_ 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_HTTPError,
  10     compat_str,
  11     compat_urllib_parse_unquote,
  12 )
  13 from ..utils import (
  14     ExtractorError,
  15     int_or_none,
  16     parse_age_limit,
  17     parse_duration,
  18     try_get,
  19     unified_timestamp,
  20 )
  21
  22
  23 class FOXIE(AdobePassIE):
  24     _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
  25     _TESTS = [{
  26         # clip
  27         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  28         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  29         'info_dict': {
  30             'id': '4b765a60490325103ea69888fb2bd4e8',
  31             'ext': 'mp4',
  32             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  33             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  34             'duration': 102,
  35             'timestamp': 1504291893,
  36             'upload_date': '20170901',
  37             'creator': 'FOX',
  38             'series': 'Gotham',
  39             'age_limit': 14,
  40         },
  41         'params': {
  42             'skip_download': True,
  43         },
  44     }, {
  45         # episode, geo-restricted
  46         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  47         'only_matching': True,
  48     }, {
  49         # episode, geo-restricted, tv provided required
  50         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
  51         'only_matching': True,
  52     }]
  53     _HOME_PAGE_URL = 'https://www.fox.com/'
  54     _API_KEY = 'abdcbed02c124d393b39e818a4312055'
  55     _access_token = None
  56
  57     def _call_api(self, path, video_id, data=None):
  58         headers = {
  59             'X-Api-Key': self._API_KEY,
  60         }
  61         if self._access_token:
  62             headers['Authorization'] = 'Bearer ' + self._access_token
  63         return self._download_json(
  64             'https://api2.fox.com/v2.0/' + path,
  65             video_id, data=data, headers=headers)
  66
  67     def _real_initialize(self):
  68         if not self._access_token:
  69             mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
  70             if mvpd_auth:
  71                 self._access_token = (self._parse_json(compat_urllib_parse_unquote(
  72                     mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
  73             if not self._access_token:
  74                 self._access_token = self._call_api(
  75                     'login', None, json.dumps({
  76                         'deviceId': compat_str(uuid.uuid4()),
  77                     }).encode())['accessToken']
  78
  79     def _real_extract(self, url):
  80         video_id = self._match_id(url)
  81
  82         video = self._call_api('vodplayer/' + video_id, video_id)
  83
  84         title = video['name']
  85         release_url = video['url']
  86         m3u8_url = self._download_json(release_url, video_id)['playURL']
  87         formats = self._extract_m3u8_formats(
  88             m3u8_url, video_id, 'mp4',
  89             entry_protocol='m3u8_native', m3u8_id='hls')
  90         self._sort_formats(formats)
  91
  92         data = try_get(
  93             video, lambda x: x['trackingData']['properties'], dict) or {}
  94
  95         duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
  96             video.get('duration')) or parse_duration(video.get('duration'))
  97         timestamp = unified_timestamp(video.get('datePublished'))
  98         creator = data.get('brand') or data.get('network') or video.get('network')
  99         series = video.get('seriesName') or data.get(
 100             'seriesName') or data.get('show')
 101
 102         subtitles = {}
 103         for doc_rel in video.get('documentReleases', []):
 104             rel_url = doc_rel.get('url')
 105             if not url or doc_rel.get('format') != 'SCC':
 106                 continue
 107             subtitles['en'] = [{
 108                 'url': rel_url,
 109                 'ext': 'scc',
 110             }]
 111             break
 112
 113         return {
 114             'id': video_id,
 115             'title': title,
 116             'formats': formats,
 117             'description': video.get('description'),
 118             'duration': duration,
 119             'timestamp': timestamp,
 120             'age_limit': parse_age_limit(video.get('contentRating')),
 121             'creator': creator,
 122             'series': series,
 123             'season_number': int_or_none(video.get('seasonNumber')),
 124             'episode': video.get('name'),
 125             'episode_number': int_or_none(video.get('episodeNumber')),
 126             'release_year': int_or_none(video.get('releaseYear')),
 127             'subtitles': subtitles,
 128         }