yt-dlp/yt_dlp/extractor/lci.py
Pccode66 7a5c1cfe93
Completely change project name to yt-dlp (#85)
* All modules and binary names are changed
* All documentation references changed
* yt-dlp no longer loads youtube-dlc config files
* All URLs changed to point to organization account

Co-authored-by: Pccode66
Co-authored-by: pukkandan
2021-02-25 00:15:56 +05:30

27 lines
953 B
Python

# 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)
wat_id = self._search_regex(
(r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'),
webpage, 'wat id')
return self.url_result('wat:' + wat_id, 'Wat', wat_id)