8 from .common
import InfoExtractor
9 from ..compat
import compat_str
10 from ..networking
.exceptions
import HTTPError
22 class HotStarBaseIE(InfoExtractor
):
23 _BASE_URL
= 'https://www.hotstar.com'
24 _API_URL
= 'https://api.hotstar.com'
25 _AKAMAI_ENCRYPTION_KEY
= b
'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
27 def _call_api_v1(self
, path
, *args
, **kwargs
):
28 return self
._download
_json
(
29 f
'{self._API_URL}/o/v1/{path}', *args
, **kwargs
,
30 headers
={'x-country-code': 'IN', 'x-platform-code': 'PCTV'}
)
32 def _call_api_impl(self
, path
, video_id
, query
, st
=None, cookies
=None):
33 st
= int_or_none(st
) or int(time
.time())
35 auth
= 'st=%d~exp=%d~acl=/*' % (st
, exp
)
36 auth
+= '~hmac=' + hmac
.new(self
._AKAMAI
_ENCRYPTION
_KEY
, auth
.encode(), hashlib
.sha256
).hexdigest()
38 if cookies
and cookies
.get('userUP'):
39 token
= cookies
.get('userUP').value
41 token
= self
._download
_json
(
42 f
'{self._API_URL}/um/v3/users',
43 video_id
, note
='Downloading token',
44 data
=json
.dumps({"device_ids": [{"id": compat_str(uuid.uuid4()), "type": "device_id"}
]}).encode('utf-8'),
47 'x-hs-platform': 'PCTV', # or 'web'
48 'Content-Type': 'application/json',
51 response
= self
._download
_json
(
52 f
'{self._API_URL}/{path}', video_id
, query
=query
,
55 'x-hs-appversion': '6.72.2',
56 'x-hs-platform': 'web',
57 'x-hs-usertoken': token
,
60 if response
['message'] != "Playback URL's fetched successfully":
62 response
['message'], expected
=True)
63 return response
['data']
65 def _call_api_v2(self
, path
, video_id
, st
=None, cookies
=None):
66 return self
._call
_api
_impl
(
67 f
'{path}/content/{video_id}', video_id
, st
=st
, cookies
=cookies
, query
={
68 'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
69 'device-id': cookies
.get('device_id').value
if cookies
.get('device_id') else compat_str(uuid
.uuid4()),
74 def _playlist_entries(self
, path
, item_id
, root
=None, **kwargs
):
75 results
= self
._call
_api
_v
1(path
, item_id
, **kwargs
)['body']['results']
76 for video
in traverse_obj(results
, (('assets', None), 'items', ...)):
77 if video
.get('contentId'):
78 yield self
.url_result(
79 HotStarIE
._video
_url
(video
['contentId'], root
=root
), HotStarIE
, video
['contentId'])
82 class HotStarIE(HotStarBaseIE
):
85 https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
87 (?P<type>movies|sports|clips|episode|(?P<tv>tv|shows))/
88 (?(tv)(?:[^/?#]+/){2}|[^?#]*)
95 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
99 'title': 'Can You Not Spread Rumours?',
100 'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
101 'timestamp': 1447248600,
102 'upload_date': '20151111',
104 'episode': 'Can You Not Spread Rumours?',
106 'params': {'skip_download': 'm3u8'}
,
108 'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
112 'title': 'Janhvi Targets Suman',
113 'description': 'md5:78a85509348910bd1ca31be898c5796b',
114 'timestamp': 1556670600,
115 'upload_date': '20190501',
117 'channel': 'StarPlus',
119 'series': 'Ek Bhram - Sarvagun Sampanna',
120 'season': 'Chapter 1',
123 'episode': 'Janhvi Targets Suman',
127 'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
131 'title': 'Anupama, Anuj Share a Moment',
132 'season': 'Chapter 1',
133 'description': 'md5:8d74ed2248423b8b06d5c8add4d7a0c0',
134 'timestamp': 1678149000,
135 'channel': 'StarPlus',
139 'upload_date': '20230307',
140 'episode': 'Anupama, Anuj Share a Moment',
141 'episode_number': 853,
145 'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
147 'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
151 'title': 'Back To School',
152 'season': 'Chapter 1',
153 'description': 'md5:b0d6a4c8a650681491e7405496fc7e13',
154 'timestamp': 1650564000,
155 'channel': 'Hotstar Specials',
156 'series': 'Kana Kaanum Kaalangal',
159 'upload_date': '20220421',
160 'episode': 'Back To School',
166 'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
170 'title': 'E3 - SaiRat, Kahani Pyaar Ki',
171 'description': 'md5:e3b4b3203bc0c5396fe7d0e4948a6385',
172 'episode': 'E3 - SaiRat, Kahani Pyaar Ki',
173 'upload_date': '20210606',
174 'timestamp': 1622943900,
178 'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
183 'release_year': 2015,
184 'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
185 'timestamp': 1462149000,
186 'upload_date': '20160502',
191 'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
192 'only_matching': True,
194 'url': 'https://www.hotstar.com/in/sports/cricket/follow-the-blues-2021/recap-eng-fight-back-on-day-2/1260066104',
