1 from .brightcove
import BrightcoveNewIE
2 from .common
import InfoExtractor
3 from .theplatform
import ThePlatformFeedIE
4 from .youtube
import YoutubeIE
8 get_element_html_by_id
,
19 class CBSBaseIE(ThePlatformFeedIE
): # XXX: Do not subclass from concrete IE
20 def _parse_smil_subtitles(self
, smil
, namespace
=None, subtitles_lang
='en'):
22 for k
, ext
in [('sMPTE-TTCCURL', 'tt'), ('ClosedCaptionURL', 'ttml'), ('webVTTCaptionURL', 'vtt')]:
23 cc_e
= find_xpath_attr(smil
, self
._xpath
_ns
('.//param', namespace
), 'name', k
)
25 cc_url
= cc_e
.get('value')
27 subtitles
.setdefault(subtitles_lang
, []).append({
33 def _extract_common_video_info(self
, content_id
, asset_types
, mpx_acc
, extra_info
):
34 tp_path
= 'dJ5BDC/media/guid/%d/%s' % (mpx_acc
, content_id
)
35 tp_release_url
= f
'https://link.theplatform.com/s/{tp_path}'
36 info
= self
._extract
_theplatform
_metadata
(tp_path
, content_id
)
38 formats
, subtitles
= [], {}
40 for asset_type
, query
in asset_types
.items():
42 tp_formats
, tp_subtitles
= self
._extract
_theplatform
_smil
(
43 update_url_query(tp_release_url
, query
), content_id
,
44 'Downloading %s SMIL data' % asset_type
)
45 except ExtractorError
as e
:
47 if asset_type
!= 'fallback':
49 query
['formats'] = '' # blank query to check if expired
51 tp_formats
, tp_subtitles
= self
._extract
_theplatform
_smil
(
52 update_url_query(tp_release_url
, query
), content_id
,
53 'Downloading %s SMIL data, trying again with another format' % asset_type
)
54 except ExtractorError
as e
:
57 formats
.extend(tp_formats
)
58 subtitles
= self
._merge
_subtitles
(subtitles
, tp_subtitles
)
59 if last_e
and not formats
:
60 self
.raise_no_formats(last_e
, True, content_id
)
65 'subtitles': subtitles
,
67 info
.update({k: v for k, v in extra_info.items() if v is not None}
)
70 def _extract_video_info(self
, *args
, **kwargs
):
71 # Extract assets + metadata and call _extract_common_video_info
72 raise NotImplementedError('This method must be implemented by subclasses')
74 def _real_extract(self
, url
):
75 return self
._extract
_video
_info
(self
._match
_id
(url
))
78 class CBSIE(CBSBaseIE
):
82 https?://(?:www\.)?(?:
83 cbs\.com/(?:shows|movies)/(?:video|[^/]+/video|[^/]+)/|
84 colbertlateshow\.com/(?:video|podcasts)/)
87 # All tests are blocked outside US
89 'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/',
91 'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R',
93 'title': 'Tough As Nails - Dreams Never Die',
94 'description': 'md5:a3535a62531cdd52b0364248a2c1ae33',
96 'timestamp': 1639015200,
97 'upload_date': '20211209',
98 'uploader': 'CBSI-NEW',
102 'skip_download': True,
105 'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/',
107 'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1',
108 'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)',
109 'timestamp': 1647488100,
110 'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439',
111 'uploader': 'CBSI-NEW',
112 'upload_date': '20220317',
115 'ignore_no_formats_error': True,
116 'skip_download': True,
118 'expected_warnings': [
119 'This content expired on', 'No video formats found', 'Requested format is not available'],
121 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
122 'only_matching': True,
124 'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
125 'only_matching': True,
128 def _extract_video_info(self
, content_id
, site
='cbs', mpx_acc
=2198311517):
129 items_data
= self
._download
_xml
(
130 'https://can.cbs.com/thunder/player/videoPlayerService.php',
131 content_id
, query
={'partner': site, 'contentId': content_id}
)
132 video_data
= xpath_element(items_data
, './/item')
133 title
= xpath_text(video_data
, 'videoTitle', 'title') or xpath_text(video_data
, 'videotitle', 'title')
137 for item
in items_data
.findall('.//item'):
138 asset_type
= xpath_text(item
, 'assetType')
141 'assetTypes': asset_type
,
144 # fallback for content_ids that videoPlayerService doesn't return anything for
145 asset_type
= 'fallback'
146 query
['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
147 del query
