2 from __future__ import unicode_literals
6 from .common import InfoExtractor
12 class CNETIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
15 'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
17 'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
19 'title': 'Hands-on with Microsoft Windows 8.1 Update',
20 'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
21 'thumbnail': 're:^http://.*/flmswindows8.jpg$',
22 'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
23 'uploader': 'Sarah Mitroff',
26 'skip_download': 'requires rtmpdump',
29 'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
31 'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
33 'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
34 'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
35 'uploader': 'Ashley Esqueda',
36 'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
39 'skip_download': True, # requires rtmpdump
43 def _real_extract(self, url):
44 display_id = self._match_id(url)
45 webpage = self._download_webpage(url, display_id)
47 data_json = self._html_search_regex(
48 r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
50 data = json.loads(data_json)
53 vdata = data['videos'][0]
55 raise ExtractorError('Cannot find video data')
57 mpx_account = data['config']['players']['default']['mpx_account']
58 vid = vdata['files'].get('rtmp', vdata['files']['hds'])
59 tp_link = 'http://link.theplatform.com/s/%s/%s' % (mpx_account, vid)
61 video_id = vdata['id']
62 title = vdata.get('headline')
64 title = vdata.get('title')
66 raise ExtractorError('Cannot find title!')
67 thumbnail = vdata.get('image', {}).get('path')
68 author = vdata.get('author')
70 uploader = '%s %s' % (author['firstName'], author['lastName'])
71 uploader_id = author.get('id')
77 '_type': 'url_transparent',
80 'display_id': display_id,
83 'uploader_id': uploader_id,
84 'thumbnail': thumbnail,