]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/vidio.py
[extractor] Better error message for DRM (#729)
[yt-dlp.git] / yt_dlp / extractor / vidio.py
CommitLineData
7def3571
T
1# coding: utf-8
2from __future__ import unicode_literals
3
7def3571 4
0fc832e1 5from .common import InfoExtractor
2181983a 6from ..utils import (
11cc4571 7 clean_html,
10bb7e51
M
8 ExtractorError,
9 get_element_by_class,
2181983a 10 int_or_none,
11 parse_iso8601,
f2cd7060 12 smuggle_url,
2181983a 13 str_or_none,
14 strip_or_none,
15 try_get,
f2cd7060 16 unsmuggle_url,
10bb7e51 17 urlencode_postdata,
2181983a 18)
7def3571
T
19
20
f2cd7060 21class VidioBaseIE(InfoExtractor):
10bb7e51
M
22 _LOGIN_URL = 'https://www.vidio.com/users/login'
23 _NETRC_MACHINE = 'vidio'
24
25 def _login(self):
26 username, password = self._get_login_info()
27 if username is None:
28 return
29
30 def is_logged_in():
31 res = self._download_json(
32 'https://www.vidio.com/interactions.json', None, 'Checking if logged in', fatal=False) or {}
33 return bool(res.get('current_user'))
34
35 if is_logged_in():
36 return
37
38 login_page = self._download_webpage(
39 self._LOGIN_URL, None, 'Downloading log in page')
40
41 login_form = self._form_hidden_inputs("login-form", login_page)
42 login_form.update({
43 'user[login]': username,
44 'user[password]': password,
45 })
46 login_post, login_post_urlh = self._download_webpage_handle(
47 self._LOGIN_URL, None, 'Logging in', data=urlencode_postdata(login_form), expected_status=[302, 401])
48
49 if login_post_urlh.status == 401:
11cc4571 50 if get_element_by_class('onboarding-content-register-popup__title', login_post):
10bb7e51 51 raise ExtractorError(
11cc4571
M
52 'Unable to log in: The provided email has not registered yet.', expected=True)
53
54 reason = get_element_by_class('onboarding-form__general-error', login_post) or get_element_by_class('onboarding-modal__title', login_post)
55 if 'Akun terhubung ke' in reason:
56 raise ExtractorError(
57 'Unable to log in: Your account is linked to a social media account. '
58 'Use --cookies to provide account credentials instead', expected=True)
59 elif reason:
60 subreason = get_element_by_class('onboarding-modal__description-text', login_post) or ''
61 raise ExtractorError(
62 'Unable to log in: %s. %s' % (reason, clean_html(subreason)), expected=True)
10bb7e51 63 raise ExtractorError('Unable to log in')
7def3571 64
2181983a 65 def _real_initialize(self):
66 self._api_key = self._download_json(
67 'https://www.vidio.com/auth', None, data=b'')['api_key']
10bb7e51 68 self._login()
0fc832e1 69
f2cd7060
M
70 def _call_api(self, url, video_id, note=None):
71 return self._download_json(url, video_id, note=note, headers={
72 'Content-Type': 'application/vnd.api+json',
73 'X-API-KEY': self._api_key,
74 })
75
76
77class VidioIE(VidioBaseIE):
78 _VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
79 _TESTS = [{
80 'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
81 'md5': 'cd2801394afc164e9775db6a140b91fe',
82 'info_dict': {
83 'id': '165683',
84 'display_id': 'dj_ambred-booyah-live-2015',
85 'ext': 'mp4',
86 'title': 'DJ_AMBRED - Booyah (Live 2015)',
87 'description': 'md5:27dc15f819b6a78a626490881adbadf8',
88 'thumbnail': r're:^https?://.*\.jpg$',
89 'duration': 149,
90 'like_count': int,
91 'uploader': 'TWELVE Pic',
92 'timestamp': 1444902800,
93 'upload_date': '20151015',
94 'uploader_id': 'twelvepictures',
95 'channel': 'Cover Music Video',
96 'channel_id': '280236',
97 'view_count': int,
98 'dislike_count': int,
99 'comment_count': int,
100 'tags': 'count:4',
101 },
102 }, {
103 'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
104 'only_matching': True,
105 }, {
106 # Premier-exclusive video
107 'url': 'https://www.vidio.com/watch/1550718-stand-by-me-doraemon',
108 'only_matching': True
