1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-21 11:55:54 +01:00
yt-dlp/youtube_dl/extractor/cbs.py

59 lines
2.3 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-12-16 03:53:43 +01:00
from .common import InfoExtractor
class CBSIE(InfoExtractor):
2015-06-09 17:39:45 +02:00
_VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
2013-12-16 03:53:43 +01:00
_TESTS = [{
'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
'info_dict': {
'id': '4JUVEwq3wUT7',
2015-06-09 17:39:45 +02:00
'display_id': 'connect-chat-feat-garth-brooks',
'ext': 'flv',
'title': 'Connect Chat feat. Garth Brooks',
'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
'duration': 1495,
2013-12-16 03:53:43 +01:00
},
'params': {
2013-12-16 03:53:43 +01:00
# rtmp download
'skip_download': True,
2013-12-16 03:53:43 +01:00
},
'_skip': 'Blocked outside the US',
}, {
'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
'info_dict': {
2014-08-27 13:41:24 +02:00
'id': 'WWF_5KqY3PK1',
2015-06-09 17:39:45 +02:00
'display_id': 'st-vincent',
'ext': 'flv',
'title': 'Live on Letterman - St. Vincent',
'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
'duration': 3221,
},
'params': {
# rtmp download
'skip_download': True,
},
'_skip': 'Blocked outside the US',
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
'only_matching': True,
}, {
2015-06-09 17:39:45 +02:00
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
}]
2013-12-16 03:53:43 +01:00
def _real_extract(self, url):
2015-06-09 17:39:45 +02:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2013-12-16 03:53:43 +01:00
real_id = self._search_regex(
[r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
webpage, 'real video ID')
2015-06-09 17:39:45 +02:00
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': 'theplatform:%s' % real_id,
'display_id': display_id,
}