mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-04 15:33:16 +00:00
Add test. Clear dead VRT extractors
This commit is contained in:
bergoid
parent
0e5d60d206
commit
f0075841e8
|
|
@ -246,12 +246,6 @@
|
||||||
from .canalalpha import CanalAlphaIE
|
from .canalalpha import CanalAlphaIE
|
||||||
from .canalplus import CanalplusIE
|
from .canalplus import CanalplusIE
|
||||||
from .canalc2 import Canalc2IE
|
from .canalc2 import Canalc2IE
|
||||||
from .canvas import (
|
|
||||||
CanvasIE,
|
|
||||||
CanvasEenIE,
|
|
||||||
VrtNUIE,
|
|
||||||
DagelijkseKostIE,
|
|
||||||
)
|
|
||||||
from .carambatv import (
|
from .carambatv import (
|
||||||
CarambaTVIE,
|
CarambaTVIE,
|
||||||
CarambaTVPageIE,
|
CarambaTVPageIE,
|
||||||
|
|
@ -786,7 +780,6 @@
|
||||||
from .karrierevideos import KarriereVideosIE
|
from .karrierevideos import KarriereVideosIE
|
||||||
from .keezmovies import KeezMoviesIE
|
from .keezmovies import KeezMoviesIE
|
||||||
from .kelbyone import KelbyOneIE
|
from .kelbyone import KelbyOneIE
|
||||||
from .ketnet import KetnetIE
|
|
||||||
from .khanacademy import (
|
from .khanacademy import (
|
||||||
KhanAcademyIE,
|
KhanAcademyIE,
|
||||||
KhanAcademyUnitIE,
|
KhanAcademyUnitIE,
|
||||||
|
|
|
||||||
|
|
@ -1,367 +0,0 @@
|
||||||
import json
|
|
||||||
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
|
||||||
from .gigya import GigyaBaseIE
|
|
||||||
from ..compat import compat_HTTPError
|
|
||||||
from ..utils import (
|
|
||||||
ExtractorError,
|
|
||||||
clean_html,
|
|
||||||
float_or_none,
|
|
||||||
get_element_by_class,
|
|
||||||
str_or_none,
|
|
||||||
strip_or_none,
|
|
||||||
url_or_none,
|
|
||||||
urlencode_postdata
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class CanvasIE(InfoExtractor):
|
|
||||||
_VALID_URL = r'https://media-services-public\.vrt\.be/media-aggregator/v2/media-items/(?P<video_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_TOKEN = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v2'
|
|
||||||
_REST_API_BASE_VIDEO = 'https://media-services-public.vrt.be/media-aggregator/v2'
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
mobj = self._match_valid_url(url)
|
|
||||||
video_id = mobj.group('video_id')
|
|
||||||
|
|
||||||
data = None
|
|
||||||
|
|
||||||
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_TOKEN, video_id,
|
|
||||||
'Downloading token', headers=headers, data=json.dumps({
|
|
||||||
'identityToken': vrtnutoken
|
|
||||||
}).encode('utf-8'))['vrtPlayerToken']
|
|
||||||
data = self._download_json(
|
|
||||||
'%s/media-items/%s' % (self._REST_API_BASE_VIDEO, video_id),
|
|
||||||
video_id, 'Downloading video JSON', query={
|
|
||||||
'vrtPlayerToken': vrtPlayerToken,
|
|
||||||
'client': 'vrtnu-web@PROD',
|
|
||||||
}, 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'{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,
|
|
||||||
})
|
|
||||||
self._sort_formats(formats)
|
|
||||||
|
|
||||||
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/(?P<show>.+)/(?P<year>[0-9]{4})/(?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)
|
|
||||||
|
|
||||||
episode_data = self._download_json(f'{url.strip("/")}.model.json', display_id,
|
|
||||||
'Downloading asset JSON', 'Unable to download asset JSON')
|
|
||||||
details = episode_data.get('details')
|
|
||||||
actions = details.get('actions')
|
|
||||||
episode_publication_id = actions[2].get('episodePublicationId')
|
|
||||||
episode_video_id = actions[2].get('episodeVideoId')
|
|
||||||
video_id = f'{episode_publication_id}${episode_video_id}'
