yt_dlp/extractor/cbsnews.py

   1 import base64
   2 import re
   3 import urllib.parse
   4 import zlib
   5
   6 from .anvato import AnvatoIE
   7 from .common import InfoExtractor
   8 from .paramountplus import ParamountPlusIE
   9 from ..networking import HEADRequest
  10 from ..utils import (
  11     ExtractorError,
  12     UserNotLive,
  13     determine_ext,
  14     float_or_none,
  15     format_field,
  16     int_or_none,
  17     make_archive_id,
  18     mimetype2ext,
  19     parse_duration,
  20     smuggle_url,
  21     traverse_obj,
  22     url_or_none,
  23 )
  24
  25
  26 class CBSNewsBaseIE(InfoExtractor):
  27     _LOCALES = {
  28         'atlanta': None,
  29         'baltimore': 'BAL',
  30         'boston': 'BOS',
  31         'chicago': 'CHI',
  32         'colorado': 'DEN',
  33         'detroit': 'DET',
  34         'losangeles': 'LA',
  35         'miami': 'MIA',
  36         'minnesota': 'MIN',
  37         'newyork': 'NY',
  38         'philadelphia': 'PHI',
  39         'pittsburgh': 'PIT',
  40         'sacramento': 'SAC',
  41         'sanfrancisco': 'SF',
  42         'texas': 'DAL',
  43     }
  44     _LOCALE_RE = '|'.join(map(re.escape, _LOCALES))
  45     _ANVACK = '5VD6Eyd6djewbCmNwBFnsJj17YAvGRwl'
  46
  47     def _get_item(self, webpage, display_id):
  48         return traverse_obj(self._search_json(
  49             r'CBSNEWS\.defaultPayload\s*=', webpage, 'payload', display_id,
  50             default={}), ('items', 0, {dict})) or {}
  51
  52     def _get_video_url(self, item):
  53         return traverse_obj(item, 'video', 'video2', expected_type=url_or_none)
  54
  55     def _extract_playlist(self, webpage, playlist_id):
  56         entries = [self.url_result(embed_url, CBSNewsEmbedIE) for embed_url in re.findall(
  57             r'<iframe[^>]+data-src="(https?://(?:www\.)?cbsnews\.com/embed/video/[^#]*#[^"]+)"', webpage)]
  58         if entries:
  59             return self.playlist_result(
  60                 entries, playlist_id, self._html_search_meta(['og:title', 'twitter:title'], webpage),
  61                 self._html_search_meta(['og:description', 'twitter:description', 'description'], webpage))
  62
  63     def _extract_video(self, item, video_url, video_id):
  64         if mimetype2ext(item.get('format'), default=determine_ext(video_url)) == 'mp4':
  65             formats = [{'url': video_url, 'ext': 'mp4'}]
  66
  67         else:
  68             manifest = self._download_webpage(video_url, video_id, note='Downloading m3u8 information')
  69
  70             anvato_id = self._search_regex(r'anvato-(\d+)', manifest, 'Anvato ID', default=None)
  71             # Prefer Anvato if available; cbsnews.com m3u8 formats are re-encoded from Anvato source
  72             if anvato_id:
  73                 return self.url_result(
  74                     smuggle_url(f'anvato:{self._ANVACK}:{anvato_id}', {'token': 'default'}),
  75                     AnvatoIE, url_transparent=True, _old_archive_ids=[make_archive_id(self, anvato_id)])
  76
  77             formats, _ = self._parse_m3u8_formats_and_subtitles(
  78                 manifest, video_url, 'mp4', m3u8_id='hls', video_id=video_id)
  79
  80         def get_subtitles(subs_url):
  81             return {
  82                 'en': [{
  83                     'url': subs_url,
  84                     'ext': 'dfxp',  # TTAF1
  85                 }],
  86             } if url_or_none(subs_url) else None
  87
  88         episode_meta = traverse_obj(item, {
  89             'season_number': ('season', {int_or_none}),
