mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-10-08 10:26:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixes for VRT MAX

Browse source
This commit is contained in:
bergoid 2022-09-11 19:39:17 +02:00
parent 22df97f9c5
commit d39c122abd
1 changed files with 42 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

57
yt_dlp/extractor/canvas.py
View file

@ -20,7 +20,7 @@
class CanvasIE(InfoExtractor): 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>[^/?#&]+)' _VALID_URL = r'https://media-services-public\.vrt\.be/media-aggregator/v2/media-items/(?P<video_id>.+)'
_TESTS = [{ _TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', 'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9', 'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
@ -43,37 +43,30 @@ class CanvasIE(InfoExtractor):
'HLS': 'm3u8_native', 'HLS': 'm3u8_native',
'HLS_AES': 'm3u8_native', 'HLS_AES': 'm3u8_native',
} }
_REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v2' _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): def _real_extract(self, url):
mobj = self._match_valid_url(url) mobj = self._match_valid_url(url)
site_id, video_id = mobj.group('site_id'), mobj.group('id') video_id = mobj.group('video_id')
data = None 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', vrtnutoken = self._download_json('https://token.vrt.be/refreshtoken',
video_id, note='refreshtoken: Retrieve vrtnutoken', video_id, note='refreshtoken: Retrieve vrtnutoken',
errnote='refreshtoken failed')['vrtnutoken'] errnote='refreshtoken failed')['vrtnutoken']
headers = self.geo_verification_headers() headers = self.geo_verification_headers()
headers.update({'Content-Type': 'application/json; charset=utf-8'}) headers.update({'Content-Type': 'application/json; charset=utf-8'})
vrtPlayerToken = self._download_json( vrtPlayerToken = self._download_json(
'%s/tokens' % self._REST_API_BASE, video_id, '%s/tokens' % self._REST_API_BASE_TOKEN, video_id,
'Downloading token', headers=headers, data=json.dumps({ 'Downloading token', headers=headers, data=json.dumps({
'identityToken': vrtnutoken 'identityToken': vrtnutoken
}).encode('utf-8'))['vrtPlayerToken'] }).encode('utf-8'))['vrtPlayerToken']
data = self._download_json( data = self._download_json(
'%s/videos/%s' % (self._REST_API_BASE, video_id), '%s/media-items/%s' % (self._REST_API_BASE_VIDEO, video_id),
video_id, 'Downloading video JSON', query={ video_id, 'Downloading video JSON', query={
'vrtPlayerToken': vrtPlayerToken, 'vrtPlayerToken': vrtPlayerToken,
'client': 'null', 'client': 'vrtnu-web@PROD',
}, expected_status=400) }, expected_status=400)
if 'title' not in data: if 'title' not in data:
code = data.get('code') code = data.get('code')
@ -84,7 +77,7 @@ def _real_extract(self, url):
raise ExtractorError(data.get('message') or code, expected=True) raise ExtractorError(data.get('message') or code, expected=True)
# Note: The title may be an empty string # Note: The title may be an empty string
title = data['title'] or f'{site_id} {video_id}' title = data['title'] or f'{video_id}'
description = data.get('description') description = data.get('description')
formats = [] formats = []
@ -224,7 +217,7 @@ def _real_extract(self, url):
class VrtNUIE(GigyaBaseIE): class VrtNUIE(GigyaBaseIE):
IE_DESC = 'VrtNU.be' IE_DESC = 'VrtNU.be'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?:[^/]+/){2}(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?P<show>.+)/(?P<year>[0-9]{4})/(?P<id>.+)/?'
_TESTS = [{ _TESTS = [{
# Available via old API endpoint # Available via old API endpoint
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/', 'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/',
@ -312,28 +305,21 @@ def _perform_login(self, username, password):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) 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}${episode_video_id}'
attrs = extract_attributes(self._search_regex( return {
r'(<nui-media[^>]+>)', webpage, 'media element'))
video_id = attrs['videoid']
publication_id = attrs.get('publicationid')
if publication_id:
video_id = publication_id + '$' + 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', '_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id, 'url': 'https://media-services-public.vrt.be/media-aggregator/v2/media-items/%s' % video_id,
'ie_key': CanvasIE.ie_key(), 'ie_key': 'Canvas',
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id
'season_number': int_or_none(page.get('episode_season')), }
})
class DagelijkseKostIE(InfoExtractor): class DagelijkseKostIE(InfoExtractor):
@ -382,3 +368,4 @@ def _real_extract(self, url):
'title': title, 'title': title,
'description': description, 'description': description,
} }