2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
15 class VesselIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)'
17 _API_URL_TEMPLATE
= 'https://www.vessel.com/api/view/items/%s'
18 _LOGIN_URL
= 'https://www.vessel.com/api/account/login'
19 _NETRC_MACHINE
= 'vessel'
21 'url': 'https://www.vessel.com/videos/HDN7G5UMs',
22 'md5': '455cdf8beb71c6dd797fd2f3818d05c4',
26 'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?',
27 'thumbnail': r
're:^https?://.*\.jpg$',
28 'upload_date': '20150317',
29 'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?',
33 'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346',
34 'only_matching': True,
36 'url': 'https://www.vessel.com/videos/F01_dsLj1',
37 'only_matching': True,
39 'url': 'https://www.vessel.com/videos/RRX-sir-J',
40 'only_matching': True,
44 def _extract_urls(webpage
):
45 return [url
for _
, url
in re
.findall(
46 r
'<iframe[^>]+src=(["\'])((?
:https?
:)?
//(?
:www\
.)?vessel\
.com
/embed
/[0-9a
-zA
-Z
-_
]+.*?
)\
1',
50 def make_json_request(url, data):
51 payload = json.dumps(data).encode('utf
-8')
52 req = sanitized_Request(url, payload)
53 req.add_header('Content
-Type
', 'application
/json
; charset
=utf
-8')
57 def find_assets(data, asset_type, asset_id=None):
58 for asset in data.get('assets
', []):
59 if not asset.get('type') == asset_type:
61 elif asset_id is not None and not asset.get('id') == asset_id:
66 def _check_access_rights(self, data):
67 access_info = data.get('__view
', {})
68 if not access_info.get('allow_access
', True):
69 err_code = access_info.get('error_code
') or ''
70 if err_code == 'ITEM_PAID_ONLY
':
72 'This video requires subscription
.', expected=True)
75 'Access to this content
is restricted
. (%s said
: %s)' % (self.IE_NAME, err_code), expected=True)
78 username, password = self._get_login_info()
88 login_request = VesselIE.make_json_request(self._LOGIN_URL, data)
89 self._download_webpage(login_request, None, False, 'Wrong login info
')
91 def _real_initialize(self):
94 def _real_extract(self, url):
95 video_id = self._match_id(url)
97 webpage = self._download_webpage(url, video_id)
98 data = self._parse_json(self._search_regex(
99 r'App\
.bootstrapData\
((.*?
)\
);', webpage, 'data
'), video_id)
100 asset_id = data['model
']['data
']['id']
102 req = VesselIE.make_json_request(
103 self._API_URL_TEMPLATE % asset_id, {'client
': 'web
'})
104 data = self._download_json(req, video_id)
105 video_asset_id = data.get('main_video_asset
')
107 self._check_access_rights(data)
111 VesselIE.find_assets(data, 'video
', asset_id=video_asset_id))
112 except StopIteration:
113 raise ExtractorError('No video assets found
')
116 for f in video_asset.get('sources
', []):
117 location = f.get('location
')
121 if name == 'hls
-index
':
122 formats.extend(self._extract_m3u8_formats(
123 location, video_id, ext='mp4
',
124 entry_protocol='m3u8_native
', m3u8_id='m3u8
', fatal=False))
125 elif name == 'dash
-index
':
126 formats.extend(self._extract_mpd_formats(
127 location, video_id, mpd_id='dash
', fatal=False))
131 'tbr
': f.get('bitrate
'),
132 'height
': f.get('height
'),
133 'width
': f.get('width
'),
136 self._sort_formats(formats)
139 for im_asset in VesselIE.find_assets(data, 'image
'):
141 'url
': im_asset['location
'],
142 'width
': im_asset.get('width
', 0),
143 'height
': im_asset.get('height
', 0),
148 'title
': data['title
'],
150 'thumbnails
': thumbnails,
151 'description
': data.get('short_description
'),
152 'duration
': data.get('duration
'),
153 'comment_count
': data.get('comment_count
'),
154 'like_count
': data.get('like_count
'),
155 'view_count
': data.get('view_count
'),
156 'timestamp
': parse_iso8601(data.get('released_at
')),