1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-28 02:42:52 +08:00
youtube-dl/youtube_dl/extractor/inc.py

42 lines
1.5 KiB
Python
Raw Normal View History

2017-01-09 02:28:16 +08:00
from __future__ import unicode_literals
from .common import InfoExtractor
2017-01-10 00:08:59 +08:00
from .kaltura import KalturaIE
2017-01-09 02:28:16 +08:00
class IncIE(InfoExtractor):
2017-01-10 00:08:59 +08:00
_VALID_URL = r'https?://(?:www\.)?inc\.com/(?:[^/]+/)+(?P<id>[^.]+).html'
2017-01-09 02:28:16 +08:00
_TESTS = [{
'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
'md5': '7416739c9c16438c09fa35619d6ba5cb',
'info_dict': {
'id': '1_wqig47aq',
'ext': 'mov',
'title': 'Bill Gates Says These 5 Books Will Make You Smarter',
'description': 'md5:bea7ff6cce100886fc1995acb743237e',
'timestamp': 1474414430,
'upload_date': '20160920',
'uploader_id': 'video@inc.com',
},
2017-01-10 00:08:59 +08:00
'params': {
'skip_download': True,
},
2017-01-09 02:28:16 +08:00
}, {
'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
partner_id = self._search_regex(
2017-01-10 00:08:59 +08:00
r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage, 'partner id')
2017-01-09 02:28:16 +08:00
kaltura_id = self._parse_json(self._search_regex(
2017-01-10 00:08:59 +08:00
r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
2017-01-09 02:28:16 +08:00
display_id)['vid_kaltura_id']
2017-01-10 00:08:59 +08:00
return self.url_result(
'kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())