yt_dlp/extractor/drtv.py

   1 import binascii
   2 import hashlib
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
   7 from ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     ExtractorError,
  10     float_or_none,
  11     int_or_none,
  12     mimetype2ext,
  13     str_or_none,
  14     traverse_obj,
  15     try_get,
  16     unified_timestamp,
  17     update_url_query,
  18     url_or_none,
  19 )
  20
  21 SERIES_API = 'https://production-cdn.dr-massive.com/api/page?device=web_browser&item_detail_expand=all&lang=da&max_list_prefetch=3&path=%s'
  22
  23
  24 class DRTVIE(InfoExtractor):
  25     _VALID_URL = r'''(?x)
  26                     https?://
  27                         (?:
  28                             (?:www\.)?dr\.dk/(?:tv/se|nyheder|(?:radio|lyd)(?:/ondemand)?)/(?:[^/]+/)*|
  29                             (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
  30                         )
  31                         (?P<id>[\da-z_-]+)
  32                     '''
  33     _GEO_BYPASS = False
  34     _GEO_COUNTRIES = ['DK']
  35     IE_NAME = 'drtv'
  36     _TESTS = [{
  37         'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
  38         'md5': '25e659cccc9a2ed956110a299fdf5983',
  39         'info_dict': {
  40             'id': 'klassen-darlig-taber-10',
  41             'ext': 'mp4',
  42             'title': 'Klassen - Dårlig taber (10)',
  43             'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
  44             'timestamp': 1539085800,
  45             'upload_date': '20181009',
  46             'duration': 606.84,
  47             'series': 'Klassen',
  48             'season': 'Klassen I',
  49             'season_number': 1,
  50             'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b',
  51             'episode': 'Episode 10',
  52             'episode_number': 10,
  53             'release_year': 2016,
  54         },
  55         'expected_warnings': ['Unable to download f4m manifest'],
  56         'skip': 'this video has been removed',
  57     }, {
  58         # embed
  59         'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
  60         'info_dict': {
  61             'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6',
  62             'ext': 'mp4',
  63             'title': 'christiania pusher street ryddes drdkrjpo',
  64             'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
  65             'timestamp': 1472800279,
  66             'upload_date': '20160902',
  67             'duration': 131.4,
  68         },
  69         'params': {
  70             'skip_download': True,
  71         },
  72         'expected_warnings': ['Unable to download f4m manifest'],
  73     }, {
  74         # with SignLanguage formats
  75         'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
  76         'info_dict': {
  77             'id': '00831690010',
  78             'ext': 'mp4',
  79             'title': 'Historien om Danmark: Stenalder',
  80             'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
  81             'timestamp': 1546628400,
  82             'upload_date': '20190104',
  83             'duration': 3504.618,
  84             'formats': 'mincount:20',
  85             'release_year': 2017,
  86             'season_id': 'urn:dr:mu:bundle:5afc03ad6187a4065ca5fd35',
  87             'season_number': 1,
  88             'season': 'Historien om Danmark',
  89             'series': 'Historien om Danmark',
  90         },
  91         'params': {
  92             'skip_download': True,
  93         },
  94     }, {
  95         'url': 'https://www.dr.dk/lyd/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
  96         'only_matching': True,
  97     }, {
  98         'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769',
  99         'info_dict': {
 100             'id': '00951930010',
 101             'ext': 'mp4',
 102             'title': 'Bonderøven 2019 (1:8)',
 103             'description': 'md5:b6dcfe9b6f0bea6703e9a0092739a5bd',
 104             'timestamp': 1603188600,
 105             'upload_date': '20201020',
 106             'duration': 2576.6,
 107             'season': 'Bonderøven 2019',
 108             'season_id': 'urn:dr:mu:bundle:5c201667a11fa01ca4528ce5',
 109             'release_year': 2019,
 110             'season_number': 2019,
 111             'series': 'Frank & Kastaniegaarden'
 112         },
 113         'params': {
 114             'skip_download': True,
 115         },
 116     }, {
 117         'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
 118         'only_matching': True,
 119     }, {
 120         'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
 121         'only_matching': True,
 122     }, {
 123         'url': 'https://www.dr.dk/drtv/program/jagten_220924',
 124         'only_matching': True,
 125     }, {
 126         'url': 'https://www.dr.dk/lyd/p4aarhus/regionale-nyheder-ar4/regionale-nyheder-2022-05-05-12-30-3',
 127         'info_dict': {
 128             'id': 'urn:dr:mu:programcard:6265cb2571401424d0360113',
 129             'title': "Regionale nyheder",
 130             'ext': 'mp4',
 131             'duration': 120.043,