  90             'episode_number': ('episode', {int_or_none}),
  91         }) if item.get('isFullEpisode') else {}
  92
  93         return {
  94             'id': video_id,
  95             'formats': formats,
  96             **traverse_obj(item, {
  97                 'title': (None, ('fulltitle', 'title')),
  98                 'description': 'dek',
  99                 'timestamp': ('timestamp', {lambda x: float_or_none(x, 1000)}),
 100                 'duration': ('duration', {float_or_none}),
 101                 'subtitles': ('captions', {get_subtitles}),
 102                 'thumbnail': ('images', ('hd', 'sd'), {url_or_none}),
 103                 'is_live': ('type', {lambda x: x == 'live'}),
 104             }, get_all=False),
 105             **episode_meta,
 106         }
 107
 108
 109 class CBSNewsEmbedIE(CBSNewsBaseIE):
 110     IE_NAME = 'cbsnews:embed'
 111     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/embed/video[^#]*#(?P<id>.+)'
 112     _TESTS = [{
 113         'url': 'https://www.cbsnews.com/embed/video/?v=1.c9b5b61492913d6660db0b2f03579ef25e86307a#1Vb7b9s2EP5XBAHbT6Gt98PAMKTJ0se6LVjWYWtdGBR1stlIpEBSTtwi%2F%2FvuJNkNhmHdGxgM2NL57vjd6zt%2B8PngdN%2Fyg79qeGvhzN%2FLGrS%2F%2BuBLB531V28%2B%2BO7Qg7%2Fy97r2z3xZ42NW8yLhDbA0S0KWlHnIijwKWJBHZZnHBa8Cgbpdf%2F89NM9Hi9fXifhpr8sr%2FlP848tn%2BTdXycX25zh4cdX%2FvHl6PmmPqnWQv9w8Ed%2B9GjYRim07bFEqdG%2BZVHuwTm65A7bVRrYtR5lAyMox7pigF6W4k%2By91mjspGsJ%2BwVae4%2BsvdnaO1p73HkXs%2FVisUDTGm7R8IcdnOROeq%2B19qT1amhA1VJtPenoTUgrtfKc9m7Rq8dP7nnjwOB7wg7ADdNt7VX64DWAWlKhPtmDEq22g4GF99x6Dk9E8OSsankHXqPNKDxC%2FdK7MLKTircTDgsI3mmj4OBdSq64dy7fd1x577RU1rt4cvMtOaulFYOd%2FLewRWvDO9lIgXFpZSnkZmjbv5SxKTPoQXClFbpsf%2Fhbbpzs0IB3vb8KkyzJQ%2BywOAgCrMpgRrz%2BKk4fvb7kFbR4XJCu0gAdtNO7woCwZTu%2BBUs9bam%2Fds71drVerpeisgrubLjAB4nnOSkWQnfr5W6o1ku5Xpr1MgrCbL0M0vUyDtfLLK15WiYp47xKWSLyjFVpwVmVJSLIoCjSOFkv3W7oKsVliwZJcB9nwXpZ5GEQQwY8jNKqKCBrgjTLeFxgdCIpazojDgnRtn43J6kG7nZ6cAbxh0EeFFk4%2B1u867cY5u4344n%2FxXjCqAjucdTHgLKojNKmSfO8KRsOFY%2FzKEYCKEJBzv90QA9nfm9gL%2BHulaFqUkz9ULUYxl62B3U%2FRVNLA8IhggaPycOoBuwOCESciDQVSSUgiOMsROB%2FhKfwCKOzEk%2B4k6rWd4uuT%2FwTDz7K7t3d3WLO8ISD95jSPQbayBacthbz86XVgxHwhex5zawzgDOmtp%2F3GPcXn0VXHdSS029%2Fj99UC%2FwJUvyKQ%2FzKyixIEVlYJOn4RxxuaH43Ty9fbJ5OObykHH435XAzJTHeOF4hhEUXD8URe%2FQ%2FBT%2BMpf8d5GN02Ox%2FfiGsl7TA7POu1xZ5%2BbTzcAVKMe48mqcC21hkacVEVScM26liVVBnrKkC4CLKyzAvHu0lhEaTKMFwI3a4SN9MsrfYzdBLq2vkwRD1gVviLT8kY9h2CHH6Y%2Bix6609weFtey4ESp60WtyeWMy%2BsmBuhsoKIyuoT%2Bq2R%2FrW5qi3g%2FvzS2j40DoixDP8%2BKP0yUdpXJ4l6Vla%2Bg9vce%2BC4yM5YlUcbA%2F0jLKdpmTwvsdN5z88nAIe08%2F0HgxeG1iv%2B6Hlhjh7uiW0SDzYNI92L401uha3JKYk268UVRzdOzNQvAaJqoXzAc80dAV440NZ1WVVAAMRYQ2KrGJFmDUsq8saWSnjvIj8t78y%2FRa3JRnbHVfyFpfwoDiGpPgjzekyUiKNlU3OMlwuLMmzgvEojllYVE2Z1HhImvsnk%2BuhusTEoB21PAtSFodeFK3iYhXEH9WOG2%2FkOE833sfeG%2Ff5cfHtEFNXgYes0%2FXj7aGivUgJ9XpusCtoNcNYVVnJVrrDo0OmJAutHCpuZul4W9lLcfy7BnuLPT02%2ByXsCTk%2B9zhzswIN04YueNSK%2BPtM0jS88QdLqSLJDTLsuGZJNolm2yO0PXh3UPnz9Ix5bfIAqxPjvETQsDCEiPG4QbqNyhBZISxybLnZYCrW5H3Axp690%2F0BJdXtDZ5ITuM4xj3f4oUHGzc5JeJmZKpp%2FjwKh4wMV%2FV1yx3emLoR0MwbG4K%2F%2BZgVep3PnzXGDHZ6a3i%2Fk%2BJrONDN13%2Bnq6tBTYk4o7cLGhBtqCC4KwacGHpEVuoH5JNro%2FE6JfE6d5RydbiR76k%2BW5wioDHBIjw1euhHjUGRB0y5A97KoaPx6MlL%2BwgboUVtUFRI%2FLemgTpdtF59ii7pab08kuPcfWzs0l%2FRI5takWnFpka0zOgWRtYcuf9aIxZMxlwr6IiGpsb6j2DQUXPl%2FimXI599Ev7fWjoPD78A',
 114         'info_dict': {
 115             'id': '6ZP4cXvo9FaX3VLH7MF4CgY30JFpY_GA',
 116             'ext': 'mp4',
 117             'title': 'Cops investigate gorilla incident at Cincinnati Zoo',
