]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/syfy.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
8 class SyfyIE(InfoExtractor
):
9 _VALID_URL
= r
'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
12 'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
16 'title': 'George Lucas has Advice for his Daughter',
17 'description': 'Listen to what insights George Lucas give his daughter Amanda.',
19 'add_ie': ['ThePlatform'],
21 'url': 'http://www.syfy.com/wilwheaton',
22 'md5': '94dfa54ee3ccb63295b276da08c415f6',
26 'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
27 'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
29 'add_ie': ['ThePlatform'],
30 'skip': 'Blocked outside the US',
33 def _real_extract(self
, url
):
34 mobj
= re
.match(self
._VALID
_URL
, url
)
35 video_name
= mobj
.group('video_name')
37 generic_webpage
= self
._download
_webpage
(url
, video_name
)
38 video_id
= self
._search
_regex
(
39 r
'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
40 generic_webpage
, 'video ID')
41 url
= 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
42 video_name
, video_name
, video_id
)
44 video_id
= mobj
.group('id')
45 webpage
= self
._download
_webpage
(url
, video_id
)
46 return self
.url_result(self
._og
_search
_video
_url
(webpage
))