yt_dlp/extractor/noovo.py

   1 from .brightcove import BrightcoveNewIE
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     int_or_none,
   5     js_to_json,
   6     smuggle_url,
   7     try_get,
   8 )
   9
  10
  11 class NoovoIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
  13     _TESTS = [{
  14         # clip
  15         'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
  16         'info_dict': {
  17             'id': '5386045029001',
  18             'ext': 'mp4',
  19             'title': 'Chrysler Imperial',
  20             'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
  21             'timestamp': 1491399228,
  22             'upload_date': '20170405',
  23             'uploader_id': '618566855001',
  24             'series': 'RPM+',
  25         },
  26         'params': {
  27             'skip_download': True,
  28         },
  29     }, {
  30         # episode
  31         'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
  32         'info_dict': {
  33             'id': '5395865725001',
  34             'title': 'Épisode 13 : Les retrouvailles',
  35             'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
  36             'ext': 'mp4',
  37             'timestamp': 1492019320,
  38             'upload_date': '20170412',
  39             'uploader_id': '618566855001',
  40             'series': "L'amour est dans le pré",
  41             'season_number': 5,
  42             'episode': 'Épisode 13',
  43             'episode_number': 13,
  44         },
  45         'params': {
  46             'skip_download': True,
  47         },
  48     }]
  49     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         brightcove_id = self._search_regex(
  57             r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
  58
  59         data = self._parse_json(
  60             self._search_regex(
  61                 r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data',
  62                 default='{}'),
  63             video_id, transform_source=js_to_json, fatal=False)
  64
  65         title = try_get(
  66             data, lambda x: x['video']['nom'],
  67             str) or self._html_search_meta(
  68             'dcterms.Title', webpage, 'title', fatal=True)
  69
  70         description = self._html_search_meta(
  71             ('dcterms.Description', 'description'), webpage, 'description')
  72
  73         series = try_get(
  74             data, lambda x: x['emission']['nom']) or self._search_regex(
  75             r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
  76             webpage, 'series', default=None)
  77
  78         season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
  79         season = try_get(season_el, lambda x: x['nom'], str)
  80         season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
  81
  82         episode_el = try_get(season_el, lambda x: x['episode'], dict) or {}
  83         episode = try_get(episode_el, lambda x: x['nom'], str)
  84         episode_number = int_or_none(try_get(episode_el, lambda x: x['numero']))
  85
  86         return {
  87             '_type': 'url_transparent',
  88             'ie_key': BrightcoveNewIE.ie_key(),
  89             'url': smuggle_url(
  90                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
  91                 {'geo_countries': ['CA']}),
  92             'id': brightcove_id,
  93             'title': title,
  94             'description': description,
  95             'series': series,
  96             'season': season,
  97             'season_number': season_number,
  98             'episode': episode,
  99             'episode_number': episode_number,
 100         }