2 from __future__
import unicode_literals
12 from .common
import InfoExtractor
13 from ..compat
import (
15 compat_urllib_parse_urlencode
,
25 class VRVBaseIE(InfoExtractor
):
32 def _call_api(self
, path
, video_id
, note
, data
=None):
33 # https://tools.ietf.org/html/rfc5849#section-3
34 base_url
= self
._API
_DOMAIN
+ '/core/' + path
36 ('oauth_consumer_key', self
._API
_PARAMS
['oAuthKey']),
37 ('oauth_nonce', ''.join([random
.choice(string
.ascii_letters
) for _
in range(32)])),
38 ('oauth_signature_method', 'HMAC-SHA1'),
39 ('oauth_timestamp', int(time
.time())),
42 query
.append(('oauth_token', self
._TOKEN
))
43 encoded_query
= compat_urllib_parse_urlencode(query
)
44 headers
= self
.geo_verification_headers()
46 data
= json
.dumps(data
).encode()
47 headers
['Content-Type'] = 'application/json'
48 base_string
= '&'.join([
49 'POST' if data
else 'GET',
50 compat_urllib_parse
.quote(base_url
, ''),
51 compat_urllib_parse
.quote(encoded_query
, '')])
52 oauth_signature
= base64
.b64encode(hmac
.new(
53 (self
._API
_PARAMS
['oAuthSecret'] + '&' + self
._TOKEN
_SECRET
).encode('ascii'),
54 base_string
.encode(), hashlib
.sha1
).digest()).decode()
55 encoded_query
+= '&oauth_signature=' + compat_urllib_parse
.quote(oauth_signature
, '')
57 return self
._download
_json
(
58 '?'.join([base_url
, encoded_query
]), video_id
,
59 note
='Downloading %s JSON metadata' % note
, headers
=headers
, data
=data
)
60 except ExtractorError
as e
:
61 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 401:
62 raise ExtractorError(json
.loads(e
.cause
.read().decode())['message'], expected
=True)
65 def _call_cms(self
, path
, video_id
, note
):
66 if not self
._CMS
_SIGNING
:
67 self
._CMS
_SIGNING
= self
._call
_api
('index', video_id
, 'CMS Signing')['cms_signing']
68 return self
._download
_json
(
69 self
._API
_DOMAIN
+ path
, video_id
, query
=self
._CMS
_SIGNING
,
70 note
='Downloading %s JSON metadata' % note
, headers
=self
.geo_verification_headers())
72 def _get_cms_resource(self
, resource_key
, video_id
):
73 return self
._call
_api
(
74 'cms_resource', video_id
, 'resource path', data
={
75 'resource_key': resource_key
,
76 })['__links__']['cms_resource']['href']
78 def _real_initialize(self
):
79 webpage
= self
._download
_webpage
(
80 'https://vrv.co/', None, headers
=self
.geo_verification_headers())
81 self
._API
_PARAMS
= self
._parse
_json
(self
._search
_regex
(
83 r
'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)',
84 r
'window\.__APP_CONFIG__\s*=\s*({.+})'
85 ], webpage
, 'app config'), None)['cxApiParams']
86 self
._API
_DOMAIN
= self
._API
_PARAMS
.get('apiDomain', 'https://api.vrv.co')
89 class VRVIE(VRVBaseIE
):
91 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
93 'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
97 'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
98 'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
99 'uploader_id': 'seeso',
103 'skip_download': True,
106 _NETRC_MACHINE
= 'vrv'
108 def _real_initialize(self
):
109 super(VRVIE
, self
)._real
_initialize
()
111 email
, password
= self
._get
_login
_info
()
115 token_credentials
= self
._call
_api
(
116 'authenticate/by:credentials', None, 'Token Credentials', data
={
118 'password': password
,
120 self
._TOKEN
= token_credentials
['oauth_token']
121 self
._TOKEN
_SECRET
= token_credentials
['oauth_token_secret']
123 def _extract_vrv_formats(self
, url
, video_id
, stream_format
, audio_lang
, hardsub_lang
):
124 if not url
or stream_format
not in ('hls', 'dash'):
126 assert audio_lang
or hardsub_lang
129 stream_id_list
.append('audio-%s' % audio_lang
)
