]>
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/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
72 'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
73 'md5': 'cd2801394afc164e9775db6a140b91fe',
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',
95 'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
96 'only_matching': True,
98 # Premier-exclusive video
99 'url': 'https://www.vidio.com/watch/1550718-stand-by-me-doraemon',
100 'only_matching': True
103 def _real_extract(self
, url
):
104 match
= self
._match
_valid
_url
(url
).groupdict()
105 video_id
, display_id
= match
.get('id'), match
.get('display_id')
106 data
= self
._call
_api
('https://api.vidio.com/videos/' + video_id
, display_id
)
107 video
= data
['videos'][0]
108 title
= video
['title'].strip()
109 is_premium
= video
.get('is_premium')
112 sources
= self
._download
_json
(
113 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=videos' % video_id
,
114 display_id
, note
='Downloading premier API JSON')
115 if not (sources
.get('source') or sources
.get('source_dash')):
116 self
.raise_login_required('This video is only available for registered users with the appropriate subscription')
118 formats
, subs
= [], {}
119 if sources
.get('source'):
120 hls_formats
, hls_subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
121 sources
['source'], display_id
, 'mp4', 'm3u8_native')
122 formats
.extend(hls_formats
)
123 subs
.update(hls_subs
)
124 if sources
.get('source_dash'): # TODO: Find video example with source_dash
125 dash_formats
, dash_subs
= self
._extract
_mpd
_formats
_and
_subtitles
(
126 sources
['source_dash'], display_id
, 'dash')
127 formats
.extend(dash_formats
)
128 subs
.update(dash_subs
)
130 hls_url
= data
['clips'][0]['hls_url']
131 formats
, subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
132 hls_url
, display_id
, 'mp4', 'm3u8_native')
134 self
._sort
_formats
(formats
)
136 get_first
= lambda x
: try_get(data
, lambda y
: y
[x
+ 's'][0], dict) or {}
137 channel
= get_first('channel')
138 user
= get_first('user')
139 username
= user
.get('username')
140 get_count
= lambda x
: int_or_none(video
.get('total_' + x
))
144 'display_id': display_id
,
146 'description': strip_or_none(video
.get('description')),
147 'thumbnail': video
.get('image_url_medium'),
148 'duration': int_or_none(video
.get('duration')),
149 'like_count': get_count('likes'),
152 'uploader': user
.get('name'),
153 'timestamp': parse_iso8601(video
.get('created_at')),
154 'uploader_id': username
,
155 'uploader_url': format_field(username
, None, 'https://www.vidio.com/@%s'),
156 'channel': channel
.get('name'),
157 'channel_id': str_or_none(channel
.get('id')),
158 'view_count': get_count('view_count'),
159 'dislike_count': get_count('dislikes'),
160 'comment_count': get_count('comments'),
161 'tags': video
.get('tag_list'),
165 class VidioPremierIE(VidioBaseIE
):
166 _VALID_URL
= r
'https?://(?:www\.)?vidio\.com/premier/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
168 'url': 'https://www.vidio.com/premier/2885/badai-pasti-berlalu',
169 'playlist_mincount': 14,
171 # Series with both free and premier-exclusive videos
172 'url': 'https://www.vidio.com/premier/2567/sosmed',
173 'only_matching': True,
176 def _playlist_entries(self
, playlist_url
, display_id
):
179 playlist_json
= self
._call
_api
(playlist_url
, display_id
, 'Downloading API JSON page %s' % index
)
180 for video_json
in playlist_json
.get('data', []):
181 link
= video_json
['links']['watchpage']
182 yield self
.url_result(link
, 'Vidio', video_json
['id'])
183 playlist_url
= try_get(playlist_json
, lambda x
: x
['links']['next'])
186 def _real_extract(self
, url
):
187 url
, idata
= unsmuggle_url(url
