_ 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 compat_str
   9 from ..utils import (
  10     int_or_none,
  11     parse_age_limit,
  12     parse_duration,
  13     try_get,
  14     unified_timestamp,
  15     update_url_query,
  16 )
  17
  18
  19 class FOXIE(AdobePassIE):
  20     _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)'
  21     _TESTS = [{
  22         # clip
  23         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
  24         'md5': 'ebd296fcc41dd4b19f8115d8461a3165',
  25         'info_dict': {
  26             'id': '4b765a60490325103ea69888fb2bd4e8',
  27             'ext': 'mp4',
  28             'title': 'Aftermath: Bruce Wayne Develops Into The Dark Knight',
  29             'description': 'md5:549cd9c70d413adb32ce2a779b53b486',
  30             'duration': 102,
  31             'timestamp': 1504291893,
  32             'upload_date': '20170901',
  33             'creator': 'FOX',
  34             'series': 'Gotham',
  35         },
  36         'params': {
  37             'skip_download': True,
  38         },
  39     }, {
  40         # episode, geo-restricted
  41         'url': 'https://www.fox.com/watch/087036ca7f33c8eb79b08152b4dd75c1/',
  42         'only_matching': True,
  43     }, {
  44         # episode, geo-restricted, tv provided required
  45         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/',
  49         'only_matching': True,
  50     }]
  51     _access_token = None
  52
  53     def _call_api(self, path, video_id, data=None):
  54         headers = {
  55             'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd',
  56         }
  57         if self._access_token:
  58             headers['Authorization'] = 'Bearer ' + self._access_token
  59         return self._download_json(
  60             'https://api2.fox.com/v2.0/' + path,
  61             video_id, data=data, headers=headers)
  62
  63     def _real_initialize(self):
  64         self._access_token = self._call_api(
  65             'login', None, json.dumps({
  66                 'deviceId': compat_str(uuid.uuid4()),
  67             }).encode())['accessToken']
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71
  72         video = self._call_api('vodplayer/' + video_id, video_id)
  73
  74         title = video['name']
  75         release_url = video['url']
  76
  77         data = try_get(
  78             video, lambda x: x['trackingData']['properties'], dict) or {}
  79
  80         rating = video.get('contentRating')
  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         m3u8_url = self._download_json(release_url, video_id)['playURL']
  90         formats = self._extract_m3u8_formats(
  91             m3u8_url, video_id, 'mp4',
  92             entry_protocol='m3u8_native', m3u8_id='hls')
  93         self._sort_formats(formats)
  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(rating),
 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         }