_ Git - youtube-dl/blob - 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 )
  15
  16
  17 class FOXIE(AdobePassIE):
  18     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
  19     _TESTS = [{
  20         # clip
  21         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  22         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  23         'info_dict': {
  24             'id': '4b765a60490325103ea69888fb2bd4e8',
  25             'ext': 'mp4',
  26             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  27             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  28             'duration': 102,
  29             'timestamp': 1504291893,
  30             'upload_date': '20170901',
  31             'creator': 'FOX',
  32             'series': 'Gotham',
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37     }, {
  38         # episode, geo-restricted
  39         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  40         'only_matching': True,
  41     }, {
  42         # episode, geo-restricted, tv provided required
  43         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
  44         'only_matching': True,
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49
  50         video = self._download_json(
  51             'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
  52             video_id, headers={
  53                 'apikey': 'abdcbed02c124d393b39e818a4312055',
  54                 'Content-Type': 'application/json',
  55                 'Referer': url,
  56             })
  57
  58         title = video['name']
  59         release_url = video['videoRelease']['url']
  60
  61         description = video.get('description')
  62         duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
  63             video.get('duration')) or parse_duration(video.get('duration'))
  64         timestamp = unified_timestamp(video.get('datePublished'))
  65         age_limit = parse_age_limit(video.get('contentRating'))
  66
  67         data = try_get(
  68             video, lambda x: x['trackingData']['properties'], dict) or {}
  69
  70         creator = data.get('brand') or data.get('network') or video.get('network')
  71
  72         series = video.get('seriesName') or data.get(
  73             'seriesName') or data.get('show')
  74         season_number = int_or_none(video.get('seasonNumber'))
  75         episode = video.get('name')
  76         episode_number = int_or_none(video.get('episodeNumber'))
  77         release_year = int_or_none(video.get('releaseYear'))
  78
  79         if data.get('authRequired'):
  80             # TODO: AP
  81             pass
  82
  83         info = {
  84             'id': video_id,
  85             'title': title,
  86             'description': description,
  87             'duration': duration,
  88             'timestamp': timestamp,
  89             'age_limit': age_limit,
  90             'creator': creator,
  91             'series': series,
  92             'season_number': season_number,
  93             'episode': episode,
  94             'episode_number': episode_number,
  95             'release_year': release_year,
  96         }
  97
  98         urlh = self._request_webpage(HEADRequest(release_url), video_id)
  99         video_url = compat_str(urlh.geturl())
 100
 101         if UplynkPreplayIE.suitable(video_url):
 102             info.update({
 103                 '_type': 'url_transparent',
 104                 'url': video_url,
 105                 'ie_key': UplynkPreplayIE.ie_key(),
 106             })
 107         else:
 108             m3u8_url = self._download_json(release_url, video_id)['playURL']
 109             formats = self._extract_m3u8_formats(
 110                 m3u8_url, video_id, 'mp4',
 111                 entry_protocol='m3u8_native', m3u8_id='hls')
 112             self._sort_formats(formats)
 113             info['formats'] = formats
 114         return info