yt_dlp/extractor/cbsinteractive.py

   1 from .cbs import CBSIE
   2 from ..utils import int_or_none
   3
   4
   5 class CBSInteractiveIE(CBSIE):  # XXX: Do not subclass from concrete IE
   6     _VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P<id>[^/?]+)'
   7     _TESTS = [{
   8         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
   9         'info_dict': {
  10             'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00',
  11             'display_id': 'hands-on-with-microsofts-windows-8-1-update',
  12             'ext': 'mp4',
  13             'title': 'Hands-on with Microsoft Windows 8.1 Update',
  14             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
  15             'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
  16             'uploader': 'Sarah Mitroff',
  17             'duration': 70,
  18             'timestamp': 1396479627,
  19             'upload_date': '20140402',
  20         },
  21         'params': {
  22             # m3u8 download
  23             'skip_download': True,
  24         },
  25     }, {
  26         'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
  27         'md5': 'f11d27b2fa18597fbf92444d2a9ed386',
  28         'info_dict': {
  29             'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK',
  30             'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187',
  31             'ext': 'mp4',
  32             'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
  33             'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f',
  34             'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
  35             'uploader': 'Ashley Esqueda',
  36             'duration': 1482,
  37             'timestamp': 1433289889,
  38             'upload_date': '20150603',
  39         },
  40     }, {
  41         'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
  42         'info_dict': {
  43             'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt',
  44             'display_id': 'video-keeping-android-smartphones-and-tablets-secure',
  45             'ext': 'mp4',
  46             'title': 'Video: Keeping Android smartphones and tablets secure',
  47             'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
  48             'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
  49             'uploader': 'Adrian Kingsley-Hughes',
  50             'duration': 731,
  51             'timestamp': 1449129925,
  52             'upload_date': '20151203',
  53         },
  54         'params': {
  55             # m3u8 download
  56             'skip_download': True,
  57         },
  58     }, {
  59         'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/',
  60         'only_matching': True,
  61     }]
  62
  63     MPX_ACCOUNTS = {
  64         'cnet': 2198311517,
  65         'zdnet': 2387448114,
  66     }
  67
  68     def _real_extract(self, url):
  69         site, display_id = self._match_valid_url(url).groups()
  70         webpage = self._download_webpage(url, display_id)
  71
  72         data_json = self._html_search_regex(
  73             r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'",
  74             webpage, 'data json')
  75         data = self._parse_json(data_json, display_id)
  76         vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0]
  77
  78         video_id = vdata['mpxRefId']
  79
  80         title = vdata['title']
  81         author = vdata.get('author')
  82         if author:
  83             uploader = '%s %s' % (author['firstName'], author['lastName'])
  84             uploader_id = author.get('id')
  85         else:
  86             uploader = None
  87             uploader_id = None
  88
  89         info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site])
  90         info.update({
  91             'id': video_id,
  92             'display_id': display_id,
  93             'title': title,
  94             'duration': int_or_none(vdata.get('duration')),
  95             'uploader': uploader,
  96             'uploader_id': uploader_id,
  97         })
  98         return info