2 from __future__
import unicode_literals
12 from .common
import InfoExtractor
13 from ..compat
import (
15 compat_urllib_parse_urlencode
,
27 class VRVBaseIE(InfoExtractor
):
34 def _call_api(self
, path
, video_id
, note
, data
=None):
35 # https://tools.ietf.org/html/rfc5849#section-3
36 base_url
= self
._API
_DOMAIN
+ '/core/' + path
38 ('oauth_consumer_key', self
._API
_PARAMS
['oAuthKey']),
39 ('oauth_nonce', ''.join([random
.choice(string
.ascii_letters
) for _
in range(32)])),
40 ('oauth_signature_method', 'HMAC-SHA1'),
41 ('oauth_timestamp', int(time
.time())),
44 query
.append(('oauth_token', self
._TOKEN
))
45 encoded_query
= compat_urllib_parse_urlencode(query
)
46 headers
= self
.geo_verification_headers()
48 data
= json
.dumps(data
).encode()
49 headers
['Content-Type'] = 'application/json'
50 base_string
= '&'.join([
51 'POST' if data
else 'GET',
52 compat_urllib_parse
.quote(base_url
, ''),
53 compat_urllib_parse
.quote(encoded_query
, '')])
54 oauth_signature
= base64
.b64encode(hmac
.new(
55 (self
._API
_PARAMS
['oAuthSecret'] + '&' + self
._TOKEN
_SECRET
).encode('ascii'),
56 base_string
.encode(), hashlib
.sha1
).digest()).decode()
57 encoded_query
+= '&oauth_signature=' + compat_urllib_parse
.quote(oauth_signature
, '')
59 return self
._download
_json
(
60 '?'.join([base_url
, encoded_query
]), video_id
,
61 note
='Downloading %s JSON metadata' % note
, headers
=headers
, data
=data
)
62 except ExtractorError
as e
:
63 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
64 raise ExtractorError(json
.loads(e
.cause
.read().decode())['message'], expected
=True)
67 def _call_cms(self
, path
, video_id
, note
):
68 if not self
._CMS
_SIGNING
:
69 index
= self
._call
_api
('index', video_id
, 'CMS Signing')
70 self
._CMS
_SIGNING
= index
.get('cms_signing') or {}
71 if not self
._CMS
_SIGNING
:
72 for signing_policy
in index
.get('signing_policies', []):
73 signing_path
= signing_policy
.get('path')
74 if signing_path
and signing_path
.startswith('/cms/'):
75 name
, value
= signing_policy
.get('name'), signing_policy
.get('value')
77 self
._CMS
_SIGNING
[name
] = value
78 return self
._download
_json
(
79 self
._API
_DOMAIN
+ path
, video_id
, query
=self
._CMS
_SIGNING
,
80 note
='Downloading %s JSON metadata' % note
, headers
=self
.geo_verification_headers())
82 def _get_cms_resource(self
, resource_key
, video_id
):
83 return self
._call
_api
(
84 'cms_resource', video_id
, 'resource path', data
={
85 'resource_key': resource_key
,
86 })['__links__']['cms_resource']['href']
88 def _real_initialize(self
):
89 webpage
= self
._download
_webpage
(
90 'https://vrv.co/', None, headers
=self
.geo_verification_headers())
91 self
._API
_PARAMS
= self
._parse
_json
(self
._search
_regex
(
93 r
'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
94 r
'window\.__APP_CONFIG__\s*=\s*({.+})'
95 ], webpage
, 'app config'), None)['cxApiParams']
96 self
._API
_DOMAIN
= self
._API
_PARAMS
.get('apiDomain', 'https://api.vrv.co')
99 class VRVIE(VRVBaseIE
):
101 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
103 'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
107 'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
108 'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
109 'uploader_id': 'seeso',
113 'skip_download': True,
117 'url': 'https://vrv.co/watch/G6NQXZ1J6/Lily-CAT',
120 'title': 'Lily C.A.T',
121 'description': 'md5:988b031e7809a6aeb60968be4af7db07',
125 _NETRC_MACHINE
= 'vrv'
127 def _real_initialize(self
):
128 super(VRVIE
, self
)._real
_initialize
()
130 email
, password
= self
._get
_login
_info
()
134 token_credentials
= self
._call
_api
(
135 'authenticate/by:credentials', None, 'Token Credentials', data
={
137 'password': password
,
139 self
._TOKEN
= token_credentials
['oauth_token']
140 self
._TOKEN
_SECRET
= token_credentials
['oauth_token_secret']
142 def _extract_vrv_formats(self
, url
, video_id
, stream_format
, audio_lang
, hardsub_lang
):
143 if not url
or stream_format
not in ('hls', 'dash', 'adaptive_hls'):
145 format_id
= join_nonempty(
147 audio_lang
