aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/hotstar.py
blob: 8de9c4fafb852456ba772090f50ccdef3c5065d2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
# coding: utf-8
from __future__ import unicode_literals

import hashlib
import hmac
import time

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    try_get,
)


class HotStarBaseIE(InfoExtractor):
    _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'

    def _call_api(self, path, video_id, query_name='contentId'):
        st = int(time.time())
        exp = st + 6000
        auth = 'st=%d~exp=%d~acl=/*' % (st, exp)
        auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
        response = self._download_json(
            'https://api.hotstar.com/' + path,
            video_id, headers={
                'hotstarauth': auth,
                'x-country-code': 'IN',
                'x-platform-code': 'JIO',
            }, query={
                query_name: video_id,
                'tas': 10000,
            })
        if response['statusCode'] != 'OK':
            raise ExtractorError(
                response['body']['message'], expected=True)
        return response['body']['results']


class HotStarIE(HotStarBaseIE):
    IE_NAME = 'hotstar'
    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
    _TESTS = [{
        # contentData
        'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273',
        'info_dict': {
            'id': '1000076273',
            'ext': 'mp4',
            'title': 'Can You Not Spread Rumours?',
            'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
            'timestamp': 1447248600,
            'upload_date': '20151111',
            'duration': 381,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        }
    }, {
        # contentDetail
        'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
        'only_matching': True,
    }, {
        'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583',
        'only_matching': True,
    }, {
        'url': 'http://www.hotstar.com/1000000515',
        'only_matching': True,
    }]
    _GEO_BYPASS = False

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)
        app_state = self._parse_json(self._search_regex(
            r'<script>window\.APP_STATE\s*=\s*({.+?})</script>',
            webpage, 'app state'), video_id)
        video_data = {}
        getters = list(
            lambda x, k=k: x['initialState']['content%s' % k]['content']
            for k in ('Data', 'Detail')
        )
        for v in app_state.values():
            content = try_get(v, getters, dict)
            if content and content.get('contentId') == video_id:
                video_data = content
                break

        title = video_data['title']

        if video_data.get('drmProtected'):
            raise ExtractorError('This video is DRM protected.', expected=True)

        formats = []
        format_data = self._call_api('h/v1/play', video_id)['item']
        format_url = format_data['playbackUrl']
        ext = determine_ext(format_url)
        if ext == 'm3u8':
            try:
                formats.extend(self._extract_m3u8_formats(
                    format_url, video_id, 'mp4', m3u8_id='hls'))
            except ExtractorError as e:
                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
                    self.raise_geo_restricted(countries=['IN'])
                raise
        elif ext == 'f4m':
            # produce broken files
            pass
        else:
            formats.append({
                'url': format_url,
                'width': int_or_none(format_data.get('width')),
                'height': int_or_none(format_data.get('height')),
            })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'description': video_data.get('description'),
            'duration': int_or_none(video_data.get('duration')),
            'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')),
            'formats': formats,
            'channel': video_data.get('channelName'),
            'channel_id': video_data.get('channelId'),
            'series': video_data.get('showName'),
            'season': video_data.get('seasonName'),
            'season_number': int_or_none(video_data.get('seasonNo')),
            'season_id': video_data.get('seasonId'),
            'episode': title,
            'episode_number': int_or_none(video_data.get('episodeNo')),
        }


class HotStarPlaylistIE(HotStarBaseIE):
    IE_NAME = 'hotstar:playlist'
    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
    _TESTS = [{
        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
        'info_dict': {
            'id': '3_2_26',
        },
        'playlist_mincount': 20,
    }, {
        'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')

        entries = [
            self.url_result(
                'https://www.hotstar.com/%s' % video['contentId'],
                ie=HotStarIE.ie_key(), video_id=video['contentId'])
            for video in collection['assets']['items']
            if video.get('contentId')]

        return self.playlist_result(entries, playlist_id)