yt_dlp/extractor/tvanouvelles.py

   1 import re
   2
   3 from .brightcove import BrightcoveNewIE
   4 from .common import InfoExtractor
   5
   6
   7 class TVANouvellesIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/videos/(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'http://www.tvanouvelles.ca/videos/5117035533001',
  11         'info_dict': {
  12             'id': '5117035533001',
  13             'ext': 'mp4',
  14             'title': 'L’industrie du taxi dénonce l’entente entre Québec et Uber: explications',
  15             'description': 'md5:479653b7c8cf115747bf5118066bd8b3',
  16             'uploader_id': '1741764581',
  17             'timestamp': 1473352030,
  18             'upload_date': '20160908',
  19         },
  20         'add_ie': ['BrightcoveNew'],
  21     }
  22     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1741764581/default_default/index.html?videoId=%s'
  23
  24     def _real_extract(self, url):
  25         brightcove_id = self._match_id(url)
  26         return self.url_result(
  27             self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  28             BrightcoveNewIE.ie_key(), brightcove_id)
  29
  30
  31 class TVANouvellesArticleIE(InfoExtractor):
  32     _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/(?:[^/]+/)+(?P<id>[^/?#&]+)'
  33     _TEST = {
  34         'url': 'http://www.tvanouvelles.ca/2016/11/17/des-policiers-qui-ont-la-meche-un-peu-courte',
  35         'info_dict': {
  36             'id': 'des-policiers-qui-ont-la-meche-un-peu-courte',
  37             'title': 'Des policiers qui ont «la mèche un peu courte»?',
  38             'description': 'md5:92d363c8eb0f0f030de9a4a84a90a3a0',
  39         },
  40         'playlist_mincount': 4,
  41     }
  42
  43     @classmethod
  44     def suitable(cls, url):
  45         return False if TVANouvellesIE.suitable(url) else super().suitable(url)
  46
  47     def _real_extract(self, url):
  48         display_id = self._match_id(url)
  49
  50         webpage = self._download_webpage(url, display_id)
  51
  52         entries = [
  53             self.url_result(
  54                 'http://www.tvanouvelles.ca/videos/{}'.format(mobj.group('id')),
  55                 ie=TVANouvellesIE.ie_key(), video_id=mobj.group('id'))
  56             for mobj in re.finditer(
  57                 r'data-video-id=(["\'])?(?P<id>\d+)', webpage)]
  58
  59         title = self._og_search_title(webpage, fatal=False)
  60         description = self._og_search_description(webpage)
  61
  62         return self.playlist_result(entries, display_id, title, description)