 118             'description': 'md5:fee7441ab8aaeb3c693482394738102b',
 119             'duration': 350,
 120             'timestamp': 1464719713,
 121             'upload_date': '20160531',
 122             'thumbnail': r're:^https?://.*\.jpg$',
 123         },
 124         'params': {'skip_download': 'm3u8'},
 125     }]
 126
 127     def _real_extract(self, url):
 128         item = traverse_obj(self._parse_json(zlib.decompress(base64.b64decode(
 129             urllib.parse.unquote(self._match_id(url))),
 130             -zlib.MAX_WBITS).decode(), None), ('video', 'items', 0, {dict})) or {}
 131
 132         video_id = item['mpxRefId']
 133         video_url = self._get_video_url(item)
 134         if not video_url:
 135             # Old embeds redirect user to ParamountPlus but most links are 404
 136             pplus_url = f'https://www.paramountplus.com/shows/video/{video_id}'
 137             try:
 138                 self._request_webpage(HEADRequest(pplus_url), video_id)
 139                 return self.url_result(pplus_url, ParamountPlusIE)
 140             except ExtractorError:
 141                 self.raise_no_formats('This video is no longer available', True, video_id)
 142
 143         return self._extract_video(item, video_url, video_id)
 144
 145
 146 class CBSNewsIE(CBSNewsBaseIE):
 147     IE_NAME = 'cbsnews'
 148     IE_DESC = 'CBS News'
 149     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|video)/(?P<id>[\w-]+)'
 150
 151     _TESTS = [
 152         {
 153             # 60 minutes
 154             'url': 'http://www.cbsnews.com/news/artificial-intelligence-positioned-to-be-a-game-changer/',
 155             'info_dict': {
 156                 'id': 'Y_nf_aEg6WwO9OLAq0MpKaPgfnBUxfW4',
 157                 'ext': 'flv',
 158                 'title': 'Artificial Intelligence, real-life applications',
 159                 'description': 'md5:a7aaf27f1b4777244de8b0b442289304',
 160                 'thumbnail': r're:^https?://.*\.jpg$',
 161                 'duration': 317,
 162                 'uploader': 'CBSI-NEW',
 163                 'timestamp': 1476046464,
 164                 'upload_date': '20161009',
 165             },
 166             'skip': 'This video is no longer available',
 167         },
 168         {
 169             'url': 'https://www.cbsnews.com/video/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
 170             'info_dict': {
 171                 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
 172                 'ext': 'mp4',
 173                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
 174                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
 175                 'upload_date': '20140404',
 176                 'timestamp': 1396650660,
 177                 'thumbnail': r're:^https?://.*\.jpg$',
 178                 'duration': 205,
 179                 'subtitles': {
 180                     'en': [{
 181                         'ext': 'dfxp',
 182                     }],
 183                 },
 184             },
 185             'params': {
 186                 'skip_download': 'm3u8',
 187             },
 188         },
 189         {
 190             # 48 hours
 191             'url': 'http://www.cbsnews.com/news/maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved/',
 192             'info_dict': {
 193                 'id': 'maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved',
 194                 'title': 'Cold as Ice',
 195                 'description': 'Can a childhood memory solve the 1957 murder of 7-year-old Maria Ridulph?',