109 }]
110
2181983a 111 def _real_extract(self, url):
5ad28e7f 112 match = self._match_valid_url(url).groupdict()
f2cd7060
M
113 video_id, display_id = match.get('id'), match.get('display_id')
114 data = self._call_api('https://api.vidio.com/videos/' + video_id, display_id)
2181983a 115 video = data['videos'][0]
116 title = video['title'].strip()
46c43ffc 117 is_premium = video.get('is_premium')
f2cd7060 118
46c43ffc
M
119 if is_premium:
120 sources = self._download_json(
121 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=videos' % video_id,
122 display_id, note='Downloading premier API JSON')
123 if not (sources.get('source') or sources.get('source_dash')):
f2cd7060 124 self.raise_login_required('This video is only available for registered users with the appropriate subscription')
46c43ffc
M
125
126 formats, subs = [], {}
127 if sources.get('source'):
128 hls_formats, hls_subs = self._extract_m3u8_formats_and_subtitles(
129 sources['source'], display_id, 'mp4', 'm3u8_native')
130 formats.extend(hls_formats)
131 subs.update(hls_subs)
132 if sources.get('source_dash'): # TODO: Find video example with source_dash
133 dash_formats, dash_subs = self._extract_mpd_formats_and_subtitles(
134 sources['source_dash'], display_id, 'dash')
135 formats.extend(dash_formats)
136 subs.update(dash_subs)
137 else:
138 hls_url = data['clips'][0]['hls_url']
139 formats, subs = self._extract_m3u8_formats_and_subtitles(
140 hls_url, display_id, 'mp4', 'm3u8_native')
0fc832e1 141
07ad0cf3 142 self._sort_formats(formats)
0fc832e1 143
2181983a 144 get_first = lambda x: try_get(data, lambda y: y[x + 's'][0], dict) or {}
145 channel = get_first('channel')
146 user = get_first('user')
147 username = user.get('username')
148 get_count = lambda x: int_or_none(video.get('total_' + x))
7def3571
T
149
150 return {
151 'id': video_id,
0fc832e1
S
152 'display_id': display_id,
153 'title': title,
2181983a 154 'description': strip_or_none(video.get('description')),
155 'thumbnail': video.get('image_url_medium'),
156 'duration': int_or_none(video.get('duration')),
157 'like_count': get_count('likes'),
0fc832e1 158 'formats': formats,
46c43ffc 159 'subtitles': subs,
2181983a 160 'uploader': user.get('name'),
161 'timestamp': parse_iso8601(video.get('created_at')),
162 'uploader_id': username,
163 'uploader_url': 'https://www.vidio.com/@' + username if username else None,
164 'channel': channel.get('name'),
165 'channel_id': str_or_none(channel.get('id')),
166 'view_count': get_count('view_count'),
167 'dislike_count': get_count('dislikes'),
168 'comment_count': get_count('comments'),
169 'tags': video.get('tag_list'),
7def3571 170 }
f2cd7060
M
171
172
173class VidioPremierIE(VidioBaseIE):
174 _VALID_URL = r'https?://(?:www\.)?vidio\.com/premier/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
175 _TESTS = [{
176 'url': 'https://www.vidio.com/premier/2885/badai-pasti-berlalu',
177 'playlist_mincount': 14,
178 }, {
179 # Series with both free and premier-exclusive videos
180 'url': 'https://www.vidio.com/premier/2567/sosmed',
181 'only_matching': True,
182 }]
183
184 def _playlist_entries(self, playlist_url, display_id):
185 index = 1
186 while playlist_url:
187 playlist_json = self._call_api(playlist_url, display_id, 'Downloading API JSON page %s' % index)
188 for video_json in playlist_json.get('data', []):
189 link = video_json['links']['watchpage']
190 yield self.url_result(link, 'Vidio', video_json['id'])
191 playlist_url = try_get(playlist_json, lambda x: x['links']['next'])
192 index += 1
193
194 def _real_extract(self, url):
195 url, idata = unsmuggle_url(url, {})
5ad28e7f 196 playlist_id, display_id = self._match_valid_url(url).groups()
f2cd7060
M
197
198 playlist_url = idata.get('url')
199 if playlist_url: # Smuggled data contains an API URL. Download only that playlist
