87f63567b5b117688cdc5',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 283.02,
},
'expected_warnings': ['is not a supported codec'],
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = strip_or_none(get_element_by_class(
'dish-metadata__title', webpage
) or self._html_search_meta(
'twitter:title', webpage))
description = clean_html(get_element_by_class(
'dish-description', webpage)
) or self._html_search_meta(
('description', 'twitter:description', 'og:description'),
webpage)
video_id = self._html_search_regex(
r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
group='id')
return {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
}
yt_dlp/extractor/caracoltv.py
+136
View File
@@ -0,0 +1,136 @@
import base64
import json
import uuid
from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
traverse_obj,
urljoin,
)
class CaracolTvPlayIE(InfoExtractor):
_VALID_URL = r'https?://play\.caracoltv\.com/videoDetails/(?P<id>[^/?#]+)'
_NETRC_MACHINE = 'caracoltv-play'
_TESTS = [{
'url': 'https://play.caracoltv.com/videoDetails/OTo4NGFmNjUwOWQ2ZmM0NTg2YWRiOWU0MGNhOWViOWJkYQ==',
'info_dict': {
'id': 'OTo4NGFmNjUwOWQ2ZmM0NTg2YWRiOWU0MGNhOWViOWJkYQ==',
'title': 'La teoría del promedio',
'description': 'md5:1cdd6d2c13f19ef0d9649ab81a023ac3',
},
'playlist_count': 6,
}, {
'url': 'https://play.caracoltv.com/videoDetails/OTo3OWM4ZTliYzQxMmM0MTMxYTk4Mjk2YjdjNGQ4NGRkOQ==/ella?season=0',
'info_dict': {
'id': 'OTo3OWM4ZTliYzQxMmM0MTMxYTk4Mjk2YjdjNGQ4NGRkOQ==',
'title': 'Ella',
'description': 'md5:a639b1feb5ddcc0cff92a489b4e544b8',
},
'playlist_count': 10,
}, {
'url': 'https://play.caracoltv.com/videoDetails/OTpiYTY1YTVmOTI5MzI0ZWJhOGZiY2Y3MmRlOWZlYmJkOA==/la-vuelta-al-mundo-en-80-risas-2022?season=0',
'info_dict': {
'id': 'OTpiYTY1YTVmOTI5MzI0ZWJhOGZiY2Y3MmRlOWZlYmJkOA==',
'title': 'La vuelta al mundo en 80 risas 2022',
'description': 'md5:e97aac36106e5c37ebf947b3350106a4',
},
'playlist_count': 17,
}, {
'url': 'https://play.caracoltv.com/videoDetails/MzoxX3BwbjRmNjB1',
'only_matching': True,
}]
_USER_TOKEN = None
def _extract_app_token(self, webpage):
config_js_path = self._search_regex(
r'<script[^>]+src\s*=\s*"([^"]+coreConfig.js[^"]+)', webpage, 'config js url', fatal=False)
mediation_config = {} if not config_js_path else self._search_json(
r'mediation\s*:', self._download_webpage(
urljoin('https://play.caracoltv.com/', config_js_path), None, fatal=False, note='Extracting JS config'),
'mediation_config', None, transform_source=js_to_json, fatal=False)
key = traverse_obj(
mediation_config, ('live', 'key')) or '795cd9c089a1fc48094524a5eba85a3fca1331817c802f601735907c8bbb4f50'
secret = traverse_obj(
mediation_config, ('live', 'secret')) or '64dec00a6989ba83d087621465b5e5d38bdac22033b0613b659c442c78976fa0'
return base64.b64encode(f'{key}:{secret}'.encode()).decode()
def _perform_login(self, email, password):
webpage = self._download_webpage('https://play.caracoltv.com/', None, fatal=False)
app_token = self._extract_app_token(webpage)
bearer_token = self._download_json(
'https://eu-gateway.inmobly.com/applications/oauth', None, data=b'', note='Retrieving bearer token',
headers={'Authorization': f'Basic {app_token}'})['token']
self._USER_TOKEN = self._download_json(
'https://eu-gateway.inmobly.com/user/login', None, note='Performing login', headers={
'Content-Type': 'application/json',
'Authorization': f'Bearer {bearer_token}',
}, data=json.dumps({
'device_data': {
'device_id': str(uuid.uuid4()),
'device_token': '',
'device_type': 'web'
},
'login_data': {
'enabled': True,
'email': email,
'password': password,
}
}).encode())['user_token']
def _extract_video(self, video_data, series_id=None, season_id=None, season_number=None):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_data['stream_url'], series_id, 'mp4')
return {
'id': video_data['id'],
'title': video_data.get('name'),
'description': video_data.get('description'),
'formats': formats,
'subtitles': subtitles,
'thumbnails': traverse_obj(
video_data, ('extra_thumbs', ..., {'url': 'thumb_url', 'height': 'height', 'width': 'width'})),
'series_id': series_id,
'season_id': season_id,
'season_number': int_or_none(season_number),
'episode_number': int_or_none(video_data.get('item_order')),
'is_live': video_data.get('entry_type') == 3,
}
def _extract_series_seasons(self, seasons, series_id):
for season in seasons:
api_response = self._download_json(
'https://eu-gateway.inmobly.com/feed', series_id, query={'season_id': season['id']},
headers={'Authorization': f'Bearer {self._USER_TOKEN}'})
season_number = season.get('order')
for episode in api_response['items']:
yield self._extract_video(episode, series_id, season['id'], season_number)
def _real_extract(self, url):
series_id = self._match_id(url)
if self._USER_TOKEN is None:
self._perform_login('guest@inmobly.com', 'Test@gus1')
api_response = self._download_json(
'https://eu-gateway.inmobly.com/feed', series_id, query={'include_ids': series_id},
headers={'Authorization': f'Bearer {self._USER_TOKEN}'})['items'][0]
if not api_response.get('seasons'):
return self._extract_video(api_response)
return self.playlist_result(
self._extract_series_seasons(api_response['seasons'], series_id),
series_id, **traverse_obj(api_response, {
'title': 'name',
'description': 'description',
}))
yt_dlp/extractor/carambatv.py
-105
View File
@@ -1,105 +0,0 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
format_field,
float_or_none,
int_or_none,
try_get,
)
from .videomore import VideomoreIE
class CarambaTVIE(InfoExtractor):
_VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
_TESTS = [{
'url': 'http://video1.carambatv.ru/v/191910501',
'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
'info_dict': {
'id': '191910501',
'ext': 'mp4',
'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 2678.31,
},
}, {
'url': 'carambatv:191910501',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
video_id)
title = video['title']
base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
formats = [{
'url': base_url + f['fn'],
'height': int_or_none(f.get('height')),
'format_id': format_field(f, 'height', '%sp'),
} for f in video['qualities'] if f.get('fn')]
thumbnail = video.get('splash')
duration = float_or_none(try_get(
video, lambda x: x['annotations'][0]['end_time'], compat_str))
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}
class CarambaTVPageIE(InfoExtractor):
_VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
'md5': 'a49fb0ec2ad66503eeb46aac237d3c86',
'info_dict': {
'id': '475222',
'ext': 'flv',
'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
'thumbnail': r're:^https?://.*\.jpg',
# duration reported by videomore is incorrect
'duration': int,
},
'add_ie': [VideomoreIE.ie_key()],
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
videomore_url = VideomoreIE._extract_url(webpage)
if not videomore_url:
videomore_id = self._search_regex(
r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
default=None)
if videomore_id:
videomore_url = 'videomore:%s' % videomore_id
if videomore_url:
title = self._og_search_title(webpage)
return {
'_type': 'url_transparent',
'url': videomore_url,
'ie_key': VideomoreIE.ie_key(),
'title': title,
}
video_url = self._og_search_property('video:iframe', webpage, default=None)
if not video_url:
video_id = self._search_regex(
r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
webpage, 'video id')
video_url = 'carambatv:%s' % video_id
return self.url_result(video_url, CarambaTVIE.ie_key())
yt_dlp/extractor/cbc.py
+245 -52
View File
@@ -1,21 +1,25 @@
import re
import json
import base64
import json
import re
import time
import urllib.parse
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
ExtractorError,
int_or_none,
join_nonempty,
js_to_json,
orderedSet,
parse_iso8601,
smuggle_url,
strip_or_none,
traverse_obj,
try_get,
ExtractorError,
)
@@ -63,6 +67,7 @@ class CBCIE(InfoExtractor):
'uploader': 'CBCC-NEW',
'timestamp': 255977160,
},
'skip': '404 Not Found',
}, {
# multiple iframes
'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot',
@@ -94,7 +99,7 @@ class CBCIE(InfoExtractor):