 196             },
 197             'playlist_mincount': 7,
 198         },
 199         {
 200             'url': 'https://www.cbsnews.com/video/032823-cbs-evening-news/',
 201             'info_dict': {
 202                 'id': '_2wuO7hD9LwtyM_TwSnVwnKp6kxlcXgE',
 203                 'ext': 'mp4',
 204                 'title': 'CBS Evening News, March 28, 2023',
 205                 'description': 'md5:db20615aae54adc1d55a1fd69dc75d13',
 206                 'duration': 1189,
 207                 'timestamp': 1680042600,
 208                 'upload_date': '20230328',
 209                 'season': 'Season 2023',
 210                 'season_number': 2023,
 211                 'episode': 'Episode 83',
 212                 'episode_number': 83,
 213                 'thumbnail': r're:^https?://.*\.jpg$',
 214             },
 215             'params': {
 216                 'skip_download': 'm3u8',
 217             },
 218         },
 219     ]
 220
 221     def _real_extract(self, url):
 222         display_id = self._match_id(url)
 223         webpage = self._download_webpage(url, display_id)
 224
 225         playlist = self._extract_playlist(webpage, display_id)
 226         if playlist:
 227             return playlist
 228
 229         item = self._get_item(webpage, display_id)
 230         video_id = item.get('mpxRefId') or display_id
 231         video_url = self._get_video_url(item)
 232         if not video_url:
 233             self.raise_no_formats('No video content was found', expected=True, video_id=video_id)
 234
 235         return self._extract_video(item, video_url, video_id)
 236
 237
 238 class CBSLocalBaseIE(CBSNewsBaseIE):
 239     def _real_extract(self, url):
 240         display_id = self._match_id(url)
 241         webpage = self._download_webpage(url, display_id)
 242
 243         item = self._get_item(webpage, display_id)
 244         video_id = item.get('mpxRefId') or display_id
 245         anvato_id = None
 246         video_url = self._get_video_url(item)
 247
 248         if not video_url:
 249             anv_params = self._search_regex(
 250                 r'<iframe[^>]+\bdata-src="https?://w3\.mp\.lura\.live/player/prod/v3/anvload\.html\?key=([^"]+)"',
 251                 webpage, 'Anvato URL', default=None)
 252
 253             if not anv_params:
 254                 playlist = self._extract_playlist(webpage, display_id)
 255                 if playlist:
 256                     return playlist
 257                 self.raise_no_formats('No video content was found', expected=True, video_id=video_id)
 258
 259             anv_data = self._parse_json(base64.urlsafe_b64decode(f'{anv_params}===').decode(), video_id)
 260             anvato_id = anv_data['v']
 261             return self.url_result(
 262                 smuggle_url(f'anvato:{anv_data.get("anvack") or self._ANVACK}:{anvato_id}', {
 263                     'token': anv_data.get('token') or 'default',
 264                 }), AnvatoIE, url_transparent=True, _old_archive_ids=[make_archive_id(self, anvato_id)])
 265
 266         return self._extract_video(item, video_url, video_id)
 267
 268
 269 class CBSLocalIE(CBSLocalBaseIE):
 270     _VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?:{CBSNewsBaseIE._LOCALE_RE})/(?:live/)?video/(?P<id>[\w-]+)'
 271     _TESTS = [{
 272         # Anvato video via defaultPayload JSON
 273         'url': 'https://www.cbsnews.com/newyork/video/1st-cannabis-dispensary-opens-in-queens/',
 274         'info_dict': {
 275             'id': '6376747',
 276             'ext': 'mp4',