 132             'series': 'P4 Østjylland regionale nyheder',
 133             'timestamp': 1651746600,
 134             'season': 'Regionale nyheder',
 135             'release_year': 0,
 136             'season_id': 'urn:dr:mu:bundle:61c26889539f0201586b73c5',
 137             'description': '',
 138             'upload_date': '20220505',
 139         },
 140         'params': {
 141             'skip_download': True,
 142         },
 143     }]
 144
 145     def _real_extract(self, url):
 146         raw_video_id = self._match_id(url)
 147
 148         webpage = self._download_webpage(url, raw_video_id)
 149
 150         if '>Programmet er ikke længere tilgængeligt' in webpage:
 151             raise ExtractorError(
 152                 'Video %s is not available' % raw_video_id, expected=True)
 153
 154         video_id = self._search_regex(
 155             (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
 156              r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
 157             webpage, 'video id', default=None)
 158
 159         if not video_id:
 160             video_id = self._search_regex(
 161                 r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
 162                 webpage, 'urn', default=None)
 163             if video_id:
 164                 video_id = compat_urllib_parse_unquote(video_id)
 165
 166         _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard'
 167         query = {'expanded': 'true'}
 168
 169         if video_id:
 170             programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id)
 171         else:
 172             programcard_url = _PROGRAMCARD_BASE
 173             page = self._parse_json(
 174                 self._search_regex(
 175                     r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage,
 176                     'data'), '1')['cache']['page']
 177             page = page[list(page.keys())[0]]
 178             item = try_get(
 179                 page, (lambda x: x['item'], lambda x: x['entries'][0]['item']),
 180                 dict)
 181             video_id = item['customId'].split(':')[-1]
 182             query['productionnumber'] = video_id
 183
 184         data = self._download_json(
 185             programcard_url, video_id, 'Downloading video JSON', query=query)
 186
 187         supplementary_data = {}
 188         if re.search(r'_\d+$', raw_video_id):
 189             supplementary_data = self._download_json(
 190                 SERIES_API % f'/episode/{raw_video_id}', raw_video_id, fatal=False) or {}
 191
 192         title = str_or_none(data.get('Title')) or re.sub(
 193             r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',
 194             self._og_search_title(webpage))
 195         description = self._og_search_description(
 196             webpage, default=None) or data.get('Description')
 197
 198         timestamp = unified_timestamp(
 199             data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime'))
 200
 201         thumbnail = None
 202         duration = None
 203
 204         restricted_to_denmark = False
 205
 206         formats = []
 207         subtitles = {}
 208
 209         assets = []
 210         primary_asset = data.get('PrimaryAsset')
 211         if isinstance(primary_asset, dict):
 212             assets.append(primary_asset)
 213         secondary_assets = data.get('SecondaryAssets')
 214         if isinstance(secondary_assets, list):
 215             for secondary_asset in secondary_assets:
 216                 if isinstance(secondary_asset, dict):
 217                     assets.append(secondary_asset)
 218
 219         def hex_to_bytes(hex):
 220             return binascii.a2b_hex(hex.encode('ascii'))
 221
 222         def decrypt_uri(e):
 223             n = int(e[2:10], 16)
 224             a = e[10 + n:]
 225             data = hex_to_bytes(e[10:10 + n])
 226             key = hashlib.sha256(('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest()
 227             iv = hex_to_bytes(a)
 228             decrypted = unpad_pkcs7(aes_cbc_decrypt_bytes(data, key, iv))
 229             return decrypted.decode('utf-8').split('?')[0]
 230
 231         for asset in assets:
 232             kind = asset.get('Kind')
 233             if kind == 'Image':
 234                 thumbnail = url_or_none(asset.get('Uri'))
 235             elif kind in ('VideoResource', 'AudioResource'):
 236                 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
 237                 restricted_to_denmark = asset.get('RestrictedToDenmark')
 238                 asset_target = asset.get('Target')
 239                 for link in asset.get('Links', []):
 240                     uri = link.get('Uri')
 241                     if not uri:
 242                         encrypted_uri = link.get('EncryptedUri')
 243                         if not encrypted_uri:
 244                             continue
 245                         try:
 246                             uri = decrypt_uri(encrypted_uri)
 247                         except Exception:
 248                             self.report_warning(
 249                                 'Unable to decrypt EncryptedUri', video_id)
 250                             continue
