1 from .common
import InfoExtractor
2 from .jwplatform
import JWPlatformIE
5 class BusinessInsiderIE(InfoExtractor
):
6 _VALID_URL
= r
'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
8 'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
9 'md5': 'ffed3e1e12a6f950aa2f7d83851b497a',
13 'title': 'Bananas give you more radiation exposure than living next to a nuclear power plant',
14 'description': 'md5:0175a3baf200dd8fa658f94cade841b3',
15 'upload_date': '20160611',
16 'timestamp': 1465675620,
19 'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
20 'md5': '43f438dbc6da0b89f5ac42f68529d84a',
24 'title': 'Deze dingen zorgen ervoor dat je minder snel een date scoort',
25 'description': 'md5:2af8975825d38a4fed24717bbe51db49',
26 'upload_date': '20170705',
27 'timestamp': 1499270528,
30 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
31 'only_matching': True,
34 def _real_extract(self
, url
):
35 video_id
= self
._match
_id
(url
)
36 webpage
= self
._download
_webpage
(url
, video_id
)
37 jwplatform_id
= self
._search
_regex
(
38 (r
'data-media-id=["\']([a
-zA
-Z0
-9]{8}
)',
39 r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
40 r'id["\']?\s
*:\s
*["\']?([a-zA-Z0-9]{8})',
41 r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'),
42 webpage, 'jwplatform id')
43 return self.url_result(
44 f'jwplatform:{jwplatform_id}', ie=JWPlatformIE.ie_key(),