youtube_dl/extractor/fox.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .adobepass import AdobePassIE
   5 from .uplynk import UplynkPreplayIE
   6 from ..compat import compat_str
   7 from ..utils import (
   8     HEADRequest,
   9     int_or_none,
  10     parse_age_limit,
  11     parse_duration,
  12     try_get,
  13     unified_timestamp,
  14     update_url_query,
  15 )
  16
  17
  18 class FOXIE(AdobePassIE):
  19     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
  20     _TESTS = [{
  21         # clip
  22         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  23         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  24         'info_dict': {
  25             'id': '4b765a60490325103ea69888fb2bd4e8',
  26             'ext': 'mp4',
  27             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  28             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  29             'duration': 102,
  30             'timestamp': 1504291893,
  31             'upload_date': '20170901',
  32             'creator': 'FOX',
  33             'series': 'Gotham',
  34         },
  35         'params': {
  36             'skip_download': True,
  37         },
  38     }, {
  39         # episode, geo-restricted
  40         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  41         'only_matching': True,
  42     }, {
  43         # episode, geo-restricted, tv provided required
  44         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50
  51         video = self._download_json(
  52             'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
  53             video_id, headers={
  54                 'apikey': 'abdcbed02c124d393b39e818a4312055',
  55                 'Content-Type': 'application/json',
  56                 'Referer': url,
  57             })
  58
  59         title = video['name']
  60         release_url = video['videoRelease']['url']
  61
  62         description = video.get('description')
  63         duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
  64             video.get('duration')) or parse_duration(video.get('duration'))
  65         timestamp = unified_timestamp(video.get('datePublished'))
  66         rating = video.get('contentRating')
  67         age_limit = parse_age_limit(rating)
  68
  69         data = try_get(
  70             video, lambda x: x['trackingData']['properties'], dict) or {}
  71
  72         creator = data.get('brand') or data.get('network') or video.get('network')
  73
  74         series = video.get('seriesName') or data.get(
  75             'seriesName') or data.get('show')
  76         season_number = int_or_none(video.get('seasonNumber'))
  77         episode = video.get('name')
  78         episode_number = int_or_none(video.get('episodeNumber'))
  79         release_year = int_or_none(video.get('releaseYear'))
  80
  81         if data.get('authRequired'):
  82             resource = self._get_mvpd_resource(
  83                 'fbc-fox', title, video.get('guid'), rating)
  84             release_url = update_url_query(
  85                 release_url, {
  86                     'auth': self._extract_mvpd_auth(
  87                         url, video_id, 'fbc-fox', resource)
  88                 })
  89
  90         subtitles = {}
  91         for doc_rel in video.get('documentReleases', []):
  92             rel_url = doc_rel.get('url')
  93             if not url or doc_rel.get('format') != 'SCC':
  94                 continue
  95             subtitles['en'] = [{
  96                 'url': rel_url,
  97                 'ext': 'scc',
  98             }]
  99             break
 100
 101         info = {
 102             'id': video_id,
 103             'title': title,
 104             'description': description,
 105             'duration': duration,
 106             'timestamp': timestamp,
 107             'age_limit': age_limit,
 108             'creator': creator,
 109             'series': series,
 110             'season_number': season_number,
 111             'episode': episode,
 112             'episode_number': episode_number,
 113             'release_year': release_year,
 114             'subtitles': subtitles,
 115         }
 116
 117         urlh = self._request_webpage(HEADRequest(release_url), video_id)
 118         video_url = compat_str(urlh.geturl())
 119
 120         if UplynkPreplayIE.suitable(video_url):
 121             info.update({
 122                 '_type': 'url_transparent',
 123                 'url': video_url,
 124                 'ie_key': UplynkPreplayIE.ie_key(),
 125             })
 126         else:
 127             m3u8_url = self._download_json(release_url, video_id)['playURL']
 128             formats = self._extract_m3u8_formats(
 129                 m3u8_url, video_id, 'mp4',
 130                 entry_protocol='m3u8_native', m3u8_id='hls')
 131             self._sort_formats(formats)
 132             info['formats'] = formats
 133         return info