]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/vidio.py
1 from .common
import InfoExtractor
18 class VidioBaseIE(InfoExtractor
):
19 _LOGIN_URL
= 'https://www.vidio.com/users/login'
20 _NETRC_MACHINE
= 'vidio'
22 def _perform_login(self
, username
, password
):
24 res
= self
._download
_json
(
25 'https://www.vidio.com/interactions.json', None, 'Checking if logged in', fatal
=False) or {}
26 return bool(res
.get('current_user'))
31 login_page
= self
._download
_webpage
(
32 self
._LOGIN
_URL
, None, 'Downloading log in page')
34 login_form
= self
._form
_hidden
_inputs
("login-form", login_page
)
36 'user[login]': username
,
37 'user[password]': password
,
39 login_post
, login_post_urlh
= self
._download
_webpage
_handle
(
40 self
._LOGIN
_URL
, None, 'Logging in', data
=urlencode_postdata(login_form
), expected_status
=[302, 401])
42 if login_post_urlh
.status
== 401:
43 if get_element_by_class('onboarding-content-register-popup__title', login_post
):
45 'Unable to log in: The provided email has not registered yet.', expected
=True)
47 reason
= get_element_by_class('onboarding-form__general-error', login_post
) or get_element_by_class('onboarding-modal__title', login_post
)
48 if 'Akun terhubung ke' in reason
:
50 'Unable to log in: Your account is linked to a social media account. '
51 'Use --cookies to provide account credentials instead', expected
=True)
53 subreason
= get_element_by_class('onboarding-modal__description-text', login_post
) or ''
55 'Unable to log in: %s. %s' % (reason
, clean_html(subreason
)), expected
=True)
56 raise ExtractorError('Unable to log in')
58 def _initialize_pre_login(self
):
59 self
._api
_key
= self
._download
_json
(
60 'https://www.vidio.com/auth', None, data
=b
'')['api_key']
62 def _call_api(self
, url
, video_id
, note
=None):
63 return self
._download
_json
(url
, video_id
, note
=note
, headers
={
64 'Content-Type': 'application/vnd.api+json',
65 'X-API-KEY': self
._api
_key
,
69 class VidioIE(VidioBaseIE
):
70 _VALID_URL
= r
'https?://(?:www\.)?vidio\.com/(watch|embed)/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
72 'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
73 'md5': 'abac81b1a205a8d94c609a473b5ea62a',
76 'display_id': 'dj_ambred-booyah-live-2015',
78 'title': 'DJ_AMBRED - Booyah (Live 2015)',
79 'description': 'md5:27dc15f819b6a78a626490881adbadf8',
80 'thumbnail': r
're:^https?://.*\.jpg$',
83 'uploader': 'TWELVE Pic',
84 'timestamp': 1444902800,
85 'upload_date': '20151015',
86 'uploader_id': 'twelvepictures',
87 'channel': 'Cover Music Video',
88 'channel_id': '280236',
93 'uploader_url': 'https://www.vidio.com/@twelvepictures',
96 'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
97 'only_matching': True,
99 # Premier-exclusive video
100 'url': 'https://www.vidio.com/watch/1550718-stand-by-me-doraemon',
101 'only_matching': True
103 # embed url from https://enamplus.liputan6.com/read/5033648/video-fakta-temuan-suspek-cacar-monyet-di-jawa-tengah
104 'url': 'https://www.vidio.com/embed/7115874-fakta-temuan-suspek-cacar-monyet-di-jawa-tengah',
108 'channel_id': '40172876',
109 'comment_count': int,
110 'uploader_id': 'liputan6',
112 'dislike_count': int,
113 'upload_date': '20220804',
114 'uploader': 'Liputan6.com',
115 'display_id': 'fakta-temuan-suspek-cacar-monyet-di-jawa-tengah',
116 'channel': 'ENAM PLUS 165',
117 'timestamp': 1659605520,
118 'title': 'Fakta Temuan Suspek Cacar Monyet di Jawa Tengah',
121 'tags': ['monkeypox indonesia', 'cacar monyet menyebar', 'suspek cacar monyet di indonesia', 'fakta', 'hoax atau bukan?', 'jawa tengah'],
