youtube_dl/extractor/cbsinteractive.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .cbs import CBSIE
   7 from ..utils import int_or_none
   8
   9
  10 class CBSInteractiveIE(CBSIE):
  11     _VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P<id>[^/?]+)'
  12     _TESTS = [{
  13         'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
  14         'info_dict': {
  15             'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00',
  16             'display_id': 'hands-on-with-microsofts-windows-8-1-update',
  17             'ext': 'mp4',
  18             'title': 'Hands-on with Microsoft Windows 8.1 Update',
  19             'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
  20             'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
  21             'uploader': 'Sarah Mitroff',
  22             'duration': 70,
  23             'timestamp': 1396479627,
  24             'upload_date': '20140402',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         },
  30     }, {
  31         'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
  32         'md5': 'f11d27b2fa18597fbf92444d2a9ed386',
  33         'info_dict': {
  34             'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK',
  35             'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187',
  36             'ext': 'mp4',
  37             'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
  38             'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f',
  39             'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
  40             'uploader': 'Ashley Esqueda',
  41             'duration': 1482,
  42             'timestamp': 1433289889,
  43             'upload_date': '20150603',
  44         },
  45     }, {
  46         'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
  47         'info_dict': {
  48             'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt',
  49             'display_id': 'video-keeping-android-smartphones-and-tablets-secure',
  50             'ext': 'mp4',
  51             'title': 'Video: Keeping Android smartphones and tablets secure',
  52             '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.',
  53             'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
  54             'uploader': 'Adrian Kingsley-Hughes',
  55             'duration': 731,
  56             'timestamp': 1449129925,
  57             'upload_date': '20151203',
  58         },
  59         'params': {
  60             # m3u8 download
  61             'skip_download': True,
  62         },
  63     }, {
  64         'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/',
  65         'only_matching': True,
  66     }]
  67
  68     MPX_ACCOUNTS = {
  69         'cnet': 2198311517,
  70         'zdnet': 2387448114,
  71     }
  72
  73     def _real_extract(self, url):
  74         site, display_id = re.match(self._VALID_URL, url).groups()
  75         webpage = self._download_webpage(url, display_id)
  76
  77         data_json = self._html_search_regex(
  78             r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'",
  79             webpage, 'data json')
  80         data = self._parse_json(data_json, display_id)
  81         vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0]
  82
  83         video_id = vdata['mpxRefId']
  84
  85         title = vdata['title']
  86         author = vdata.get('author')
  87         if author:
  88             uploader = '%s %s' % (author['firstName'], author['lastName'])
  89             uploader_id = author.get('id')
  90         else:
  91             uploader = None
  92             uploader_id = None
  93
  94         info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site])
  95         info.update({
  96             'id': video_id,
  97             'display_id': display_id,
  98             'title': title,
  99             'duration': int_or_none(vdata.get('duration')),
 100             'uploader': uploader,
 101             'uploader_id': uploader_id,
 102         })
 103         return info