5 from .common
import InfoExtractor
6 from ..utils
import ExtractorError
, parse_iso8601
8 _BASE_URL_RE
= r
'https?://(?:www\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
11 class NebulaBaseIE(InfoExtractor
):
12 _NETRC_MACHINE
= 'watchnebula'
14 _nebula_api_token
= None
15 _nebula_bearer_token
= None
17 def _perform_nebula_auth(self
, username
, password
):
18 if not username
or not password
:
19 self
.raise_login_required(method
='password')
21 data
= json
.dumps({'email': username, 'password': password}
).encode('utf8')
22 response
= self
._download
_json
(
23 'https://api.watchnebula.com/api/v1/auth/login/',
24 data
=data
, fatal
=False, video_id
=None,
26 'content-type': 'application/json',
27 # Submitting the 'sessionid' cookie always causes a 403 on auth endpoint
30 note
='Logging in to Nebula with supplied credentials',
31 errnote
='Authentication failed or rejected')
32 if not response
or not response
.get('key'):
33 self
.raise_login_required(method
='password')
35 return response
['key']
37 def _call_nebula_api(self
, url
, video_id
=None, method
='GET', auth_type
='api', note
=''):
38 assert method
in ('GET', 'POST',)
39 assert auth_type
in ('api', 'bearer',)
42 authorization
= f
'Token {self._nebula_api_token}' if auth_type
== 'api' else f
'Bearer {self._nebula_bearer_token}'
43 return self
._download
_json
(
44 url
, video_id
, note
=note
, headers
={'Authorization': authorization}
,
45 data
=b
'' if method
== 'POST' else None)
49 except ExtractorError
as exc
:
50 # if 401 or 403, attempt credential re-auth and retry
51 if exc
.cause
and isinstance(exc
.cause
, urllib
.error
.HTTPError
) and exc
.cause
.code
in (401, 403):
52 self
.to_screen(f
'Reauthenticating to Nebula and retrying, because last {auth_type} call resulted in error {exc.cause.code}')
58 def _fetch_nebula_bearer_token(self
):
60 Get a Bearer token for the Nebula API. This will be required to fetch video meta data.
62 response
= self
._call
_nebula
_api
('https://api.watchnebula.com/api/v1/authorization/',
64 note
='Authorizing to Nebula')
65 return response
['token']
67 def _fetch_video_formats(self
, slug
):
68 stream_info
= self
._call
_nebula
_api
(f
'https://content.watchnebula.com/video/{slug}/stream/',
71 note
='Fetching video stream info')
72 manifest_url
= stream_info
['manifest']
73 return self
._extract
_m
3u8_formats
_and
_subtitles
(manifest_url
, slug
)
75 def _build_video_info(self
, episode
):
76 fmts
, subs
= self
._fetch
_video
_formats
(episode
['slug'])
77 channel_slug
= episode
['channel_slug']
78 channel_title
= episode
['channel_title']
80 'id': episode
['zype_id'],
81 'display_id': episode
['slug'],
84 'webpage_url': f
'https://nebula.tv/{episode["slug"]}',
85 'title': episode
['title'],
86 'description': episode
['description'],
87 'timestamp': parse_iso8601(episode
['published_at']),
89 # 'id': tn.get('name'), # this appears to be null
90 'url': tn
['original'],
92 } for key
, tn
in episode
['assets']['thumbnail'].items()],
93 'duration': episode
['duration'],
94 'channel': channel_title
,
95 'channel_id': channel_slug
,
96 'channel_url': f
'https://nebula.tv/{channel_slug}',
97 'uploader': channel_title
,
98 'uploader_id': channel_slug
,
99 'uploader_url': f
'https://nebula.tv/{channel_slug}',
100 'series': channel_title
,
101 'creator': channel_title
,
104 def _perform_login(self
, username
=None, password
=None):
105 self
._nebula
_api
_token
= self
._perform
_nebula
_auth
(username
, password
)
106 self
._nebula
_bearer
_token
= self
._fetch
_nebula
_bearer
_token
()
109 class NebulaIE(NebulaBaseIE
):
110 _VALID_URL
= rf
'{_BASE_URL_RE}/videos/(?P<id>[-\w]+)'
113 'url': 'https://nebula.tv/videos/that-time-disney-remade-beauty-and-the-beast',
114 'md5': '14944cfee8c7beeea106320c47560efc',
116 'id': '5c271b40b13fd613090034fd',
118 'title': 'That Time Disney Remade Beauty and the Beast',
119 'description': 'Note: this video was originally posted on YouTube with the sponsor read included. We weren’t able to remove it without reducing video quality, so it’s presented here in its original context.',
120 'upload_date': '20180731',
121 'timestamp': 1533009600,
122 'channel': 'Lindsay Ellis',
123 'channel_id': 'lindsayellis',
124 'uploader': 'Lindsay Ellis',
125 'uploader_id': 'lindsayellis',
126 'timestamp': 1533009600,
127 'uploader_url': 'https://nebula.tv/lindsayellis',
128 'series': 'Lindsay Ellis',
129 'display_id': 'that-time-disney-remade-beauty-and-the-beast',
130 'channel_url': 'https://nebula.tv/lindsayellis',
131 'creator': 'Lindsay Ellis',
133 'thumbnail': r
