youtube_dl/extractor/tvanouvelles.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .brightcove import BrightcoveNewIE
   8
   9
  10 class TVANouvellesIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/videos/(?P<id>\d+)'
  12     _TEST = {
  13         'url': 'http://www.tvanouvelles.ca/videos/5117035533001',
  14         'info_dict': {
  15             'id': '5117035533001',
  16             'ext': 'mp4',
  17             'title': 'L’industrie du taxi dénonce l’entente entre Québec et Uber: explications',
  18             'description': 'md5:479653b7c8cf115747bf5118066bd8b3',
  19             'uploader_id': '1741764581',
  20             'timestamp': 1473352030,
  21             'upload_date': '20160908',
  22         },
  23         'add_ie': ['BrightcoveNew'],
  24     }
  25     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1741764581/default_default/index.html?videoId=%s'
  26
  27     def _real_extract(self, url):
  28         brightcove_id = self._match_id(url)
  29         return self.url_result(
  30             self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  31             BrightcoveNewIE.ie_key(), brightcove_id)
  32
  33
  34 class TVANouvellesArticleIE(InfoExtractor):
  35     _VALID_URL = r'https?://(?:www\.)?tvanouvelles\.ca/(?:[^/]+/)+(?P<id>[^/?#&]+)'
  36     _TEST = {
  37         'url': 'http://www.tvanouvelles.ca/2016/11/17/des-policiers-qui-ont-la-meche-un-peu-courte',
  38         'info_dict': {
  39             'id': 'des-policiers-qui-ont-la-meche-un-peu-courte',
  40             'title': 'Des policiers qui ont «la mèche un peu courte»?',
  41             'description': 'md5:92d363c8eb0f0f030de9a4a84a90a3a0',
  42         },
  43         'playlist_mincount': 4,
  44     }
  45
  46     @classmethod
  47     def suitable(cls, url):
  48         return False if TVANouvellesIE.suitable(url) else super(TVANouvellesArticleIE, cls).suitable(url)
  49
  50     def _real_extract(self, url):
  51         display_id = self._match_id(url)
  52
  53         webpage = self._download_webpage(url, display_id)
  54
  55         entries = [
  56             self.url_result(
  57                 'http://www.tvanouvelles.ca/videos/%s' % mobj.group('id'),
  58                 ie=TVANouvellesIE.ie_key(), video_id=mobj.group('id'))
  59             for mobj in re.finditer(
  60                 r'data-video-id=(["\'])?(?P<id>\d+)', webpage)]
  61
  62         title = self._og_search_title(webpage, fatal=False)
  63         description = self._og_search_description(webpage)
  64
  65         return self.playlist_result(entries, display_id, title, description)