_ Git - youtube-dl/blob - youtube_dl/extractor/cbs.py

   1 from __future__ import unicode_literals
   2
   3 from .theplatform import ThePlatformIE
   4 from ..utils import (
   5     xpath_text,
   6     xpath_element,
   7     int_or_none,
   8     ExtractorError,
   9     find_xpath_attr,
  10 )
  11
  12
  13 class CBSIE(ThePlatformIE):
  14     _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
  15
  16     _TESTS = [{
  17         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
  18         'info_dict': {
  19             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
  20             'display_id': 'connect-chat-feat-garth-brooks',
  21             'ext': 'mp4',
  22             'title': 'Connect Chat feat. Garth Brooks',
  23             '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!',
  24             'duration': 1495,
  25         },
  26         'params': {
  27             # rtmp download
  28             'skip_download': True,
  29         },
  30         '_skip': 'Blocked outside the US',
  31     }, {
  32         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
  33         'info_dict': {
  34             'id': 'WWF_5KqY3PK1',
  35             'display_id': 'st-vincent',
  36             'ext': 'flv',
  37             'title': 'Live on Letterman - St. Vincent',
  38             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
  39             'duration': 3221,
  40         },
  41         'params': {
  42             # rtmp download
  43             'skip_download': True,
  44         },
  45         '_skip': 'Blocked outside the US',
  46     }, {
  47         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
  48         'only_matching': True,
  49     }, {
  50         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
  51         'only_matching': True,
  52     }]
  53     TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?manifest=m3u&mbr=true'
  54
  55     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
  56         closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
  57         return {
  58             'en': [{
  59                 'ext': 'ttml',
  60                 'url': closed_caption_e.attrib['value'],
  61             }]
  62         } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
  63
  64     def _real_extract(self, url):
  65         display_id = self._match_id(url)
  66         webpage = self._download_webpage(url, display_id)
  67         content_id = self._search_regex(
  68             [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
  69             webpage, 'content id')
  70         items_data = self._download_xml(
  71             'http://can.cbs.com/thunder/player/videoPlayerService.php',
  72             content_id, query={'partner': 'cbs', 'contentId': content_id})
  73         video_data = xpath_element(items_data, './/item')
  74         title = xpath_text(video_data, 'videoTitle', 'title', True)
  75
  76         subtitles = {}
  77         formats = []
  78         for item in items_data.findall('.//item'):
  79             pid = xpath_text(item, 'pid')
  80             if not pid:
  81                 continue
  82             try:
  83                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
  84                     self.TP_RELEASE_URL_TEMPLATE % pid, content_id, 'Downloading %s SMIL data' % pid)
  85             except ExtractorError:
  86                 continue
  87             formats.extend(tp_formats)
  88             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  89         self._sort_formats(formats)
  90
  91         info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
  92         info.update({
  93             'id': content_id,
  94             'display_id': display_id,
  95             'title': title,
  96             'series': xpath_text(video_data, 'seriesTitle'),
  97             'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
  98             'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
  99             'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
 100             'thumbnail': xpath_text(video_data, 'previewImageURL'),
 101             'formats': formats,
 102             'subtitles': subtitles,
 103         })
 104         return info