['assetTypes']
148 if asset_type
in asset_types
:
150 elif any(excluded
in asset_type
for excluded
in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
151 if 'DASH_CENC' in asset_type
:
154 if asset_type
.startswith('HLS') or 'StreamPack' in asset_type
:
155 query
['formats'] = 'MPEG4,M3U'
156 elif asset_type
in ('RTMP', 'WIFI', '3G'):
157 query
['formats'] = 'MPEG4,FLV'
158 asset_types
[asset_type
] = query
160 if not asset_types
and has_drm
:
161 self
.report_drm(content_id
)
163 return self
._extract
_common
_video
_info
(content_id
, asset_types
, mpx_acc
, extra_info
={
165 'series': xpath_text(video_data
, 'seriesTitle'),
166 'season_number': int_or_none(xpath_text(video_data
, 'seasonNumber')),
167 'episode_number': int_or_none(xpath_text(video_data
, 'episodeNumber')),
168 'duration': int_or_none(xpath_text(video_data
, 'videoLength'), 1000),
169 'thumbnail': url_or_none(xpath_text(video_data
, 'previewImageURL')),
173 class ParamountPressExpressIE(InfoExtractor
):
174 _VALID_URL
= r
'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)'
176 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx',
177 'md5': '56631dbcadaab980d1fc47cb7b76cba4',
179 'id': '6322981580112',
181 'title': 'I’m Felicia',
182 'description': 'md5:88fad93f8eede1c9c8f390239e4c6290',
183 'uploader_id': '6055873637001',
184 'upload_date': '20230320',
185 'timestamp': 1679334960,
187 'thumbnail': r
're:^https://.+\.jpg',
191 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc',
192 'md5': 'edcb03e3210b88a3e56c05aa863e0e5b',
194 'id': '6323036027112',
196 'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More',
197 'description': 'md5:b929867a357aac5544b783d834c78383',
198 'uploader_id': '6055873637001',
199 'upload_date': '20230321',
200 'timestamp': 1679430180,
202 'thumbnail': r
're:^https://.+\.jpg',
206 'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck',
210 'title': 'Rugrats | Season 2 Official Trailer | Paramount+',
211 'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de',
212 'uploader': 'Paramount Plus',
213 'uploader_id': '@paramountplus',
214 'uploader_url': 'http://www.youtube.com/@paramountplus',
215 'channel': 'Paramount Plus',
216 'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg',
217 'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg',
218 'upload_date': '20230316',
221 'availability': 'public',
222 'live_status': 'not_live',
223 'playable_in_embed': True,
226 'channel_follower_count': int,
227 'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg',
228 'categories': ['Entertainment'],
232 'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw',
236 'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME',
237 'description': 'md5:39581bcc3fd810209b642609f448af70',
238 'uploader': 'SHOWTIME',
239 'uploader_id': '@Showtime',
240 'uploader_url': 'http://www.youtube.com/@Showtime',
241 'channel': 'SHOWTIME',
242 'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ',
243 'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ',
244 'upload_date': '20230209',
247 'availability': 'public',
248 'live_status': 'not_live',
249 'playable_in_embed': True,
252 'comment_count': int,
253 'channel_follower_count': int,
254 'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp',
255 'categories': ['People & Blogs'],
260 def _real_extract(self
, url
):
261 display_id
, is_youtube
= self
._match
_valid
_url
(url
).group('id', 'yt')
263 return self
.url_result(display_id
, YoutubeIE
)
265 webpage
= self
._download
_webpage
(url
, display_id
)
266 video_id
= self
._search
_regex
(
267 r
'\bvideo_id\s*=\s*["\'](\d
+)["\']\s*,', webpage, 'Brightcove ID')
268 token = self._search_regex(r'\btoken\s*=\s*["\']([\w
.-]+)["\']', webpage, 'token')
270 player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '')
271 account_id = player.get('data-account') or '6055873637001'
272 player_id = player.get('data-player') or 'OtLKgXlO9F'
273 embed = player.get('data-embed') or 'default'
275 return self.url_result(smuggle_url(
276 f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}',
277 {'token': token}), BrightcoveNewIE)