131 stream_id_list
.append('hardsub-%s' % hardsub_lang
)
132 stream_id
= '-'.join(stream_id_list
)
133 format_id
= '%s-%s' % (stream_format
, stream_id
)
134 if stream_format
== 'hls':
135 adaptive_formats
= self
._extract
_m
3u8_formats
(
136 url
, video_id
, 'mp4', m3u8_id
=format_id
,
137 note
='Downloading %s m3u8 information' % stream_id
,
139 elif stream_format
== 'dash':
140 adaptive_formats
= self
._extract
_mpd
_formats
(
141 url
, video_id
, mpd_id
=format_id
,
142 note
='Downloading %s MPD information' % stream_id
,
145 for f
in adaptive_formats
:
146 if f
.get('acodec') != 'none':
147 f
['language'] = audio_lang
148 return adaptive_formats
150 def _real_extract(self
, url
):
151 video_id
= self
._match
_id
(url
)
153 object_data
= self
._call
_cms
(self
._get
_cms
_resource
(
154 'cms:/objects/' + video_id
, video_id
), video_id
, 'object')['items'][0]
155 resource_path
= object_data
['__links__']['resource']['href']
156 video_data
= self
._call
_cms
(resource_path
, video_id
, 'video')
157 title
= video_data
['title']
159 streams_path
= video_data
['__links__'].get('streams', {}).get('href')
161 self
.raise_login_required()
162 streams_json
= self
._call
_cms
(streams_path
, video_id
, 'streams')
164 audio_locale
= streams_json
.get('audio_locale')
166 for stream_type
, streams
in streams_json
.get('streams', {}).items():
167 if stream_type
in ('adaptive_hls', 'adaptive_dash'):
168 for stream
in streams
.values():
169 formats
.extend(self
._extract
_vrv
_formats
(
170 stream
.get('url'), video_id
, stream_type
.split('_')[1],
171 audio_locale
, stream
.get('hardsub_locale')))
172 self
._sort
_formats
(formats
)
175 for subtitle
in streams_json
.get('subtitles', {}).values():
176 subtitle_url
= subtitle
.get('url')
179 subtitles
.setdefault(subtitle
.get('locale', 'en-US'), []).append({
181 'ext': subtitle
.get('format', 'ass'),
185 for thumbnail
in video_data
.get('images', {}).get('thumbnails', []):
186 thumbnail_url
= thumbnail
.get('source')
187 if not thumbnail_url
:
190 'url': thumbnail_url
,
191 'width': int_or_none(thumbnail
.get('width')),
192 'height': int_or_none(thumbnail
.get('height')),
199 'subtitles': subtitles
,
200 'thumbnails': thumbnails
,
201 'description': video_data
.get('description'),
202 'duration': float_or_none(video_data
.get('duration_ms'), 1000),
203 'uploader_id': video_data
.get('channel_id'),
204 'series': video_data
.get('series_title'),
205 'season': video_data
.get('season_title'),
206 'season_number': int_or_none(video_data
.get('season_number')),
207 'season_id': video_data
.get('season_id'),
209 'episode_number': int_or_none(video_data
.get('episode_number')),
210 'episode_id': video_data
.get('production_episode_id'),
214 class VRVSeriesIE(VRVBaseIE
):
215 IE_NAME
= 'vrv:series'
216 _VALID_URL
= r
'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
218 'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
222 'playlist_mincount': 11,
225 def _real_extract(self
, url
):
226 series_id
= self
._match
_id
(url
)
228 seasons_path
= self
._get
_cms
_resource
(
229 'cms:/seasons?series_id=' + series_id
, series_id
)
230 seasons_data
= self
._call
_cms
(seasons_path
, series_id
, 'seasons')
233 for season
in seasons_data
.get('items', []):
234 episodes_path
= season
['__links__']['season/episodes']['href']
235 episodes
= self
._call
_cms
(episodes_path
, series_id
, 'episodes')
236 for episode
in episodes
.get('items', []):
237 episode_id
= episode
['id']
238 entries
.append(self
.url_result(
239 'https://vrv.co/watch/' + episode_id
,
240 'VRV', episode_id
, episode
.get('title')))
242 return self
.playlist_result(entries
, series_id
)