yt_dlp/extractor/amcnetworks.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .theplatform import ThePlatformIE
   7 from ..utils import (
   8     int_or_none,
   9     parse_age_limit,
  10     try_get,
  11     update_url_query,
  12 )
  13
  14
  15 class AMCNetworksIE(ThePlatformIE):
  16     _VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
  17     _TESTS = [{
  18         'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
  19         'info_dict': {
  20             'id': '4Lq1dzOnZGt0',
  21             'ext': 'mp4',
  22             'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
  23             '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.",
  24             'upload_date': '20201120',
  25             'timestamp': 1605904350,
  26             'uploader': 'AMCN',
  27         },
  28         'params': {
  29             # m3u8 download
  30             'skip_download': True,
  31         },
  32     }, {
  33         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
  37         'only_matching': True,
  38     }, {
  39         'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://www.ifc.com/movies/chaos',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
  46         'only_matching': True,
  47     }, {
  48         'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
  49         'only_matching': True,
  50     }, {
  51         'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
  55         'only_matching': True,
  56     }]
  57     _REQUESTOR_ID_MAP = {
  58         'amc': 'AMC',
  59         'bbcamerica': 'BBCA',
  60         'ifc': 'IFC',
  61         'sundancetv': 'SUNDANCE',
  62         'wetv': 'WETV',
  63     }
  64
  65     def _real_extract(self, url):
  66         site, display_id = re.match(self._VALID_URL, url).groups()
  67         requestor_id = self._REQUESTOR_ID_MAP[site]
  68         page_data = self._download_json(
  69             'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
  70             % (requestor_id.lower(), display_id), display_id)['data']
  71         properties = page_data.get('properties') or {}
  72         query = {
  73             'mbr': 'true',
  74             'manifest': 'm3u',
  75         }
  76
  77         video_player_count = 0
  78         try:
  79             for v in page_data['children']:
  80                 if v.get('type') == 'video-player':
  81                     releasePid = v['properties']['currentVideo']['meta']['releasePid']
  82                     tp_path = 'M_UwQC/' + releasePid
  83                     media_url = 'https://link.theplatform.com/s/' + tp_path
  84                     video_player_count += 1
  85         except KeyError:
  86             pass
  87         if video_player_count > 1:
  88             self.report_warning(
  89                 'The JSON data has %d video players. Only one will be extracted' % video_player_count)
  90
  91         # Fall back to videoPid if releasePid not found.
  92         # TODO: Fall back to videoPid if releasePid manifest uses DRM.
  93         if not video_player_count:
  94             tp_path = 'M_UwQC/media/' + properties['videoPid']
  95             media_url = 'https://link.theplatform.com/s/' + tp_path
  96
  97         theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
  98         info = self._parse_theplatform_metadata(theplatform_metadata)
  99         video_id = theplatform_metadata['pid']
 100         title = theplatform_metadata['title']
 101         rating = try_get(
 102             theplatform_metadata, lambda x: x['ratings'][0]['rating'])
 103         video_category = properties.get('videoCategory')
 104         if video_category and video_category.endswith('-Auth'):
 105             resource = self._get_mvpd_resource(
 106                 requestor_id, title, video_id, rating)
 107             query['auth'] = self._extract_mvpd_auth(
 108                 url, video_id, requestor_id, resource)
 109         media_url = update_url_query(media_url, query)
 110         formats, subtitles = self._extract_theplatform_smil(
 111             media_url, video_id)
 112         self._sort_formats(formats)
 113
 114         thumbnails = []
 115         thumbnail_urls = [properties.get('imageDesktop')]
 116         if 'thumbnail' in info:
 117             thumbnail_urls.append(info.pop('thumbnail'))
 118         for thumbnail_url in thumbnail_urls:
 119             if not thumbnail_url:
 120                 continue
 121             mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
 122             thumbnails.append({
 123                 'url': thumbnail_url,
 124                 'width': int(mobj.group(1)) if mobj else None,
 125                 'height': int(mobj.group(2)) if mobj else None,
 126             })
 127
 128         info.update({
 129             'age_limit': parse_age_limit(rating),
 130             'formats': formats,
 131             'id': video_id,
 132             'subtitles': subtitles,
 133             'thumbnails': thumbnails,
 134         })
 135         ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
 136         if ns_keys:
 137             ns = list(ns_keys)[0]
 138             episode = theplatform_metadata.get(ns + '$episodeTitle') or None
 139             episode_number = int_or_none(
 140                 theplatform_metadata.get(ns + '$episode'))
 141             season_number = int_or_none(
 142                 theplatform_metadata.get(ns + '$season'))
 143             series = theplatform_metadata.get(ns + '$show') or None
 144             info.update({
 145                 'episode': episode,
 146                 'episode_number': episode_number,
 147                 'season_number': season_number,
 148                 'series': series,
 149             })
 150         return info