]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/fox.py
Update upstream source from tag 'upstream/2019.09.28'
[youtubedl] / 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 _GEO_BYPASS = False
54 _HOME_PAGE_URL = 'https://www.fox.com/'
55 _API_KEY = 'abdcbed02c124d393b39e818a4312055'
56 _access_token = None
57
58 def _call_api(self, path, video_id, data=None):
59 headers = {
60 'X-Api-Key': self._API_KEY,
61 }
62 if self._access_token:
63 headers['Authorization'] = 'Bearer ' + self._access_token
64 try:
65 return self._download_json(
66 'https://api2.fox.com/v2.0/' + path,
67 video_id, data=data, headers=headers)
68 except ExtractorError as e:
69 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
70 entitlement_issues = self._parse_json(
71 e.cause.read().decode(), video_id)['entitlementIssues']
72 for e in entitlement_issues:
73 if e.get('errorCode') == 1005:
74 raise ExtractorError(
75 'This video is only available via cable service provider '
76 'subscription. You may want to use --cookies.', expected=True)
77 messages = ', '.join([e['message'] for e in entitlement_issues])
78 raise ExtractorError(messages, expected=True)
79 raise
80
81 def _real_initialize(self):
82 if not self._access_token:
83 mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth')
84 if mvpd_auth:
85 self._access_token = (self._parse_json(compat_urllib_parse_unquote(
86 mvpd_auth.value), None, fatal=False) or {}).get('accessToken')
87 if not self._access_token:
88 self._access_token = self._call_api(
89 'login', None, json.dumps({
90 'deviceId': compat_str(uuid.uuid4()),
91 }).encode())['accessToken']
92
93 def _real_extract(self, url):
94 video_id = self._match_id(url)
95
96 video = self._call_api('vodplayer/' + video_id, video_id)
97
98 title = video['name']
99 release_url = video['url']
100 try:
101 m3u8_url = self._download_json(release_url, video_id)['playURL']
102 except ExtractorError as e:
103 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
104 error = self._parse_json(e.cause.read().decode(), video_id)
105 if error.get('exception') == 'GeoLocationBlocked':
106 self.raise_geo_restricted(countries=['US'])
107 raise ExtractorError(error['description'], expected=True)
108 raise
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
114 data = try_get(
115 video, lambda x: x['trackingData']['properties'], dict) or {}
116
117 duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
118 video.get('duration')) or parse_duration(video.get('duration'))
119 timestamp = unified_timestamp(video.get('datePublished'))
120 creator = data.get('brand') or data.get('network') or video.get('network')
121 series = video.get('seriesName') or data.get(
122 'seriesName') or data.get('show')
123
124 subtitles = {}
125 for doc_rel in video.get('documentReleases', []):
126 rel_url = doc_rel.get('url')
127 if not url or doc_rel.get('format') != 'SCC':
128 continue
129 subtitles['en'] = [{
130 'url': rel_url,
131 'ext': 'scc',
132 }]
133 break
134
135 return {
136 'id': video_id,
137 'title': title,
138 'formats': formats,
139 'description': video.get('description'),
140 'duration': duration,
141 'timestamp': timestamp,
142 'age_limit': parse_age_limit(video.get('contentRating')),
143 'creator': creator,
144 'series': series,
145 'season_number': int_or_none(video.get('seasonNumber')),
146 'episode': video.get('name'),
147 'episode_number': int_or_none(video.get('episodeNumber')),
148 'release_year': int_or_none(video.get('releaseYear')),
149 'subtitles': subtitles,
150 }