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'url': 'https://media-services-public.vrt.be/media-aggregator/v2/media-items/%s' % video_id,
|
|
||||||
'ie_key': 'Canvas',
|
|
||||||
'id': video_id,
|
|
||||||
'display_id': display_id
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
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$',
|
|
||||||
'duration': 283.02,
|
|
||||||
},
|
|
||||||
'expected_warnings': ['is not a supported codec'],
|
|
||||||
}
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
display_id = self._match_id(url)
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
|
||||||
|
|
||||||
title = strip_or_none(get_element_by_class(
|
|
||||||
'dish-metadata__title', webpage
|
|
||||||
) or self._html_search_meta(
|
|
||||||
'twitter:title', webpage))
|
|
||||||
|
|
||||||
description = clean_html(get_element_by_class(
|
|
||||||
'dish-description', webpage)
|
|
||||||
) or self._html_search_meta(
|
|
||||||
('description', 'twitter:description', 'og:description'),
|
|
||||||
webpage)
|
|
||||||
|
|
||||||
video_id = self._html_search_regex(
|
|
||||||
r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
|
|
||||||
group='id')
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
|
|
||||||
'ie_key': CanvasIE.ie_key(),
|
|
||||||
'id': video_id,
|
|
||||||
'display_id': display_id,
|
|
||||||
'title': title,
|
|
||||||
'description': description,
|
|
||||||
}
|
|
||||||
|
|
@ -1,70 +0,0 @@
|
||||||
from .canvas import CanvasIE
|
|
||||||
from .common import InfoExtractor
|
|
||||||
from ..compat import compat_urllib_parse_unquote
|
|
||||||
from ..utils import (
|
|
||||||
int_or_none,
|
|
||||||
parse_iso8601,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class KetnetIE(InfoExtractor):
|
|
||||||
_VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?P<id>(?:[^/]+/)*[^/?#&]+)'
|
|
||||||
_TESTS = [{
|
|
||||||
'url': 'https://www.ketnet.be/kijken/n/nachtwacht/3/nachtwacht-s3a1-de-greystook',
|
|
||||||
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'pbs-pub-aef8b526-115e-4006-aa24-e59ff6c6ef6f$vid-ddb815bf-c8e7-467b-8879-6bad7a32cebd',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'Nachtwacht - Reeks 3: Aflevering 1',
|
|
||||||
'description': 'De Nachtwacht krijgt te maken met een parasiet',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'duration': 1468.02,
|
|
||||||
'timestamp': 1609225200,
|
|
||||||
'upload_date': '20201229',
|
|
||||||
'series': 'Nachtwacht',
|
|
||||||
'season': 'Reeks 3',
|
|
||||||
'episode': 'De Greystook',
|
|
||||||
'episode_number': 1,
|
|
||||||
},
|
|
||||||
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.ketnet.be/themas/karrewiet/jaaroverzicht-20200/karrewiet-het-jaar-van-black-mamba',
|
|
||||||
'only_matching': True,
|
|
||||||
}]
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
display_id = self._match_id(url)
|
|
||||||
|
|
||||||
video = self._download_json(
|
|
||||||
'https://senior-bff.ketnet.be/graphql', display_id, query={
|
|
||||||
'query': '''{
|
|
||||||
video(id: "content/ketnet/nl/%s.model.json") {
|
|
||||||
description
|
|
||||||
episodeNr
|
|
||||||
imageUrl
|
|
||||||
mediaReference
|
|
||||||
programTitle
|
|
||||||
publicationDate
|
|
||||||
seasonTitle
|
|
||||||
subtitleVideodetail
|
|
||||||
titleVideodetail
|
|
||||||
}
|
|
||||||
}''' % display_id,
|
|
||||||
})['data']['video']
|
|
||||||
|
|
||||||
mz_id = compat_urllib_parse_unquote(video['mediaReference'])
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'id': mz_id,
|
|
||||||
'title': video['titleVideodetail'],
|
|
||||||
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/' + mz_id,
|
