aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/viki.py
blob: 0d634068910eeb8ec6c2abdc43f7f52b37c25d58 (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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
# coding: utf-8
from __future__ import unicode_literals

import json
import time
import hmac
import hashlib
import itertools

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_age_limit,
    parse_iso8601,
    sanitized_Request,
)


class VikiBaseIE(InfoExtractor):
    _VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
    _API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com'
    _API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s'

    _APP = '65535a'
    _APP_VERSION = '2.2.5.1428709186'
    _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'

    _NETRC_MACHINE = 'viki'

    _token = None

    _ERRORS = {
        'geo': 'Sorry, this content is not available in your region.',
        'upcoming': 'Sorry, this content is not yet available.',
        # 'paywall': 'paywall',
    }

    def _prepare_call(self, path, timestamp=None, post_data=None):
        path += '?' if '?' not in path else '&'
        if not timestamp:
            timestamp = int(time.time())
        query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
        if self._token:
            query += '&token=%s' % self._token
        sig = hmac.new(
            self._APP_SECRET.encode('ascii'),
            query.encode('ascii'),
            hashlib.sha1
        ).hexdigest()
        url = self._API_URL_TEMPLATE % (query, sig)
        return sanitized_Request(
            url, json.dumps(post_data).encode('utf-8')) if post_data else url

    def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
        resp = self._download_json(
            self._prepare_call(path, timestamp, post_data), video_id, note)

        error = resp.get('error')
        if error:
            if error == 'invalid timestamp':
                resp = self._download_json(
                    self._prepare_call(path, int(resp['current_timestamp']), post_data),
                    video_id, '%s (retry)' % note)
                error = resp.get('error')
            if error:
                self._raise_error(resp['error'])

        return resp

    def _raise_error(self, error):
        raise ExtractorError(
            '%s returned error: %s' % (self.IE_NAME, error),
            expected=True)

    def _check_errors(self, data):
        for reason, status in data.get('blocking', {}).items():
            if status and reason in self._ERRORS:
                raise ExtractorError('%s said: %s' % (
                    self.IE_NAME, self._ERRORS[reason]), expected=True)

    def _real_initialize(self):
        self._login()

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            return

        login_form = {
            'login_id': username,
            'password': password,
        }

        login = self._call_api(
            'sessions.json', None,
            'Logging in as %s' % username, post_data=login_form)

        self._token = login.get('token')
        if not self._token:
            self.report_warning('Unable to get session token, login has probably failed')

    @staticmethod
    def dict_selection(dict_obj, preferred_key, allow_fallback=True):
        if preferred_key in dict_obj:
            return dict_obj.get(preferred_key)

        if not allow_fallback:
            return

        filtered_dict = list(filter(None, [dict_obj.get(k) for k in dict_obj.keys()]))
        return filtered_dict[0] if filtered_dict else None


class VikiIE(VikiBaseIE):
    IE_NAME = 'viki'
    _VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE
    _TESTS = [{
        'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
        'info_dict': {
            'id': '1023585v',
            'ext': 'mp4',
            'title': 'Heirs Episode 14',
            'uploader': 'SBS',
            'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
            'upload_date': '20131121',
            'age_limit': 13,
        },
        'skip': 'Blocked in the US',
    }, {
        # clip
        'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
        'md5': 'feea2b1d7b3957f70886e6dfd8b8be84',
        'info_dict': {
            'id': '1067139v',
            'ext': 'mp4',
            'title': "'The Avengers: Age of Ultron' Press Conference",
            'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
            'duration': 352,
            'timestamp': 1430380829,
            'upload_date': '20150430',
            'uploader': 'Arirang TV',
            'like_count': int,
            'age_limit': 0,
        }
    }, {
        'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
        'info_dict': {
            'id': '1048879v',
            'ext': 'mp4',
            'title': 'Ankhon Dekhi',
            'duration': 6512,
            'timestamp': 1408532356,
            'upload_date': '20140820',
            'uploader': 'Spuul',
            'like_count': int,
            'age_limit': 13,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
        'skip': 'Blocked in the US',
    }, {
        # episode
        'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
        'md5': '1f54697dabc8f13f31bf06bb2e4de6db',
        'info_dict': {
            'id': '44699v',
            'ext': 'mp4',
            'title': 'Boys Over Flowers - Episode 1',
            'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
            'duration': 4204,
            'timestamp': 1270496524,
            'upload_date': '20100405',
            'uploader': 'group8',
            'like_count': int,
            'age_limit': 13,
        }
    }, {
        # youtube external
        'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
        'md5': '63f8600c1da6f01b7640eee7eca4f1da',
        'info_dict': {
            'id': '50562v',
            'ext': 'webm',
            'title': 'Poor Nastya [COMPLETE] - Episode 1',
            'description': '',
            'duration': 606,
            'timestamp': 1274949505,
            'upload_date': '20101213',
            'uploader': 'ad14065n',
            'uploader_id': 'ad14065n',
            'like_count': int,
            'age_limit': 13,
        }
    }, {
        'url': 'http://www.viki.com/player/44699v',
        'only_matching': True,
    }, {
        # non-English description
        'url': 'http://www.viki.com/videos/158036v-love-in-magic',
        'md5': '013dc282714e22acf9447cad14ff1208',
        'info_dict': {
            'id': '158036v',
            'ext': 'mp4',
            'uploader': 'I Planet Entertainment',
            'upload_date': '20111122',
            'timestamp': 1321985454,
            'description': 'md5:44b1e46619df3a072294645c770cef36',
            'title': 'Love In Magic',
            'age_limit': 13,
        },
    }]

