0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 03:33:02 +00:00
yt-dlp/yt_dlp/extractor/lci.py

27 lines
953 B
Python
Raw Normal View History

2016-09-06 19:47:42 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class LCIIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
_TEST = {
'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
'info_dict': {
'id': '13244802',
'ext': 'mp4',
'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2018-08-19 19:15:48 +00:00
wat_id = self._search_regex(
(r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
webpage, 'wat id')
2016-09-06 19:47:42 +00:00
return self.url_result('wat:' + wat_id, 'Wat', wat_id)