're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
137 'url': 'https://nebula.tv/videos/the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
138 'md5': 'd05739cf6c38c09322422f696b569c23',
140 'id': '5e7e78171aaf320001fbd6be',
142 'title': 'Landing Craft - How The Allies Got Ashore',
143 'description': r
're:^In this episode we explore the unsung heroes of D-Day, the landing craft.',
144 'upload_date': '20200327',
145 'timestamp': 1585348140,
146 'channel': 'Real Engineering',
147 'channel_id': 'realengineering',
148 'uploader': 'Real Engineering',
149 'uploader_id': 'realengineering',
150 'series': 'Real Engineering',
151 'display_id': 'the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
152 'creator': 'Real Engineering',
154 'channel_url': 'https://nebula.tv/realengineering',
155 'uploader_url': 'https://nebula.tv/realengineering',
156 'thumbnail': r
're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
160 'url': 'https://nebula.tv/videos/money-episode-1-the-draw',
161 'md5': 'ebe28a7ad822b9ee172387d860487868',
163 'id': '5e779ebdd157bc0001d1c75a',
165 'title': 'Episode 1: The Draw',
166 'description': r
'contains:There’s free money on offer… if the players can all work together.',
167 'upload_date': '20200323',
168 'timestamp': 1584980400,
169 'channel': 'Tom Scott Presents: Money',
170 'channel_id': 'tom-scott-presents-money',
171 'uploader': 'Tom Scott Presents: Money',
172 'uploader_id': 'tom-scott-presents-money',
173 'uploader_url': 'https://nebula.tv/tom-scott-presents-money',
175 'channel_url': 'https://nebula.tv/tom-scott-presents-money',
176 'series': 'Tom Scott Presents: Money',
177 'display_id': 'money-episode-1-the-draw',
178 'thumbnail': r
're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
179 'creator': 'Tom Scott Presents: Money',
183 'url': 'https://watchnebula.com/videos/money-episode-1-the-draw',
184 'only_matching': True,
188 def _fetch_video_metadata(self
, slug
):
189 return self
._call
_nebula
_api
(f
'https://content.watchnebula.com/video/{slug}/',
192 note
='Fetching video meta data')
194 def _real_extract(self
, url
):
195 slug
= self
._match
_id
(url
)
196 video
= self
._fetch
_video
_metadata
(slug
)
197 return self
._build
_video
_info
(video
)
200 class NebulaSubscriptionsIE(NebulaBaseIE
):
201 IE_NAME
= 'nebula:subscriptions'
202 _VALID_URL
= rf
'{_BASE_URL_RE}/myshows'
205 'url': 'https://nebula.tv/myshows',
206 'playlist_mincount': 1,
213 def _generate_playlist_entries(self
):
214 next_url
= 'https://content.watchnebula.com/library/video/?page_size=100'
217 channel
= self
._call
_nebula
_api
(next_url
, 'myshows', auth_type
='bearer',
218 note
=f
'Retrieving subscriptions page {page_num}')
219 for episode
in channel
['results']:
220 yield self
._build
_video
_info
(episode
)
221 next_url
= channel
['next']
224 def _real_extract(self
, url
):
225 return self
.playlist_result(self
._generate
_playlist
_entries
(), 'myshows')
228 class NebulaChannelIE(NebulaBaseIE
):
229 IE_NAME
= 'nebula:channel'
230 _VALID_URL
= rf
'{_BASE_URL_RE}/(?!myshows|videos/)(?P<id>[-\w]+)'
233 'url': 'https://nebula.tv/tom-scott-presents-money',
235 'id': 'tom-scott-presents-money',
236 'title': 'Tom Scott Presents: Money',
237 'description': 'Tom Scott hosts a series all about trust, negotiation and money.',
241 'url': 'https://nebula.tv/lindsayellis',
243 'id': 'lindsayellis',
244 'title': 'Lindsay Ellis',
245 'description': 'Enjoy these hottest of takes on Disney, Transformers, and Musicals.',
247 'playlist_mincount': 2,
251 def _generate_playlist_entries(self
, collection_id
, channel
):
252 episodes
= channel
['episodes']['results']
253 for page_num
in itertools
.count(2):
254 for episode
in episodes
:
255 yield self
._build
_video
_info
(episode
)
256 next_url
= channel
['episodes']['next']
259 channel
= self
._call
_nebula
_api
(next_url
, collection_id
, auth_type
='bearer',
260 note
=f
'Retrieving channel page {page_num}')
261 episodes
= channel
['episodes']['results']
263 def _real_extract(self
, url
):
264 collection_id
= self
._match
_id
(url
)
265 channel_url
= f
'https://content.watchnebula.com/video/channels/{collection_id}/'
266 channel
= self
._call
_nebula
_api
(channel_url
, collection_id
, auth_type
='bearer', note
='Retrieving channel')
267 channel_details
= channel
['details']
269 return self
.playlist_result(
270 entries
=self
._generate
_playlist
_entries
(collection_id
, channel
),
271 playlist_id
=collection_id
,
272 playlist_title
=channel_details
['title'],
273 playlist_description
=channel_details
['description']