200 playlist_id = idata['id']
201 return self.playlist_result(
202 self._playlist_entries(playlist_url, playlist_id),
203 playlist_id=playlist_id, playlist_title=idata.get('title'))
204
205 playlist_data = self._call_api('https://api.vidio.com/content_profiles/%s/playlists' % playlist_id, display_id)
206
207 return self.playlist_from_matches(
208 playlist_data.get('data', []), playlist_id=playlist_id, ie=self.ie_key(),
209 getter=lambda data: smuggle_url(url, {
210 'url': data['relationships']['videos']['links']['related'],
211 'id': data['id'],
212 'title': try_get(data, lambda x: x['attributes']['name'])
213 }))
214
215
216class VidioLiveIE(VidioBaseIE):
217 _VALID_URL = r'https?://(?:www\.)?vidio\.com/live/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
218 _TESTS = [{
219 'url': 'https://www.vidio.com/live/204-sctv',
220 'info_dict': {
221 'id': '204',
222 'title': 'SCTV',
223 'uploader': 'SCTV',
224 'uploader_id': 'sctv',
225 'thumbnail': r're:^https?://.*\.jpg$',
226 },
227 }, {
228 # Premier-exclusive livestream
229 'url': 'https://www.vidio.com/live/6362-tvn',
230 'only_matching': True,
231 }, {
232 # DRM premier-exclusive livestream
233 'url': 'https://www.vidio.com/live/6299-bein-1',
234 'only_matching': True,
235 }]
236
237 def _real_extract(self, url):
5ad28e7f 238 video_id, display_id = self._match_valid_url(url).groups()
f2cd7060
M
239 stream_data = self._call_api(
240 'https://www.vidio.com/api/livestreamings/%s/detail' % video_id, display_id)
241 stream_meta = stream_data['livestreamings'][0]
242 user = stream_data.get('users', [{}])[0]
243
244 title = stream_meta.get('title')
245 username = user.get('username')
246
247 formats = []
248 if stream_meta.get('is_drm'):
249 if not self.get_param('allow_unplayable_formats'):
88acdbc2 250 self.report_drm(video_id)
f2cd7060
M
251 if stream_meta.get('is_premium'):
252 sources = self._download_json(
253 'https://www.vidio.com/interactions_stream.json?video_id=%s&type=livestreamings' % video_id,
254 display_id, note='Downloading premier API JSON')
255 if not (sources.get('source') or sources.get('source_dash')):
256 self.raise_login_required('This video is only available for registered users with the appropriate subscription')
257
258 if str_or_none(sources.get('source')):
259 token_json = self._download_json(
260 'https://www.vidio.com/live/%s/tokens' % video_id,
261 display_id, note='Downloading HLS token JSON', data=b'')
262 formats.extend(self._extract_m3u8_formats(
263 sources['source'] + '?' + token_json.get('token', ''), display_id, 'mp4', 'm3u8_native'))
264 if str_or_none(sources.get('source_dash')):
265 pass
266 else:
267 if stream_meta.get('stream_token_url'):
268 token_json = self._download_json(
269 'https://www.vidio.com/live/%s/tokens' % video_id,
270 display_id, note='Downloading HLS token JSON', data=b'')
271 formats.extend(self._extract_m3u8_formats(
272 stream_meta['stream_token_url'] + '?' + token_json.get('token', ''),
273 display_id, 'mp4', 'm3u8_native'))
274 if stream_meta.get('stream_dash_url'):
275 pass
276 if stream_meta.get('stream_url'):
277 formats.extend(self._extract_m3u8_formats(
278 stream_meta['stream_url'], display_id, 'mp4', 'm3u8_native'))
279 self._sort_formats(formats)
280
281 return {
282 'id': video_id,
283 'display_id': display_id,
284 'title': title,
285 'is_live': True,
286 'description': strip_or_none(stream_meta.get('description')),
287 'thumbnail': stream_meta.get('image'),
288 'like_count': int_or_none(stream_meta.get('like')),
289 'dislike_count': int_or_none(stream_meta.get('dislike')),
290 'formats': formats,
291 'uploader': user.get('name'),
292 'timestamp': parse_iso8601(stream_meta.get('start_time')),
293 'uploader_id': username,
294 'uploader_url': 'https://www.vidio.com/@' + username if username else None,
295 }