aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nexx.py
blob: 071879ba4f5317326ebed99ee59e8a6f4e6b4ce4 (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
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
# coding: utf-8
from __future__ import unicode_literals

import hashlib
import random
import re
import time

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_duration,
    try_get,
    urlencode_postdata,
)


class NexxIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                        (?:
                            https?://api\.nexx(?:\.cloud|cdn\.com)/v3/(?P<domain_id>\d+)/videos/byid/|
                            nexx:(?P<domain_id_s>\d+):
                        )
                        (?P<id>\d+)
                    '''
    _TESTS = [{
        # movie
        'url': 'https://api.nexx.cloud/v3/748/videos/byid/128907',
        'md5': '16746bfc28c42049492385c989b26c4a',
        'info_dict': {
            'id': '128907',
            'ext': 'mp4',
            'title': 'Stiftung Warentest',
            'alt_title': 'Wie ein Test abläuft',
            'description': 'md5:d1ddb1ef63de721132abd38639cc2fd2',
            'release_year': 2013,
            'creator': 'SPIEGEL TV',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 2509,
            'timestamp': 1384264416,
            'upload_date': '20131112',
        },
        'params': {
            'format': 'bestvideo',
        },
    }, {
        # episode
        'url': 'https://api.nexx.cloud/v3/741/videos/byid/247858',
        'info_dict': {
            'id': '247858',
            'ext': 'mp4',
            'title': 'Return of the Golden Child (OV)',
            'description': 'md5:5d969537509a92b733de21bae249dc63',
            'release_year': 2017,
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 1397,
            'timestamp': 1495033267,
            'upload_date': '20170517',
            'episode_number': 2,
            'season_number': 2,
        },
        'params': {
            'format': 'bestvideo',
            'skip_download': True,
        },
    }, {
        'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907',
        'only_matching': True,
    }, {
        'url': 'nexx:748:128907',
        'only_matching': True,
    }]

    @staticmethod
    def _extract_domain_id(webpage):
        mobj = re.search(
            r'<script\b[^>]+\bsrc=["\'](?:https?:)?//require\.nexx(?:\.cloud|cdn\.com)/(?P<id>\d+)',
            webpage)
        return mobj.group('id') if mobj else None

    @staticmethod
    def _extract_urls(webpage):
        # Reference:
        # 1. https://nx-s.akamaized.net/files/201510/44.pdf

        entries = []

        # JavaScript Integration
        domain_id = NexxIE._extract_domain_id(webpage)
        if domain_id:
            for video_id in re.findall(
                    r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)',
                    webpage):
                entries.append(
                    'https://api.nexx.cloud/v3/%s/videos/byid/%s'
                    % (domain_id, video_id))

        # TODO: support more embed formats

        return entries

    @staticmethod
    def _extract_url(webpage):
        return NexxIE._extract_urls(webpage)[0]

    def _handle_error(self, response):
        status = int_or_none(try_get(
            response, lambda x: x['metadata']['status']) or 200)
        if 200 <= status < 300:
            return
        raise ExtractorError(
            '%s said: %s' % (self.IE_NAME, response['metadata']['errorhint']),
            expected=True)

    def _call_api(self, domain_id, path, video_id, data=None, headers={}):
        headers['Content-Type'] = 'application/x-www-form-urlencoded; charset=UTF-8'
        result = self._download_json(
            'https://api.nexx.cloud/v3/%s/%s' % (domain_id, path), video_id,
            'Downloading %s JSON' % path, data=urlencode_postdata(data),
            headers=headers)
        self._handle_error(result)
        return result['result']

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        domain_id = mobj.group('domain_id') or mobj.group('domain_id_s')
        video_id = mobj.group('id')

        # Reverse engineered from JS code (see getDeviceID function)
        device_id = '%d:%d:%d%d' % (
            random.randint(1, 4), int(time.time()),
            random.randint(1e4, 99999), random.randint(1, 9))

        result = self._call_api(domain_id, 'session/init', video_id, data={
            'nxp_devh': device_id,
            'nxp_userh': '',
            'precid': '0',
            'playlicense': '0',
            'screenx': '1920',
            'screeny': '1080',
            'playerversion': '6.0.00',
            'gateway': 'html5',
            'adGateway': '',
            'explicitlanguage': 'en-US',
            'addTextTemplates': '1',
            'addDomainData': '1',
            'addAdModel': '1',
        }, headers={
            'X-Request-Enable-Auth-Fallback': '1',
        })

        cid = result['general']['cid']