# multiple CBC.APP.Caffeine.initInstance(...)
'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
'info_dict': {
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks', # FIXME
'id': 'dog-indoor-exercise-winter-1.3928238',
'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
},
@@ -146,7 +151,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
'md5': '64d25f841ddf4ddb28a235338af32e2c',
@@ -159,22 +164,31 @@ class CBCPlayerIE(InfoExtractor):
'upload_date': '20160210',
'uploader': 'CBCC-NEW',
},
'skip': 'Geo-restricted to Canada',
'skip': 'Geo-restricted to Canada and no longer available',
}, {
# Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
'url': 'http://www.cbc.ca/player/play/2657631896',
'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2657631896',
'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
'info_dict': {
'id': '2657631896',
'ext': 'mp3',
'title': 'CBC Montreal is organizing its first ever community hackathon!',
'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
'description': 'md5:dd3b692f0a139b0369943150bd1c46a9',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
},
}, {
'url': 'http://www.cbc.ca/player/play/2164402062',
'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
@@ -184,11 +198,104 @@ class CBCPlayerIE(InfoExtractor):
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'media_type': 'Excerpt',
},
}, {
# Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
'url': 'https://www.cbc.ca/player/play/1.2985700',
'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
'info_dict': {
'id': '2657631896',
'ext': 'mp3',
'title': 'CBC Montreal is organizing its first ever community hackathon!',
'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
},
}, {
'url': 'https://www.cbc.ca/player/play/1.1711287',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'ext': 'mp4',
'title': 'Cancer survivor four times over',
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'media_type': 'Excerpt',
},
}, {
# Has subtitles
# These broadcasts expire after ~1 month, can find new test URL here:
# https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
'url': 'https://www.cbc.ca/player/play/1.7159484',
'md5': '6ed6cd0fc2ef568d2297ba68a763d455',
'info_dict': {
'id': '2324213316001',
'ext': 'mp4',
'title': 'The National | School boards sue social media giants',
'description': 'md5:4b4db69322fa32186c3ce426da07402c',
'timestamp': 1711681200,
'duration': 2743.400,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg',
'uploader': 'CBCC-NEW',
'chapters': 'count:5',
'upload_date': '20240329',
'categories': 'count:4',
'series': 'The National - Full Show',
'tags': 'count:1',
'creators': ['News'],
'location': 'Canada',
'media_type': 'Full Program',
},
}, {
'url': 'cbcplayer:1.7159484',
'only_matching': True,
}, {
'url': 'cbcplayer:2164402062',
'only_matching': True,
}, {
'url': 'http://www.cbc.ca/player/play/2657631896',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
if '.' in video_id:
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
video_id = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage,
'initial state', video_id)['video']['currentClip']['mediaId']
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
@@ -197,12 +304,45 @@ class CBCPlayerIE(InfoExtractor):
'force_smil_url': True
}),
'id': video_id,
'_format_sort_fields': ('res', 'proto') # Prioritize direct http formats over HLS
}
class CBCPlayerPlaylistIE(InfoExtractor):
IE_NAME = 'cbc.ca:player:playlist'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:player/)(?!play/)(?P<id>[^?#]+)'
_TESTS = [{
'url': 'https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast',
'playlist_mincount': 25,
'info_dict': {
'id': 'news/tv shows/the national/latest broadcast',
}
}, {
'url': 'https://www.cbc.ca/player/news/Canada/North',
'playlist_mincount': 25,
'info_dict': {
'id': 'news/canada/north',
}
}]
def _real_extract(self, url):
playlist_id = urllib.parse.unquote(self._match_id(url)).lower()
webpage = self._download_webpage(url, playlist_id)
json_content = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', playlist_id)
def entries():
for video_id in traverse_obj(json_content, (
'video', 'clipsByCategory', lambda k, _: k.lower() == playlist_id, 'items', ..., 'id'
)):
yield self.url_result(f'https://www.cbc.ca/player/play/{video_id}', CBCPlayerIE)
return self.playlist_result(entries(), playlist_id)
class CBCGemIE(InfoExtractor):
IE_NAME = 'gem.cbc.ca'
_VALID_URL = r'https?://gem\.cbc\.ca/media/(?P<id>[0-9a-z-]+/s[0-9]+[a-z][0-9]+)'
_VALID_URL = r'https?://gem\.cbc\.ca/(?:media/)?(?P<id>[0-9a-z-]+/s[0-9]+[a-z][0-9]+)'
_TESTS = [{
# This is a normal, public, TV show video
'url': 'https://gem.cbc.ca/media/schitts-creek/s06e01',
@@ -245,6 +385,9 @@ class CBCGemIE(InfoExtractor):
},
'params': {'format': 'bv'},
'skip': 'Geo-restricted to Canada',
}, {
'url': 'https://gem.cbc.ca/nadiyas-family-favourites/s01e01',
'only_matching': True,
}]
_GEO_COUNTRIES = ['CA']
@@ -275,12 +418,12 @@ class CBCGemIE(InfoExtractor):
data = json.dumps({'jwt': sig}).encode()
headers = {'content-type': 'application/json', 'ott-device-type': 'web'}
resp = self._download_json('https://services.radio-canada.ca/ott/cbc-api/v2/token',
None, data=data, headers=headers)
None, data=data, headers=headers, expected_status=426)
cbc_access_token = resp['accessToken']
headers = {'content-type': 'application/json', 'ott-device-type': 'web', 'ott-access-token': cbc_access_token}
resp = self._download_json('https://services.radio-canada.ca/ott/cbc-api/v2/profile',
None, headers=headers)
None, headers=headers, expected_status=426)
return resp['claimsToken']
def _get_claims_token_expiry(self):
@@ -322,7 +465,7 @@ class CBCGemIE(InfoExtractor):
url = re.sub(r'(Manifest\(.*?),format=[\w-]+(.*?\))', r'\1\2', base_url)
secret_xml = self._download_xml(url, video_id, note='Downloading secret XML', fatal=False)
if not secret_xml:
if not isinstance(secret_xml, xml.etree.ElementTree.Element):
return
for child in secret_xml:
@@ -346,7 +489,9 @@ class CBCGemIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._download_json('https://services.radio-canada.ca/ott/cbc-api/v2/assets/' + video_id, video_id)
video_info = self._download_json(
f'https://services.radio-canada.ca/ott/cbc-api/v2/assets/{video_id}',
video_id, expected_status=426)
email, password = self._get_login_info()
if email and password:
@@ -401,7 +546,7 @@ class CBCGemIE(InfoExtractor):
class CBCGemPlaylistIE(InfoExtractor):
IE_NAME = 'gem.cbc.ca:playlist'
_VALID_URL = r'https?://gem\.cbc\.ca/media/(?P<id>(?P<show>[0-9a-z-]+)/s(?P<season>[0-9]+))/?(?:[?#]|$)'
_VALID_URL = r'https?://gem\.cbc\.ca/(?:media/)?(?P<id>(?P<show>[0-9a-z-]+)/s(?P<season>[0-9]+))/?(?:[?#]|$)'
_TESTS = [{
# TV show playlist, all public videos
'url': 'https://gem.cbc.ca/media/schitts-creek/s06',
@@ -410,7 +555,14 @@ class CBCGemPlaylistIE(InfoExtractor):
'id': 'schitts-creek/s06',
'title': 'Season 6',
'description': 'md5:6a92104a56cbeb5818cc47884d4326a2',
'series': 'Schitt\'s Creek',
'season_number': 6,
'season': 'Season 6',
'thumbnail': 'https://images.radio-canada.ca/v1/synps-cbc/season/perso/cbc_schitts_creek_season_06_carousel_v03.jpg?impolicy=ott&im=Resize=(_Size_)&quality=75',
},
}, {
'url': 'https://gem.cbc.ca/schitts-creek/s06',
'only_matching': True,
}]
_API_BASE = 'https://services.radio-canada.ca/ott/cbc-api/v2/shows/'
@@ -418,7 +570,7 @@ class CBCGemPlaylistIE(InfoExtractor):
match = self._match_valid_url(url)
season_id = match.group('id')
show = match.group('show')
show_info = self._download_json(self._API_BASE + show, season_id)
show_info = self._download_json(self._API_BASE + show, season_id, expected_status=426)
season = int(match.group('season'))
season_info = next((s for s in show_info['seasons'] if s.get('season') == season), None)
@@ -470,49 +622,90 @@ class CBCGemPlaylistIE(InfoExtractor):
class CBCGemLiveIE(InfoExtractor):
IE_NAME = 'gem.cbc.ca:live'
_VALID_URL = r'https?://gem\.cbc\.ca/live/(?P<id>\d+)'
_TEST = {
'url': 'https://gem.cbc.ca/live/920604739687',
'info_dict': {
'title': 'Ottawa',
'description': 'The live TV channel and local programming from Ottawa',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
'is_live': True,
'id': 'AyqZwxRqh8EH',
'ext': 'mp4',
'timestamp': 1492106160,
'upload_date': '20170413',
'uploader': 'CBCC-NEW',
_VALID_URL = r'https?://gem\.cbc\.ca/live(?:-event)?/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://gem.cbc.ca/live/920604739687',
'info_dict': {
'title': 'Ottawa',
'description': 'The live TV channel and local programming from Ottawa',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
'is_live': True,
'id': 'AyqZwxRqh8EH',
'ext': 'mp4',
'timestamp': 1492106160,
'upload_date': '20170413',
'uploader': 'CBCC-NEW',
},
'skip': 'Live might have ended',
},
'skip': 'Live might have ended',
}
# It's unclear where the chars at the end come from, but they appear to be
# constant. Might need updating in the future.
# There are two URLs, some livestreams are in one, and some
# in the other. The JSON schema is the same for both.
_API_URLS = ['https://tpfeed.cbc.ca/f/ExhSPC/t_t3UKJR6MAT', 'https://tpfeed.cbc.ca/f/ExhSPC/FNiv9xQx_BnT']
{
'url': 'https://gem.cbc.ca/live/44',
'info_dict': {
'id': '44',
'ext': 'mp4',
'is_live': True,
'title': r're:^Ottawa [0-9\-: ]+',
'description': 'The live TV channel and local programming from Ottawa',
'live_status': 'is_live',
'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*'
},
'params': {'skip_download': True},
'skip': 'Live might have ended',
},
{
'url': 'https://gem.cbc.ca/live-event/10835',
'info_dict': {
'id': '10835',
'ext': 'mp4',
'is_live': True,
'title': r're:^The National \| Biden’s trip wraps up, Paltrow testifies, Bird flu [0-9\-: ]+',
'description': 'March 24, 2023 | President Biden’s Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
'live_status': 'is_live',
'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
'timestamp': 1679706000,
'upload_date': '20230325',
},
'params': {'skip_download': True},
'skip': 'Live might have ended',
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
for api_url in self._API_URLS:
video_info = next((
stream for stream in self._download_json(api_url, video_id)['entries']
if stream.get('guid') == video_id), None)
if video_info:
break
else:
# Two types of metadata JSON
if not video_info.get('formattedIdMedia'):
video_info = traverse_obj(
video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
get_all=False, default={})
video_stream_id = video_info.get('formattedIdMedia')
if not video_stream_id:
raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
stream_data = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
'appCode': 'mpx',
'connectionType': 'hd',
'deviceType': 'ipad',
'idMedia': video_stream_id,
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestType': 'desktop',
})
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': video_info['content'][0]['url'],
'id': video_id,
'title': video_info.get('title'),
'description': video_info.get('description'),
'tags': try_get(video_info, lambda x: x['keywords'].split(', ')),
'thumbnail': video_info.get('cbc$staticImage'),
'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
'is_live': True,
**traverse_obj(video_info, {
'title': 'title',
'description': 'description',
'thumbnail': ('images', 'card', 'url'),
'timestamp': ('airDate', {parse_iso8601}),
})
}
yt_dlp/extractor/cbs.py
+116
View File
@@ -1,8 +1,14 @@
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from .theplatform import ThePlatformFeedIE
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
extract_attributes,
get_element_html_by_id,
int_or_none,
find_xpath_attr,
smuggle_url,
xpath_element,
