]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hotstar.py
bf5717f1bf1f8366e45222e716951fb11069e8f6
[youtubedl] / youtube_dl / extractor / hotstar.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import hashlib
5 import hmac
6 import time
7
8 from .common import InfoExtractor
9 from ..compat import compat_HTTPError
10 from ..utils import (
11 determine_ext,
12 ExtractorError,
13 int_or_none,
14 try_get,
15 )
16
17
18 class HotStarBaseIE(InfoExtractor):
19 _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
20
21 def _call_api(self, path, video_id, query_name='contentId'):
22 st = int(time.time())
23 exp = st + 6000
24 auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
25 auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
26 response = self._download_json(
27 'https://api.hotstar.com/' + path,
28 video_id, headers={
29 'hotstarauth': auth,
30 'x-country-code': 'IN',
31 'x-platform-code': 'JIO',
32 }, query={
33 query_name: video_id,
34 'tas': 10000,
35 })
36 if response['statusCode'] != 'OK':
37 raise ExtractorError(
38 response['body']['message'], expected=True)
39 return response['body']['results']
40
41
42 class HotStarIE(HotStarBaseIE):
43 IE_NAME = 'hotstar'
44 _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
45 _TESTS = [{
46 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
47 'info_dict': {
48 'id': '1000076273',
49 'ext': 'mp4',
50 'title': 'Can You Not Spread Rumours?',
51 'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
52 'timestamp': 1447248600,
53 'upload_date': '20151111',
54 'duration': 381,
55 },
56 'params': {
57 # m3u8 download
58 'skip_download': True,
59 }
60 }, {
61 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
62 'only_matching': True,
63 }, {
64 'url': 'http://www.hotstar.com/1000000515',
65 'only_matching': True,
66 }]
67 _GEO_BYPASS = False
68
69 def _real_extract(self, url):
70 video_id = self._match_id(url)
71
72 webpage = self._download_webpage(url, video_id)
73 app_state = self._parse_json(self._search_regex(
74 r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
75 webpage, 'app state'), video_id)
76 video_data = {}
77 for v in app_state.values():
78 content = try_get(v, lambda x: x['initialState']['contentData']['content'], dict)
79 if content and content.get('contentId') == video_id:
80 video_data = content
81
82 title = video_data['title']
83
84 if video_data.get('drmProtected'):
85 raise ExtractorError('This video is DRM protected.', expected=True)
86
87 formats = []
88 format_data = self._call_api('h/v1/play', video_id)['item']
89 format_url = format_data['playbackUrl']
90 ext = determine_ext(format_url)
91 if ext == 'm3u8':
92 try:
93 formats.extend(self._extract_m3u8_formats(
94 format_url, video_id, 'mp4', m3u8_id='hls'))
95 except ExtractorError as e:
96 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
97 self.raise_geo_restricted(countries=['IN'])
98 raise
99 elif ext == 'f4m':
100 # produce broken files
101 pass
102 else:
103 formats.append({
104 'url': format_url,
105 'width': int_or_none(format_data.get('width')),
106 'height': int_or_none(format_data.get('height')),
107 })
108 self._sort_formats(formats)
109
110 return {
111 'id': video_id,
112 'title': title,
113 'description': video_data.get('description'),
114 'duration': int_or_none(video_data.get('duration')),
115 'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
116 'formats': formats,
117 'channel': video_data.get('channelName'),
118 'channel_id': video_data.get('channelId'),
119 'series': video_data.get('showName'),
120 'season': video_data.get('seasonName'),
121 'season_number': int_or_none(video_data.get('seasonNo')),
122 'season_id': video_data.get('seasonId'),
123 'episode': title,
124 'episode_number': int_or_none(video_data.get('episodeNo')),
125 }
126
127
128 class HotStarPlaylistIE(HotStarBaseIE):
129 IE_NAME = 'hotstar:playlist'
130 _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
131 _TESTS = [{
132 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
133 'info_dict': {
134 'id': '3_2_26',
135 },
136 'playlist_mincount': 20,
137 }, {
138 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
139 'only_matching': True,
140 }]
141
142 def _real_extract(self, url):
143 playlist_id = self._match_id(url)
144
145 collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')
146
147 entries = [
148 self.url_result(
149 'https://www.hotstar.com/%s' % video['contentId'],
150 ie=HotStarIE.ie_key(), video_id=video['contentId'])
151 for video in collection['assets']['items']
152 if video.get('contentId')]
153
154 return self.playlist_result(entries, playlist_id)