_ 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 CBSBaseIE(ThePlatformIE):
  14     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
  15         closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
  16         return {
  17             'en': [{
  18                 'ext': 'ttml',
  19                 'url': closed_caption_e.attrib['value'],
  20             }]
  21         } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
  22
  23
  24 class CBSIE(CBSBaseIE):
  25     _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)'
  26
  27     _TESTS = [{
  28         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
  29         'info_dict': {
  30             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
  31             'display_id': 'connect-chat-feat-garth-brooks',
  32             'ext': 'mp4',
  33             'title': 'Connect Chat feat. Garth Brooks',
  34             '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!',
  35             'duration': 1495,
  36         },
  37         'params': {
  38             # rtmp download
  39             'skip_download': True,
  40         },
  41         '_skip': 'Blocked outside the US',
  42     }, {
  43         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
  44         'info_dict': {
  45             'id': 'WWF_5KqY3PK1',
  46             'display_id': 'st-vincent',
  47             'ext': 'flv',
  48             'title': 'Live on Letterman - St. Vincent',
  49             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
  50             'duration': 3221,
  51         },
  52         'params': {
  53             # rtmp download
  54             'skip_download': True,
  55         },
  56         '_skip': 'Blocked outside the US',
  57     }, {
  58         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
  59         'only_matching': True,
  60     }, {
  61         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
  62         'only_matching': True,
  63     }]
  64     TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?manifest=m3u&mbr=true'
  65
  66     def _real_extract(self, url):
  67         display_id = self._match_id(url)
  68         webpage = self._download_webpage(url, display_id)
  69         content_id = self._search_regex(
  70             [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
  71             webpage, 'content id')
  72         items_data = self._download_xml(
  73             'http://can.cbs.com/thunder/player/videoPlayerService.php',
  74             content_id, query={'partner': 'cbs', 'contentId': content_id})
  75         video_data = xpath_element(items_data, './/item')
  76         title = xpath_text(video_data, 'videoTitle', 'title', True)
  77
  78         subtitles = {}
  79         formats = []
  80         for item in items_data.findall('.//item'):
  81             pid = xpath_text(item, 'pid')
  82             if not pid:
  83                 continue
  84             try:
  85                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
  86                     self.TP_RELEASE_URL_TEMPLATE % pid, content_id, 'Downloading %s SMIL data' % pid)
  87             except ExtractorError:
  88                 continue
  89             formats.extend(tp_formats)
  90             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  91         self._sort_formats(formats)
  92
  93         info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
  94         info.update({
  95             'id': content_id,
  96             'display_id': display_id,
  97             'title': title,
  98             'series': xpath_text(video_data, 'seriesTitle'),
  99             'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
 100             'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
 101             'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
 102             'thumbnail': xpath_text(video_data, 'previewImageURL'),
 103             'formats': formats,
 104             'subtitles': subtitles,
 105         })
 106         return info