aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/hrti.py
blob: 23f7b1fc9550a40a74476b3f414d90425acfca7e (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
# coding: utf-8
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
    clean_html,
    ExtractorError,
    int_or_none,
    parse_age_limit,
    sanitized_Request,
    try_get,
)


class HRTiBaseIE(InfoExtractor):
    """
        Base Information Extractor for Croatian Radiotelevision
        video on demand site https://hrti.hrt.hr
        Reverse engineered from the JavaScript app in app.min.js
    """
    _NETRC_MACHINE = 'hrti'

    _APP_LANGUAGE = 'hr'
    _APP_VERSION = '1.1'
    _APP_PUBLICATION_ID = 'all_in_one'
    _API_URL = 'http://clientapi.hrt.hr/client_api.php/config/identify/format/json'

    def _initialize_api(self):
        init_data = {
            'application_publication_id': self._APP_PUBLICATION_ID
        }

        uuid = self._download_json(
            self._API_URL, None, note='Downloading uuid',
            errnote='Unable to download uuid',
            data=json.dumps(init_data).encode('utf-8'))['uuid']

        app_data = {
            'uuid': uuid,
            'application_publication_id': self._APP_PUBLICATION_ID,
            'application_version': self._APP_VERSION
        }

        req = sanitized_Request(self._API_URL, data=json.dumps(app_data).encode('utf-8'))
        req.get_method = lambda: 'PUT'

        resources = self._download_json(
            req, None, note='Downloading session information',
            errnote='Unable to download session information')

        self._session_id = resources['session_id']

        modules = resources['modules']

        self._search_url = modules['vod_catalog']['resources']['search']['uri'].format(
            language=self._APP_LANGUAGE,
            application_id=self._APP_PUBLICATION_ID)

        self._login_url = (modules['user']['resources']['login']['uri']
                           + '/format/json').format(session_id=self._session_id)

        self._logout_url = modules['user']['resources']['logout']['uri']

    def _login(self):
        username, password = self._get_login_info()
        # TODO: figure out authentication with cookies
        if username is None or password is None:
            self.raise_login_required()

        auth_data = {
            'username': username,
            'password': password,
        }

        try:
            auth_info = self._download_json(
                self._login_url, None, note='Logging in', errnote='Unable to log in',
                data=json.dumps(auth_data).encode('utf-8'))
        except ExtractorError as e:
            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 406:
                auth_info = self._parse_json(e.cause.read().encode('utf-8'), None)
            else:
                raise

        error_message = auth_info.get('error', {}).get('message')
        if error_message:
            raise ExtractorError(
                '%s said: %s' % (self.IE_NAME, error_message),
                expected=True)

        self._token = auth_info['secure_streaming_token']

    def _real_initialize(self):
        self._initialize_api()
        self._login()


class HRTiIE(HRTiBaseIE):
    _VALID_URL = r'''(?x)
                        (?:
                            hrti:(?P<short_id>[0-9]+)|
                            https?://
                                hrti\.hrt\.hr/(?:\#/)?video/show/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?
                        )
                    '''
    _TESTS = [{
        'url': 'https://hrti.hrt.hr/#/video/show/2181385/republika-dokumentarna-serija-16-hd',
        'info_dict': {
            'id': '2181385',
            'display_id': 'republika-dokumentarna-serija-16-hd',
            'ext': 'mp4',
            'title': 'REPUBLIKA, dokumentarna serija (1/6) (HD)',
            'description': 'md5:48af85f620e8e0e1df4096270568544f',
            'duration': 2922,
            'view_count': int,
            'average_rating': int,
            'episode_number': int,
            'season_number': int,
            'age_limit': 12,
        },
        'skip': 'Requires account credentials',
    }, {
        'url': 'https://hrti.hrt.hr/#/video/show/2181385/',
        'only_matching': True,
    }, {
        'url': 'hrti:2181385',
        'only_matching': True,
    }, {
        'url': 'https://hrti.hrt.hr/video/show/3873068/cuvar-dvorca-dramska-serija-14',
        'only_matching': True,
    }]

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

        video = self._download_json(
            '%s/video_id/%s/format/json' % (self._search_url, video_id),
            display_id, 'Downloading video metadata JSON')['video'][0]

        title_info = video['title']
        title = title_info['title_long']

        movie = video['video_assets']['movie'][0]
        m3u8_url = movie['url'].format(TOKEN=self._token)
        formats = self._extract_m3u8_formats(
            m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native',
            m3u8_id='hls')
        self._sort_formats(formats)

        description = clean_html(title_info.get('summary_long'))
        age_limit = parse_age_limit(video.get('parental_control', {}).get('rating'))
        view_count = int_or_none(video.get('views'))
        average_rating = int_or_none(video.get('user_rating'))
        duration = int_or_none(movie.get('duration'))

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'duration': duration,
            'view_count': view_count,
            'average_rating': average_rating,
            'age_limit': age_limit,
            'formats': formats,
        }


class HRTiPlaylistIE(HRTiBaseIE):
    _VALID_URL = r'https?://hrti\.hrt\.hr/(?:#/)?video/list/category/(?P<id>[0-9]+)/(?P<display_id>[^/]+)?'
    _TESTS = [{
        'url': 'https://hrti.hrt.hr/#/video/list/category/212/ekumena',
        'info_dict': {
            'id': '212',
            'title': 'ekumena',
        },
        'playlist_mincount': 8,
        'skip': 'Requires account credentials',
    }, {
        'url': 'https://hrti.hrt.hr/#/video/list/category/212/',
        'only_matching': True,
    }, {
        'url': 'https://hrti.hrt.hr/video/list/category/212/ekumena',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        category_id = mobj.group('id')
        display_id = mobj.group('display_id') or category_id

        response = self._download_json(
            '%s/category_id/%s/format/json' % (self._search_url, category_id),
            display_id, 'Downloading video metadata JSON')

        video_ids = try_get(
            response, lambda x: x['video_listings'][0]['alternatives'][0]['list'],
            list) or [video['id'] for video in response.get('videos', []) if video.get('id')]

        entries = [self.url_result('hrti:%s' % video_id) for video_id in video_ids]

        return self.playlist_result(entries, category_id, display_id)