xpath_text,
update_url_query,
@@ -70,6 +76,7 @@ class CBSBaseIE(ThePlatformFeedIE): # XXX: Do not subclass from concrete IE
class CBSIE(CBSBaseIE):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
cbs:|
@@ -95,6 +102,7 @@ class CBSIE(CBSBaseIE):
# m3u8 download
'skip_download': True,
},
'skip': 'Subscription required',
}, {
'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
'info_dict': {
@@ -111,6 +119,7 @@ class CBSIE(CBSBaseIE):
},
'expected_warnings': [
'This content expired on', 'No video formats found', 'Requested format is not available'],
'skip': '404 Not Found',
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
'only_matching': True,
@@ -162,3 +171,110 @@ class CBSIE(CBSBaseIE):
'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
})
class ParamountPressExpressIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx',
'md5': '56631dbcadaab980d1fc47cb7b76cba4',
'info_dict': {
'id': '6322981580112',
'ext': 'mp4',
'title': 'I’m Felicia',
'description': 'md5:88fad93f8eede1c9c8f390239e4c6290',
'uploader_id': '6055873637001',
'upload_date': '20230320',
'timestamp': 1679334960,
'duration': 49.557,
'thumbnail': r're:^https://.+\.jpg',
'tags': [],
},
}, {
'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc',
'md5': 'edcb03e3210b88a3e56c05aa863e0e5b',
'info_dict': {
'id': '6323036027112',
'ext': 'mp4',
'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More',
'description': 'md5:b929867a357aac5544b783d834c78383',
'uploader_id': '6055873637001',
'upload_date': '20230321',
'timestamp': 1679430180,
'duration': 132.032,
'thumbnail': r're:^https://.+\.jpg',
'tags': [],
},
}, {
'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck',
'info_dict': {
'id': 'OX9wJWOcqck',
'ext': 'mp4',
'title': 'Rugrats | Season 2 Official Trailer | Paramount+',
'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de',
'uploader': 'Paramount Plus',
'uploader_id': '@paramountplus',
'uploader_url': 'http://www.youtube.com/@paramountplus',
'channel': 'Paramount Plus',
'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg',
'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg',
'upload_date': '20230316',
'duration': 88,
'age_limit': 0,
'availability': 'public',
'live_status': 'not_live',
'playable_in_embed': True,
'view_count': int,
'like_count': int,
'channel_follower_count': int,
'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg',
'categories': ['Entertainment'],
'tags': ['Rugrats'],
},
}, {
'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw',
'info_dict': {
'id': '_ljssSoDLkw',
'ext': 'mp4',
'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME',
'description': 'md5:39581bcc3fd810209b642609f448af70',
'uploader': 'SHOWTIME',
'uploader_id': '@Showtime',
'uploader_url': 'http://www.youtube.com/@Showtime',
'channel': 'SHOWTIME',
'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ',
'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ',
'upload_date': '20230209',
'duration': 49,
'age_limit': 0,
'availability': 'public',
'live_status': 'not_live',
'playable_in_embed': True,
'view_count': int,
'like_count': int,
'comment_count': int,
'channel_follower_count': int,
'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp',
'categories': ['People & Blogs'],
'tags': 'count:27',
},
}]
def _real_extract(self, url):
display_id, is_youtube = self._match_valid_url(url).group('id', 'yt')
if is_youtube:
return self.url_result(display_id, YoutubeIE)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'\bvideo_id\s*=\s*["\'](\d+)["\']\s*,', webpage, 'Brightcove ID')
token = self._search_regex(r'\btoken\s*=\s*["\']([\w.-]+)["\']', webpage, 'token')
player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '')
account_id = player.get('data-account') or '6055873637001'
player_id = player.get('data-player') or 'OtLKgXlO9F'
embed = player.get('data-embed') or 'default'
return self.url_result(smuggle_url(
f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}',
{'token': token}), BrightcoveNewIE)
yt_dlp/extractor/cbsinteractive.py
-98
View File
@@ -1,98 +0,0 @@
from .cbs import CBSIE
from ..utils import int_or_none
class CBSInteractiveIE(CBSIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P<id>[^/?]+)'
_TESTS = [{
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'info_dict': {
'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00',
'display_id': 'hands-on-with-microsofts-windows-8-1-update',
'ext': 'mp4',
'title': 'Hands-on with Microsoft Windows 8.1 Update',
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
'uploader': 'Sarah Mitroff',
'duration': 70,
'timestamp': 1396479627,
'upload_date': '20140402',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
'md5': 'f11d27b2fa18597fbf92444d2a9ed386',
'info_dict': {
'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK',
'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187',
'ext': 'mp4',
'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f',
'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
'uploader': 'Ashley Esqueda',
'duration': 1482,
'timestamp': 1433289889,
'upload_date': '20150603',
},
}, {
'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
'info_dict': {
'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt',
'display_id': 'video-keeping-android-smartphones-and-tablets-secure',
'ext': 'mp4',
'title': 'Video: Keeping Android smartphones and tablets secure',
'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
'uploader': 'Adrian Kingsley-Hughes',
'duration': 731,
'timestamp': 1449129925,
'upload_date': '20151203',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/',
'only_matching': True,
}]
MPX_ACCOUNTS = {
'cnet': 2198311517,
'zdnet': 2387448114,
}
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'",
webpage, 'data json')
data = self._parse_json(data_json, display_id)
vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0]
video_id = vdata['mpxRefId']
title = vdata['title']
author = vdata.get('author')
if author:
uploader = '%s %s' % (author['firstName'], author['lastName'])
uploader_id = author.get('id')
else:
uploader = None
uploader_id = None
info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site])
info.update({
'id': video_id,
'display_id': display_id,
'title': title,
'duration': int_or_none(vdata.get('duration')),
'uploader': uploader,
'uploader_id': uploader_id,
})
return info
yt_dlp/extractor/cbslocal.py
-116
View File
@@ -1,116 +0,0 @@
from .anvato import AnvatoIE
from .sendtonews import SendtoNewsIE
from ..compat import compat_urlparse
from ..utils import (
parse_iso8601,
unified_timestamp,
)
class CBSLocalIE(AnvatoIE): # XXX: Do not subclass from concrete IE
_VALID_URL_BASE = r'https?://[a-z]+\.cbslocal\.com/'
_VALID_URL = _VALID_URL_BASE + r'video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://newyork.cbslocal.com/video/3580809-a-very-blue-anniversary/',
'info_dict': {
'id': '3580809',
'ext': 'mp4',
'title': 'A Very Blue Anniversary',
'description': 'CBS2’s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',
},
'categories': [
'Stations\\Spoken Word\\WCBSTV',
'Syndication\\AOL',
'Syndication\\MSN',
'Syndication\\NDN',
'Syndication\\Yahoo',
'Content\\News',
'Content\\News\\Local News',
],
'tags': ['CBS 2 News Weekends', 'Cindy Hsu', 'Blue Man Group'],
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mcp_id = self._match_id(url)
return self.url_result(
'anvato:anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67:' + mcp_id, 'Anvato', mcp_id)
class CBSLocalArticleIE(AnvatoIE): # XXX: Do not subclass from concrete IE
_VALID_URL = CBSLocalIE._VALID_URL_BASE + r'\d+/\d+/\d+/(?P<id>[0-9a-z-]+)'
_TESTS = [{
# Anvato backend
'url': 'http://losangeles.cbslocal.com/2016/05/16/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis',
'md5': 'f0ee3081e3843f575fccef901199b212',
'info_dict': {
'id': '3401037',
'ext': 'mp4',
'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'',
'description': 'Collapsing seats have been the focus of scrutiny for decades, though experts say remarkably little has been done to address the issue. Randy Paige reports.',
'thumbnail': 're:^https?://.*',
'timestamp': 1463440500,
'upload_date': '20160516',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',
},
'categories': [
'Stations\\Spoken Word\\KCBSTV',
'Syndication\\MSN',
'Syndication\\NDN',
'Syndication\\AOL',
'Syndication\\Yahoo',
'Syndication\\Tribune',
'Syndication\\Curb.tv',
'Content\\News'
],
'tags': ['CBS 2 News Evening'],
},
}, {
# SendtoNews embed
'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
'info_dict': {
'id': 'GxfCe0Zo7D-175909-5588',
},
'playlist_count': 9,
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
sendtonews_url = SendtoNewsIE._extract_url(webpage)
if sendtonews_url:
return self.url_result(
compat_urlparse.urljoin(url, sendtonews_url),
ie=SendtoNewsIE.ie_key())
info_dict = self._extract_anvato_videos(webpage, display_id)
timestamp = unified_timestamp(self._html_search_regex(
r'class="(?:entry|post)-date"[^>]*>([^<]+)', webpage,
'released date', default=None)) or parse_iso8601(
self._html_search_meta('uploadDate', webpage))
info_dict.update({
'display_id': display_id,
'timestamp': timestamp,
})
return info_dict
yt_dlp/extractor/cbsnews.py
+341 -41
View File
@@ -1,36 +1,153 @@
import base64
import re
import urllib.error
import urllib.parse
import zlib
from .anvato import AnvatoIE
from .common import InfoExtractor
from .cbs import CBSIE
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
from .paramountplus import ParamountPlusIE
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
UserNotLive,
determine_ext,
float_or_none,
format_field,
int_or_none,
make_archive_id,
mimetype2ext,
parse_duration,
smuggle_url,
traverse_obj,
url_or_none,
)
class CBSNewsEmbedIE(CBSIE): # XXX: Do not subclass from concrete IE
class CBSNewsBaseIE(InfoExtractor):
_LOCALES = {
'atlanta': None,
'baltimore': 'BAL',
'boston': 'BOS',
'chicago': 'CHI',
'colorado': 'DEN',
'detroit': 'DET',
'losangeles': 'LA',
'miami': 'MIA',
'minnesota': 'MIN',
'newyork': 'NY',
'philadelphia': 'PHI',
'pittsburgh': 'PIT',
'sacramento': 'SAC',
'sanfrancisco': 'SF',
'texas': 'DAL',
}
_LOCALE_RE = '|'.join(map(re.escape, _LOCALES))
_ANVACK = '5VD6Eyd6djewbCmNwBFnsJj17YAvGRwl'
def _get_item(self, webpage, display_id):
return traverse_obj(self._search_json(
r'CBSNEWS\.defaultPayload\s*=', webpage, 'payload', display_id,
default={}), ('items', 0, {dict})) or {}
def _get_video_url(self, item):
return traverse_obj(item, 'video', 'video2', expected_type=url_or_none)
def _extract_playlist(self, webpage, playlist_id):
entries = [self.url_result(embed_url, CBSNewsEmbedIE) for embed_url in re.findall(
r'<iframe[^>]+data-src="(https?://(?:www\.)?cbsnews\.com/embed/video/[^#]*#[^"]+)"', webpage)]
if entries:
return self.playlist_result(
entries, playlist_id, self._html_search_meta(['og:title', 'twitter:title'], webpage),
self._html_search_meta(['og:description', 'twitter:description', 'description'], webpage))
def _extract_video(self, item, video_url, video_id):
if mimetype2ext(item.get('format'), default=determine_ext(video_url)) == 'mp4':
formats = [{'url': video_url, 'ext': 'mp4'}]
else:
manifest = self._download_webpage(video_url, video_id, note='Downloading m3u8 information')
anvato_id = self._search_regex(r'anvato-(\d+)', manifest, 'Anvato ID', default=None)
# Prefer Anvato if available; cbsnews.com m3u8 formats are re-encoded from Anvato source
if anvato_id:
return self.url_result(
smuggle_url(f'anvato:{self._ANVACK}:{anvato_id}', {'token': 'default'}),
AnvatoIE, url_transparent=True, _old_archive_ids=[make_archive_id(self, anvato_id)])
formats, _ = self._parse_m3u8_formats_and_subtitles(
manifest, video_url, 'mp4', m3u8_id='hls', video_id=video_id)
