Cool_Tools/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-20 05:47:24 +01:00
Code Issues Packages Projects Releases Wiki Activity

[ie/npo] Fix hetklokhuis extractor

Browse Source
This commit is contained in:
DTrombett 2024-10-11 20:25:03 +02:00
parent 2e9c00649c
commit e569c03196
No known key found for this signature in database
GPG Key ID: FD8700F69650F6AA
1 changed files with 24 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
yt_dlp/extractor/npo.py
View File

@ -247,20 +247,6 @@ def _real_extract(self, url):
return self._extract_product_id_information(self._match_id(url)) return self._extract_product_id_information(self._match_id(url))
class NPODataMidEmbedIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
return {
'_type': 'url_transparent',
'ie_key': 'NPO',
'url': f'npo:{video_id}',
'display_id': display_id,
}
class SchoolTVIE(NPOBaseIE): class SchoolTVIE(NPOBaseIE):
IE_NAME = 'schooltv' IE_NAME = 'schooltv'
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video-item/(?P<id>[^/?#&]+)'
@ -279,29 +265,40 @@ class SchoolTVIE(NPOBaseIE):
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = re.search(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url)))).group(1) video_id = self._search_regex(r'id=([a-zA-Z0-9_]+)', self._html_search_meta(('og:video', 'og:video:secure_url'), self._download_webpage(url, self._match_id(url))), 'video id')
return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token']) return self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
class HetKlokhuisIE(NPODataMidEmbedIE): class HetKlokhuisIE(NPOBaseIE):
IE_NAME = 'hetklokhuis' IE_NAME = 'hetklokhuis'
_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = { _TEST = {
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven', 'url': 'https://hetklokhuis.nl/dossier/142/zoek-het-uit/tv-uitzending/2987/aliens',
'md5': '679d610017689ecc798b316b8daa34e7',
'info_dict': { 'info_dict': {
'id': 'VPWON_1260528', 'id': 'VPWON_1225126',
'display_id': 'Zwaartekrachtsgolven', 'ext': 'mp4',
'ext': 'm4v', 'duration': 852.27,
'title': 'Het Klokhuis: Zwaartekrachtsgolven', 'channel_id': 'NED3',
'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48', 'description': 'md5:17681c9644521344a0573e04c78912d7',
'upload_date': '20170223', 'title': 'Aliens',
}, 'genres': ['Jeugd', 'Informatief'],
'params': { 'thumbnail': 'https://images.poms.omroep.nl/image/s1080/624824',
'skip_download': True, 'uploader_id': 'NED3',
'series': 'Zoek Het Uit!',
}, },
} }
def _real_extract(self, url):
webpage = self._download_webpage(url, self._match_id(url))
series, title = self._html_search_meta('og:title', webpage, 'title').split(' - ')
video_id = self._html_search_regex(r'data-mid="([a-zA-Z0-9_]+)"', webpage, 'video id')
data = self._extract_info_from_token(video_id, self._download_json(f'https://api3.schooltv.nl/player/{video_id}', video_id, 'Downloading token JSON')['data']['token'])
data['series'] = series
data['title'] = title
return data
class NPOPlaylistBaseIE(NPOBaseIE): # XXX: Do not subclass from concrete IE class NPOPlaylistBaseIE(NPOBaseIE): # XXX: Do not subclass from concrete IE
def _real_extract(self, url): def _real_extract(self, url):