        # As described in [1] X-Request-Token generation algorithm is
        # as follows:
        #   md5( operation + domain_id + domain_secret )
        # where domain_secret is a static value that will be given by nexx.tv
        # as per [1]. Here is how this "secret" is generated (reversed
        # from _play.api.init function, search for clienttoken). So it's
        # actually not static and not that much of a secret.
        # 1. https://nexxtvstorage.blob.core.windows.net/files/201610/27.pdf
        secret = result['device']['clienttoken'][int(device_id[0]):]
        secret = secret[0:len(secret) - int(device_id[-1])]

        op = 'byid'

        # Reversed from JS code for _play.api.call function (search for
        # X-Request-Token)
        request_token = hashlib.md5(
            ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest()

        video = self._call_api(
            domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={
                'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description',
                'addInteractionOptions': '1',
                'addStatusDetails': '1',
                'addStreamDetails': '1',
                'addCaptions': '1',
                'addScenes': '1',
                'addHotSpots': '1',
                'addBumpers': '1',
                'captionFormat': 'data',
            }, headers={
                'X-Request-CID': cid,
                'X-Request-Token': request_token,
            })

        general = video['general']
        title = general['title']

        stream_data = video['streamdata']
        language = general.get('language_raw') or ''

        # TODO: reverse more cdns and formats

        cdn = stream_data['cdnType']
        assert cdn == 'azure'

        azure_locator = stream_data['azureLocator']

        AZURE_URL = 'http://nx-p%02d.akamaized.net/'

        for secure in ('s', ''):
            cdn_shield = stream_data.get('cdnShieldHTTP%s' % secure.upper())
            if cdn_shield:
                azure_base = 'http%s://%s' % (secure, cdn_shield)
                break
        else:
            azure_base = AZURE_URL % int(stream_data['azureAccount'].replace('nexxplayplus', ''))

        is_ml = ',' in language
        azure_m3u8_url = '%s%s/%s_src%s.ism/Manifest(format=m3u8-aapl)' % (
            azure_base, azure_locator, video_id, ('_manifest' if is_ml else ''))

        protection_token = try_get(
            video, lambda x: x['protectiondata']['token'], compat_str)
        if protection_token:
            azure_m3u8_url += '?hdnts=%s' % protection_token

        formats = self._extract_m3u8_formats(
            azure_m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
            m3u8_id='%s-hls' % cdn)
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'alt_title': general.get('subtitle'),
            'description': general.get('description'),
            'release_year': int_or_none(general.get('year')),
            'creator': general.get('studio') or general.get('studio_adref'),
            'thumbnail': try_get(
                video, lambda x: x['imagedata']['thumb'], compat_str),
            'duration': parse_duration(general.get('runtime')),
            'timestamp': int_or_none(general.get('uploaded')),
            'episode_number': int_or_none(try_get(
                video, lambda x: x['episodedata']['episode'])),
            'season_number': int_or_none(try_get(
                video, lambda x: x['episodedata']['season'])),
            'formats': formats,
        }


class NexxEmbedIE(InfoExtractor):
    _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P<id>[^/?#&]+)'
    _TEST = {
        'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1',
        'md5': '16746bfc28c42049492385c989b26c4a',
        'info_dict': {
            'id': '161464',
            'ext': 'mp4',
            'title': 'Nervenkitzel Achterbahn',
            'alt_title': 'Karussellbauer in Deutschland',
            'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
            'release_year': 2005,
            'creator': 'SPIEGEL TV',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 2761,
            'timestamp': 1394021479,
            'upload_date': '20140305',
        },
        'params': {
            'format': 'bestvideo',
            'skip_download': True,
        },
    }

    @staticmethod
    def _extract_urls(webpage):
        # Reference:
        # 1. https://nx-s.akamaized.net/files/201510/44.pdf

        # iFrame Embed Integration
        return [mobj.group('url') for mobj in re.finditer(
            r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:(?!\1).)+)\1',
            webpage)]

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

        webpage = self._download_webpage(url, embed_id)

        return self.url_result(NexxIE._extract_url(webpage), ie=NexxIE.ie_key())