 251                     uri = url_or_none(uri)
 252                     if not uri:
 253                         continue
 254                     target = link.get('Target')
 255                     format_id = target or ''
 256                     if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
 257                         preference = -1
 258                         format_id += '-%s' % asset_target
 259                     elif asset_target == 'Default':
 260                         preference = 1
 261                     else:
 262                         preference = None
 263                     if target == 'HDS':
 264                         f4m_formats = self._extract_f4m_formats(
 265                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
 266                             video_id, preference, f4m_id=format_id, fatal=False)
 267                         if kind == 'AudioResource':
 268                             for f in f4m_formats:
 269                                 f['vcodec'] = 'none'
 270                         formats.extend(f4m_formats)
 271                     elif target == 'HLS':
 272                         formats.extend(self._extract_m3u8_formats(
 273                             uri, video_id, 'mp4', entry_protocol='m3u8_native',
 274                             quality=preference, m3u8_id=format_id,
 275                             fatal=False))
 276                     else:
 277                         bitrate = link.get('Bitrate')
 278                         if bitrate:
 279                             format_id += '-%s' % bitrate
 280                         formats.append({
 281                             'url': uri,
 282                             'format_id': format_id,
 283                             'tbr': int_or_none(bitrate),
 284                             'ext': link.get('FileFormat'),
 285                             'vcodec': 'none' if kind == 'AudioResource' else None,
 286                             'quality': preference,
 287                         })
 288             subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist')
 289             if isinstance(subtitles_list, list):
 290                 LANGS = {
 291                     'Danish': 'da',
 292                 }
 293                 for subs in subtitles_list:
 294                     if not isinstance(subs, dict):
 295                         continue
 296                     sub_uri = url_or_none(subs.get('Uri'))
 297                     if not sub_uri:
 298                         continue
 299                     lang = subs.get('Language') or 'da'
 300                     subtitles.setdefault(LANGS.get(lang, lang), []).append({
 301                         'url': sub_uri,
 302                         'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
 303                     })
 304
 305         if not formats and restricted_to_denmark:
 306             self.raise_geo_restricted(
 307                 'Unfortunately, DR is not allowed to show this program outside Denmark.',
 308                 countries=self._GEO_COUNTRIES)
 309
 310         return {
 311             'id': video_id,
 312             'title': title,
 313             'description': description,
 314             'thumbnail': thumbnail,
 315             'timestamp': timestamp,
 316             'duration': duration,
 317             'formats': formats,
 318             'subtitles': subtitles,
 319             'series': str_or_none(data.get('SeriesTitle')),
 320             'season': str_or_none(data.get('SeasonTitle')),
 321             'season_number': int_or_none(data.get('SeasonNumber')),
 322             'season_id': str_or_none(data.get('SeasonUrn')),
 323             'episode': traverse_obj(supplementary_data, ('entries', 0, 'item', 'contextualTitle')) or str_or_none(data.get('EpisodeTitle')),
 324             'episode_number': traverse_obj(supplementary_data, ('entries', 0, 'item', 'episodeNumber')) or int_or_none(data.get('EpisodeNumber')),
 325             'release_year': int_or_none(data.get('ProductionYear')),
 326         }
 327
 328
 329 class DRTVLiveIE(InfoExtractor):
 330     IE_NAME = 'drtv:live'
 331     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
 332     _GEO_COUNTRIES = ['DK']
 333     _TEST = {
 334         'url': 'https://www.dr.dk/tv/live/dr1',
 335         'info_dict': {
 336             'id': 'dr1',
 337             'ext': 'mp4',
 338             'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 339         },
 340         'params': {
 341             # m3u8 download
 342             'skip_download': True,
 343         },
 344     }
 345
 346     def _real_extract(self, url):
 347         channel_id = self._match_id(url)
 348         channel_data = self._download_json(
 349             'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
 350             channel_id)
 351         title = channel_data['Title']
 352
 353         formats = []
 354         for streaming_server in channel_data.get('StreamingServers', []):
 355             server = streaming_server.get('Server')
 356             if not server:
 357                 continue
 358             link_type = streaming_server.get('LinkType')