, {})
188 playlist_id
, display_id
= self
._match
_valid
_url
(url
).groups()
190 playlist_url
= idata
.get('url')
191 if playlist_url
: # Smuggled data contains an API URL. Download only that playlist
192 playlist_id
= idata
['id']
193 return self
.playlist_result(
194 self
._playlist
_entries
(playlist_url
, playlist_id
),
195 playlist_id
=playlist_id
, playlist_title
=idata
.get('title'))
197 playlist_data
= self
._call
_api
('https://api.vidio.com/content_profiles/%s/playlists' % playlist_id
, display_id
)
199 return self
.playlist_from_matches(
200 playlist_data
.get('data', []), playlist_id
=playlist_id
, ie
=self
.ie_key(),
201 getter
=lambda data
: smuggle_url(url
, {
202 'url': data
['relationships']['videos']['links']['related'],
204 'title': try_get(data
, lambda x
: x
['attributes']['name'])
208 class VidioLiveIE(VidioBaseIE
):
209 _VALID_URL
= r
'https?://(?:www\.)?vidio\.com/live/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
211 'url': 'https://www.vidio.com/live/204-sctv',
216 'uploader_id': 'sctv',
217 'thumbnail': r
're:^https?://.*\.jpg$',
220 # Premier-exclusive livestream
221 'url': 'https://www.vidio.com/live/6362-tvn',
222 'only_matching': True,
224 # DRM premier-exclusive livestream
225 'url': 'https://www.vidio.com/live/6299-bein-1',
226 'only_matching': True,
229 def _real_extract(self
, url
):
230 video_id
, display_id
= self
._match
_valid
_url
(url
).groups()
231 stream_data
= self
._call
_api
(
232 'https://www.vidio.com/api/livestreamings/%s/detail' % video_id
, display_id
)
233 stream_meta
= stream_data
['livestreamings'][0]
234 user
= stream_data
.get('users', [{}])[0]
236 title
= stream_meta
.get('title')
237 username
= user
.get('username')
240 if stream_meta
.get('is_drm'):
241 if not self
.get_param('allow_unplayable_formats'):
242 self
.report_drm(video_id
)
243 if stream_meta
.get('is_premium'):
244 sources
= self
._download
_json
(
245 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=livestreamings' % video_id
,
246 display_id
, note
='Downloading premier API JSON')
247 if not (sources
.get('source') or sources
.get('source_dash')):
248 self
.raise_login_required('This video is only available for registered users with the appropriate subscription')
250 if str_or_none(sources
.get('source')):
251 token_json
= self
._download
_json
(
252 'https://www.vidio.com/live/%s/tokens' % video_id
,
253 display_id
, note
='Downloading HLS token JSON', data
=b
'')
254 formats
.extend(self
._extract
_m
3u8_formats
(
255 sources
['source'] + '?' + token_json
.get('token', ''), display_id
, 'mp4', 'm3u8_native'))
256 if str_or_none(sources
.get('source_dash')):
259 if stream_meta
.get('stream_token_url'):
260 token_json
= self
._download
_json
(
261 'https://www.vidio.com/live/%s/tokens' % video_id
,
262 display_id
, note
='Downloading HLS token JSON', data
=b
'')
263 formats
.extend(self
._extract
_m
3u8_formats
(
264 stream_meta
['stream_token_url'] + '?' + token_json
.get('token', ''),
265 display_id
, 'mp4', 'm3u8_native'))
266 if stream_meta
.get('stream_dash_url'):
268 if stream_meta
.get('stream_url'):
269 formats
.extend(self
._extract
_m
3u8_formats
(
270 stream_meta
['stream_url'], display_id
, 'mp4', 'm3u8_native'))
271 self
._sort
_formats
(formats
)
275 'display_id': display_id
,
278 'description': strip_or_none(stream_meta
.get('description')),
279 'thumbnail': stream_meta
.get('image'),
280 'like_count': int_or_none(stream_meta
.get('like')),
281 'dislike_count': int_or_none(stream_meta
.get('dislike')),
283 'uploader': user
.get('name'),
284 'timestamp': parse_iso8601(stream_meta
.get('start_time')),
285 'uploader_id': username
,
286 'uploader_url': format_field(username
, None, 'https://www.vidio.com/@%s'),