yt_dlp/extractor/ninenow.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     ExtractorError,
   5     float_or_none,
   6     int_or_none,
   7     smuggle_url,
   8     str_or_none,
   9     try_get,
  10     unified_strdate,
  11     unified_timestamp,
  12 )
  13
  14
  15 class NineNowIE(InfoExtractor):
  16     IE_NAME = '9now.com.au'
  17     _VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/]+/){2}(?P<id>[^/?#]+)'
  18     _GEO_COUNTRIES = ['AU']
  19     _TESTS = [{
  20         # clip
  21         'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
  22         'md5': '17cf47d63ec9323e562c9957a968b565',
  23         'info_dict': {
  24             'id': '16801',
  25             'ext': 'mp4',
  26             'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
  27             'description': 'Is a boycott of the NAB Cup "on the table"?',
  28             'uploader_id': '4460760524001',
  29             'upload_date': '20160713',
  30             'timestamp': 1468421266,
  31         },
  32         'skip': 'Only available in Australia',
  33     }, {
  34         # episode
  35         'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
  36         'only_matching': True,
  37     }, {
  38         # DRM protected
  39         'url': 'https://www.9now.com.au/andrew-marrs-history-of-the-world/season-1/episode-1',
  40         'only_matching': True,
  41     }, {
  42         # episode of series
  43         'url': 'https://www.9now.com.au/lego-masters/season-3/episode-3',
  44         'info_dict': {
  45             'id': '6249614030001',
  46             'title': 'Episode 3',
  47             'ext': 'mp4',
  48             'season_number': 3,
  49             'episode_number': 3,
  50             'description': 'In the first elimination of the competition, teams will have 10 hours to build a world inside a snow globe.',
  51             'uploader_id': '4460760524001',
  52             'timestamp': 1619002200,
  53             'upload_date': '20210421',
  54         },
  55         'expected_warnings': ['Ignoring subtitle tracks'],
  56         'params': {
  57             'skip_download': True,
  58         }
  59     }]
  60     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId=%s'
  61
  62     def _real_extract(self, url):
  63         display_id = self._match_id(url)
  64         webpage = self._download_webpage(url, display_id)
  65         page_data = self._parse_json(self._search_regex(
  66             r'window\.__data\s*=\s*({.*?});', webpage,
  67             'page data', default='{}'), display_id, fatal=False)
  68         if not page_data:
  69             page_data = self._parse_json(self._parse_json(self._search_regex(
  70                 r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
  71                 webpage, 'page data'), display_id), display_id)
  72
  73         for kind in ('episode', 'clip'):
  74             current_key = page_data.get(kind, {}).get(
  75                 'current%sKey' % kind.capitalize())
  76             if not current_key:
  77                 continue
  78             cache = page_data.get(kind, {}).get('%sCache' % kind, {})
  79             if not cache:
  80                 continue
  81             common_data = {
  82                 'episode': (cache.get(current_key) or list(cache.values())[0])[kind],
  83                 'season': (cache.get(current_key) or list(cache.values())[0]).get('season', None)
  84             }
  85             break
  86         else:
  87             raise ExtractorError('Unable to find video data')
  88
  89         if not self.get_param('allow_unplayable_formats') and try_get(common_data, lambda x: x['episode']['video']['drm'], bool):
  90             self.report_drm(display_id)
  91         brightcove_id = try_get(
  92             common_data, lambda x: x['episode']['video']['brightcoveId'], compat_str) or 'ref:%s' % common_data['episode']['video']['referenceId']
  93         video_id = str_or_none(try_get(common_data, lambda x: x['episode']['video']['id'])) or brightcove_id
  94
  95         title = try_get(common_data, lambda x: x['episode']['name'], compat_str)
  96         season_number = try_get(common_data, lambda x: x['season']['seasonNumber'], int)
  97         episode_number = try_get(common_data, lambda x: x['episode']['episodeNumber'], int)
  98         timestamp = unified_timestamp(try_get(common_data, lambda x: x['episode']['airDate'], compat_str))
  99         release_date = unified_strdate(try_get(common_data, lambda x: x['episode']['availability'], compat_str))
 100         thumbnails_data = try_get(common_data, lambda x: x['episode']['image']['sizes'], dict) or {}
 101         thumbnails = [{
 102             'id': thumbnail_id,
 103             'url': thumbnail_url,
 104             'width': int_or_none(thumbnail_id[1:]),
 105         } for thumbnail_id, thumbnail_url in thumbnails_data.items()]
 106
 107         return {
 108             '_type': 'url_transparent',
 109             'url': smuggle_url(
 110                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
 111                 {'geo_countries': self._GEO_COUNTRIES}),
 112             'id': video_id,
 113             'title': title,
 114             'description': try_get(common_data, lambda x: x['episode']['description'], compat_str),
 115             'duration': float_or_none(try_get(common_data, lambda x: x['episode']['video']['duration'], float), 1000),
 116             'thumbnails': thumbnails,
 117             'ie_key': 'BrightcoveNew',
 118             'season_number': season_number,
 119             'episode_number': episode_number,
 120             'timestamp': timestamp,
 121             'release_date': release_date,
 122         }