youtube_dl/extractor/rds.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     parse_iso8601,
   8     js_to_json,
   9 )
  10 from ..compat import compat_str
  11
  12
  13 class RDSIE(InfoExtractor):
  14     IE_DESC = 'RDS.ca'
  15     _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+'
  16
  17     _TESTS = [{
  18         # has two 9c9media ContentPackages, the web player selects the first ContentPackage
  19         'url': 'https://www.rds.ca/videos/Hockey/NationalHockeyLeague/teams/9/forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande-3.1377606',
  20         'info_dict': {
  21             'id': '2083309',
  22             'display_id': 'forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande',
  23             'ext': 'flv',
  24             'title': 'Forum du 5 à 7 : Kotkaniemi de retour de Finlande',
  25             'description': 'md5:83fa38ecc4a79b19e433433254077f25',
  26             'timestamp': 1606129030,
  27             'upload_date': '20201123',
  28             'duration': 773.039,
  29         }
  30     }, {
  31         'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         display_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, display_id)
  39
  40         item = self._parse_json(self._search_regex(r'(?s)itemToPush\s*=\s*({.+?});', webpage, 'item'), display_id, js_to_json)
  41         video_id = compat_str(item['id'])
  42         title = item.get('title') or self._og_search_title(webpage) or self._html_search_meta(
  43             'title', webpage, 'title', fatal=True)
  44         description = self._og_search_description(webpage) or self._html_search_meta(
  45             'description', webpage, 'description')
  46         thumbnail = item.get('urlImageBig') or self._og_search_thumbnail(webpage) or self._search_regex(
  47             [r'<link[^>]+itemprop="thumbnailUrl"[^>]+href="([^"]+)"',
  48              r'<span[^>]+itemprop="thumbnailUrl"[^>]+content="([^"]+)"'],
  49             webpage, 'thumbnail', fatal=False)
  50         timestamp = parse_iso8601(self._search_regex(
  51             r'<span[^>]+itemprop="uploadDate"[^>]+content="([^"]+)"',
  52             webpage, 'upload date', fatal=False))
  53         duration = parse_duration(self._search_regex(
  54             r'<span[^>]+itemprop="duration"[^>]+content="([^"]+)"',
  55             webpage, 'duration', fatal=False))
  56         age_limit = self._family_friendly_search(webpage)
  57
  58         return {
  59             '_type': 'url_transparent',
  60             'id': video_id,
  61             'display_id': display_id,
  62             'url': '9c9media:rds_web:%s' % video_id,
  63             'title': title,
  64             'description': description,
  65             'thumbnail': thumbnail,
  66             'timestamp': timestamp,
  67             'duration': duration,
  68             'age_limit': age_limit,
  69             'ie_key': 'NineCNineMedia',
  70         }