def get_subtitles(subs_url):
return {
'en': [{
'url': subs_url,
'ext': 'dfxp', # TTAF1
}],
} if url_or_none(subs_url) else None
episode_meta = traverse_obj(item, {
'season_number': ('season', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
}) if item.get('isFullEpisode') else {}
return {
'id': video_id,
'formats': formats,
**traverse_obj(item, {
'title': (None, ('fulltitle', 'title')),
'description': 'dek',
'timestamp': ('timestamp', {lambda x: float_or_none(x, 1000)}),
'duration': ('duration', {float_or_none}),
'subtitles': ('captions', {get_subtitles}),
'thumbnail': ('images', ('hd', 'sd'), {url_or_none}),
'is_live': ('type', {lambda x: x == 'live'}),
}, get_all=False),
**episode_meta,
}
class CBSNewsEmbedIE(CBSNewsBaseIE):
IE_NAME = 'cbsnews:embed'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/embed/video[^#]*#(?P<id>.+)'
_TESTS = [{
'url': 'https://www.cbsnews.com/embed/video/?v=1.c9b5b61492913d6660db0b2f03579ef25e86307a#1Vb7b9s2EP5XBAHbT6Gt98PAMKTJ0se6LVjWYWtdGBR1stlIpEBSTtwi%2F%2FvuJNkNhmHdGxgM2NL57vjd6zt%2B8PngdN%2Fyg79qeGvhzN%2FLGrS%2F%2BuBLB531V28%2B%2BO7Qg7%2Fy97r2z3xZ42NW8yLhDbA0S0KWlHnIijwKWJBHZZnHBa8Cgbpdf%2F89NM9Hi9fXifhpr8sr%2FlP848tn%2BTdXycX25zh4cdX%2FvHl6PmmPqnWQv9w8Ed%2B9GjYRim07bFEqdG%2BZVHuwTm65A7bVRrYtR5lAyMox7pigF6W4k%2By91mjspGsJ%2BwVae4%2BsvdnaO1p73HkXs%2FVisUDTGm7R8IcdnOROeq%2B19qT1amhA1VJtPenoTUgrtfKc9m7Rq8dP7nnjwOB7wg7ADdNt7VX64DWAWlKhPtmDEq22g4GF99x6Dk9E8OSsankHXqPNKDxC%2FdK7MLKTircTDgsI3mmj4OBdSq64dy7fd1x577RU1rt4cvMtOaulFYOd%2FLewRWvDO9lIgXFpZSnkZmjbv5SxKTPoQXClFbpsf%2Fhbbpzs0IB3vb8KkyzJQ%2BywOAgCrMpgRrz%2BKk4fvb7kFbR4XJCu0gAdtNO7woCwZTu%2BBUs9bam%2Fds71drVerpeisgrubLjAB4nnOSkWQnfr5W6o1ku5Xpr1MgrCbL0M0vUyDtfLLK15WiYp47xKWSLyjFVpwVmVJSLIoCjSOFkv3W7oKsVliwZJcB9nwXpZ5GEQQwY8jNKqKCBrgjTLeFxgdCIpazojDgnRtn43J6kG7nZ6cAbxh0EeFFk4%2B1u867cY5u4344n%2FxXjCqAjucdTHgLKojNKmSfO8KRsOFY%2FzKEYCKEJBzv90QA9nfm9gL%2BHulaFqUkz9ULUYxl62B3U%2FRVNLA8IhggaPycOoBuwOCESciDQVSSUgiOMsROB%2FhKfwCKOzEk%2B4k6rWd4uuT%2FwTDz7K7t3d3WLO8ISD95jSPQbayBacthbz86XVgxHwhex5zawzgDOmtp%2F3GPcXn0VXHdSS029%2Fj99UC%2FwJUvyKQ%2FzKyixIEVlYJOn4RxxuaH43Ty9fbJ5OObykHH435XAzJTHeOF4hhEUXD8URe%2FQ%2FBT%2BMpf8d5GN02Ox%2FfiGsl7TA7POu1xZ5%2BbTzcAVKMe48mqcC21hkacVEVScM26liVVBnrKkC4CLKyzAvHu0lhEaTKMFwI3a4SN9MsrfYzdBLq2vkwRD1gVviLT8kY9h2CHH6Y%2Bix6609weFtey4ESp60WtyeWMy%2BsmBuhsoKIyuoT%2Bq2R%2FrW5qi3g%2FvzS2j40DoixDP8%2BKP0yUdpXJ4l6Vla%2Bg9vce%2BC4yM5YlUcbA%2F0jLKdpmTwvsdN5z88nAIe08%2F0HgxeG1iv%2B6Hlhjh7uiW0SDzYNI92L401uha3JKYk268UVRzdOzNQvAaJqoXzAc80dAV440NZ1WVVAAMRYQ2KrGJFmDUsq8saWSnjvIj8t78y%2FRa3JRnbHVfyFpfwoDiGpPgjzekyUiKNlU3OMlwuLMmzgvEojllYVE2Z1HhImvsnk%2BuhusTEoB21PAtSFodeFK3iYhXEH9WOG2%2FkOE833sfeG%2Ff5cfHtEFNXgYes0%2FXj7aGivUgJ9XpusCtoNcNYVVnJVrrDo0OmJAutHCpuZul4W9lLcfy7BnuLPT02%2ByXsCTk%2B9zhzswIN04YueNSK%2BPtM0jS88QdLqSLJDTLsuGZJNolm2yO0PXh3UPnz9Ix5bfIAqxPjvETQsDCEiPG4QbqNyhBZISxybLnZYCrW5H3Axp690%2F0BJdXtDZ5ITuM4xj3f4oUHGzc5JeJmZKpp%2FjwKh4wMV%2FV1yx3emLoR0MwbG4K%2F%2BZgVep3PnzXGDHZ6a3i%2Fk%2BJrONDN13%2Bnq6tBTYk4o7cLGhBtqCC4KwacGHpEVuoH5JNro%2FE6JfE6d5RydbiR76k%2BW5wioDHBIjw1euhHjUGRB0y5A97KoaPx6MlL%2BwgboUVtUFRI%2FLemgTpdtF59ii7pab08kuPcfWzs0l%2FRI5takWnFpka0zOgWRtYcuf9aIxZMxlwr6IiGpsb6j2DQUXPl%2FimXI599Ev7fWjoPD78A',
'only_matching': True,
'info_dict': {
'id': '6ZP4cXvo9FaX3VLH7MF4CgY30JFpY_GA',
'ext': 'mp4',
'title': 'Cops investigate gorilla incident at Cincinnati Zoo',
'description': 'md5:fee7441ab8aaeb3c693482394738102b',
'duration': 350,
'timestamp': 1464719713,
'upload_date': '20160531',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
item = self._parse_json(zlib.decompress(compat_b64decode(
compat_urllib_parse_unquote(self._match_id(url))),
-zlib.MAX_WBITS).decode('utf-8'), None)['video']['items'][0]
return self._extract_video_info(item['mpxRefId'], 'cbsnews')
item = traverse_obj(self._parse_json(zlib.decompress(base64.b64decode(
urllib.parse.unquote(self._match_id(url))),
-zlib.MAX_WBITS).decode(), None), ('video', 'items', 0, {dict})) or {}
video_id = item['mpxRefId']
video_url = self._get_video_url(item)
if not video_url:
# Old embeds redirect user to ParamountPlus but most links are 404
pplus_url = f'https://www.paramountplus.com/shows/video/{video_id}'
try:
self._request_webpage(HEADRequest(pplus_url), video_id)
return self.url_result(pplus_url, ParamountPlusIE)
except ExtractorError:
self.raise_no_formats('This video is no longer available', True, video_id)
return self._extract_video(item, video_url, video_id)
class CBSNewsIE(CBSIE): # XXX: Do not subclass from concrete IE
class CBSNewsIE(CBSNewsBaseIE):
IE_NAME = 'cbsnews'
IE_DESC = 'CBS News'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|video)/(?P<id>[\da-z_-]+)'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|video)/(?P<id>[\w-]+)'
_TESTS = [
{
@@ -47,10 +164,7 @@ class CBSNewsIE(CBSIE): # XXX: Do not subclass from concrete IE
'timestamp': 1476046464,
'upload_date': '20161009',
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'This video is no longer available',
},
{
'url': 'https://www.cbsnews.com/video/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
@@ -61,48 +175,234 @@ class CBSNewsIE(CBSIE): # XXX: Do not subclass from concrete IE
'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
'upload_date': '20140404',
'timestamp': 1396650660,
'uploader': 'CBSI-NEW',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 205,
'subtitles': {
'en': [{
'ext': 'ttml',
'ext': 'dfxp',
}],
},
},
'params': {
# m3u8 download
'skip_download': True,
'skip_download': 'm3u8',
},
},
{
# 48 hours
'url': 'http://www.cbsnews.com/news/maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved/',
'info_dict': {
'id': 'maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved',
'title': 'Cold as Ice',
'description': 'Can a childhood memory solve the 1957 murder of 7-year-old Maria Ridulph?',
},
'playlist_mincount': 7,
},
{
'url': 'https://www.cbsnews.com/video/032823-cbs-evening-news/',
'info_dict': {
'id': '_2wuO7hD9LwtyM_TwSnVwnKp6kxlcXgE',
'ext': 'mp4',
'title': 'CBS Evening News, March 28, 2023',
'description': 'md5:db20615aae54adc1d55a1fd69dc75d13',
'duration': 1189,
'timestamp': 1680042600,
'upload_date': '20230328',
'season': 'Season 2023',
'season_number': 2023,
'episode': 'Episode 83',
'episode_number': 83,
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': 'm3u8',
},
},
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for embed_url in re.findall(r'<iframe[^>]+data-src="(https?://(?:www\.)?cbsnews\.com/embed/video/[^#]*#[^"]+)"', webpage):
entries.append(self.url_result(embed_url, CBSNewsEmbedIE.ie_key()))
if entries:
return self.playlist_result(
entries, playlist_title=self._html_search_meta(['og:title', 'twitter:title'], webpage),
playlist_description=self._html_search_meta(['og:description', 'twitter:description', 'description'], webpage))
playlist = self._extract_playlist(webpage, display_id)
if playlist:
return playlist
item = self._parse_json(self._html_search_regex(
r'CBSNEWS\.defaultPayload\s*=\s*({.+})',
webpage, 'video JSON info'), display_id)['items'][0]
return self._extract_video_info(item['mpxRefId'], 'cbsnews')
item = self._get_item(webpage, display_id)
video_id = item.get('mpxRefId') or display_id
video_url = self._get_video_url(item)
if not video_url:
self.raise_no_formats('No video content was found', expected=True, video_id=video_id)
return self._extract_video(item, video_url, video_id)
class CBSLocalBaseIE(CBSNewsBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
item = self._get_item(webpage, display_id)
video_id = item.get('mpxRefId') or display_id
anvato_id = None
video_url = self._get_video_url(item)
if not video_url:
anv_params = self._search_regex(
r'<iframe[^>]+\bdata-src="https?://w3\.mp\.lura\.live/player/prod/v3/anvload\.html\?key=([^"]+)"',
webpage, 'Anvato URL', default=None)
if not anv_params:
playlist = self._extract_playlist(webpage, display_id)
if playlist:
return playlist
self.raise_no_formats('No video content was found', expected=True, video_id=video_id)
anv_data = self._parse_json(base64.urlsafe_b64decode(f'{anv_params}===').decode(), video_id)
anvato_id = anv_data['v']
return self.url_result(
smuggle_url(f'anvato:{anv_data.get("anvack") or self._ANVACK}:{anvato_id}', {
'token': anv_data.get('token') or 'default',
}), AnvatoIE, url_transparent=True, _old_archive_ids=[make_archive_id(self, anvato_id)])
return self._extract_video(item, video_url, video_id)
class CBSLocalIE(CBSLocalBaseIE):
_VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?:{CBSNewsBaseIE._LOCALE_RE})/(?:live/)?video/(?P<id>[\w-]+)'
_TESTS = [{
# Anvato video via defaultPayload JSON
'url': 'https://www.cbsnews.com/newyork/video/1st-cannabis-dispensary-opens-in-queens/',
'info_dict': {
'id': '6376747',
'ext': 'mp4',
'title': '1st cannabis dispensary opens in Queens',
'description': 'The dispensary is women-owned and located in Jamaica.',
'uploader': 'CBS',
'duration': 20,
'timestamp': 1680193657,
'upload_date': '20230330',
'categories': ['Stations\\Spoken Word\\WCBSTV', 'Content\\Google', 'Content\\News', 'Content\\News\\Local News'],
'tags': 'count:11',
'thumbnail': 're:^https?://.*',
'_old_archive_ids': ['cbslocal 6376747'],
},
'params': {'skip_download': 'm3u8'},
}, {
# cbsnews.com video via defaultPayload JSON
'url': 'https://www.cbsnews.com/newyork/live/video/20230330171655-the-city-is-sounding-the-alarm-on-dangerous-social-media-challenges/',
'info_dict': {
'id': 'sJqfw7YvgSC6ant2zVmzt3y1jYKoL5J3',
'ext': 'mp4',
'title': 'the city is sounding the alarm on dangerous social media challenges',
'description': 'md5:8eccc9b1b73be5138a52e9c4350d2cd6',
'thumbnail': 'https://images-cbsn.cbsnews.com/prod/2023/03/30/story_22509622_1680196925.jpg',
'duration': 41.0,
'timestamp': 1680196615,
'upload_date': '20230330',
},
'params': {'skip_download': 'm3u8'},
}]
class CBSLocalArticleIE(CBSLocalBaseIE):
_VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?:{CBSNewsBaseIE._LOCALE_RE})/news/(?P<id>[\w-]+)'
_TESTS = [{
# Anvato video via iframe embed
'url': 'https://www.cbsnews.com/newyork/news/mta-station-agents-leaving-their-booths-to-provide-more-direct-customer-service/',
'playlist_count': 2,
'info_dict': {
'id': 'mta-station-agents-leaving-their-booths-to-provide-more-direct-customer-service',
'title': 'MTA station agents begin leaving their booths to provide more direct customer service',
'description': 'The more than 2,200 agents will provide face-to-face customer service to passengers.',
},
}, {
'url': 'https://www.cbsnews.com/losangeles/news/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis/',
'md5': 'f0ee3081e3843f575fccef901199b212',
'info_dict': {
'id': '3401037',
'ext': 'mp4',
'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'',
'thumbnail': 're:^https?://.*',
'timestamp': 1463440500,
'upload_date': '20160516',
},
'skip': 'Video has been removed',
}]
class CBSNewsLiveBaseIE(CBSNewsBaseIE):
def _get_id(self, url):
raise NotImplementedError('This method must be implemented by subclasses')
def _real_extract(self, url):
video_id = self._get_id(url)
if not video_id:
raise ExtractorError('Livestream is not available', expected=True)
data = traverse_obj(self._download_json(
'https://feeds-cbsn.cbsnews.com/2.0/rundown/', video_id, query={
'partner': 'cbsnsite',
'edition': video_id,
'type': 'live',
}), ('navigation', 'data', 0, {dict}))
video_url = traverse_obj(data, (('videoUrlDAI', ('videoUrl', 'base')), {url_or_none}), get_all=False)
if not video_url:
raise UserNotLive(video_id=video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'is_live': True,
**traverse_obj(data, {
'title': 'headline',
'description': 'rundown_slug',
'thumbnail': ('images', 'thumbnail_url_hd', {url_or_none}),
}),
}
class CBSLocalLiveIE(CBSNewsLiveBaseIE):
_VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?P<id>{CBSNewsBaseIE._LOCALE_RE})/live/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.cbsnews.com/losangeles/live/',
'info_dict': {
'id': 'CBSN-LA',
'ext': 'mp4',
'title': str,
'description': r're:KCBS/CBSN_LA.CRISPIN.\w+.RUNDOWN \w+ \w+',
'thumbnail': r're:^https?://.*\.jpg$',
'live_status': 'is_live',
},
'params': {'skip_download': 'm3u8'},
}]
def _get_id(self, url):
return format_field(self._LOCALES, self._match_id(url), 'CBSN-%s')
class CBSNewsLiveIE(CBSNewsLiveBaseIE):
IE_NAME = 'cbsnews:live'
IE_DESC = 'CBS News Livestream'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.cbsnews.com/live/',
'info_dict': {
'id': 'CBSN-US',
'ext': 'mp4',
'title': str,
'description': r're:\w+ \w+ CRISPIN RUNDOWN',
'thumbnail': r're:^https?://.*\.jpg$',
'live_status': 'is_live',
},
'params': {'skip_download': 'm3u8'},
}]
def _get_id(self, url):
return 'CBSN-US'
class CBSNewsLiveVideoIE(InfoExtractor):
@@ -111,7 +411,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
# Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
_TEST = {
_TESTS = [{
'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
'info_dict': {
'id': 'clinton-sanders-prepare-to-face-off-in-nh',
@@ -120,7 +420,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
'duration': 334,
},
'skip': 'Video gone',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
@@ -131,13 +431,13 @@ class CBSNewsLiveVideoIE(InfoExtractor):
'dvr_slug': display_id,
})
formats = self._extract_akamai_formats(video_info['url'], display_id)
return {
'id': display_id,
'display_id': display_id,
'title': video_info['headline'],
'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
'duration': parse_duration(video_info.get('segmentDur')),
'formats': formats,
'formats': self._extract_akamai_formats(video_info['url'], display_id),
**traverse_obj(video_info, {
'title': 'headline',
'thumbnail': ('thumbnail_url_hd', {url_or_none}),
'duration': ('segmentDur', {parse_duration}),
}),
}
yt_dlp/extractor/cbssports.py
+3
View File
@@ -8,6 +8,7 @@ from ..utils import (
# class CBSSportsEmbedIE(CBSBaseIE):
class CBSSportsEmbedIE(InfoExtractor):
_WORKING = False
IE_NAME = 'cbssports:embed'
_VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
(?:
@@ -75,6 +76,7 @@ class CBSSportsBaseIE(InfoExtractor):
class CBSSportsIE(CBSSportsBaseIE):
_WORKING = False
IE_NAME = 'cbssports'
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
_TESTS = [{
@@ -92,6 +94,7 @@ class CBSSportsIE(CBSSportsBaseIE):
class TwentyFourSevenSportsIE(CBSSportsBaseIE):
_WORKING = False
IE_NAME = '247sports'
_VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
_TESTS = [{
yt_dlp/extractor/ccc.py
+8 -1
View File
@@ -90,10 +90,17 @@ class CCCPlaylistIE(InfoExtractor):
'id': '30c3',
},
'playlist_count': 135,
}, {
'url': 'https://media.ccc.de/c/DS2023',
'info_dict': {
'title': 'Datenspuren 2023',
'id': 'DS2023',
},
'playlist_count': 37
}]
def _real_extract(self, url):
playlist_id = self._match_id(url).lower()
playlist_id = self._match_id(url)
conf = self._download_json(
'https://media.ccc.de/public/conferences/' + playlist_id,
yt_dlp/extractor/ccma.py
+6
View File
@@ -1,6 +1,7 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
determine_ext,
int_or_none,
parse_duration,
parse_resolution,
@@ -60,6 +61,7 @@ class CCMAIE(InfoExtractor):
'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
'media': media_type,
'idint': media_id,
'format': 'dm',
})
formats = []
@@ -69,6 +71,10 @@ class CCMAIE(InfoExtractor):
format_url = url_or_none(format_.get('file'))
if not format_url:
continue
if determine_ext(format_url) == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, media_id, mpd_id='dash', fatal=False))
continue
label = format_.get('label')
f = parse_resolution(label)
f.update({
yt_dlp/extractor/cctv.py
+15 -1
View File
@@ -88,6 +88,20 @@ class CCTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# videoCenterId: "id"
'url': 'http://news.cctv.com/2024/02/21/ARTIcU5tKIOIF2myEGCATkLo240221.shtml',
'info_dict': {
'id': '5c846c0518444308ba32c4159df3b3e0',
'ext': 'mp4',
'title': '《平“语”近人——习近平喜欢的典故》第三季 第5集：风物长宜放眼量',
'uploader': 'yangjuan',
'timestamp': 1708554940,
'upload_date': '20240221',
},
'params': {
'skip_download': True,
},
}, {
# var ids = ["id"]
'url': 'http://www.ncpa-classic.com/clt/more/416/index.shtml',
@@ -128,7 +142,7 @@ class CCTVIE(InfoExtractor):
video_id = self._search_regex(
[r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
r'videoCenterId(?:["\']\s*,|:)\s*["\']([\da-fA-F]+)',
r'changePlayer\s*\(\s*["\']([\da-fA-F]+)',
r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)',
r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)',
yt_dlp/extractor/cda.py
+3 -3
View File
@@ -1,6 +1,6 @@
import base64
import codecs
import datetime
import datetime as dt
import hashlib
import hmac
import json
@@ -134,7 +134,7 @@ class CDAIE(InfoExtractor):
self._API_HEADERS['User-Agent'] = f'pl.cda 1.0 (version {app_version}; Android {android_version}; {phone_model})'
cached_bearer = self.cache.load(self._BEARER_CACHE, username) or {}
if cached_bearer.get('valid_until', 0) > datetime.datetime.now().timestamp() + 5:
if cached_bearer.get('valid_until', 0) > dt.datetime.now().timestamp() + 5:
self._API_HEADERS['Authorization'] = f'Bearer {cached_bearer["token"]}'
return
@@ -154,7 +154,7 @@ class CDAIE(InfoExtractor):
})
self.cache.store(self._BEARER_CACHE, username, {
'token': token_res['access_token'],
'valid_until': token_res['expires_in'] + datetime.datetime.now().timestamp(),
'valid_until': token_res['expires_in'] + dt.datetime.now().timestamp(),
})
self._API_HEADERS['Authorization'] = f'Bearer {token_res["access_token"]}'
yt_dlp/extractor/ceskatelevize.py
+16 -16
View File
@@ -1,20 +1,20 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
)
from ..compat import compat_urllib_parse_unquote, compat_urllib_parse_urlparse
from ..networking import Request
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
str_or_none,
traverse_obj,
urlencode_postdata,
USER_AGENTS,
)
USER_AGENTS = {
'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
}
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
@@ -51,7 +51,7 @@ class CeskaTelevizeIE(InfoExtractor):
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'only_matching': True,
'info_dict': {
'id': 402,
'id': '402',
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
@@ -97,7 +97,7 @@ class CeskaTelevizeIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
parsed_url = compat_urllib_parse_urlparse(urlh.url)
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title:
@@ -163,16 +163,16 @@ class CeskaTelevizeIE(InfoExtractor):
entries = []
for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request(
req = Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
req.add_header('x-addr', '127.0.0.1')
req.add_header('X-Requested-With', 'XMLHttpRequest')
req.headers['Content-type'] = 'application/x-www-form-urlencoded'
req.headers['x-addr'] = '127.0.0.1'
req.headers['X-Requested-With'] = 'XMLHttpRequest'
if user_agent:
req.add_header('User-Agent', user_agent)
req.add_header('Referer', url)
req.headers['User-Agent'] = user_agent
req.headers['Referer'] = url
playlistpage = self._download_json(req, playlist_id, fatal=False)
@@ -183,8 +183,8 @@ class CeskaTelevizeIE(InfoExtractor):
if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
req = Request(compat_urllib_parse_unquote(playlist_url))
req.headers['Referer'] = url
playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist:
yt_dlp/extractor/cgtn.py
+11 -7
View File
@@ -17,6 +17,7 @@ class CGTNIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1615295940,
'upload_date': '20210309',
'categories': ['Video'],
},
'params': {
'skip_download': True
@@ -29,8 +30,8 @@ class CGTNIE(InfoExtractor):
'title': 'China, Indonesia vow to further deepen maritime cooperation',
'thumbnail': r're:^https?://.*\.png$',
'description': 'China and Indonesia vowed to upgrade their cooperation into the maritime sector and also for political security, economy, and cultural and people-to-people exchanges.',
'author': 'CGTN',
'category': 'China',
'creators': ['CGTN'],
'categories': ['China'],
'timestamp': 1622950200,
'upload_date': '20210606',
},
@@ -45,7 +46,12 @@ class CGTNIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
download_url = self._html_search_regex(r'data-video ="(?P<url>.+m3u8)"', webpage, 'download_url')
datetime_str = self._html_search_regex(r'<span class="date">\s*(.+?)\s*</span>', webpage, 'datetime_str', fatal=False)
datetime_str = self._html_search_regex(
r'<span class="date">\s*(.+?)\s*</span>', webpage, 'datetime_str', fatal=False)
category = self._html_search_regex(
r'<span class="section">\s*(.+?)\s*</span>', webpage, 'category', fatal=False)
author = self._search_regex(
r'<div class="news-author-name">\s*(.+?)\s*</div>', webpage, 'author', default=None)
return {
'id': video_id,
@@ -53,9 +59,7 @@ class CGTNIE(InfoExtractor):
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': self._extract_m3u8_formats(download_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'),
'category': self._html_search_regex(r'<span class="section">\s*(.+?)\s*</span>',
webpage, 'category', fatal=False),
'author': self._html_search_regex(r'<div class="news-author-name">\s*(.+?)\s*</div>',
webpage, 'author', default=None, fatal=False),
'categories': [category] if category else None,
'creators': [author] if author else None,
'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600),
}
yt_dlp/extractor/channel9.py
-252
View File
@@ -1,252 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
parse_iso8601,
qualities,
unescapeHTML,
)
class Channel9IE(InfoExtractor):
IE_DESC = 'Channel 9'
IE_NAME = 'channel9'
_VALID_URL = r'https?://(?:www\.)?(?:channel9\.msdn\.com|s\.ch9\.ms)/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
_EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b']
_TESTS = [{
'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
'md5': '32083d4eaf1946db6d454313f44510ca',
'info_dict': {
'id': '6c413323-383a-49dc-88f9-a22800cab024',
'ext': 'wmv',
'title': 'Developer Kick-Off Session: Stuff We Love',
'description': 'md5:b80bf9355a503c193aff7ec6cd5a7731',
'duration': 4576,
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1377717420,
'upload_date': '20130828',
'session_code': 'KOS002',
'session_room': 'Arena 1A',
'session_speakers': 'count:5',
},
}, {
'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
'md5': 'dcf983ee6acd2088e7188c3cf79b46bc',
'info_dict': {
'id': 'fe8e435f-bb93-4e01-8e97-a28c01887024',
'ext': 'wmv',
'title': 'Self-service BI with Power BI - nuclear testing',
'description': 'md5:2d17fec927fc91e9e17783b3ecc88f54',
'duration': 1540,
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1386381991,
'upload_date': '20131207',
'authors': ['Mike Wilmot'],
},
}, {
# low quality mp4 is best
'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
'info_dict': {
'id': '33ad69d2-6a4e-4172-83a1-a523013dec76',
'ext': 'mp4',
'title': 'Ranges for the Standard Library',
'description': 'md5:9895e0a9fd80822d2f01c454b8f4a372',
'duration': 5646,
'thumbnail': r're:https?://.*\.jpg',
'upload_date': '20150930',
'timestamp': 1443640735,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
'info_dict': {
'id': 'Events/DEVintersection/DEVintersection-2016',
'title': 'DEVintersection 2016 Orlando Sessions',
},
'playlist_mincount': 14,
}, {
'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
'only_matching': True,
}, {
'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman',
'only_matching': True,
}]
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
def _extract_list(self, video_id, rss_url=None):