 359             for quality in streaming_server.get('Qualities', []):
 360                 for stream in quality.get('Streams', []):
 361                     stream_path = stream.get('Stream')
 362                     if not stream_path:
 363                         continue
 364                     stream_url = update_url_query(
 365                         '%s/%s' % (server, stream_path), {'b': ''})
 366                     if link_type == 'HLS':
 367                         formats.extend(self._extract_m3u8_formats(
 368                             stream_url, channel_id, 'mp4',
 369                             m3u8_id=link_type, fatal=False, live=True))
 370                     elif link_type == 'HDS':
 371                         formats.extend(self._extract_f4m_formats(update_url_query(
 372                             '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
 373                             channel_id, f4m_id=link_type, fatal=False))
 374
 375         return {
 376             'id': channel_id,
 377             'title': title,
 378             'thumbnail': channel_data.get('PrimaryImageUri'),
 379             'formats': formats,
 380             'is_live': True,
 381         }
 382
 383
 384 class DRTVSeasonIE(InfoExtractor):
 385     IE_NAME = 'drtv:season'
 386     _VALID_URL = r'https?://(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/saeson/(?P<display_id>[\w-]+)_(?P<id>\d+)'
 387     _GEO_COUNTRIES = ['DK']
 388     _TESTS = [{
 389         'url': 'https://www.dr.dk/drtv/saeson/frank-and-kastaniegaarden_9008',
 390         'info_dict': {
 391             'id': '9008',
 392             'display_id': 'frank-and-kastaniegaarden',
 393             'title': 'Frank & Kastaniegaarden',
 394             'series': 'Frank & Kastaniegaarden',
 395         },
 396         'playlist_mincount': 8
 397     }, {
 398         'url': 'https://www.dr.dk/drtv/saeson/frank-and-kastaniegaarden_8761',
 399         'info_dict': {
 400             'id': '8761',
 401             'display_id': 'frank-and-kastaniegaarden',
 402             'title': 'Frank & Kastaniegaarden',
 403             'series': 'Frank & Kastaniegaarden',
 404         },
 405         'playlist_mincount': 19
 406     }]
 407
 408     def _real_extract(self, url):
 409         display_id, season_id = self._match_valid_url(url).group('display_id', 'id')
 410         data = self._download_json(SERIES_API % f'/saeson/{display_id}_{season_id}', display_id)
 411
 412         entries = [{
 413             '_type': 'url',
 414             'url': f'https://www.dr.dk/drtv{episode["path"]}',
 415             'ie_key': DRTVIE.ie_key(),
 416             'title': episode.get('title'),
 417             'episode': episode.get('episodeName'),
 418             'description': episode.get('shortDescription'),
 419             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 420             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber')),
 421             'episode_number': episode.get('episodeNumber'),
 422         } for episode in traverse_obj(data, ('entries', 0, 'item', 'episodes', 'items'))]
 423
 424         return {
 425             '_type': 'playlist',
 426             'id': season_id,
 427             'display_id': display_id,
 428             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
 429             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 430             'entries': entries,
 431             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber'))
 432         }
 433
 434
 435 class DRTVSeriesIE(InfoExtractor):
 436     IE_NAME = 'drtv:series'
 437     _VALID_URL = r'https?://(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/serie/(?P<display_id>[\w-]+)_(?P<id>\d+)'
 438     _GEO_COUNTRIES = ['DK']
 439     _TESTS = [{
 440         'url': 'https://www.dr.dk/drtv/serie/frank-and-kastaniegaarden_6954',
 441         'info_dict': {
 442             'id': '6954',
 443             'display_id': 'frank-and-kastaniegaarden',
 444             'title': 'Frank & Kastaniegaarden',
 445             'series': 'Frank & Kastaniegaarden',
 446         },
 447         'playlist_mincount': 15
 448     }]
 449
 450     def _real_extract(self, url):
 451         display_id, series_id = self._match_valid_url(url).group('display_id', 'id')
 452         data = self._download_json(SERIES_API % f'/serie/{display_id}_{series_id}', display_id)
 453
 454         entries = [{
 455             '_type': 'url',
 456             'url': f'https://www.dr.dk/drtv{season.get("path")}',
 457             'ie_key': DRTVSeasonIE.ie_key(),
 458             'title': season.get('title'),
 459             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 460             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber'))
 461         } for season in traverse_obj(data, ('entries', 0, 'item', 'show', 'seasons', 'items'))]
 462
 463         return {
 464             '_type': 'playlist',
 465             'id': series_id,
 466             'display_id': display_id,
 467             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
 468             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 469             'entries': entries
 470         }