 277             'title': '1st cannabis dispensary opens in Queens',
 278             'description': 'The dispensary is women-owned and located in Jamaica.',
 279             'uploader': 'CBS',
 280             'duration': 20,
 281             'timestamp': 1680193657,
 282             'upload_date': '20230330',
 283             'categories': ['Stations\\Spoken Word\\WCBSTV', 'Content\\Google', 'Content\\News', 'Content\\News\\Local News'],
 284             'tags': 'count:11',
 285             'thumbnail': 're:^https?://.*',
 286             '_old_archive_ids': ['cbslocal 6376747'],
 287         },
 288         'params': {'skip_download': 'm3u8'},
 289     }, {
 290         # cbsnews.com video via defaultPayload JSON
 291         'url': 'https://www.cbsnews.com/newyork/live/video/20230330171655-the-city-is-sounding-the-alarm-on-dangerous-social-media-challenges/',
 292         'info_dict': {
 293             'id': 'sJqfw7YvgSC6ant2zVmzt3y1jYKoL5J3',
 294             'ext': 'mp4',
 295             'title': 'the city is sounding the alarm on dangerous social media challenges',
 296             'description': 'md5:8eccc9b1b73be5138a52e9c4350d2cd6',
 297             'thumbnail': 'https://images-cbsn.cbsnews.com/prod/2023/03/30/story_22509622_1680196925.jpg',
 298             'duration': 41.0,
 299             'timestamp': 1680196615,
 300             'upload_date': '20230330',
 301         },
 302         'params': {'skip_download': 'm3u8'},
 303     }]
 304
 305
 306 class CBSLocalArticleIE(CBSLocalBaseIE):
 307     _VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?:{CBSNewsBaseIE._LOCALE_RE})/news/(?P<id>[\w-]+)'
 308     _TESTS = [{
 309         # Anvato video via iframe embed
 310         'url': 'https://www.cbsnews.com/newyork/news/mta-station-agents-leaving-their-booths-to-provide-more-direct-customer-service/',
 311         'playlist_count': 2,
 312         'info_dict': {
 313             'id': 'mta-station-agents-leaving-their-booths-to-provide-more-direct-customer-service',
 314             'title': 'MTA station agents begin leaving their booths to provide more direct customer service',
 315             'description': 'The more than 2,200 agents will provide face-to-face customer service to passengers.',
 316         },
 317     }, {
 318         'url': 'https://www.cbsnews.com/losangeles/news/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis/',
 319         'md5': 'f0ee3081e3843f575fccef901199b212',
 320         'info_dict': {
 321             'id': '3401037',
 322             'ext': 'mp4',
 323             'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'',
 324             'thumbnail': 're:^https?://.*',
 325             'timestamp': 1463440500,
 326             'upload_date': '20160516',
 327         },
 328         'skip': 'Video has been removed',
 329     }]
 330
 331
 332 class CBSNewsLiveBaseIE(CBSNewsBaseIE):
 333     def _get_id(self, url):
 334         raise NotImplementedError('This method must be implemented by subclasses')
 335
 336     def _real_extract(self, url):
 337         video_id = self._get_id(url)
 338         if not video_id:
 339             raise ExtractorError('Livestream is not available', expected=True)
 340
 341         data = traverse_obj(self._download_json(
 342             'https://feeds-cbsn.cbsnews.com/2.0/rundown/', video_id, query={
 343                 'partner': 'cbsnsite',
 344                 'edition': video_id,
 345                 'type': 'live',
 346             }), ('navigation', 'data', 0, {dict}))
 347
