yt_dlp/extractor/ninenow.py

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