195 'only_matching': True,
197 'url': 'https://www.hotstar.com/in/sports/football/most-costly-pl-transfers-ft-grealish/1260065956',
198 'only_matching': True,
205 'episode': 'episode',
214 'vcodec': 'video_codec',
215 'dr': 'dynamic_range',
219 'language': 'language',
220 'acodec': 'audio_codec',
221 'vcodec': 'video_codec',
225 def _video_url(cls
, video_id
, video_type
=None, *, slug
='ignore_me', root
=None):
226 assert None in (video_type
, root
)
228 root
= join_nonempty(cls
._BASE
_URL
, video_type
, delim
='/')
229 return f
'{root}/{slug}/{video_id}'
231 def _real_extract(self
, url
):
232 video_id
, video_type
= self
._match
_valid
_url
(url
).group('id', 'type')
233 video_type
= self
._TYPE
.get(video_type
, video_type
)
234 cookies
= self
._get
_cookies
(url
) # Cookies before any request
236 video_data
= traverse_obj(
238 f
'{video_type}/detail', video_id
, fatal
=False, query
={'tas': 10000, 'contentId': video_id}
),
239 ('body', 'results', 'item', {dict}
)) or {}
240 if not self
.get_param('allow_unplayable_formats') and video_data
.get('drmProtected'):
241 self
.report_drm(video_id
)
243 # See https://github.com/yt-dlp/yt-dlp/issues/396
244 st
= self
._download
_webpage
_handle
(f
'{self._BASE_URL}/in', video_id
)[1].headers
.get('x-origin-date')
246 geo_restricted
= False
247 formats
, subs
= [], {}
248 headers
= {'Referer': f'{self._BASE_URL}
/in'}
250 # change to v2 in the future
251 playback_sets = self._call_api_v2('play
/v1
/playback
', video_id, st=st, cookies=cookies)['playBackSets
']
252 for playback_set in playback_sets:
253 if not isinstance(playback_set, dict):
255 tags = str_or_none(playback_set.get('tagsCombination
')) or ''
256 if any(f'{prefix}
:{ignore}
' in tags
257 for key, prefix in self._IGNORE_MAP.items()
258 for ignore in self._configuration_arg(key)):
260 tag_dict = dict((t.split(':', 1) + [None])[:2] for t in tags.split(';'))
262 format_url = url_or_none(playback_set.get('playbackUrl
'))
265 format_url = re.sub(r'(?
<=//staragvod
)(\d
)', r'web\
1', format_url)
266 ext = determine_ext(format_url)
268 current_formats, current_subs = [], {}
270 if 'package
:hls
' in tags or ext == 'm3u8
':
271 current_formats, current_subs = self._extract_m3u8_formats_and_subtitles(
272 format_url, video_id, ext='mp4
', headers=headers)
273 elif 'package
:dash
' in tags or ext == 'mpd
':
274 current_formats, current_subs = self._extract_mpd_formats_and_subtitles(
275 format_url, video_id, headers=headers)
277 pass # XXX: produce broken files
281 'width
': int_or_none(playback_set.get('width
')),
282 'height
': int_or_none(playback_set.get('height
')),
284 except ExtractorError as e:
285 if isinstance(e.cause, HTTPError) and e.cause.status == 403:
286 geo_restricted = True
289 if tag_dict.get('encryption
') not in ('plain
', None):
290 for f in current_formats:
292 for f in current_formats:
293 for k, v in self._TAG_FIELDS.items():
295 f[k] = tag_dict.get(v)
296 if f.get('vcodec
') != 'none
' and not f.get('dynamic_range
'):
297 f['dynamic_range
'] = tag_dict.get('dynamic_range
')
298 if f.get('acodec
') != 'none
' and not f.get('audio_channels
'):
299 f['audio_channels
'] = {
302 }.get(tag_dict.get('audio_channel
'))
303 f['format_note
'] = join_nonempty(
304 tag_dict.get('ladder
'),
305 tag_dict.get('audio_channel
') if f.get('acodec
') != 'none
' else None,
306 f.get('format_note
'),
309 formats.extend(current_formats)
310 subs = self._merge_subtitles(subs, current_subs)
312 if not formats and geo_restricted:
313 self.raise_geo_restricted(countries=['IN
'], metadata_available=True)
314 self._remove_duplicate_formats(formats)
316 f.setdefault('http_headers
', {}).update(headers)
320 'title
': video_data.get('title
'),
321 'description
': video_data.get('description
'),
322 'duration
': int_or_none(video_data.get('duration
')),
323 'timestamp
': int_or_none(traverse_obj(video_data, 'broadcastDate
', 'startDate
')),
324 'release_year
': int_or_none(video_data.get('year
')),
327 'channel
': video_data.get('channelName
'),
328 'channel_id
': video_data.get('channelId
'),
329 'series
': video_data.get('showName
'),
330 'season
': video_data.get('seasonName
'),
331 'season_number
': int_or_none(video_data.get('seasonNo
')),
332 'season_id
': video_data.get('seasonId
'),
333 'episode
': video_data.get('title
'),
334 'episode_number
': int_or_none(video_data.get('episodeNo
')),
338 class HotStarPrefixIE(InfoExtractor):
339 """ The "hotstar:" prefix is no longer in use, but this is kept for backward compatibility """
341 _VALID_URL = r'hotstar
:(?
