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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .theplatform import ThePlatformIE
   6 from ..utils import (
   7     xpath_text,
   8     xpath_element,
   9     int_or_none,
  10     find_xpath_attr,
  11 )
  12
  13
  14 class CBSBaseIE(ThePlatformIE):
  15     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
  16         closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL')
  17         return {
  18             'en': [{
  19                 'ext': 'ttml',
  20                 'url': closed_caption_e.attrib['value'],
  21             }]
  22         } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
  23
  24
  25 class CBSIE(CBSBaseIE):
  26     _VALID_URL = r'(?:cbs:(?P<content_id>\w+)|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<display_id>[^/]+))'
  27
  28     _TESTS = [{
  29         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
  30         'info_dict': {
  31             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
  32             'display_id': 'connect-chat-feat-garth-brooks',
  33             'ext': 'mp4',
  34             'title': 'Connect Chat feat. Garth Brooks',
  35             '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!',
  36             'duration': 1495,
  37             'timestamp': 1385585425,
  38             'upload_date': '20131127',
  39             'uploader': 'CBSI-NEW',
  40         },
  41         'params': {
  42             # rtmp download
  43             'skip_download': True,
  44         },
  45         '_skip': 'Blocked outside the US',
  46     }, {
  47         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
  48         'info_dict': {
  49             'id': 'WWF_5KqY3PK1',
  50             'display_id': 'st-vincent',
  51             'ext': 'flv',
  52             'title': 'Live on Letterman - St. Vincent',
  53             'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
  54             'duration': 3221,
  55         },
  56         'params': {
  57             # rtmp download
  58             'skip_download': True,
  59         },
  60         '_skip': 'Blocked outside the US',
  61     }, {
  62         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
  63         'only_matching': True,
  64     }, {
  65         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
  66         'only_matching': True,
  67     }]
  68     TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
  69
  70     def _real_extract(self, url):
  71         content_id, display_id = re.match(self._VALID_URL, url).groups()
  72         if not content_id:
  73             webpage = self._download_webpage(url, display_id)
  74             content_id = self._search_regex(
  75                 [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"],
  76                 webpage, 'content id')
  77         items_data = self._download_xml(
  78             'http://can.cbs.com/thunder/player/videoPlayerService.php',
  79             content_id, query={'partner': 'cbs', 'contentId': content_id})
  80         video_data = xpath_element(items_data, './/item')
  81         title = xpath_text(video_data, 'videoTitle', 'title', True)
  82
  83         subtitles = {}
  84         formats = []
  85         for item in items_data.findall('.//item'):
  86             pid = xpath_text(item, 'pid')
  87             if not pid:
  88                 continue
  89             tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid
  90             if '.m3u8' in xpath_text(item, 'contentUrl', default=''):
  91                 tp_release_url += '&manifest=m3u'
  92             tp_formats, tp_subtitles = self._extract_theplatform_smil(
  93                 tp_release_url, content_id, 'Downloading %s SMIL data' % pid)
  94             formats.extend(tp_formats)
  95             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  96         self._sort_formats(formats)
  97
  98         info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id)
  99         info.update({
 100             'id': content_id,
 101             'display_id': display_id,
 102             'title': title,
 103             'series': xpath_text(video_data, 'seriesTitle'),
 104             'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
 105             'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
 106             'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
 107             'thumbnail': xpath_text(video_data, 'previewImageURL'),
 108             'formats': formats,
 109             'subtitles': subtitles,
 110         })
 111         return info