and 'audio-%s' % audio_lang
,
148 hardsub_lang
and 'hardsub-%s' % hardsub_lang
)
149 if 'hls' in stream_format
:
150 adaptive_formats
= self
._extract
_m
3u8_formats
(
151 url
, video_id
, 'mp4', m3u8_id
=format_id
,
152 note
='Downloading %s information' % format_id
,
154 elif stream_format
== 'dash':
155 adaptive_formats
= self
._extract
_mpd
_formats
(
156 url
, video_id
, mpd_id
=format_id
,
157 note
='Downloading %s information' % format_id
,
160 for f
in adaptive_formats
:
161 if f
.get('acodec') != 'none':
162 f
['language'] = audio_lang
163 return adaptive_formats
165 def _real_extract(self
, url
):
166 video_id
= self
._match
_id
(url
)
168 object_data
= self
._call
_cms
(self
._get
_cms
_resource
(
169 'cms:/objects/' + video_id
, video_id
), video_id
, 'object')['items'][0]
170 resource_path
= object_data
['__links__']['resource']['href']
171 video_data
= self
._call
_cms
(resource_path
, video_id
, 'video')
172 title
= video_data
['title']
173 description
= video_data
.get('description')
175 if video_data
.get('__class__') == 'movie_listing':
176 items
= self
._call
_cms
(
177 video_data
['__links__']['movie_listing/movies']['href'],
178 video_id
, 'movie listing').get('items') or []
182 item_id
= item
.get('id')
185 entries
.append(self
.url_result(
186 'https://vrv.co/watch/' + item_id
,
187 self
.ie_key(), item_id
, item
.get('title')))
188 return self
.playlist_result(entries
, video_id
, title
, description
)
189 video_data
= items
[0]
191 streams_path
= video_data
['__links__'].get('streams', {}).get('href')
193 self
.raise_login_required()
194 streams_json
= self
._call
_cms
(streams_path
, video_id
, 'streams')
196 audio_locale
= streams_json
.get('audio_locale')
198 for stream_type
, streams
in streams_json
.get('streams', {}).items():
199 if stream_type
in ('adaptive_hls', 'adaptive_dash'):
200 for stream
in streams
.values():
201 formats
.extend(self
._extract
_vrv
_formats
(
202 stream
.get('url'), video_id
, stream_type
.split('_')[1],
203 audio_locale
, stream
.get('hardsub_locale')))
204 self
._sort
_formats
(formats
)
207 for k
in ('captions', 'subtitles'):
208 for subtitle
in streams_json
.get(k
, {}).values():
209 subtitle_url
= subtitle
.get('url')
212 subtitles
.setdefault(subtitle
.get('locale', 'en-US'), []).append({
214 'ext': subtitle
.get('format', 'ass'),
218 for thumbnail
in traverse_obj(video_data
, ('images', 'thumbnail', ..., ...)) or []:
219 thumbnail_url
= thumbnail
.get('source')
220 if not thumbnail_url
:
223 'url': thumbnail_url
,
224 'width': int_or_none(thumbnail
.get('width')),
225 'height': int_or_none(thumbnail
.get('height')),
232 'subtitles': subtitles
,
233 'thumbnails': thumbnails
,
234 'description': description
,
235 'duration': float_or_none(video_data
.get('duration_ms'), 1000),
236 'uploader_id': video_data
.get('channel_id'),
237 'series': video_data
.get('series_title'),
238 'season': video_data
.get('season_title'),
239 'season_number': int_or_none(video_data
.get('season_number')),
240 'season_id': video_data
.get('season_id'),
242 'episode_number': int_or_none(video_data
.get('episode_number')),
243 'episode_id': video_data
.get('production_episode_id'),
247 class VRVSeriesIE(VRVBaseIE
):
248 IE_NAME
= 'vrv:series'
249 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
251 'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
255 'playlist_mincount': 11,
258 def _real_extract(self
, url
):
259 series_id
= self
._match
_id
(url
)
261 seasons_path
= self
._get
_cms
_resource
(
262 'cms:/seasons?series_id=' + series_id
, series_id
)
263 seasons_data
= self
._call
_cms
(seasons_path
, series_id
, 'seasons')
266 for season
in seasons_data
.get('items', []):
267 episodes_path
= season
['__links__']['season/episodes']['href']
268 episodes
= self
._call
_cms
(episodes_path
, series_id
, 'episodes')
269 for episode
in episodes
.get('items', []):
270 episode_id
= episode
['id']
271 entries
.append(self
.url_result(
272 'https://vrv.co/watch/' + episode_id
,
273 'VRV', episode_id
, episode
.get('title')))
275 return self
.playlist_result(entries
, series_id
)