yt_dlp/extractor/ninenow.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     float_or_none,
  10     smuggle_url,
  11     str_or_none,
  12     try_get,
  13     unified_strdate,
  14     unified_timestamp,
  15 )
  16
  17
  18 class NineNowIE(InfoExtractor):
  19     IE_NAME = '9now.com.au'
  20     _VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/]+/){2}(?P<id>[^/?#]+)'
  21     _GEO_COUNTRIES = ['AU']
  22     _TESTS = [{
  23         # clip
  24         'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
  25         'md5': '17cf47d63ec9323e562c9957a968b565',
  26         'info_dict': {
  27             'id': '16801',
  28             'ext': 'mp4',
  29             'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
  30             'description': 'Is a boycott of the NAB Cup "on the table"?',
  31             'uploader_id': '4460760524001',
  32             'upload_date': '20160713',
  33             'timestamp': 1468421266,
  34         },
  35         'skip': 'Only available in Australia',
  36     }, {
  37         # episode
  38         'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
  39         'only_matching': True,
  40     }, {
  41         # DRM protected
  42         'url': 'https://www.9now.com.au/andrew-marrs-history-of-the-world/season-1/episode-1',
  43         'only_matching': True,
  44     }, {
  45         # episode of series
  46         'url': 'https://www.9now.com.au/lego-masters/season-3/episode-3',
  47         'info_dict': {
  48             'id': '6249614030001',
  49             'title': 'Episode 3',
  50             'ext': 'mp4',
  51             'season_number': 3,
  52             'episode_number': 3,
  53             'description': 'In the first elimination of the competition, teams will have 10 hours to build a world inside a snow globe.',
  54             'uploader_id': '4460760524001',
  55             'timestamp': 1619002200,
  56             'upload_date': '20210421',
  57         },
  58         'expected_warnings': ['Ignoring subtitle tracks'],
  59         'params':{
  60             'skip_download': True,
  61         }
  62     }]
  63     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId=%s'
  64
  65     def _real_extract(self, url):
  66         display_id = self._match_id(url)
  67         webpage = self._download_webpage(url, display_id)
  68         page_data = self._parse_json(self._search_regex(
  69             r'window\.__data\s*=\s*({.*?});', webpage,
  70             'page data', default='{}'), display_id, fatal=False)
  71         if not page_data:
  72             page_data = self._parse_json(self._parse_json(self._search_regex(
  73                 r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
  74                 webpage, 'page data'), display_id), display_id)
  75
  76         for kind in ('episode', 'clip'):
  77             current_key = page_data.get(kind, {}).get(
  78                 'current%sKey' % kind.capitalize())
  79             if not current_key:
  80                 continue
  81             cache = page_data.get(kind, {}).get('%sCache' % kind, {})
  82             if not cache:
  83                 continue
  84             common_data = {
  85                 'episode': (cache.get(current_key) or list(cache.values())[0])[kind],
  86                 'season': (cache.get(current_key) or list(cache.values())[0]).get('season', None)
  87             }
  88             break
  89         else:
  90             raise ExtractorError('Unable to find video data')
  91
  92         if not self.get_param('allow_unplayable_formats') and try_get(common_data, lambda x: x['episode']['video']['drm'], bool):
  93             self.report_drm(display_id)
  94         brightcove_id = try_get(
  95             common_data, lambda x: x['episode']['video']['brightcoveId'], compat_str) or 'ref:%s' % common_data['episode']['video']['referenceId']
  96         video_id = str_or_none(try_get(common_data, lambda x: x['episode']['video']['id'])) or brightcove_id
  97
  98         title = try_get(common_data, lambda x: x['episode']['name'], compat_str)
  99         season_number = try_get(common_data, lambda x: x['season']['seasonNumber'], int)
 100         episode_number = try_get(common_data, lambda x: x['episode']['episodeNumber'], int)
 101         timestamp = unified_timestamp(try_get(common_data, lambda x: x['episode']['airDate'], compat_str))
 102         release_date = unified_strdate(try_get(common_data, lambda x: x['episode']['availability'], compat_str))
 103         thumbnails_data = try_get(common_data, lambda x: x['episode']['image']['sizes'], dict) or {}
 104         thumbnails = [{
 105             'id': thumbnail_id,
 106             'url': thumbnail_url,
 107             'width': int_or_none(thumbnail_id[1:]),
 108         } for thumbnail_id, thumbnail_url in thumbnails_data.items()]
 109
 110         return {
 111             '_type': 'url_transparent',
 112             'url': smuggle_url(
 113                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
 114                 {'geo_countries': self._GEO_COUNTRIES}),
 115             'id': video_id,
 116             'title': title,
 117             'description': try_get(common_data, lambda x: x['episode']['description'], compat_str),
 118             'duration': float_or_none(try_get(common_data, lambda x: x['episode']['video']['duration'], float), 1000),
 119             'thumbnails': thumbnails,
 120             'ie_key': 'BrightcoveNew',
 121             'season_number': season_number,
 122             'episode_number': episode_number,
 123             'timestamp': timestamp,
 124             'release_date': release_date,
 125         }