122 'thumbnail': 'https://thumbor.prod.vidiocdn.com/83PN-_BKm5sS7emLtRxl506MLqQ=/640x360/filters:quality(70)/vidio-web-prod-video/uploads/video/image/7115874/fakta-suspek-cacar-monyet-di-jawa-tengah-24555a.jpg',
123 'uploader_url': 'https://www.vidio.com/@liputan6',
124 'description': 'md5:6d595a18d3b19ee378e335a6f288d5ac',
128 def _real_extract(self
, url
):
129 match
= self
._match
_valid
_url
(url
).groupdict()
130 video_id
, display_id
= match
.get('id'), match
.get('display_id')
131 data
= self
._call
_api
('https://api.vidio.com/videos/' + video_id
, display_id
)
132 video
= data
['videos'][0]
133 title
= video
['title'].strip()
134 is_premium
= video
.get('is_premium')
137 sources
= self
._download
_json
(
138 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=videos' % video_id
,
139 display_id
, note
='Downloading premier API JSON')
140 if not (sources
.get('source') or sources
.get('source_dash')):
141 self
.raise_login_required('This video is only available for registered users with the appropriate subscription')
143 formats
, subs
= [], {}
144 if sources
.get('source'):
145 hls_formats
, hls_subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
146 sources
['source'], display_id
, 'mp4', 'm3u8_native')
147 formats
.extend(hls_formats
)
148 subs
.update(hls_subs
)
149 if sources
.get('source_dash'): # TODO: Find video example with source_dash
150 dash_formats
, dash_subs
= self
._extract
_mpd
_formats
_and
_subtitles
(
151 sources
['source_dash'], display_id
, 'dash')
152 formats
.extend(dash_formats
)
153 subs
.update(dash_subs
)
155 hls_url
= data
['clips'][0]['hls_url']
156 formats
, subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
157 hls_url
, display_id
, 'mp4', 'm3u8_native')
159 self
._sort
_formats
(formats
)
161 get_first
= lambda x
: try_get(data
, lambda y
: y
[x
+ 's'][0], dict) or {}
162 channel
= get_first('channel')
163 user
= get_first('user')
164 username
= user
.get('username')
165 get_count
= lambda x
: int_or_none(video
.get('total_' + x
))
169 'display_id': display_id
,
171 'description': strip_or_none(video
.get('description')),
172 'thumbnail': video
.get('image_url_medium'),
173 'duration': int_or_none(video
.get('duration')),
174 'like_count': get_count('likes'),
177 'uploader': user
.get('name'),
178 'timestamp': parse_iso8601(video
.get('created_at')),
179 'uploader_id': username
,
180 'uploader_url': format_field(username
, None, 'https://www.vidio.com/@%s'),
181 'channel': channel
.get('name'),
182 'channel_id': str_or_none(channel
.get('id')),
183 'view_count': get_count('view_count'),
184 'dislike_count': get_count('dislikes'),
185 'comment_count': get_count('comments'),
186 'tags': video
.get('tag_list'),
190 class VidioPremierIE(VidioBaseIE
):
191 _VALID_URL
= r
'https?://(?:www\.)?vidio\.com/premier/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
193 'url': 'https://www.vidio.com/premier/2885/badai-pasti-berlalu',
194 'playlist_mincount': 14,
196 # Series with both free and premier-exclusive videos
197 'url': 'https://www.vidio.com/premier/2567/sosmed',
198 'only_matching': True,
201 def _playlist_entries(self
, playlist_url
, display_id
):
204 playlist_json
= self
._call
_api
(playlist_url
, display_id
, 'Downloading API JSON page %s' % index
)
205 for video_json
in playlist_json
.get('data', []):
206 link
= video_json
['links']['watchpage']
207 yield self
.url_result(link
, 'Vidio', video_json
['id'])
208 playlist_url
= try_get(playlist_json
, lambda x
: x
['links']['next'])
211 def _real_extract(self
, url
):
212 url
, idata
= unsmuggle_url(url
, {})
213 playlist_id
, display_id
= self
._match
_valid
_url
(url
).groups()
215 playlist_url