 348         video_url = traverse_obj(data, (('videoUrlDAI', ('videoUrl', 'base')), {url_or_none}), get_all=False)
 349         if not video_url:
 350             raise UserNotLive(video_id=video_id)
 351
 352         formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, 'mp4', m3u8_id='hls')
 353
 354         return {
 355             'id': video_id,
 356             'formats': formats,
 357             'subtitles': subtitles,
 358             'is_live': True,
 359             **traverse_obj(data, {
 360                 'title': 'headline',
 361                 'description': 'rundown_slug',
 362                 'thumbnail': ('images', 'thumbnail_url_hd', {url_or_none}),
 363             }),
 364         }
 365
 366
 367 class CBSLocalLiveIE(CBSNewsLiveBaseIE):
 368     _VALID_URL = rf'https?://(?:www\.)?cbsnews\.com/(?P<id>{CBSNewsBaseIE._LOCALE_RE})/live/?(?:[?#]|$)'
 369     _TESTS = [{
 370         'url': 'https://www.cbsnews.com/losangeles/live/',
 371         'info_dict': {
 372             'id': 'CBSN-LA',
 373             'ext': 'mp4',
 374             'title': str,
 375             'description': r're:KCBS/CBSN_LA.CRISPIN.\w+.RUNDOWN \w+ \w+',
 376             'thumbnail': r're:^https?://.*\.jpg$',
 377             'live_status': 'is_live',
 378         },
 379         'params': {'skip_download': 'm3u8'},
 380     }]
 381
 382     def _get_id(self, url):
 383         return format_field(self._LOCALES, self._match_id(url), 'CBSN-%s')
 384
 385
 386 class CBSNewsLiveIE(CBSNewsLiveBaseIE):
 387     IE_NAME = 'cbsnews:live'
 388     IE_DESC = 'CBS News Livestream'
 389     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/?(?:[?#]|$)'
 390     _TESTS = [{
 391         'url': 'https://www.cbsnews.com/live/',
 392         'info_dict': {
 393             'id': 'CBSN-US',
 394             'ext': 'mp4',
 395             'title': str,
 396             'description': r're:\w+ \w+ CRISPIN RUNDOWN',
 397             'thumbnail': r're:^https?://.*\.jpg$',
 398             'live_status': 'is_live',
 399         },
 400         'params': {'skip_download': 'm3u8'},
 401     }]
 402
 403     def _get_id(self, url):
 404         return 'CBSN-US'
 405
 406
 407 class CBSNewsLiveVideoIE(InfoExtractor):
 408     IE_NAME = 'cbsnews:livevideo'
 409     IE_DESC = 'CBS News Live Videos'
 410     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
 411
 412     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
 413     _TESTS = [{
 414         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
 415         'info_dict': {
 416             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
 417             'ext': 'mp4',
 418             'title': 'Clinton, Sanders Prepare To Face Off In NH',
 419             'duration': 334,
 420         },
 421         'skip': 'Video gone',
 422     }]
 423
 424     def _real_extract(self, url):
 425         display_id = self._match_id(url)
 426
 427         video_info = self._download_json(
 428             'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
 429                 'device': 'desktop',
 430                 'dvr_slug': display_id,
 431             })
 432
 433         return {
 434             'id': display_id,
 435             'display_id': display_id,
 436             'formats': self._extract_akamai_formats(video_info['url'], display_id),
 437             **traverse_obj(video_info, {
 438                 'title': 'headline',
 439                 'thumbnail': ('thumbnail_url_hd', {url_or_none}),
 440                 'duration': ('segmentDur', {parse_duration}),
 441             }),
 442         }