|
||||||
'thumbnail': video.get('imageUrl'),
|
|
||||||
'description': video.get('description'),
|
|
||||||
'timestamp': parse_iso8601(video.get('publicationDate')),
|
|
||||||
'series': video.get('programTitle'),
|
|
||||||
'season': video.get('seasonTitle'),
|
|
||||||
'episode': video.get('subtitleVideodetail'),
|
|
||||||
'episode_number': int_or_none(video.get('episodeNr')),
|
|
||||||
'ie_key': CanvasIE.ie_key(),
|
|
||||||
}
|
|
||||||
|
|
@ -1,82 +1,178 @@
|
||||||
from .common import InfoExtractor
|
import json
|
||||||
|
|
||||||
|
from .gigya import GigyaBaseIE
|
||||||
|
from ..compat import compat_HTTPError
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
extract_attributes,
|
ExtractorError,
|
||||||
float_or_none,
|
float_or_none,
|
||||||
get_element_by_class,
|
str_or_none,
|
||||||
strip_or_none,
|
url_or_none,
|
||||||
unified_timestamp,
|
urlencode_postdata
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class VRTIE(InfoExtractor):
|
class VRTIE(GigyaBaseIE):
|
||||||
IE_DESC = 'VRT NWS, Flanders News, Flandern Info and Sporza'
|
IE_DESC = 'VRT'
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?P<site>vrt\.be/vrtnws|sporza\.be)/[a-z]{2}/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)'
|
_VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?P<id>.+)/?'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.vrt.be/vrtnws/nl/2019/05/15/beelden-van-binnenkant-notre-dame-een-maand-na-de-brand/',
|
'url': 'https://www.vrt.be/vrtnu/a-z/heizel-1985/trailer/heizel-1985-trailer/',
|
||||||
'md5': 'e1663accf5cf13f375f3cd0d10476669',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'pbs-pub-7855fc7b-1448-49bc-b073-316cb60caa71$vid-2ca50305-c38a-4762-9890-65cbd098b7bd',
|
'id': 'pbs-pub-e1d6e4ec-cbf4-451e-9e87-d835bb65cd28$vid-2ad45eb6-9bc8-40d4-ad72-5f25c0f59d75',
|
||||||
'ext': 'mp4',
|
'title': 'Trailer \'Heizel 1985\'',
|
||||||
'title': 'Beelden van binnenkant Notre-Dame, één maand na de brand',
|
'thumbnail': 'https://images.vrt.be/orig/2022/09/07/6e44ce6f-2eb3-11ed-b07d-02b7b76bf47f.jpg',
|
||||||
'description': 'Op maandagavond 15 april ging een deel van het dakgebinte van de Parijse kathedraal in vlammen op.',
|
'duration': 41.05
|
||||||
'timestamp': 1557924660,
|
|
||||||
'upload_date': '20190515',
|
|
||||||
'duration': 31.2,
|
|
||||||
},
|
},
|
||||||
}, {
|
|
||||||
'url': 'https://sporza.be/nl/2019/05/15/de-belgian-cats-zijn-klaar-voor-het-ek/',
|
|
||||||
'md5': '910bba927566e9ab992278f647eb4b75',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'pbs-pub-f2c86a46-8138-413a-a4b9-a0015a16ce2c$vid-1f112b31-e58e-4379-908d-aca6d80f8818',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'De Belgian Cats zijn klaar voor het EK mét Ann Wauters',
|
|
||||||
'timestamp': 1557923760,
|
|
||||||
'upload_date': '20190515',
|
|
||||||
'duration': 115.17,
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.vrt.be/vrtnws/en/2019/05/15/belgium_s-eurovision-entry-falls-at-the-first-hurdle/',
|
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'https://www.vrt.be/vrtnws/de/2019/05/15/aus-fuer-eliott-im-halbfinale-des-eurosongfestivals/',
|
|
||||||
'only_matching': True,
|
|
||||||
}]
|
}]
|
||||||
_CLIENT_MAP = {
|
_NETRC_MACHINE = 'vrtnu'
|
||||||
'vrt.be/vrtnws': 'vrtnieuws',
|
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
|
||||||
'sporza.be': 'sporza',
|
_CONTEXT_ID = 'R3595707040'
|
||||||
|
_REST_API_BASE_TOKEN = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v2'
|
||||||
|
_REST_API_BASE_VIDEO = 'https://media-services-public.vrt.be/media-aggregator/v2'
|
||||||
|
