lci.py (953B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 from .common import InfoExtractor 5 6 7 class LCIIE(InfoExtractor): 8 _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html' 9 _TEST = { 10 'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html', 11 'md5': '2fdb2538b884d4d695f9bd2bde137e6c', 12 'info_dict': { 13 'id': '13244802', 14 'ext': 'mp4', 15 'title': 'Hillary Clinton et sa quinte de toux, en plein meeting', 16 'description': 'md5:a4363e3a960860132f8124b62f4a01c9', 17 } 18 } 19 20 def _real_extract(self, url): 21 video_id = self._match_id(url) 22 webpage = self._download_webpage(url, video_id) 23 wat_id = self._search_regex( 24 (r'data-watid=[\'"](\d+)', r'idwat["\']?\s*:\s*["\']?(\d+)'), 25 webpage, 'wat id') 26 return self.url_result('wat:' + wat_id, 'Wat', wat_id)