if not rss_url:
rss_url = self._RSS_URL % video_id
rss = self._download_xml(rss_url, video_id, 'Downloading RSS')
entries = [self.url_result(session_url.text, 'Channel9')
for session_url in rss.findall('./channel/item/link')]
title_text = rss.find('./channel/title').text
return self.playlist_result(entries, video_id, title_text)
def _real_extract(self, url):
content_path, rss = self._match_valid_url(url).groups()
if rss:
return self._extract_list(content_path, url)
webpage = self._download_webpage(
url, content_path, 'Downloading web page')
episode_data = self._search_regex(
r"data-episode='([^']+)'", webpage, 'episode data', default=None)
if episode_data:
episode_data = self._parse_json(unescapeHTML(
episode_data), content_path)
content_id = episode_data['contentId']
is_session = '/Sessions(' in episode_data['api']
content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + '?$select=Captions,CommentCount,MediaLengthInSeconds,PublishedDate,Rating,RatingCount,Title,VideoMP4High,VideoMP4Low,VideoMP4Medium,VideoPlayerPreviewImage,VideoWMV,VideoWMVHQ,Views,'
if is_session:
content_url += 'Code,Description,Room,Slides,Speakers,ZipFile&$expand=Speakers'
else:
content_url += 'Authors,Body&$expand=Authors'
content_data = self._download_json(content_url, content_id)
title = content_data['Title']
QUALITIES = (
'mp3',
'wmv', 'mp4',
'wmv-low', 'mp4-low',
'wmv-mid', 'mp4-mid',
'wmv-high', 'mp4-high',
)
quality_key = qualities(QUALITIES)
def quality(quality_id, format_url):
return (len(QUALITIES) if '_Source.' in format_url
else quality_key(quality_id))
formats = []
urls = set()
SITE_QUALITIES = {
'MP3': 'mp3',
'MP4': 'mp4',
'Low Quality WMV': 'wmv-low',
'Low Quality MP4': 'mp4-low',
'Mid Quality WMV': 'wmv-mid',
'Mid Quality MP4': 'mp4-mid',
'High Quality WMV': 'wmv-high',
'High Quality MP4': 'mp4-high',
}
formats_select = self._search_regex(
r'(?s)<select[^>]+name=["\']format[^>]+>(.+?)</select', webpage,
'formats select', default=None)
if formats_select:
for mobj in re.finditer(
r'<option\b[^>]+\bvalue=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*(?P<format>[^<]+?)\s*<',
formats_select):
format_url = mobj.group('url')
if format_url in urls:
continue
urls.add(format_url)
format_id = mobj.group('format')
quality_id = SITE_QUALITIES.get(format_id, format_id)
formats.append({
'url': format_url,
'format_id': quality_id,
'quality': quality(quality_id, format_url),
'vcodec': 'none' if quality_id == 'mp3' else None,
})
API_QUALITIES = {
'VideoMP4Low': 'mp4-low',
'VideoWMV': 'wmv-mid',
'VideoMP4Medium': 'mp4-mid',
'VideoMP4High': 'mp4-high',
'VideoWMVHQ': 'wmv-hq',
}
for format_id, q in API_QUALITIES.items():
q_url = content_data.get(format_id)
if not q_url or q_url in urls:
continue
urls.add(q_url)
formats.append({
'url': q_url,
'format_id': q,
'quality': quality(q, q_url),
})
slides = content_data.get('Slides')
zip_file = content_data.get('ZipFile')
if not formats and not slides and not zip_file:
self.raise_no_formats(
'None of recording, slides or zip are available for %s' % content_path)
subtitles = {}
for caption in content_data.get('Captions', []):
caption_url = caption.get('Url')
if not caption_url:
continue
subtitles.setdefault(caption.get('Language', 'en'), []).append({
'url': caption_url,
'ext': 'vtt',
})
common = {
'id': content_id,
'title': title,
'description': clean_html(content_data.get('Description') or content_data.get('Body')),
'thumbnail': content_data.get('VideoPlayerPreviewImage'),
'duration': int_or_none(content_data.get('MediaLengthInSeconds')),
'timestamp': parse_iso8601(content_data.get('PublishedDate')),
'avg_rating': int_or_none(content_data.get('Rating')),
'rating_count': int_or_none(content_data.get('RatingCount')),
'view_count': int_or_none(content_data.get('Views')),
'comment_count': int_or_none(content_data.get('CommentCount')),
'subtitles': subtitles,
}
if is_session:
speakers = []
for s in content_data.get('Speakers', []):
speaker_name = s.get('FullName')
if not speaker_name:
continue
speakers.append(speaker_name)
common.update({
'session_code': content_data.get('Code'),
'session_room': content_data.get('Room'),
'session_speakers': speakers,
})
else:
authors = []
for a in content_data.get('Authors', []):
author_name = a.get('DisplayName')
if not author_name:
continue
authors.append(author_name)
common['authors'] = authors
contents = []
if slides:
d = common.copy()
d.update({'title': title + '-Slides', 'url': slides})
contents.append(d)
if zip_file:
d = common.copy()
d.update({'title': title + '-Zip', 'url': zip_file})
contents.append(d)
if formats:
d = common.copy()
d.update({'title': title, 'formats': formats})
contents.append(d)
return self.playlist_result(contents)
else:
return self._extract_list(content_path)
yt_dlp/extractor/chingari.py
-207
View File
@@ -1,207 +0,0 @@
import itertools
import json
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
str_to_int,
url_or_none,
)
class ChingariBaseIE(InfoExtractor):
def _get_post(self, id, post_data):
media_data = post_data['mediaLocation']
base_url = media_data['base']
author_data = post_data.get('authorData', {})
song_data = post_data.get('song', {}) # revist this in future for differentiating b/w 'art' and 'author'
formats = [{
'format_id': frmt,
'width': str_to_int(frmt[1:]),
'url': base_url + frmt_path,
} for frmt, frmt_path in media_data.get('transcoded', {}).items()]
if media_data.get('path'):
formats.append({
'format_id': 'original',
'format_note': 'Direct video.',
'url': base_url + '/apipublic' + media_data['path'],
'quality': 10,
})
timestamp = str_to_int(post_data.get('created_at'))
if timestamp:
timestamp = int_or_none(timestamp, 1000)
thumbnail, uploader_url = None, None
if media_data.get('thumbnail'):
thumbnail = base_url + media_data.get('thumbnail')
if author_data.get('username'):
uploader_url = 'https://chingari.io/' + author_data.get('username')
return {
'id': id,
'extractor_key': ChingariIE.ie_key(),
'extractor': 'Chingari',
'title': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'description': urllib.parse.unquote_plus(clean_html(post_data.get('caption'))),
'duration': media_data.get('duration'),
'thumbnail': url_or_none(thumbnail),
'like_count': post_data.get('likeCount'),
'view_count': post_data.get('viewsCount'),
'comment_count': post_data.get('commentCount'),
'repost_count': post_data.get('shareCount'),
'timestamp': timestamp,
'uploader_id': post_data.get('userId') or author_data.get('_id'),
'uploader': author_data.get('name'),
'uploader_url': url_or_none(uploader_url),
'track': song_data.get('title'),
'artist': song_data.get('author'),
'formats': formats,
}
class ChingariIE(ChingariBaseIE):
_VALID_URL = r'https?://(?:www\.)?chingari\.io/share/post\?id=(?P<id>[^&/#?]+)'
_TESTS = [{
'url': 'https://chingari.io/share/post?id=612f8f4ce1dc57090e8a7beb',
'info_dict': {
'id': '612f8f4ce1dc57090e8a7beb',
'ext': 'mp4',
'title': 'Happy birthday Srila Prabhupada',
'description': 'md5:c7080ebfdfeb06016e638c286d6bc3fa',
'duration': 0,
'thumbnail': 'https://media.chingari.io/uploads/c41d30e2-06b6-4e3b-9b4b-edbb929cec06-1630506826911/thumbnail/198f993f-ce87-4623-82c6-cd071bd6d4f4-1630506828016.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1630506828,
'upload_date': '20210901',
'uploader_id': '5f0403982c8bd344f4813f8c',
'uploader': 'ISKCON,Inc.',
'uploader_url': 'https://chingari.io/iskcon,inc',
'track': None,
'artist': None,
},
'params': {'skip_download': True}
}]
def _real_extract(self, url):
id = self._match_id(url)
post_json = self._download_json(f'https://api.chingari.io/post/post_details/{id}', id)
if post_json['code'] != 200:
raise ExtractorError(post_json['message'], expected=True)
post_data = post_json['data']
return self._get_post(id, post_data)
class ChingariUserIE(ChingariBaseIE):
_VALID_URL = r'https?://(?:www\.)?chingari\.io/(?!share/post)(?P<id>[^/?]+)'
_TESTS = [{
'url': 'https://chingari.io/dada1023',
'info_dict': {
'id': 'dada1023',
},
'params': {'playlistend': 3},
'playlist': [{
'url': 'https://chingari.io/share/post?id=614781f3ade60b3a0bfff42a',
'info_dict': {
'id': '614781f3ade60b3a0bfff42a',
'ext': 'mp4',
'title': '#chingaribappa ',
'description': 'md5:d1df21d84088770468fa63afe3b17857',
'duration': 7,
'thumbnail': 'https://media.chingari.io/uploads/346d86d4-abb2-474e-a164-ffccf2bbcb72-1632076273717/thumbnail/b0b3aac2-2b86-4dd1-909d-9ed6e57cf77c-1632076275552.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1632076275,
'upload_date': '20210919',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
'track': None,
'artist': None
},
'params': {'skip_download': True}
}, {
'url': 'https://chingari.io/share/post?id=6146b132bcbf860959e12cba',
'info_dict': {
'id': '6146b132bcbf860959e12cba',
'ext': 'mp4',
'title': 'Tactor harvesting',
'description': 'md5:8403f12dce68828b77ecee7eb7e887b7',
'duration': 59.3,
'thumbnail': 'https://media.chingari.io/uploads/b353ca70-7a87-400d-93a6-fa561afaec86-1632022814584/thumbnail/c09302e3-2043-41b1-a2fe-77d97e5bd676-1632022834260.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1632022834,
'upload_date': '20210919',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
'track': None,
'artist': None
},
'params': {'skip_download': True}
}, {
'url': 'https://chingari.io/share/post?id=6145651b74cb030a64c40b82',
'info_dict': {
'id': '6145651b74cb030a64c40b82',
'ext': 'mp4',
'title': '#odiabhajan ',
'description': 'md5:687ea36835b9276cf2af90f25e7654cb',
'duration': 56.67,
'thumbnail': 'https://media.chingari.io/uploads/6cbf216b-babc-4cce-87fe-ceaac8d706ac-1631937782708/thumbnail/8855754f-6669-48ce-b269-8cc0699ed6da-1631937819522.jpg',
'like_count': int,
'view_count': int,
'comment_count': int,
'repost_count': int,
'timestamp': 1631937819,
'upload_date': '20210918',
'uploader_id': '5efc4b12cca35c3d1794c2d3',
'uploader': 'dada (girish) dhawale',
'uploader_url': 'https://chingari.io/dada1023',
'track': None,
'artist': None
},
'params': {'skip_download': True}
}],
}, {
'url': 'https://chingari.io/iskcon%2Cinc',
'playlist_mincount': 1025,
'info_dict': {
'id': 'iskcon%2Cinc',
},
}]
def _entries(self, id):
skip = 0
has_more = True
for page in itertools.count():
posts = self._download_json('https://api.chingari.io/users/getPosts', id,
data=json.dumps({'userId': id, 'ownerId': id, 'skip': skip, 'limit': 20}).encode(),
headers={'content-type': 'application/json;charset=UTF-8'},
note='Downloading page %s' % page)
for post in posts.get('data', []):
post_data = post['post']
yield self._get_post(post_data['_id'], post_data)
skip += 20
has_more = posts['hasMoreData']
if not has_more:
break
def _real_extract(self, url):
alt_id = self._match_id(url)
post_json = self._download_json(f'https://api.chingari.io/user/{alt_id}', alt_id)
if post_json['code'] != 200:
raise ExtractorError(post_json['message'], expected=True)
id = post_json['data']['_id']
return self.playlist_result(self._entries(id), playlist_id=alt_id)
yt_dlp/extractor/chirbit.py
-88
View File
@@ -1,88 +0,0 @@
import re
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import parse_duration
class ChirbitIE(InfoExtractor):
IE_NAME = 'chirbit'
_VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://chirb.it/be2abG',
'info_dict': {
'id': 'be2abG',
'ext': 'mp3',
'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
'duration': 306,
'uploader': 'Gerryaudio',
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
'only_matching': True,
}, {
'url': 'https://chirb.it/wp/MN58c2',
'only_matching': True,
}]
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(
'http://chirb.it/%s' % audio_id, audio_id)
data_fd = self._search_regex(
r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'data fd', group='url')
