_ Git - youtube-dl/blob - youtube_dl/extractor/noovo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .brightcove import BrightcoveNewIE
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     smuggle_url,
  10     try_get,
  11 )
  12
  13
  14 class NoovoIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
  16     _TESTS = [{
  17         # clip
  18         'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
  19         'info_dict': {
  20             'id': '5386045029001',
  21             'ext': 'mp4',
  22             'title': 'Chrysler Imperial',
  23             'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
  24             'timestamp': 1491399228,
  25             'upload_date': '20170405',
  26             'uploader_id': '618566855001',
  27             'creator': 'vtele',
  28             'view_count': int,
  29             'series': 'RPM+',
  30         },
  31         'params': {
  32             'skip_download': True,
  33         },
  34     }, {
  35         # episode
  36         'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
  37         'info_dict': {
  38             'id': '5395865725001',
  39             'title': 'Épisode 13 : Les retrouvailles',
  40             'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
  41             'ext': 'mp4',
  42             'timestamp': 1492019320,
  43             'upload_date': '20170412',
  44             'uploader_id': '618566855001',
  45             'creator': 'vtele',
  46             'view_count': int,
  47             'series': "L'amour est dans le pré",
  48             'season_number': 5,
  49             'episode': 'Épisode 13',
  50             'episode_number': 13,
  51         },
  52         'params': {
  53             'skip_download': True,
  54         },
  55     }]
  56     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60
  61         data = self._download_json(
  62             'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
  63             video_id)['data']
  64
  65         content = try_get(data, lambda x: x['contents'][0])
  66
  67         brightcove_id = data.get('brightcoveId') or content['brightcoveId']
  68
  69         series = try_get(
  70             data, (
  71                 lambda x: x['show']['title'],
  72                 lambda x: x['season']['show']['title']),
  73             compat_str)
  74
  75         episode = None
  76         og = data.get('og')
  77         if isinstance(og, dict) and og.get('type') == 'video.episode':
  78             episode = og.get('title')
  79
  80         video = content or data
  81
  82         return {
  83             '_type': 'url_transparent',
  84             'ie_key': BrightcoveNewIE.ie_key(),
  85             'url': smuggle_url(
  86                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  87                 {'geo_countries': ['CA']}),
  88             'id': brightcove_id,
  89             'title': video.get('title'),
  90             'creator': video.get('source'),
  91             'view_count': int_or_none(video.get('viewsCount')),
  92             'series': series,
  93             'season_number': int_or_none(try_get(
  94                 data, lambda x: x['season']['seasonNumber'])),
  95             'episode': episode,
  96             'episode_number': int_or_none(data.get('episodeNumber')),
  97         }