= idata
.get('url')
216 if playlist_url
: # Smuggled data contains an API URL. Download only that playlist
217 playlist_id
= idata
['id']
218 return self
.playlist_result(
219 self
._playlist
_entries
(playlist_url
, playlist_id
),
220 playlist_id
=playlist_id
, playlist_title
=idata
.get('title'))
222 playlist_data
= self
._call
_api
('https://api.vidio.com/content_profiles/%s/playlists' % playlist_id
, display_id
)
224 return self
.playlist_from_matches(
225 playlist_data
.get('data', []), playlist_id
=playlist_id
, ie
=self
.ie_key(),
226 getter
=lambda data
: smuggle_url(url
, {
227 'url': data
['relationships']['videos']['links']['related'],
229 'title': try_get(data
, lambda x
: x
['attributes']['name'])
233 class VidioLiveIE(VidioBaseIE
):
234 _VALID_URL
= r
'https?://(?:www\.)?vidio\.com/live/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
236 'url': 'https://www.vidio.com/live/204-sctv',
241 'uploader_id': 'sctv',
242 'thumbnail': r
're:^https?://.*\.jpg$',
245 # Premier-exclusive livestream
246 'url': 'https://www.vidio.com/live/6362-tvn',
247 'only_matching': True,
249 # DRM premier-exclusive livestream
250 'url': 'https://www.vidio.com/live/6299-bein-1',
251 'only_matching': True,
254 def _real_extract(self
, url
):
255 video_id
, display_id
= self
._match
_valid
_url
(url
).groups()
256 stream_data
= self
._call
_api
(
257 'https://www.vidio.com/api/livestreamings/%s/detail' % video_id
, display_id
)
258 stream_meta
= stream_data
['livestreamings'][0]
259 user
= stream_data
.get('users', [{}])[0]
261 title
= stream_meta
.get('title')
262 username
= user
.get('username')
265 if stream_meta
.get('is_drm'):
266 if not self
.get_param('allow_unplayable_formats'):
267 self
.report_drm(video_id
)
268 if stream_meta
.get('is_premium'):
269 sources
= self
._download
_json
(
270 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=livestreamings' % video_id
,
271 display_id
, note
='Downloading premier API JSON')
272 if not (sources
.get('source') or sources
.get('source_dash')):
273 self
.raise_login_required('This video is only available for registered users with the appropriate subscription')
275 if str_or_none(sources
.get('source')):
276 token_json
= self
._download
_json
(
277 'https://www.vidio.com/live/%s/tokens' % video_id
,
278 display_id
, note
='Downloading HLS token JSON', data
=b
'')
279 formats
.extend(self
._extract
_m
3u8_formats
(
280 sources
['source'] + '?' + token_json
.get('token', ''), display_id
, 'mp4', 'm3u8_native'))
281 if str_or_none(sources
.get('source_dash')):
284 if stream_meta
.get('stream_token_url'):
285 token_json
= self
._download
_json
(
286 'https://www.vidio.com/live/%s/tokens' % video_id
,
287 display_id
, note
='Downloading HLS token JSON', data
=b
'')
288 formats
.extend(self
._extract
_m
3u8_formats
(
289 stream_meta
['stream_token_url'] + '?' + token_json
.get('token', ''),
290 display_id
, 'mp4', 'm3u8_native'))
291 if stream_meta
.get('stream_dash_url'):
293 if stream_meta
.get('stream_url'):
294 formats
.extend(self
._extract
_m
3u8_formats
(
295 stream_meta
['stream_url'], display_id
, 'mp4', 'm3u8_native'))
296 self
._sort
_formats
(formats
)
300 'display_id': display_id
,
303 'description': strip_or_none(stream_meta
.get('description')),
304 'thumbnail': stream_meta
.get('image'),
305 'like_count': int_or_none(stream_meta
.get('like')),
306 'dislike_count': int_or_none(stream_meta
.get('dislike')),
308 'uploader': user
.get('name'),
309 'timestamp': parse_iso8601(stream_meta
.get('start_time')),
310 'uploader_id': username
,
311 'uploader_url': format_field(username
, None, 'https://www.vidio.com/@%s'),