# Reverse engineered from https://chirb.it/js/chirbit.player.js (look
# for soundURL)
audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8')
title = self._search_regex(
r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
description = self._search_regex(
r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
webpage, 'description', default=None)
duration = parse_duration(self._search_regex(
r'class=["\']c-length["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
uploader = self._search_regex(
r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
webpage, 'uploader', fatal=False)
return {
'id': audio_id,
'url': audio_url,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
}
class ChirbitProfileIE(InfoExtractor):
IE_NAME = 'chirbit:profile'
_VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
_TEST = {
'url': 'http://chirbit.com/ScarletBeauty',
'info_dict': {
'id': 'ScarletBeauty',
},
'playlist_mincount': 3,
}
def _real_extract(self, url):
profile_id = self._match_id(url)
webpage = self._download_webpage(url, profile_id)
entries = [
self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)]
return self.playlist_result(entries, profile_id)
yt_dlp/extractor/chzzk.py
+139
View File
@@ -0,0 +1,139 @@
import functools
from .common import InfoExtractor
from ..utils import (
UserNotLive,
float_or_none,
int_or_none,
parse_iso8601,
url_or_none,
)
from ..utils.traversal import traverse_obj
class CHZZKLiveIE(InfoExtractor):
IE_NAME = 'chzzk:live'
_VALID_URL = r'https?://chzzk\.naver\.com/live/(?P<id>[\da-f]+)'
_TESTS = [{
'url': 'https://chzzk.naver.com/live/c68b8ef525fb3d2fa146344d84991753',
'info_dict': {
'id': 'c68b8ef525fb3d2fa146344d84991753',
'ext': 'mp4',
'title': str,
'channel': '진짜도현',
'channel_id': 'c68b8ef525fb3d2fa146344d84991753',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1705510344,
'upload_date': '20240117',
'live_status': 'is_live',
'view_count': int,
'concurrent_view_count': int,
},
'skip': 'The channel is not currently live',
}]
def _real_extract(self, url):
channel_id = self._match_id(url)
live_detail = self._download_json(
f'https://api.chzzk.naver.com/service/v2/channels/{channel_id}/live-detail', channel_id,
note='Downloading channel info', errnote='Unable to download channel info')['content']
if live_detail.get('status') == 'CLOSE':
raise UserNotLive(video_id=channel_id)
live_playback = self._parse_json(live_detail['livePlaybackJson'], channel_id)
thumbnails = []
thumbnail_template = traverse_obj(
live_playback, ('thumbnail', 'snapshotThumbnailTemplate', {url_or_none}))
if thumbnail_template and '{type}' in thumbnail_template:
for width in traverse_obj(live_playback, ('thumbnail', 'types', ..., {str})):
thumbnails.append({
'id': width,
'url': thumbnail_template.replace('{type}', width),
'width': int_or_none(width),
})
formats, subtitles = [], {}
for media in traverse_obj(live_playback, ('media', lambda _, v: url_or_none(v['path']))):
is_low_latency = media.get('mediaId') == 'LLHLS'
fmts, subs = self._extract_m3u8_formats_and_subtitles(
media['path'], channel_id, 'mp4', fatal=False, live=True,
m3u8_id='hls-ll' if is_low_latency else 'hls')
for f in fmts:
if is_low_latency:
f['source_preference'] = -2
if '-afragalow.stream-audio.stream' in f['format_id']:
f['quality'] = -2
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': channel_id,
'is_live': True,
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
**traverse_obj(live_detail, {
'title': ('liveTitle', {str}),
'timestamp': ('openDate', {functools.partial(parse_iso8601, delimiter=' ')}),
'concurrent_view_count': ('concurrentUserCount', {int_or_none}),
'view_count': ('accumulateCount', {int_or_none}),
'channel': ('channel', 'channelName', {str}),
'channel_id': ('channel', 'channelId', {str}),
'channel_is_verified': ('channel', 'verifiedMark', {bool}),
}),
}
class CHZZKVideoIE(InfoExtractor):
IE_NAME = 'chzzk:video'
_VALID_URL = r'https?://chzzk\.naver\.com/video/(?P<id>\d+)'
_TESTS = [{
'url': 'https://chzzk.naver.com/video/1754',
'md5': 'b0c0c1bb888d913b93d702b1512c7f06',
'info_dict': {
'id': '1754',
'ext': 'mp4',
'title': '치지직 테스트 방송',
'channel': '침착맨',
'channel_id': 'bb382c2c0cc9fa7c86ab3b037fb5799c',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 15577,
'timestamp': 1702970505.417,
'upload_date': '20231219',
'view_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_meta = self._download_json(
f'https://api.chzzk.naver.com/service/v2/videos/{video_id}', video_id,
note='Downloading video info', errnote='Unable to download video info')['content']
formats, subtitles = self._extract_mpd_formats_and_subtitles(
f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}', video_id,
query={
'key': video_meta['inKey'],
'env': 'real',
'lc': 'en_US',
'cpl': 'en_US',
}, note='Downloading video playback', errnote='Unable to download video playback')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(video_meta, {
'title': ('videoTitle', {str}),
'thumbnail': ('thumbnailImageUrl', {url_or_none}),
'timestamp': ('publishDateAt', {functools.partial(float_or_none, scale=1000)}),
'view_count': ('readCount', {int_or_none}),
'duration': ('duration', {int_or_none}),
'channel': ('channel', 'channelName', {str}),
'channel_id': ('channel', 'channelId', {str}),
'channel_is_verified': ('channel', 'verifiedMark', {bool}),
}),
}
yt_dlp/extractor/cinchcast.py
-56
View File
@@ -1,56 +0,0 @@
from .common import InfoExtractor
from ..utils import (
unified_strdate,
xpath_text,
)
class CinchcastIE(InfoExtractor):
_VALID_URL = r'https?://player\.cinchcast\.com/.*?(?:assetId|show_id)=(?P<id>[0-9]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1']
_TESTS = [{
'url': 'http://player.cinchcast.com/?show_id=5258197&platformId=1&assetType=single',
'info_dict': {
'id': '5258197',
'ext': 'mp3',
'title': 'Train Your Brain to Up Your Game with Coach Mandy',
'upload_date': '20130816',
},
}, {
# Actual test is run in generic, look for undergroundwellness
'url': 'http://player.cinchcast.com/?platformId=1&#038;assetType=single&#038;assetId=7141703',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
doc = self._download_xml(
'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id,
video_id)
item = doc.find('.//item')
title = xpath_text(item, './title', fatal=True)
date_str = xpath_text(
item, './{http://developer.longtailvideo.com/trac/}date')
upload_date = unified_strdate(date_str, day_first=False)
# duration is present but wrong
formats = [{
'format_id': 'main',
'url': item.find('./{http://search.yahoo.com/mrss/}content').attrib['url'],
}]
backup_url = xpath_text(
item, './{http://developer.longtailvideo.com/trac/}backupContent')
if backup_url:
formats.append({
'preference': 2, # seems to be more reliable
'format_id': 'backup',
'url': backup_url,
})
return {
'id': video_id,
'title': title,
'upload_date': upload_date,
'formats': formats,
}
yt_dlp/extractor/cinemax.py
+1
View File
@@ -2,6 +2,7 @@ from .hbo import HBOBaseIE
class CinemaxIE(HBOBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?cinemax\.com/(?P<path>[^/]+/video/[0-9a-z-]+-(?P<id>\d+))'
_TESTS = [{
'url': 'https://www.cinemax.com/warrior/video/s1-ep-1-recap-20126903',
yt_dlp/extractor/cinetecamilano.py
+2 -2
View File
@@ -1,6 +1,6 @@
import json
import urllib.error
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
float_or_none,
@@ -40,7 +40,7 @@ class CinetecaMilanoIE(InfoExtractor):
'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or ''
})
except ExtractorError as e:
if ((isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 500)
if ((isinstance(e.cause, HTTPError) and e.cause.status == 500)
or isinstance(e.cause, json.JSONDecodeError)):
self.raise_login_required(method='cookies')
raise
yt_dlp/extractor/cineverse.py
+139
View File
@@ -0,0 +1,139 @@
import re
from .common import InfoExtractor
from ..utils import (
filter_dict,
int_or_none,
parse_age_limit,
smuggle_url,
traverse_obj,
unsmuggle_url,
url_or_none,
)
class CineverseBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://www\.(?P<host>%s)' % '|'.join(map(re.escape, (
'cineverse.com',
'asiancrush.com',
'dovechannel.com',
'screambox.com',
'midnightpulp.com',
'fandor.com',
'retrocrush.tv',
)))
class CineverseIE(CineverseBaseIE):
_VALID_URL = rf'{CineverseBaseIE._VALID_URL_BASE}/watch/(?P<id>[A-Z0-9]+)'
_TESTS = [{
'url': 'https://www.asiancrush.com/watch/DMR00018919/Women-Who-Flirt',
'skip': 'geo-blocked',
'info_dict': {
'title': 'Women Who Flirt',
'ext': 'mp4',
'id': 'DMR00018919',
'modified_timestamp': 1678744575289,
'cast': ['Xun Zhou', 'Xiaoming Huang', 'Yi-Lin Sie', 'Sonia Sui', 'Quniciren'],
'duration': 5811.597,
'description': 'md5:892fd62a05611d394141e8394ace0bc6',
'age_limit': 13,
}
}, {
'url': 'https://www.retrocrush.tv/watch/1000000023016/Archenemy! Crystal Bowie',
'skip': 'geo-blocked',
'info_dict': {
'title': 'Archenemy! Crystal Bowie',
'ext': 'mp4',
'id': '1000000023016',
'episode_number': 3,
'season_number': 1,
'cast': ['Nachi Nozawa', 'Yoshiko Sakakibara', 'Toshiko Fujita'],
'age_limit': 0,
'episode': 'Episode 3',
'season': 'Season 1',
'duration': 1485.067,
'description': 'Cobra meets a beautiful bounty hunter by the name of Jane Royal.',
'series': 'Space Adventure COBRA (Original Japanese)',
}
}]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, default={})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
video_id = self._match_id(url)
html = self._download_webpage(url, video_id)
idetails = self._search_nextjs_data(html, video_id)['props']['pageProps']['idetails']
err_code = idetails.get('err_code')
if err_code == 1002:
self.raise_login_required()
elif err_code == 1200:
self.raise_geo_restricted(
'This video is not available from your location due to geo restriction. '
'You may be able to bypass it by using the /details/ page instead of the /watch/ page',
countries=smuggled_data.get('geo_countries'))
return {
'subtitles': filter_dict({
'en': traverse_obj(idetails, (('cc_url_vtt', 'subtitle_url'), {'url': {url_or_none}})) or None,
}),
'formats': self._extract_m3u8_formats(idetails['url'], video_id),
**traverse_obj(idetails, {
'title': 'title',
'id': ('details', 'item_id'),
'description': ('details', 'description'),
'duration': ('duration', {lambda x: x / 1000}),
'cast': ('details', 'cast', {lambda x: x.split(', ')}),
'modified_timestamp': ('details', 'updated_by', 0, 'update_time', 'time', {int_or_none}),
'season_number': ('details', 'season', {int_or_none}),
'episode_number': ('details', 'episode', {int_or_none}),
'age_limit': ('details', 'rating_code', {parse_age_limit}),
'series': ('details', 'series_details', 'title'),
}),
}
class CineverseDetailsIE(CineverseBaseIE):
_VALID_URL = rf'{CineverseBaseIE._VALID_URL_BASE}/details/(?P<id>[A-Z0-9]+)'
_TESTS = [{
'url': 'https://www.retrocrush.tv/details/1000000023012/Space-Adventure-COBRA-(Original-Japanese)',
'playlist_mincount': 30,
'info_dict': {
'title': 'Space Adventure COBRA (Original Japanese)',
'id': '1000000023012',
}
}, {
'url': 'https://www.asiancrush.com/details/NNVG4938/Hansel-and-Gretel',
'info_dict': {
'id': 'NNVG4938',
'ext': 'mp4',
'title': 'Hansel and Gretel',
'description': 'md5:e3e4c35309c2e82aee044f972c2fb05d',
'cast': ['Jeong-myeong Cheon', 'Eun Won-jae', 'Shim Eun-gyeong', 'Ji-hee Jin', 'Hee-soon Park', 'Lydia Park', 'Kyeong-ik Kim'],
'duration': 7030.732,
},
}]
def _real_extract(self, url):
host, series_id = self._match_valid_url(url).group('host', 'id')
html = self._download_webpage(url, series_id)
pageprops = self._search_nextjs_data(html, series_id)['props']['pageProps']
geo_countries = traverse_obj(pageprops, ('itemDetailsData', 'geo_country', {lambda x: x.split(', ')}))
geoblocked = traverse_obj(pageprops, (
'itemDetailsData', 'playback_err_msg')) == 'This title is not available in your location.'