:(?P
<type>\w
+):)?
(?P
<id>\d
+)$
'
343 'url
': 'hotstar
:1000076273',
344 'only_matching
': True,
346 'url
': 'hotstar
:movies
:1260009879',
350 'title
': 'Nuvvu Naaku Nachav
',
351 'description
': 'md5
:d43701b1314e6f8233ce33523c043b7d
',
352 'timestamp
': 1567525674,
353 'upload_date
': '20190903',
355 'episode
': 'Nuvvu Naaku Nachav
',
358 'url
': 'hotstar
:episode
:1000234847',
359 'only_matching
': True,
362 'url
': 'hotstar
:sports
:1260065956',
363 'only_matching
': True,
366 'url
': 'hotstar
:sports
:1260066104',
367 'only_matching
': True,
370 def _real_extract(self, url):
371 video_id, video_type = self._match_valid_url(url).group('id', 'type')
372 return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
375 class HotStarPlaylistIE(HotStarBaseIE):
376 IE_NAME = 'hotstar
:playlist
'
377 _VALID_URL = r'https?
://(?
:www\
.)?hotstar\
.com(?
:/in)?
/(?
:tv|shows
)(?
:/[^
/]+){2}
/list/[^
/]+/t
-(?P
<id>\w
+)'
379 'url
': 'https
://www
.hotstar
.com
/tv
/savdhaan
-india
/s
-26/list/popular
-clips
/t
-3_2_26',
383 'playlist_mincount
': 20,
385 'url
': 'https
://www
.hotstar
.com
/shows
/savdhaan
-india
/s
-26/list/popular
-clips
/t
-3_2_26',
386 'only_matching
': True,
388 'url
': 'https
://www
.hotstar
.com
/tv
/savdhaan
-india
/s
-26/list/extras
/t
-2480',
389 'only_matching
': True,
391 'url
': 'https
://www
.hotstar
.com
/in/tv
/karthika
-deepam
/15457/list/popular
-clips
/t
-3_2_1272',
392 'only_matching
': True,
395 def _real_extract(self, url):
396 id_ = self._match_id(url)
397 return self.playlist_result(
398 self._playlist_entries('tray
/find
', id_, query={'tas': 10000, 'uqId': id_}), id_)
401 class HotStarSeasonIE(HotStarBaseIE):
402 IE_NAME = 'hotstar
:season
'
403 _VALID_URL = r'(?P
<url
>https?
://(?
:www\
.)?hotstar\
.com(?
:/in)?
/(?
:tv|shows
)/[^
/]+/\w
+)/seasons
/[^
/]+/ss
-(?P
<id>\w
+)'
405 'url
': 'https
://www
.hotstar
.com
/tv
/radhakrishn
/1260000646/seasons
/season
-2/ss
-8028',
409 'playlist_mincount
': 35,
411 'url
': 'https
://www
.hotstar
.com
/in/tv
/ishqbaaz
/9567/seasons
/season
-2/ss
-4357',
415 'playlist_mincount
': 30,
417 'url
': 'https
://www
.hotstar
.com
/in/tv
/bigg
-boss
/14714/seasons
/season
-4/ss
-8208/',
421 'playlist_mincount
': 19,
423 'url
': 'https
://www
.hotstar
.com
/in/shows
/bigg
-boss
/14714/seasons
/season
-4/ss
-8208/',
424 'only_matching
': True,
427 def _real_extract(self, url):
428 url, season_id = self._match_valid_url(url).groups()
429 return self.playlist_result(self._playlist_entries(
430 'season
/asset
', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
433 class HotStarSeriesIE(HotStarBaseIE):
434 IE_NAME = 'hotstar
:series
'
435 _VALID_URL = r'(?P
<url
>https?
://(?
:www\
.)?hotstar\
.com(?
:/in)?
/(?
:tv|shows
)/[^
/]+/(?P
<id>\d
+))/?
(?
:[#?]|$)'
437 'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
441 'playlist_mincount': 690,
443 'url': 'https://www.hotstar.com/tv/dancee-/1260050431',
447 'playlist_mincount': 43,
449 'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
453 'playlist_mincount': 267,
455 'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
459 'playlist_mincount': 940,
462 def _real_extract(self
, url
):
463 url
, series_id
= self
._match
_valid
_url
(url
).groups()
464 id_
= self
._call
_api
_v
1(
465 'show/detail', series_id
, query
={'contentId': series_id}
)['body']['results']['item']['id']
467 return self
.playlist_result(self
._playlist
_entries
(
468 'tray/g/1/items', series_id
, url
, query
={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}
), series_id
)