]>
Commit | Line | Data |
---|---|---|
1 | from .brightcove import BrightcoveNewIE | |
2 | from .common import InfoExtractor | |
3 | from .theplatform import ThePlatformFeedIE | |
4 | from .youtube import YoutubeIE | |
5 | from ..utils import ( | |
6 | ExtractorError, | |
7 | extract_attributes, | |
8 | get_element_html_by_id, | |
9 | int_or_none, | |
10 | find_xpath_attr, | |
11 | smuggle_url, | |
12 | xpath_element, | |
13 | xpath_text, | |
14 | update_url_query, | |
15 | url_or_none, | |
16 | ) | |
17 | ||
18 | ||
19 | class CBSBaseIE(ThePlatformFeedIE): # XXX: Do not subclass from concrete IE | |
20 | def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): | |
21 | subtitles = {} | |
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) | |
24 | if cc_e is not None: | |
25 | cc_url = cc_e.get('value') | |
26 | if cc_url: | |
27 | subtitles.setdefault(subtitles_lang, []).append({ | |
28 | 'ext': ext, | |
29 | 'url': cc_url, | |
30 | }) | |
31 | return subtitles | |
32 | ||
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) | |
37 | ||
38 | formats, subtitles = [], {} | |
39 | last_e = None | |
40 | for asset_type, query in asset_types.items(): | |
41 | try: | |
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: | |
46 | last_e = e | |
47 | if asset_type != 'fallback': | |
48 | continue | |
49 | query['formats'] = '' # blank query to check if expired | |
50 | try: | |
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: | |
55 | last_e = e | |
56 | continue | |
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) | |
61 | ||
62 | extra_info.update({ | |
63 | 'id': content_id, | |
64 | 'formats': formats, | |
65 | 'subtitles': subtitles, | |
66 | }) | |
67 | info.update({k: v for k, v in extra_info.items() if v is not None}) | |
68 | return info | |
69 | ||
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') | |
73 | ||
74 | def _real_extract(self, url): | |
75 | return self._extract_video_info(self._match_id(url)) | |
76 | ||
77 | ||
78 | class CBSIE(CBSBaseIE): | |
79 | _WORKING = False | |
80 | _VALID_URL = r'''(?x) | |
81 | (?: | |
82 | cbs:| | |
83 | https?://(?:www\.)?(?: | |
84 | cbs\.com/(?:shows|movies)/(?:video|[^/]+/video|[^/]+)/| | |
85 | colbertlateshow\.com/(?:video|podcasts)/) | |
86 | )(?P<id>[\w-]+)''' | |
87 | ||
88 | # All tests are blocked outside US | |
89 | _TESTS = [{ | |
90 | 'url': 'https://www.cbs.com/shows/video/xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R/', | |
91 | 'info_dict': { | |
92 | 'id': 'xrUyNLtl9wd8D_RWWAg9NU2F_V6QpB3R', | |
93 | 'ext': 'mp4', | |
94 | 'title': 'Tough As Nails - Dreams Never Die', | |
95 | 'description': 'md5:a3535a62531cdd52b0364248a2c1ae33', | |
96 | 'duration': 2588, | |
97 | 'timestamp': 1639015200, | |
98 | 'upload_date': '20211209', | |
99 | 'uploader': 'CBSI-NEW', | |
100 | }, | |
101 | 'params': { | |
102 | # m3u8 download | |
103 | 'skip_download': True, | |
104 | }, | |
105 | 'skip': 'Subscription required', | |
106 | }, { | |
107 | 'url': 'https://www.cbs.com/shows/video/sZH1MGgomIosZgxGJ1l263MFq16oMtW1/', | |
108 | 'info_dict': { | |
109 | 'id': 'sZH1MGgomIosZgxGJ1l263MFq16oMtW1', | |
110 | 'title': 'The Late Show - 3/16/22 (Michael Buble, Rose Matafeo)', | |
111 | 'timestamp': 1647488100, | |
112 | 'description': 'md5:d0e6ec23c544b7fa8e39a8e6844d2439', | |
113 | 'uploader': 'CBSI-NEW', | |
114 | 'upload_date': '20220317', | |
115 | }, | |
116 | 'params': { | |
117 | 'ignore_no_formats_error': True, | |
118 | 'skip_download': True, | |
119 | }, | |
120 | 'expected_warnings': [ | |
121 | 'This content expired on', 'No video formats found', 'Requested format is not available'], | |
122 | 'skip': '404 Not Found', | |
123 | }, { | |
124 | 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/', | |
125 | 'only_matching': True, | |
126 | }, { | |
127 | 'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/', | |
128 | 'only_matching': True, | |
129 | }] | |
130 | ||
131 | def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517): | |
132 | items_data = self._download_xml( | |
133 | 'https://can.cbs.com/thunder/player/videoPlayerService.php', | |
134 | content_id, query={'partner': site, 'contentId': content_id}) | |
135 | video_data = xpath_element(items_data, './/item') | |
136 | title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title') | |
137 | ||
138 | asset_types = {} | |
139 | has_drm = False | |
140 | for item in items_data.findall('.//item'): | |
141 | asset_type = xpath_text(item, 'assetType') | |
142 | query = { | |
143 | 'mbr': 'true', | |
144 | 'assetTypes': asset_type, | |
145 | } | |
146 | if not asset_type: | |
147 | # fallback for content_ids that videoPlayerService doesn't return anything for | |
148 | asset_type = 'fallback' | |
149 | query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3' | |
150 | del query['assetTypes'] | |
151 | if asset_type in asset_types: | |
152 | continue | |
153 | elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')): | |
154 | if 'DASH_CENC' in asset_type: | |
155 | has_drm = True | |
156 | continue | |
157 | if asset_type.startswith('HLS') or 'StreamPack' in asset_type: | |