_HLS_ENTRY_PROTOCOLS_MAP = {
|
||||||
|
'HLS': 'm3u8_native',
|
||||||
|
'HLS_AES': 'm3u8_native',
|
||||||
}
|
}
|
||||||
|
|
||||||
|
_authenticated = False
|
||||||
|
|
||||||
|
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
|
||||||
|
|
||||||
|
self._authenticated = True
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
site, display_id = self._match_valid_url(url).groups()
|
display_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, display_id)
|
|
||||||
attrs = extract_attributes(self._search_regex(
|
|
||||||
r'(<[^>]+class="vrtvideo( [^"]*)?"[^>]*>)', webpage, 'vrt video'))
|
|
||||||
|
|
||||||
asset_id = attrs['data-video-id']
|
episode_data = self._download_json(f'{url.strip("/")}.model.json', display_id,
|
||||||
publication_id = attrs.get('data-publication-id')
|
'Downloading asset JSON', 'Unable to download asset JSON')
|
||||||
if publication_id:
|
details = episode_data.get('details')
|
||||||
asset_id = publication_id + '$' + asset_id
|
actions = details.get('actions')
|
||||||
client = attrs.get('data-client-code') or self._CLIENT_MAP[site]
|
episode_publication_id = actions[2].get('episodePublicationId')
|
||||||
|
episode_video_id = actions[2].get('episodeVideoId')
|
||||||
|
video_id = f'{episode_publication_id}${episode_video_id}'
|
||||||
|
|
||||||
title = strip_or_none(get_element_by_class(
|
data = None
|
||||||
'vrt-title', webpage) or self._html_search_meta(
|
vrtnutoken = ""
|
||||||
['og:title', 'twitter:title', 'name'], webpage))
|
|
||||||
description = self._html_search_meta(
|
if self._authenticated:
|
||||||
['og:description', 'twitter:description', 'description'], webpage)
|
vrtnutoken = self._download_json('https://token.vrt.be/refreshtoken',
|
||||||
if description == '…':
|
video_id, note='refreshtoken: Retrieve vrtnutoken',
|
||||||
description = None
|
errnote='refreshtoken failed')['vrtnutoken']
|
||||||
timestamp = unified_timestamp(self._html_search_meta(
|
|
||||||
'article:published_time', webpage))
|
headers = self.geo_verification_headers()
|
||||||
|
headers.update({'Content-Type': 'application/json; charset=utf-8'})
|
||||||
|
vrtPlayerToken = self._download_json(
|
||||||
|
'%s/tokens' % self._REST_API_BASE_TOKEN, video_id,
|
||||||
|
'Downloading token', headers=headers, data=json.dumps({
|
||||||
|
'identityToken': vrtnutoken
|
||||||
|
}).encode('utf-8'))['vrtPlayerToken']
|
||||||
|
|
||||||
|
data = self._download_json(
|
||||||
|
'%s/media-items/%s' % (self._REST_API_BASE_VIDEO, video_id),
|
||||||
|
video_id, 'Downloading video JSON', query={
|
||||||
|
'vrtPlayerToken': vrtPlayerToken,
|
||||||
|
'client': 'vrtnu-web@PROD',
|
||||||
|
}, 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'{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,
|
||||||
|
})
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
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 {
|
return {
|
||||||
'_type': 'url_transparent',
|
'id': video_id,
|
||||||
'id': asset_id,
|
'display_id': video_id,
|
||||||
'display_id': display_id,
|
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'description': description,
|
||||||
'thumbnail': attrs.get('data-posterimage'),
|
'formats': formats,
|
||||||
'timestamp': timestamp,
|
'duration': float_or_none(data.get('duration'), 1000),
|
||||||
'duration': float_or_none(attrs.get('data-duration'), 1000),
|
'thumbnail': data.get('posterImageUrl'),
|
||||||
'url': 'https://mediazone.vrt.be/api/v1/%s/assets/%s' % (client, asset_id),
|
'subtitles': subtitles,
|
||||||
'ie_key': 'Canvas',
|
|
||||||
}
|
}
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue