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     }, {
  30         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
  31         'only_matching': True,
  32     }, {
  33         'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://www.ifc.com/movies/chaos',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
  46         'only_matching': True,
  47     }, {
  48         'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
  49         'only_matching': True,
  50     }, {
  51         'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
  52         'only_matching': True,
  53     }]
  54     _REQUESTOR_ID_MAP = {
  55         'amc': 'AMC',
  56         'bbcamerica': 'BBCA',
  57         'ifc': 'IFC',
  58         'sundancetv': 'SUNDANCE',
  59         'wetv': 'WETV',
  60     }
  61
  62     def _real_extract(self, url):
  63         site, display_id = self._match_valid_url(url).groups()
  64         requestor_id = self._REQUESTOR_ID_MAP[site]
  65         page_data = self._download_json(
  66             'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
  67             % (requestor_id.lower(), display_id), display_id)['data']
  68         properties = page_data.get('properties') or {}
  69         query = {
  70             'mbr': 'true',
  71             'manifest': 'm3u',
  72         }
  73
  74         video_player_count = 0
  75         try:
  76             for v in page_data['children']:
  77                 if v.get('type') == 'video-player':
  78                     releasePid = v['properties']['currentVideo']['meta']['releasePid']
  79                     tp_path = 'M_UwQC/' + releasePid
  80                     media_url = 'https://link.theplatform.com/s/' + tp_path
  81                     video_player_count += 1
  82         except KeyError:
  83             pass
  84         if video_player_count > 1:
  85             self.report_warning(
  86                 'The JSON data has %d video players. Only one will be extracted' % video_player_count)
  87
  88         # Fall back to videoPid if releasePid not found.
  89         # TODO: Fall back to videoPid if releasePid manifest uses DRM.
  90         if not video_player_count:
  91             tp_path = 'M_UwQC/media/' + properties['videoPid']
  92             media_url = 'https://link.theplatform.com/s/' + tp_path
  93
  94         theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
  95         info = self._parse_theplatform_metadata(theplatform_metadata)
  96         video_id = theplatform_metadata['pid']
  97         title = theplatform_metadata['title']
  98         rating = try_get(
  99             theplatform_metadata, lambda x: x['ratings'][0]['rating'])
 100         video_category = properties.get('videoCategory')
 101         if video_category and video_category.endswith('-Auth'):
 102             resource = self._get_mvpd_resource(
 103                 requestor_id, title, video_id, rating)
 104             query['auth'] = self._extract_mvpd_auth(
 105                 url, video_id, requestor_id, resource)
 106         media_url = update_url_query(media_url, query)
 107         formats, subtitles = self._extract_theplatform_smil(
 108             media_url, video_id)
 109
 110         thumbnails = []
 111         thumbnail_urls = [properties.get('imageDesktop')]
 112         if 'thumbnail' in info:
 113             thumbnail_urls.append(info.pop('thumbnail'))
 114         for thumbnail_url in thumbnail_urls:
 115             if not thumbnail_url:
 116                 continue
 117             mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
 118             thumbnails.append({
 119                 'url': thumbnail_url,
 120                 'width': int(mobj.group(1)) if mobj else None,
 121                 'height': int(mobj.group(2)) if mobj else None,
 122             })
 123
 124         info.update({
 125             'age_limit': parse_age_limit(rating),
 126             'formats': formats,
 127             'id': video_id,
 128             'subtitles': subtitles,
 129             'thumbnails': thumbnails,
 130         })
 131         ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
 132         if ns_keys:
 133             ns = list(ns_keys)[0]
 134             episode = theplatform_metadata.get(ns + '$episodeTitle') or None
 135             episode_number = int_or_none(
 136                 theplatform_metadata.get(ns + '$episode'))
 137             season_number = int_or_none(
 138                 theplatform_metadata.get(ns + '$season'))
 139             series = theplatform_metadata.get(ns + '$show') or None
 140             info.update({
 141                 'episode': episode,
 142                 'episode_number': episode_number,
 143                 'season_number': season_number,
 144                 'series': series,
 145             })
 146         return info