10 from .common
import InfoExtractor
11 from ..compat
import compat_HTTPError
, compat_urllib_parse_urlencode
21 class VRVBaseIE(InfoExtractor
):
28 def _call_api(self
, path
, video_id
, note
, data
=None):
29 # https://tools.ietf.org/html/rfc5849#section-3
30 base_url
= self
._API
_DOMAIN
+ '/core/' + path
32 ('oauth_consumer_key', self
._API
_PARAMS
['oAuthKey']),
33 ('oauth_nonce', ''.join([random
.choice(string
.ascii_letters
) for _
in range(32)])),
34 ('oauth_signature_method', 'HMAC-SHA1'),
35 ('oauth_timestamp', int(time
.time())),
38 query
.append(('oauth_token', self
._TOKEN
))
39 encoded_query
= compat_urllib_parse_urlencode(query
)
40 headers
= self
.geo_verification_headers()
42 data
= json
.dumps(data
).encode()
43 headers
['Content-Type'] = 'application/json'
44 base_string
= '&'.join([
45 'POST' if data
else 'GET',
46 urllib
.parse
.quote(base_url
, ''),
47 urllib
.parse
.quote(encoded_query
, '')])
48 oauth_signature
= base64
.b64encode(hmac
.new(
49 (self
._API
_PARAMS
['oAuthSecret'] + '&' + self
._TOKEN
_SECRET
).encode('ascii'),
50 base_string
.encode(), hashlib
.sha1
).digest()).decode()
51 encoded_query
+= '&oauth_signature=' + urllib
.parse
.quote(oauth_signature
, '')
53 return self
._download
_json
(
54 '?'.join([base_url
, encoded_query
]), video_id
,
55 note
='Downloading %s JSON metadata' % note
, headers
=headers
, data
=data
)
56 except ExtractorError
as e
:
57 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
58 raise ExtractorError(json
.loads(e
.cause
.read().decode())['message'], expected
=True)
61 def _call_cms(self
, path
, video_id
, note
):
62 if not self
._CMS
_SIGNING
:
63 index
= self
._call
_api
('index', video_id
, 'CMS Signing')
64 self
._CMS
_SIGNING
= index
.get('cms_signing') or {}
65 if not self
._CMS
_SIGNING
:
66 for signing_policy
in index
.get('signing_policies', []):
67 signing_path
= signing_policy
.get('path')
68 if signing_path
and signing_path
.startswith('/cms/'):
69 name
, value
= signing_policy
.get('name'), signing_policy
.get('value')
71 self
._CMS
_SIGNING
[name
] = value
72 return self
._download
_json
(
73 self
._API
_DOMAIN
+ path
, video_id
, query
=self
._CMS
_SIGNING
,
74 note
='Downloading %s JSON metadata' % note
, headers
=self
.geo_verification_headers())
76 def _get_cms_resource(self
, resource_key
, video_id
):
77 return self
._call
_api
(
78 'cms_resource', video_id
, 'resource path', data
={
79 'resource_key': resource_key
,
80 })['__links__']['cms_resource']['href']
82 def _extract_vrv_formats(self
, url
, video_id
, stream_format
, audio_lang
, hardsub_lang
):
83 if not url
or stream_format
not in ('hls', 'dash', 'adaptive_hls'):
85 format_id
= join_nonempty(
87 audio_lang
and 'audio-%s' % audio_lang
,
88 hardsub_lang
and 'hardsub-%s' % hardsub_lang
)
89 if 'hls' in stream_format
:
90 adaptive_formats
= self
._extract
_m
3u8_formats
(
91 url
, video_id
, 'mp4', m3u8_id
=format_id
,
92 note
='Downloading %s information' % format_id
,
94 elif stream_format
== 'dash':
95 adaptive_formats
= self
._extract
_mpd
_formats
(
96 url
, video_id
, mpd_id
=format_id
,
97 note
='Downloading %s information' % format_id
,
100 for f
in adaptive_formats
:
101 if f
.get('acodec') != 'none':
102 f
['language'] = audio_lang
103 return adaptive_formats
105 def _set_api_params(self
):
106 webpage
= self
._download
_webpage
(
107 'https://vrv.co/', None, headers
=self
.geo_verification_headers())
108 self
._API
_PARAMS
= self
._parse
_json
(self
._search
_regex
(
110 r
'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
111 r
'window\.__APP_CONFIG__\s*=\s*({.+})'
112 ], webpage
, 'app config'), None)['cxApiParams']
113 self
._API
_DOMAIN
= self
._API
_PARAMS
.get('apiDomain', 'https://api.vrv.co')
116 class VRVIE(VRVBaseIE
):
118 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
120 'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
124 'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
125 'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
126 'uploader_id': 'seeso',
130 'skip_download': True,
134 'url': 'https://vrv.co/watch/G6NQXZ1J6/Lily-CAT',
