[arkena:lcp] Add extractors
[youtube-dl] / youtube_dl / extractor / lcp.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3 from .common import InfoExtractor
4
5 class LcpIE(InfoExtractor):
6     IE_NAME = 'LCP'
7     _VALID_URL = r'https?://(?:www\.)?lcp\.fr/(?:[^\/]+/)*(?P<id>[^/]+)'
8
9     _TESTS = [{
10         'url': 'http://www.lcp.fr/la-politique-en-video/schwartzenberg-prg-preconise-francois-hollande-de-participer-une-primaire',
11         'md5': 'ab96c4dae94322ece1e98d97c8dc7807',
12         'info_dict': {
13             'id': 'd56d03e9',
14             'url': 're:http://httpod.scdn.arkena.com/11970/d56d03e9_.*',
15             'ext': 'mp4',
16             'title': 'd56d03e9',
17             'upload_date': '20160226',
18             'timestamp': 1456488895
19         }
20     }, {
21         'url': 'http://www.lcp.fr/le-direct',
22         'info_dict': {
23             'title': 'Le direct | LCP Assembl\xe9e nationale',
24             'id': 'le-direct',
25         },
26         'playlist_mincount': 1
27     }]
28
29     def _real_extract(self, url):
30         display_id = self._match_id(url)
31         webpage = self._download_webpage(url, display_id)
32
33         embed_url_regex = r'"(?P<url>(?:https?://(?:www\.)?)?play\.lcp\.fr/embed/[A-za-z0-9]+/[A-za-z0-9]+/[A-za-z0-9]+/[A-za-z0-9]+)"'
34         embed_url = self._html_search_regex(embed_url_regex, webpage, 'player_url', default=None, fatal=False)
35         if not embed_url:
36             return self.url_result(url, 'Generic')
37
38         title = self._og_search_title(webpage, default=None)
39         return self.url_result(embed_url, 'ArkenaPlay', video_id=display_id, video_title=title)