diff options
| author | Chris Caruso <carusochrisr@gmail.com> | 2023-03-04 11:22:11 -0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-05 00:52:11 +0530 |
| commit | 1f8489cccbdc6e96027ef527b88717458f0900e8 (patch) | |
| tree | 7dba674eaf74e90737c26233eb3f862387c81397 | |
| parent | ed4cc4ea793314c50ae3f82e98248c1de1c25694 (diff) | |
| download | hypervideo-pre-1f8489cccbdc6e96027ef527b88717458f0900e8.tar.lz hypervideo-pre-1f8489cccbdc6e96027ef527b88717458f0900e8.tar.xz hypervideo-pre-1f8489cccbdc6e96027ef527b88717458f0900e8.zip | |
[extractor/lumni] Add extractor (#6302)
Authored by: carusocr
Closes #6202
| -rw-r--r-- | yt_dlp/extractor/_extractors.py | 3 | ||||
| -rw-r--r-- | yt_dlp/extractor/lumni.py | 24 |
2 files changed, 27 insertions, 0 deletions
diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 0731845ba..ccac634b3 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -962,6 +962,9 @@ from .lrt import ( LRTVODIE, LRTStreamIE ) +from .lumni import ( + LumniIE +) from .lynda import ( LyndaIE, LyndaCourseIE diff --git a/yt_dlp/extractor/lumni.py b/yt_dlp/extractor/lumni.py new file mode 100644 index 000000000..5810da0c8 --- /dev/null +++ b/yt_dlp/extractor/lumni.py @@ -0,0 +1,24 @@ +from .common import InfoExtractor +from .francetv import FranceTVIE + + +class LumniIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?lumni\.fr/video/(?P<id>[\w-]+)' + _TESTS = [{ + 'url': 'https://www.lumni.fr/video/l-homme-et-son-environnement-dans-la-revolution-industrielle', + 'md5': '960e8240c4f2c7a20854503a71e52f5e', + 'info_dict': { + 'id': 'd2b9a4e5-a526-495b-866c-ab72737e3645', + 'ext': 'mp4', + 'title': "L'homme et son environnement dans la révolution industrielle - L'ère de l'homme", + 'thumbnail': 'https://assets.webservices.francetelevisions.fr/v1/assets/images/a7/17/9f/a7179f5f-63a5-4e11-8d4d-012ab942d905.jpg', + 'duration': 230, + } + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._html_search_regex( + r'<div[^>]+data-factoryid\s*=\s*["\']([^"\']+)', webpage, 'video id') + return self.url_result(f'francetv:{video_id}', FranceTVIE, video_id) |