137 'title': 'Lily C.A.T',
138 'description': 'md5:988b031e7809a6aeb60968be4af7db07',
142 _NETRC_MACHINE
= 'vrv'
144 def _perform_login(self
, username
, password
):
145 token_credentials
= self
._call
_api
(
146 'authenticate/by:credentials', None, 'Token Credentials', data
={
148 'password': password
,
150 self
._TOKEN
= token_credentials
['oauth_token']
151 self
._TOKEN
_SECRET
= token_credentials
['oauth_token_secret']
153 def _initialize_pre_login(self
):
154 return self
._set
_api
_params
()
156 def _real_extract(self
, url
):
157 video_id
= self
._match
_id
(url
)
159 object_data
= self
._call
_cms
(self
._get
_cms
_resource
(
160 'cms:/objects/' + video_id
, video_id
), video_id
, 'object')['items'][0]
161 resource_path
= object_data
['__links__']['resource']['href']
162 video_data
= self
._call
_cms
(resource_path
, video_id
, 'video')
163 title
= video_data
['title']
164 description
= video_data
.get('description')
166 if video_data
.get('__class__') == 'movie_listing':
167 items
= self
._call
_cms
(
168 video_data
['__links__']['movie_listing/movies']['href'],
169 video_id
, 'movie listing').get('items') or []
173 item_id
= item
.get('id')
176 entries
.append(self
.url_result(
177 'https://vrv.co/watch/' + item_id
,
178 self
.ie_key(), item_id
, item
.get('title')))
179 return self
.playlist_result(entries
, video_id
, title
, description
)
180 video_data
= items
[0]
182 streams_path
= video_data
['__links__'].get('streams', {}).get('href')
184 self
.raise_login_required()
185 streams_json
= self
._call
_cms
(streams_path
, video_id
, 'streams')
187 audio_locale
= streams_json
.get('audio_locale')
189 for stream_type
, streams
in streams_json
.get('streams', {}).items():
190 if stream_type
in ('adaptive_hls', 'adaptive_dash'):
191 for stream
in streams
.values():
192 formats
.extend(self
._extract
_vrv
_formats
(
193 stream
.get('url'), video_id
, stream_type
.split('_')[1],
194 audio_locale
, stream
.get('hardsub_locale')))
195 self
._sort
_formats
(formats
)
198 for k
in ('captions', 'subtitles'):
199 for subtitle
in streams_json
.get(k
, {}).values():
200 subtitle_url
= subtitle
.get('url')
203 subtitles
.setdefault(subtitle
.get('locale', 'en-US'), []).append({
205 'ext': subtitle
.get('format', 'ass'),
209 for thumbnail
in traverse_obj(video_data
, ('images', 'thumbnail', ..., ...)) or []:
210 thumbnail_url
= thumbnail
.get('source')
211 if not thumbnail_url
:
214 'url': thumbnail_url
,
215 'width': int_or_none(thumbnail
.get('width')),
216 'height': int_or_none(thumbnail
.get('height')),
223 'subtitles': subtitles
,
224 'thumbnails': thumbnails
,
225 'description': description
,
226 'duration': float_or_none(video_data
.get('duration_ms'), 1000),
227 'uploader_id': video_data
.get('channel_id'),
228 'series': video_data
.get('series_title'),
229 'season': video_data
.get('season_title'),
230 'season_number': int_or_none(video_data
.get('season_number')),
231 'season_id': video_data
.get('season_id'),
233 'episode_number': int_or_none(video_data
.get('episode_number')),
234 'episode_id': video_data
.get('production_episode_id'),
238 class VRVSeriesIE(VRVBaseIE
):
239 IE_NAME
= 'vrv:series'
240 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
242 'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
246 'playlist_mincount': 11,
249 def _initialize_pre_login(self
):
250 return self
._set
_api
_params
()
252 def _real_extract(self
, url
):
253 series_id
= self
._match
_id
(url
)
255 seasons_path
= self
._get
_cms
_resource
(
256 'cms:/seasons?series_id=' + series_id
, series_id
)
257 seasons_data
= self
._call
_cms
(seasons_path
, series_id
, 'seasons')
260 for season
in seasons_data
.get('items', []):
261 episodes_path
= season
['__links__']['season/episodes']['href']
262 episodes
= self
._call
_cms
(episodes_path
, series_id
, 'episodes')
263 for episode
in episodes
.get('items', []):
264 episode_id
= episode
['id']
265 entries
.append(self
.url_result(
266 'https://vrv.co/watch/' + episode_id
,
267 'VRV', episode_id
, episode
.get('title')))
269 return self
.playlist_result(entries
, series_id
)