158 | query['formats'] = 'MPEG4,M3U' | |
159 | elif asset_type in ('RTMP', 'WIFI', '3G'): | |
160 | query['formats'] = 'MPEG4,FLV' | |
161 | asset_types[asset_type] = query | |
162 | ||
163 | if not asset_types and has_drm: | |
164 | self.report_drm(content_id) | |
165 | ||
166 | return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={ | |
167 | 'title': title, | |
168 | 'series': xpath_text(video_data, 'seriesTitle'), | |
169 | 'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')), | |
170 | 'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')), | |
171 | 'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000), | |
172 | 'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')), | |
173 | }) | |
174 | ||
175 | ||
176 | class ParamountPressExpressIE(InfoExtractor): | |
177 | _VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?P<yt>yt-)?video/?\?watch=(?P<id>[\w-]+)' | |
178 | _TESTS = [{ | |
179 | 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx', | |
180 | 'md5': '56631dbcadaab980d1fc47cb7b76cba4', | |
181 | 'info_dict': { | |
182 | 'id': '6322981580112', | |
183 | 'ext': 'mp4', | |
184 | 'title': 'I’m Felicia', | |
185 | 'description': 'md5:88fad93f8eede1c9c8f390239e4c6290', | |
186 | 'uploader_id': '6055873637001', | |
187 | 'upload_date': '20230320', | |
188 | 'timestamp': 1679334960, | |
189 | 'duration': 49.557, | |
190 | 'thumbnail': r're:^https://.+\.jpg', | |
191 | 'tags': [], | |
192 | }, | |
193 | }, { | |
194 | 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc', | |
195 | 'md5': 'edcb03e3210b88a3e56c05aa863e0e5b', | |
196 | 'info_dict': { | |
197 | 'id': '6323036027112', | |
198 | 'ext': 'mp4', | |
199 | 'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More', | |
200 | 'description': 'md5:b929867a357aac5544b783d834c78383', | |
201 | 'uploader_id': '6055873637001', | |
202 | 'upload_date': '20230321', | |
203 | 'timestamp': 1679430180, | |
204 | 'duration': 132.032, | |
205 | 'thumbnail': r're:^https://.+\.jpg', | |
206 | 'tags': [], | |
207 | }, | |
208 | }, { | |
209 | 'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck', | |
210 | 'info_dict': { | |
211 | 'id': 'OX9wJWOcqck', | |
212 | 'ext': 'mp4', | |
213 | 'title': 'Rugrats | Season 2 Official Trailer | Paramount+', | |
214 | 'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de', | |
215 | 'uploader': 'Paramount Plus', | |
216 | 'uploader_id': '@paramountplus', | |
217 | 'uploader_url': 'http://www.youtube.com/@paramountplus', | |
218 | 'channel': 'Paramount Plus', | |
219 | 'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg', | |
220 | 'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg', | |
221 | 'upload_date': '20230316', | |
222 | 'duration': 88, | |
223 | 'age_limit': 0, | |
224 | 'availability': 'public', | |
225 | 'live_status': 'not_live', | |
226 | 'playable_in_embed': True, | |
227 | 'view_count': int, | |
228 | 'like_count': int, | |
229 | 'channel_follower_count': int, | |
230 | 'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg', | |
231 | 'categories': ['Entertainment'], | |
232 | 'tags': ['Rugrats'], | |
233 | }, | |
234 | }, { | |
235 | 'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw', | |
236 | 'info_dict': { | |
237 | 'id': '_ljssSoDLkw', | |
238 | 'ext': 'mp4', | |
239 | 'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME', | |
240 | 'description': 'md5:39581bcc3fd810209b642609f448af70', | |
241 | 'uploader': 'SHOWTIME', | |
242 | 'uploader_id': '@Showtime', | |
243 | 'uploader_url': 'http://www.youtube.com/@Showtime', | |
244 | 'channel': 'SHOWTIME', | |
245 | 'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ', | |
246 | 'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ', | |
247 | 'upload_date': '20230209', | |
248 | 'duration': 49, | |
249 | 'age_limit': 0, | |
250 | 'availability': 'public', | |
251 | 'live_status': 'not_live', | |
252 | 'playable_in_embed': True, | |
253 | 'view_count': int, | |
254 | 'like_count': int, | |
255 | 'comment_count': int, | |
256 | 'channel_follower_count': int, | |
257 | 'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp', | |
258 | 'categories': ['People & Blogs'], | |
259 | 'tags': 'count:27', | |
260 | }, | |
261 | }] | |
262 | ||
263 | def _real_extract(self, url): | |
264 | display_id, is_youtube = self._match_valid_url(url).group('id', 'yt') | |
265 | if is_youtube: | |
266 | return self.url_result(display_id, YoutubeIE) | |
267 | ||
268 | webpage = self._download_webpage(url, display_id) | |
269 | video_id = self._search_regex( | |
270 | r'\bvideo_id\s*=\s*["\'](\d+)["\']\s*,', webpage, 'Brightcove ID') | |
271 | token = self._search_regex(r'\btoken\s*=\s*["\']([\w.-]+)["\']', webpage, 'token') | |
272 | ||
273 | player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '') | |
274 | account_id = player.get('data-account') or '6055873637001' | |
275 | player_id = player.get('data-player') or 'OtLKgXlO9F' | |
276 | embed = player.get('data-embed') or 'default' | |
277 | ||
278 | return self.url_result(smuggle_url( | |
279 | f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}', | |
280 | {'token': token}), BrightcoveNewIE) |