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
|
from __future__ import unicode_literals
import re
import time
import hmac
import hashlib
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
parse_iso8601,
)
from .common import InfoExtractor
class VikiBaseIE(InfoExtractor):
_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)'
def _prepare_call(self, path, timestamp=None):
path += '?' if '?' not in path else '&'
if not timestamp:
timestamp = int(time.time())
query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp)
sig = hmac.new(
self._APP_SECRET.encode('ascii'),
query.encode('ascii'),
hashlib.sha1
).hexdigest()
return self._API_URL_TEMPLATE % (query, sig)
def _call_api(self, path, video_id, note, timestamp=None):
resp = self._download_json(
self._prepare_call(path, timestamp), 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'])),
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)
class VikiIE(VikiBaseIE):
IE_NAME = 'viki'
_VALID_URL = r'https?://(?:www\.)?viki\.com/(?:videos|player)/(?P<id>[0-9]+v)'
_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': '86c0b5dbd4d83a6611a79987cc7a1989',
'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,
}
}, {
# episode
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
'md5': '190f3ef426005ba3a080a63325955bc3',
'info_dict': {
'id': '44699v',
'ext': 'mp4',
'title': 'Boys Over Flowers - Episode 1',
'description': 'md5:52617e4f729c7d03bfd4bcbbb6e946f2',
'duration': 4155,
'timestamp': 1270496524,
'upload_date': '20100405',
'uploader': 'group8',
'like_count': int,
'age_limit': 13,
}
}, {
'url': 'http://www.viki.com/player/44699v',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
streams = self._call_api(
'videos/%s/streams.json' % video_id, video_id,
'Downloading video streams JSON')
formats = []
for format_id, stream_dict in streams.items():
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
for protocol, format_dict in stream_dict.items():
if format_id == 'm3u8':
formats = self._extract_m3u8_formats(
format_dict['url'], video_id, 'mp4', m3u8_id='m3u8-%s' % protocol)
else:
formats.append({
'url': format_dict['url'],
'format_id': '%s-%s' % (format_id, protocol),
'height': height,
})
self._sort_formats(formats)
video = self._call_api(
'videos/%s.json' % video_id, video_id, 'Downloading video JSON')
title = None
titles = video.get('titles')
if titles:
title = titles.get('en') or titles[titles.keys()[0]]
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')
if container_titles:
container_title = container_titles.get('en') or container_titles[titles.keys()[0]]
title = '%s - %s' % (container_title, title)
descriptions = video.get('descriptions')
description = descriptions.get('en') or descriptions[titles.keys()[0]] if descriptions else None
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')]
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'uploader': uploader,
'like_count': like_count,
'age_limit': age_limit,
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles,
}
class VikiChannelIE(InfoExtractor):
IE_NAME = 'viki:channel'
_VALID_URL = r'https?://(?:www\.)?viki\.com/tv/(?P<id>[0-9]+c)'
_TESTS = [{
'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
'info_dict': {
'id': '50c',
'title': 'Boys Over Flowers',
'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
},
'playlist_count': 70,
}, {
'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
'info_dict': {
'id': '1354c',
'title': 'Poor Nastya [COMPLETE]',
'description': 'md5:05bf5471385aa8b21c18ad450e350525',
},
'playlist_count': 127,
}]
_API_BASE = 'http://api.viki.io/v4/containers'
_APP = '100000a'
_PER_PAGE = 25
def _real_extract(self, url):
channel_id = self._match_id(url)
channel = self._download_json(
'%s/%s.json?app=%s' % (self._API_BASE, channel_id, self._APP),
channel_id, 'Downloading channel JSON')
titles = channel['titles']
title = titles.get('en') or titles[titles.keys()[0]]
descriptions = channel['descriptions']
description = descriptions.get('en') or descriptions[descriptions.keys()[0]]
entries = []
for video_type in ('episodes', 'clips'):
page_url = '%s/%s/%s.json?app=%s&per_page=%d&sort=number&direction=asc&with_paging=true&page=1' % (self._API_BASE, channel_id, video_type, self._APP, self._PER_PAGE)
while page_url:
page = self._download_json(
page_url, channel_id,
'Downloading %s JSON page #%s'
% (video_type, re.search(r'[?&]page=([0-9]+)', page_url).group(1)))
for video in page['response']:
video_id = video['id']
entries.append(self.url_result(
'http://www.viki.com/videos/%s' % video_id, 'Viki', video_id))
page_url = page['pagination']['next']
return self.playlist_result(entries, channel_id, title, description)
|