def item_result(item):
item_url = f'https://www.{host}/watch/{item["item_id"]}/{item["title"]}'
if geoblocked:
item_url = smuggle_url(item_url, {'geo_countries': geo_countries})
return self.url_result(item_url, CineverseIE)
season = traverse_obj(pageprops, ('seasonEpisodes', ..., 'episodes', lambda _, v: v['item_id'] and v['title']))
if season:
return self.playlist_result([item_result(ep) for ep in season], playlist_id=series_id,
playlist_title=traverse_obj(pageprops, ('itemDetailsData', 'title')))
return item_result(pageprops['itemDetailsData'])
yt_dlp/extractor/ciscowebex.py
+1 -1
View File
@@ -33,7 +33,7 @@ class CiscoWebexIE(InfoExtractor):
if rcid:
webpage = self._download_webpage(url, None, note='Getting video ID')
url = self._search_regex(self._VALID_URL, webpage, 'redirection url', group='url')
url = self._request_webpage(url, None, note='Resolving final URL').geturl()
url = self._request_webpage(url, None, note='Resolving final URL').url
mobj = self._match_valid_url(url)
subdomain = mobj.group('subdomain')
siteurl = mobj.group('siteurl_1') or mobj.group('siteurl_2')
yt_dlp/extractor/clipchamp.py
+61
View File
@@ -0,0 +1,61 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
traverse_obj,
unified_timestamp,
url_or_none,
)
class ClipchampIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clipchamp\.com/watch/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://clipchamp.com/watch/gRXZ4ZhdDaU',
'info_dict': {
'id': 'gRXZ4ZhdDaU',
'ext': 'mp4',
'title': 'Untitled video',
'uploader': 'Alexander Schwartz',
'timestamp': 1680805580,
'upload_date': '20230406',
'thumbnail': r're:^https?://.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}]
_STREAM_URL_TMPL = 'https://%s.cloudflarestream.com/%s/manifest/video.%s'
_STREAM_URL_QUERY = {'parentOrigin': 'https://clipchamp.com'}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['video']
storage_location = data.get('storage_location')
if storage_location != 'cf_stream':
raise ExtractorError(f'Unsupported clip storage location "{storage_location}"')
path = data['download_url']
iframe = self._download_webpage(
f'https://iframe.cloudflarestream.com/{path}', video_id, 'Downloading player iframe')
subdomain = self._search_regex(
r'\bcustomer-domain-prefix=["\']([\w-]+)["\']', iframe,
'subdomain', fatal=False) or 'customer-2ut9yn3y6fta1yxe'
formats = self._extract_mpd_formats(
self._STREAM_URL_TMPL % (subdomain, path, 'mpd'), video_id,
query=self._STREAM_URL_QUERY, fatal=False, mpd_id='dash')
formats.extend(self._extract_m3u8_formats(
self._STREAM_URL_TMPL % (subdomain, path, 'm3u8'), video_id, 'mp4',
query=self._STREAM_URL_QUERY, fatal=False, m3u8_id='hls'))
return {
'id': video_id,
'formats': formats,
'uploader': ' '.join(traverse_obj(data, ('creator', ('first_name', 'last_name'), {str}))) or None,
**traverse_obj(data, {
'title': ('project', 'project_name', {str}),
'timestamp': ('created_at', {unified_timestamp}),
'thumbnail': ('thumbnail_url', {url_or_none}),
}),
}
yt_dlp/extractor/cliphunter.py
-76
View File
@@ -1,76 +0,0 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
url_or_none,
)
class CliphunterIE(InfoExtractor):
IE_NAME = 'cliphunter'
_VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
_TESTS = [{
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
'id': '1012420',
'ext': 'flv',
'title': 'Fun Jynx Maze solo',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
},
'skip': 'Video gone',
}, {
'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
'info_dict': {
'id': '2019449',
'ext': 'mp4',
'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
gexo_files = self._parse_json(
self._search_regex(
r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
video_id)
formats = []
for format_id, f in gexo_files.items():
video_url = url_or_none(f.get('url'))
if not video_url:
continue
fmt = f.get('fmt')
height = f.get('h')
format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
formats.append({
'url': video_url,
'format_id': format_id,
'width': int_or_none(f.get('w')),
'height': int_or_none(height),
'tbr': int_or_none(f.get('br')),
})
thumbnail = self._search_regex(
r"var\s+mov_thumb\s*=\s*'([^']+)';",
webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'title': video_title,
'formats': formats,
'age_limit': self._rta_search(webpage),
'thumbnail': thumbnail,
}
yt_dlp/extractor/cliprs.py
+1
View File
@@ -2,6 +2,7 @@ from .onet import OnetBaseIE
class ClipRsIE(OnetBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
_TEST = {
'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',
yt_dlp/extractor/clipsyndicate.py
-52
View File
@@ -1,52 +0,0 @@
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
fix_xml_ampersands
)
class ClipsyndicateIE(InfoExtractor):
_VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
'md5': '4d7d549451bad625e0ff3d7bd56d776c',
'info_dict': {
'id': '4629301',
'ext': 'mp4',
'title': 'Brick Briscoe',
'duration': 612,
'thumbnail': r're:^https?://.+\.jpg',
},
}, {
'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
js_player = self._download_webpage(
'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
video_id, 'Downlaoding player')
# it includes a required token
flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
pdoc = self._download_xml(
'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
video_id, 'Downloading video info',
transform_source=fix_xml_ampersands)
track_doc = pdoc.find('trackList/track')
def find_param(name):
node = find_xpath_attr(track_doc, './/param', 'name', name)
if node is not None:
return node.attrib['value']
return {
'id': video_id,
'title': find_param('title'),
'url': track_doc.find('location').text,
'thumbnail': find_param('thumbnail'),
'duration': int(find_param('duration')),
}
yt_dlp/extractor/closertotruth.py
+1
View File
@@ -4,6 +4,7 @@ from .common import InfoExtractor
class CloserToTruthIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
yt_dlp/extractor/cloudflarestream.py
+30 -14
View File
@@ -4,27 +4,25 @@ from .common import InfoExtractor
class CloudflareStreamIE(InfoExtractor):
_SUBDOMAIN_RE = r'(?:(?:watch|iframe|customer-\w+)\.)?'
_DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
_EMBED_RE = r'embed\.%s/embed/[^/]+\.js\?.*?\bvideo=' % _DOMAIN_RE
_EMBED_RE = rf'embed\.{_DOMAIN_RE}/embed/[^/]+\.js\?.*?\bvideo='
_ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+'
_VALID_URL = r'''(?x)
https?://
(?:
(?:watch\.)?%s/|
%s
)
(?P<id>%s)
''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE)
_EMBED_REGEX = [fr'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE}).*?)\1']
_VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}{_DOMAIN_RE}/|{_EMBED_RE})(?P<id>{_ID_RE})'
_EMBED_REGEX = [
rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE}).*?)\1',
rf'<iframe[^>]+\bsrc=["\'](?P<url>https?://{_SUBDOMAIN_RE}{_DOMAIN_RE}/[\da-f]{{32}})',
]
_TESTS = [{
'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
'info_dict': {
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
'thumbnail': 'https://videodelivery.net/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': True,
'skip_download': 'm3u8',
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -35,6 +33,21 @@ class CloudflareStreamIE(InfoExtractor):
}, {
'url': 'https://embed.videodelivery.net/embed/r4xu.fla9.latest.js?video=81d80727f3022488598f68d323c1ad5e',
'only_matching': True,
}, {
'url': 'https://customer-aw5py76sw8wyqzmh.cloudflarestream.com/2463f6d3e06fa29710a337f5f5389fd8/iframe',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://upride.cc/incident/shoulder-pass-at-light/',
'info_dict': {
'id': 'eaef9dea5159cf968be84241b5cedfe7',
'ext': 'mp4',
'title': 'eaef9dea5159cf968be84241b5cedfe7',
'thumbnail': 'https://videodelivery.net/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': 'm3u8',
},
}]
def _real_extract(self, url):
@@ -46,15 +59,18 @@ class CloudflareStreamIE(InfoExtractor):
video_id.split('.')[1] + '==='), video_id)['sub']
manifest_base_url = base_url + 'manifest/video.'
formats = self._extract_m3u8_formats(
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
manifest_base_url + 'm3u8', video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
formats.extend(self._extract_mpd_formats(
manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False))
fmts, subs = self._extract_mpd_formats_and_subtitles(
manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'title': video_id,
'thumbnail': base_url + 'thumbnails/thumbnail.jpg',
'formats': formats,
'subtitles': subtitles,
}
yt_dlp/extractor/cloudy.py
-57
View File
@@ -1,57 +0,0 @@
from .common import InfoExtractor
from ..utils import (
str_to_int,
unified_strdate,
)
class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec'
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',
'md5': '29832b05028ead1b58be86bf319397ca',
'info_dict': {
'id': 'af511e2527aac',
'ext': 'mp4',
'title': 'Funny Cats and Animals Compilation june 2013',
'upload_date': '20130913',
'view_count': int,
}
}, {
'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.cloudy.ec/embed.php', video_id, query={
'id': video_id,
'playerPage': 1,
'autoplay': 1,
})
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
webpage = self._download_webpage(
'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
if webpage:
info.update({
'title': self._search_regex(
r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
'upload_date': unified_strdate(self._search_regex(
r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
'upload date', fatal=False)),
'view_count': str_to_int(self._search_regex(
r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
})
if not info.get('title'):
info['title'] = video_id
info['id'] = video_id
return info
yt_dlp/extractor/cloudycdn.py
+79
View File
@@ -0,0 +1,79 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class CloudyCDNIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//embed\.cloudycdn\.services/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://embed.cloudycdn.services/ltv/media/46k_d23-6000-105?',
'md5': '64f72a360ca530d5ed89c77646c9eee5',
'info_dict': {
'id': '46k_d23-6000-105',
'ext': 'mp4',
'timestamp': 1700589151,
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
}
}, {
'url': 'https://embed.cloudycdn.services/izm/media/26e_lv-8-5-1',
'md5': '798828a479151e2444d8dcfbec76e482',
'info_dict': {
'id': '26e_lv-8-5-1',
'ext': 'mp4',
'title': 'LV-8-5-1',
'timestamp': 1669767167,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'duration': 1205,
'upload_date': '20221130',
}
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.tavaklase.lv/video/es-esmu-mina-um-2/',
'md5': '63074e8e6c84ac2a01f2fb8bf03b8f43',
'info_dict': {
'id': 'cqd_lib-2',
'ext': 'mp4',
'upload_date': '20230223',
'duration': 629,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'timestamp': 1677181513,
'title': 'LIB-2',
}
}]
def _real_extract(self, url):
site_id, video_id = self._match_valid_url(url).group('site_id', 'id')
data = self._download_json(
f'https://player.cloudycdn.services/player/{site_id}/media/{video_id}/',
video_id, data=urlencode_postdata({
'version': '6.4.0',
'referer': url,
}))
formats, subtitles = [], {}
for m3u8_url in traverse_obj(data, ('source', 'sources', ..., 'src', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(data, {
'title': ('name', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': ('upload_date', {parse_iso8601}),
'thumbnail': ('source', 'poster', {url_or_none}),
}),
}

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