yt_dlp/extractor/amcnetworks.py

   1 import re
   2
   3 from .theplatform import ThePlatformIE
   4 from ..utils import (
   5     int_or_none,
   6     parse_age_limit,
   7     try_get,
   8     update_url_query,
   9 )
  10
  11
  12 class AMCNetworksIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
  13     _VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
  14     _TESTS = [{
  15         'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
  16         'info_dict': {
  17             'id': '4Lq1dzOnZGt0',
  18             'ext': 'mp4',
  19             'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
  20             'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
  21             'upload_date': '20201120',
  22             'timestamp': 1605904350,
  23             'uploader': 'AMCN',
  24         },
  25         'params': {
  26             # m3u8 download
  27             'skip_download': True,
  28         },
  29         'skip': '404 Not Found',
  30     }, {
  31         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.ifc.com/movies/chaos',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
  47         'only_matching': True,
  48     }, {
  49         'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
  50         'only_matching': True,
  51     }, {
  52         'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
  53         'only_matching': True,
  54     }]
  55     _REQUESTOR_ID_MAP = {
  56         'amc': 'AMC',
  57         'bbcamerica': 'BBCA',
  58         'ifc': 'IFC',
  59         'sundancetv': 'SUNDANCE',
  60         'wetv': 'WETV',
  61     }
  62
  63     def _real_extract(self, url):
  64         site, display_id = self._match_valid_url(url).groups()
  65         requestor_id = self._REQUESTOR_ID_MAP[site]
  66         page_data = self._download_json(
  67             f'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/{requestor_id.lower()}/url/{display_id}',
  68             display_id)['data']
  69         properties = page_data.get('properties') or {}
  70         query = {
  71             'mbr': 'true',
  72             'manifest': 'm3u',
  73         }
  74
  75         video_player_count = 0
  76         try:
  77             for v in page_data['children']:
  78                 if v.get('type') == 'video-player':
  79                     release_pid = v['properties']['currentVideo']['meta']['releasePid']
  80                     tp_path = 'M_UwQC/' + release_pid
  81                     media_url = 'https://link.theplatform.com/s/' + tp_path
  82                     video_player_count += 1
  83         except KeyError:
  84             pass
  85         if video_player_count > 1:
  86             self.report_warning(
  87                 f'The JSON data has {video_player_count} video players. Only one will be extracted')
  88
  89         # Fall back to videoPid if releasePid not found.
  90         # TODO: Fall back to videoPid if releasePid manifest uses DRM.
  91         if not video_player_count:
  92             tp_path = 'M_UwQC/media/' + properties['videoPid']
  93             media_url = 'https://link.theplatform.com/s/' + tp_path
  94
  95         theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
  96         info = self._parse_theplatform_metadata(theplatform_metadata)
  97         video_id = theplatform_metadata['pid']
  98         title = theplatform_metadata['title']
  99         rating = try_get(
 100             theplatform_metadata, lambda x: x['ratings'][0]['rating'])
 101         video_category = properties.get('videoCategory')
 102         if video_category and video_category.endswith('-Auth'):
 103             resource = self._get_mvpd_resource(
 104                 requestor_id, title, video_id, rating)
 105             query['auth'] = self._extract_mvpd_auth(
 106                 url, video_id, requestor_id, resource)
 107         media_url = update_url_query(media_url, query)
 108         formats, subtitles = self._extract_theplatform_smil(
 109             media_url, video_id)
 110
 111         thumbnails = []
 112         thumbnail_urls = [properties.get('imageDesktop')]
 113         if 'thumbnail' in info:
 114             thumbnail_urls.append(info.pop('thumbnail'))
 115         for thumbnail_url in thumbnail_urls:
 116             if not thumbnail_url:
 117                 continue
 118             mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
 119             thumbnails.append({
 120                 'url': thumbnail_url,
 121                 'width': int(mobj.group(1)) if mobj else None,
 122                 'height': int(mobj.group(2)) if mobj else None,
 123             })
 124
 125         info.update({
 126             'age_limit': parse_age_limit(rating),
 127             'formats': formats,
 128             'id': video_id,
 129             'subtitles': subtitles,
 130             'thumbnails': thumbnails,
 131         })
 132         ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
 133         if ns_keys:
 134             ns = next(iter(ns_keys))
 135             episode = theplatform_metadata.get(ns + '$episodeTitle') or None
 136             episode_number = int_or_none(
 137                 theplatform_metadata.get(ns + '$episode'))
 138             season_number = int_or_none(
 139                 theplatform_metadata.get(ns + '$season'))
 140             series = theplatform_metadata.get(ns + '$show') or None
 141             info.update({
 142                 'episode': episode,
 143                 'episode_number': episode_number,
 144                 'season_number': season_number,
 145                 'series': series,
 146             })
 147         return info