1 from __future__ import unicode_literals
3 from .common import InfoExtractor
4 from .kaltura import KalturaIE
7 class IncIE(InfoExtractor):
8 _VALID_URL = r'https?://(?:www\.)?inc\.com/(?:[^/]+/)+(?P<id>[^.]+).html'
10 'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
11 'md5': '7416739c9c16438c09fa35619d6ba5cb',
15 'title': 'Bill Gates Says These 5 Books Will Make You Smarter',
16 'description': 'md5:bea7ff6cce100886fc1995acb743237e',
17 'timestamp': 1474414430,
18 'upload_date': '20160920',
19 'uploader_id': 'video@inc.com',
22 'skip_download': True,
25 # div with id=kaltura_player_1_kqs38cgm
26 'url': 'https://www.inc.com/oscar-raymundo/richard-branson-young-entrepeneurs.html',
30 'title': 'Branson: "In the end, you have to say, Screw it. Just do it."',
31 'description': 'md5:21b832d034f9af5191ca5959da5e9cb6',
32 'timestamp': 1364403232,
33 'upload_date': '20130327',
34 'uploader_id': 'incdigital@inc.com',
37 'skip_download': True,
40 'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
41 'only_matching': True,
44 def _real_extract(self, url):
45 display_id = self._match_id(url)
46 webpage = self._download_webpage(url, display_id)
48 partner_id = self._search_regex(
49 r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage,
50 'partner id', default='1034971')
52 kaltura_id = self._search_regex(
53 r'id=(["\'])kaltura_player_(?P<id>.+?)\1', webpage, 'kaltura id',
54 default=None, group='id') or self._parse_json(self._search_regex(
55 r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
56 display_id)['vid_kaltura_id']
58 return self.url_result(
59 'kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())