administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 10:50:38 +00:00
Code Issues Projects Releases Wiki Activity

[ie/LCI] Fix extractor (#10025)

Browse Source 
Authored by: ocococococ
This commit is contained in:
ocococococ 2024-05-26 23:33:15 +02:00 committed by GitHub
parent 119d41f270
commit 5a2eebc767
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 24 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/lci.py
View File

@ -1,9 +1,25 @@
from .common import InfoExtractor from .common import InfoExtractor
from .wat import WatIE
from ..utils import ExtractorError, int_or_none
from ..utils.traversal import traverse_obj
class LCIIE(InfoExtractor): class LCIIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:lci|tf1info)\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html' _VALID_URL = r'https?://(?:www\.)?(?:lci|tf1info)\.fr/(?:[^/?#]+/)+[\w-]+-(?P<id>\d+)\.html'
_TESTS = [{ _TESTS = [{
'url': 'https://www.tf1info.fr/replay-lci/videos/video-24h-pujadas-du-vendredi-24-mai-6708-2300831.html',
'info_dict': {
'id': '14113788',
'ext': 'mp4',
'title': '24H Pujadas du vendredi 24 mai 2024',
'thumbnail': 'https://photos.tf1.fr/1280/720/24h-pujadas-du-24-mai-2024-55bf2d-0@1x.jpg',
'upload_date': '20240524',
'duration': 6158,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.tf1info.fr/politique/election-presidentielle-2022-second-tour-j-2-marine-le-pen-et-emmanuel-macron-en-interview-de-lci-vendredi-soir-2217486.html', 'url': 'https://www.tf1info.fr/politique/election-presidentielle-2022-second-tour-j-2-marine-le-pen-et-emmanuel-macron-en-interview-de-lci-vendredi-soir-2217486.html',
'info_dict': { 'info_dict': {
'id': '13875948', 'id': '13875948',
@ -24,5 +40,10 @@ class LCIIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
wat_id = self._search_regex(r'watId["\']?\s*:\s*["\']?(\d+)', webpage, 'wat id') next_data = self._search_nextjs_data(webpage, video_id)
return self.url_result('wat:' + wat_id, 'Wat', wat_id) wat_id = traverse_obj(next_data, (
'props', 'pageProps', 'page', 'tms', 'videos', {dict.keys}, ..., {int_or_none}, any))
if wat_id is None:
raise ExtractorError('Could not find wat_id')
return self.url_result(f'wat:{wat_id}', WatIE, str(wat_id))