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

        video = self._call_api(
            'videos/%s.json' % video_id, video_id, 'Downloading video JSON')

        self._check_errors(video)

        title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
        if not title:
            title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
            container_titles = video.get('container', {}).get('titles', {})
            container_title = self.dict_selection(container_titles, 'en')
            title = '%s - %s' % (container_title, title)

        description = self.dict_selection(video.get('descriptions', {}), 'en')

        duration = int_or_none(video.get('duration'))
        timestamp = parse_iso8601(video.get('created_at'))
        uploader = video.get('author')
        like_count = int_or_none(video.get('likes', {}).get('count'))
        age_limit = parse_age_limit(video.get('rating'))

        thumbnails = []
        for thumbnail_id, thumbnail in video.get('images', {}).items():
            thumbnails.append({
                'id': thumbnail_id,
                'url': thumbnail.get('url'),
            })

        subtitles = {}
        for subtitle_lang, _ in video.get('subtitle_completions', {}).items():
            subtitles[subtitle_lang] = [{
                'ext': subtitles_format,
                'url': self._prepare_call(
                    'videos/%s/subtitles/%s.%s' % (video_id, subtitle_lang, subtitles_format)),
            } for subtitles_format in ('srt', 'vtt')]

        result = {
            'id': video_id,
            'title': title,
            'description': description,
            'duration': duration,
            'timestamp': timestamp,
            'uploader': uploader,
            'like_count': like_count,
            'age_limit': age_limit,
            'thumbnails': thumbnails,
            'subtitles': subtitles,
        }

        streams = self._call_api(
            'videos/%s/streams.json' % video_id, video_id,
            'Downloading video streams JSON')

        if 'external' in streams:
            result.update({
                '_type': 'url_transparent',
                'url': streams['external']['url'],
            })
            return result

        formats = []
        for format_id, stream_dict in streams.items():
            height = int_or_none(self._search_regex(
                r'^(\d+)[pP]$', format_id, 'height', default=None))
            for protocol, format_dict in stream_dict.items():
                if format_id == 'm3u8':
                    m3u8_formats = self._extract_m3u8_formats(
                        format_dict['url'], video_id, 'mp4',
                        entry_protocol='m3u8_native', preference=-1,
                        m3u8_id='m3u8-%s' % protocol, fatal=False)
                    # Despite CODECS metadata in m3u8 all video-only formats
                    # are actually video+audio
                    for f in m3u8_formats:
                        if f.get('acodec') == 'none' and f.get('vcodec') != 'none':
                            f['acodec'] = None
                    formats.extend(m3u8_formats)
                else:
                    formats.append({
                        'url': format_dict['url'],
                        'format_id': '%s-%s' % (format_id, protocol),
                        'height': height,
                    })
        self._sort_formats(formats)

        result['formats'] = formats
        return result


class VikiChannelIE(VikiBaseIE):
    IE_NAME = 'viki:channel'
    _VALID_URL = r'%s(?:tv|news|movies|artists)/(?P<id>[0-9]+c)' % VikiBaseIE._VALID_URL_BASE
    _TESTS = [{
        'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
        'info_dict': {
            'id': '50c',
            'title': 'Boys Over Flowers',
            'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
        },
        'playlist_mincount': 71,
    }, {
        'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
        'info_dict': {
            'id': '1354c',
            'title': 'Poor Nastya [COMPLETE]',
            'description': 'md5:05bf5471385aa8b21c18ad450e350525',
        },
        'playlist_count': 127,
    }, {
        'url': 'http://www.viki.com/news/24569c-showbiz-korea',
        'only_matching': True,
    }, {
        'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005',
        'only_matching': True,
    }, {
        'url': 'http://www.viki.com/artists/2141c-shinee',
        'only_matching': True,
    }]

    _PER_PAGE = 25

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

        channel = self._call_api(
            'containers/%s.json' % channel_id, channel_id,
            'Downloading channel JSON')

        self._check_errors(channel)

        title = self.dict_selection(channel['titles'], 'en')

        description = self.dict_selection(channel['descriptions'], 'en')

        entries = []
        for video_type in ('episodes', 'clips', 'movies'):
            for page_num in itertools.count(1):
                page = self._call_api(
                    'containers/%s/%s.json?per_page=%d&sort=number&direction=asc&with_paging=true&page=%d'
                    % (channel_id, video_type, self._PER_PAGE, page_num), channel_id,
                    'Downloading %s JSON page #%d' % (video_type, page_num))
                for video in page['response']:
                    video_id = video['id']
                    entries.append(self.url_result(
                        'http://www.viki.com/videos/%s' % video_id, 'Viki'))
                if not page['pagination']['next']:
                    break

        return self.playlist_result(entries, channel_id, title, description)