forked from yt-dlp/yt-dlp
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[ie/LCI] Fix extractor (yt-dlp#10025)
Authored by: ocococococ
- Loading branch information
1 parent
119d41f
commit 5a2eebc
Showing
1 changed file
with
24 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,9 +1,25 @@ | ||
from .common import InfoExtractor | ||
from .wat import WatIE | ||
from ..utils import ExtractorError, int_or_none | ||
from ..utils.traversal import traverse_obj | ||
|
||
|
||
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 = [{ | ||
'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/[email protected]', | ||
'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', | ||
'info_dict': { | ||
'id': '13875948', | ||
|
@@ -24,5 +40,10 @@ class LCIIE(InfoExtractor): | |
def _real_extract(self, url): | ||
video_id = self._match_id(url) | ||
webpage = self._download_webpage(url, video_id) | ||
wat_id = self._search_regex(r'watId["\']?\s*:\s*["\']?(\d+)', webpage, 'wat id') | ||
return self.url_result('wat:' + wat_id, 'Wat', wat_id) | ||
next_data = self._search_nextjs_data(webpage, video_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)) |