1 from __future__
import unicode_literals
3 from .theplatform
import ThePlatformFeedIE
14 class CBSBaseIE(ThePlatformFeedIE
):
15 def _parse_smil_subtitles(self
, smil
, namespace
=None, subtitles_lang
='en'):
17 for k
, ext
in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
18 cc_e
= find_xpath_attr(smil
, self
._xpath
_ns
('.//param', namespace
), 'name', k
)
20 cc_url
= cc_e
.get('value')
22 subtitles
.setdefault(subtitles_lang
, []).append({
29 class CBSIE(CBSBaseIE
):
30 _VALID_URL
= r
'(?:cbs:|https?://(?:www\.)?(?:(?:cbs\.com|paramountplus\.com)/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
33 'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
35 'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
37 'title': 'Connect Chat feat. Garth Brooks',
38 '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!',
40 'timestamp': 1385585425,
41 'upload_date': '20131127',
42 'uploader': 'CBSI-NEW',
46 'skip_download': True,
48 '_skip': 'Blocked outside the US',
50 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
51 'only_matching': True,
53 'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
54 'only_matching': True,
56 'url': 'https://www.paramountplus.com/shows/star-trek-discovery/video/l5ANMH9wM7kxwV1qr4u1xn88XOhYMlZX/star-trek-discovery-the-vulcan-hello/',
57 'only_matching': True,
60 def _extract_video_info(self
, content_id
, site
='cbs', mpx_acc
=2198311517):
61 items_data
= self
._download
_xml
(
62 'https://can.cbs.com/thunder/player/videoPlayerService.php',
63 content_id
, query
={'partner': site, 'contentId': content_id}
)
64 video_data
= xpath_element(items_data
, './/item')
65 title
= xpath_text(video_data
, 'videoTitle', 'title') or xpath_text(video_data
, 'videotitle', 'title')
66 tp_path
= 'dJ5BDC/media/guid/%d/%s' % (mpx_acc
, content_id
)
67 tp_release_url
= 'https://link.theplatform.com/s/' + tp_path
73 for item
in items_data
.findall('.//item'):
74 asset_type
= xpath_text(item
, 'assetType')
75 if not asset_type
or asset_type
in asset_types
or 'HLS_FPS' in asset_type
or 'DASH_CENC' in asset_type
:
77 asset_types
.append(asset_type
)
80 'assetTypes': asset_type
,
82 if asset_type
.startswith('HLS') or asset_type
in ('OnceURL', 'StreamPack'):
83 query
['formats'] = 'MPEG4,M3U'
84 elif asset_type
in ('RTMP', 'WIFI', '3G'):
85 query
['formats'] = 'MPEG4,FLV'
87 tp_formats
, tp_subtitles
= self
._extract
_theplatform
_smil
(
88 update_url_query(tp_release_url
, query
), content_id
,
89 'Downloading %s SMIL data' % asset_type
)
90 except ExtractorError
as e
:
93 formats
.extend(tp_formats
)
94 subtitles
= self
._merge
_subtitles
(subtitles
, tp_subtitles
)
95 if last_e
and not formats
:
97 self
._sort
_formats
(formats
)
99 info
= self
._extract
_theplatform
_metadata
(tp_path
, content_id
)
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'),
109 'subtitles': subtitles
,
113 def _real_extract(self
, url
):
114 content_id
= self
._match
_id
(url
)
115 return self
._extract
_video
_info
(content_id
)