yt_dlp/extractor/ninecninemedia.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5     parse_iso8601,
   6     str_or_none,
   7     try_get,
   8 )
   9
  10
  11 class NineCNineMediaIE(InfoExtractor):
  12     IE_NAME = '9c9media'
  13     _GEO_COUNTRIES = ['CA']
  14     _VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
  15     _API_BASE_TEMPLATE = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/'
  16
  17     def _real_extract(self, url):
  18         destination_code, content_id = self._match_valid_url(url).groups()
  19         api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
  20         content = self._download_json(api_base_url, content_id, query={
  21             '$include': '[Media.Name,Season,ContentPackages.Duration,ContentPackages.Id]',
  22         })
  23         title = content['Name']
  24         content_package = content['ContentPackages'][0]
  25         package_id = content_package['Id']
  26         content_package_url = api_base_url + f'contentpackages/{package_id}/'
  27         content_package = self._download_json(
  28             content_package_url, content_id, query={
  29                 '$include': '[HasClosedCaptions]',
  30             })
  31
  32         if (not self.get_param('allow_unplayable_formats')
  33                 and try_get(content_package, lambda x: x['Constraints']['Security']['Type'])):
  34             self.report_drm(content_id)
  35
  36         manifest_base_url = content_package_url + 'manifest.'
  37         formats = []
  38         formats.extend(self._extract_m3u8_formats(
  39             manifest_base_url + 'm3u8', content_id, 'mp4',
  40             'm3u8_native', m3u8_id='hls', fatal=False))
  41         formats.extend(self._extract_f4m_formats(
  42             manifest_base_url + 'f4m', content_id,
  43             f4m_id='hds', fatal=False))
  44         formats.extend(self._extract_mpd_formats(
  45             manifest_base_url + 'mpd', content_id,
  46             mpd_id='dash', fatal=False))
  47
  48         thumbnails = []
  49         for image in (content.get('Images') or []):
  50             image_url = image.get('Url')
  51             if not image_url:
  52                 continue
  53             thumbnails.append({
  54                 'url': image_url,
  55                 'width': int_or_none(image.get('Width')),
  56                 'height': int_or_none(image.get('Height')),
  57             })
  58
  59         tags, categories = [], []
  60         for source_name, container in (('Tags', tags), ('Genres', categories)):
  61             for e in content.get(source_name, []):
  62                 e_name = e.get('Name')
  63                 if not e_name:
  64                     continue
  65                 container.append(e_name)
  66
  67         season = content.get('Season') or {}
  68
  69         info = {
  70             'id': content_id,
  71             'title': title,
  72             'description': content.get('Desc') or content.get('ShortDesc'),
  73             'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
  74             'episode_number': int_or_none(content.get('Episode')),
  75             'season': season.get('Name'),
  76             'season_number': int_or_none(season.get('Number')),
  77             'season_id': str_or_none(season.get('Id')),
  78             'series': try_get(content, lambda x: x['Media']['Name']),
  79             'tags': tags,
  80             'categories': categories,
  81             'duration': float_or_none(content_package.get('Duration')),
  82             'formats': formats,
  83             'thumbnails': thumbnails,
  84         }
  85
  86         if content_package.get('HasClosedCaptions'):
  87             info['subtitles'] = {
  88                 'en': [{
  89                     'url': manifest_base_url + 'vtt',
  90                     'ext': 'vtt',
  91                 }, {
  92                     'url': manifest_base_url + 'srt',
  93                     'ext': 'srt',
  94                 }],
  95             }
  96
  97         return info
  98
  99
 100 class CPTwentyFourIE(InfoExtractor):
 101     IE_NAME = 'cp24'
 102     _GEO_COUNTRIES = ['CA']
 103     _VALID_URL = r'https?://(?:www\.)?cp24\.com/news/(?P<id>[^?#]+)'
 104
 105     _TESTS = [{
 106         'url': 'https://www.cp24.com/news/video-shows-atm-being-ripped-out-of-business-by-pickup-truck-driver-in-mississauga-1.5676877',
 107         'info_dict': {
 108             'id': '2328005',
 109             'ext': 'mp4',
 110             'title': 'WATCH: Truck rips ATM from Mississauga business',
 111             'description': 'md5:cf7498480885f080a754389a2b2f7073',
 112             'timestamp': 1637618377,
 113             'season': 'Season 0',
 114             'season_number': 0,
 115             'season_id': '57974',
 116             'series': 'CTV News Toronto',
 117             'duration': 26.86,
 118             'thumbnail': 'http://images2.9c9media.com/image_asset/2014_11_5_2eb609a0-475b-0132-fbd6-34b52f6f1279_jpg_2000x1125.jpg',
 119             'upload_date': '20211122',
 120         },
 121         'params': {'skip_download': True, 'format': 'bv'},
 122     }]
 123
 124     def _real_extract(self, url):
 125         display_id = self._match_id(url)
 126         webpage = self._download_webpage(url, display_id)
 127         video_id, destination = self._search_regex(
 128             r'getAuthStates\("(?P<id>[^"]+)",\s?"(?P<destination>[^"]+)"\);',
 129             webpage, 'video id and destination', group=('id', 'destination'))
 130         return self.url_result(f'9c9media:{destination}:{video_id}', NineCNineMediaIE, video_id)