_ Git - youtube-dl/blob - youtube_dl/extractor/fox.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import uuid
   6
   7 from .adobepass import AdobePassIE
   8 from ..compat import (
   9     compat_str,
  10     compat_urllib_parse_unquote,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     parse_age_limit,
  15     parse_duration,
  16     try_get,
  17     unified_timestamp,
  18 )
  19
  20
  21 class FOXIE(AdobePassIE):
  22     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
  23     _TESTS = [{
  24         # clip
  25         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  26         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  27         'info_dict': {
  28             'id': '4b765a60490325103ea69888fb2bd4e8',
  29             'ext': 'mp4',
  30             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  31             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  32             'duration': 102,
  33             'timestamp': 1504291893,
  34             'upload_date': '20170901',
  35             'creator': 'FOX',
  36             'series': 'Gotham',
  37             'age_limit': 14,
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42     }, {
  43         # episode, geo-restricted
  44         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  45         'only_matching': True,
  46     }, {
  47         # episode, geo-restricted, tv provided required
  48         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
  49         'only_matching': True,
  50     }]
  51     _HOME_PAGE_URL = 'https://www.fox.com/'
  52     _API_KEY = 'abdcbed02c124d393b39e818a4312055'
  53     _access_token = None
  54
  55     def _call_api(self, path, video_id, data=None):
  56         headers = {
  57             'X-Api-Key': self._API_KEY,
  58         }
  59         if self._access_token:
  60             headers['Authorization'] = 'Bearer ' + self._access_token
  61         return self._download_json(
  62             'https://api2.fox.com/v2.0/' + path,
  63             video_id, data=data, headers=headers)
  64
  65     def _real_initialize(self):
  66         if not self._access_token:
  67             mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
  68             if mvpd_auth:
  69                 self._access_token = (self._parse_json(compat_urllib_parse_unquote(
  70                     mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
  71             if not self._access_token:
  72                 self._access_token = self._call_api(
  73                     'login', None, json.dumps({
  74                         'deviceId': compat_str(uuid.uuid4()),
  75                     }).encode())['accessToken']
  76
  77     def _real_extract(self, url):
  78         video_id = self._match_id(url)
  79
  80         video = self._call_api('vodplayer/' + video_id, video_id)
  81
  82         title = video['name']
  83         release_url = video['url']
  84         m3u8_url = self._download_json(release_url, video_id)['playURL']
  85         formats = self._extract_m3u8_formats(
  86             m3u8_url, video_id, 'mp4',
  87             entry_protocol='m3u8_native', m3u8_id='hls')
  88         self._sort_formats(formats)
  89
  90         data = try_get(
  91             video, lambda x: x['trackingData']['properties'], dict) or {}
  92
  93         duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
  94             video.get('duration')) or parse_duration(video.get('duration'))
  95         timestamp = unified_timestamp(video.get('datePublished'))
  96         creator = data.get('brand') or data.get('network') or video.get('network')
  97         series = video.get('seriesName') or data.get(
  98             'seriesName') or data.get('show')
  99
 100         subtitles = {}
 101         for doc_rel in video.get('documentReleases', []):
 102             rel_url = doc_rel.get('url')
 103             if not url or doc_rel.get('format') != 'SCC':
 104                 continue
 105             subtitles['en'] = [{
 106                 'url': rel_url,
 107                 'ext': 'scc',
 108             }]
 109             break
 110
 111         return {
 112             'id': video_id,
 113             'title': title,
 114             'formats': formats,
 115             'description': video.get('description'),
 116             'duration': duration,
 117             'timestamp': timestamp,
 118             'age_limit': parse_age_limit(video.get('contentRating')),
 119             'creator': creator,
 120             'series': series,
 121             'season_number': int_or_none(video.get('seasonNumber')),
 122             'episode': video.get('name'),
 123             'episode_number': int_or_none(video.get('episodeNumber')),
 124             'release_year': int_or_none(video.get('releaseYear')),
 125             'subtitles': subtitles,
 126         }