yt_dlp/extractor/ndr.py

   1 import re
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     determine_ext,
   8     int_or_none,
   9     merge_dicts,
  10     parse_iso8601,
  11     qualities,
  12     try_get,
  13     urljoin,
  14 )
  15
  16
  17 class NDRBaseIE(InfoExtractor):
  18     def _real_extract(self, url):
  19         mobj = self._match_valid_url(url)
  20         display_id = next(group for group in mobj.groups() if group)
  21         webpage = self._download_webpage(url, display_id)
  22         return self._extract_embed(webpage, display_id, url)
  23
  24
  25 class NDRIE(NDRBaseIE):
  26     IE_NAME = 'ndr'
  27     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
  28     _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
  29     _TESTS = [{
  30         # httpVideo, same content id
  31         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
  32         'md5': '6515bc255dc5c5f8c85bbc38e035a659',
  33         'info_dict': {
  34             'id': 'hafengeburtstag988',
  35             'display_id': 'Party-Poette-und-Parade',
  36             'ext': 'mp4',
  37             'title': 'Party, Pötte und Parade',
  38             'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c',
  39             'uploader': 'ndrtv',
  40             'timestamp': 1431255671,
  41             'upload_date': '20150510',
  42             'duration': 3498,
  43         },
  44         'params': {
  45             'skip_download': True,
  46         },
  47         'expected_warnings': ['Unable to download f4m manifest'],
  48     }, {
  49         # httpVideo, different content id
  50         'url': 'http://www.ndr.de/sport/fussball/40-Osnabrueck-spielt-sich-in-einen-Rausch,osna270.html',
  51         'md5': '1043ff203eab307f0c51702ec49e9a71',
  52         'info_dict': {
  53             'id': 'osna272',
  54             'display_id': '40-Osnabrueck-spielt-sich-in-einen-Rausch',
  55             'ext': 'mp4',
  56             'title': 'Osnabrück - Wehen Wiesbaden: Die Highlights',
  57             'description': 'md5:32e9b800b3d2d4008103752682d5dc01',
  58             'uploader': 'ndrtv',
  59             'timestamp': 1442059200,
  60             'upload_date': '20150912',
  61             'duration': 510,
  62         },
  63         'params': {
  64             'skip_download': True,
  65         },
  66         'skip': 'No longer available',
  67     }, {
  68         # httpAudio, same content id
  69         'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
  70         'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
  71         'info_dict': {
  72             'id': 'audio51535',
  73             'display_id': 'La-Valette-entgeht-der-Hinrichtung',
  74             'ext': 'mp3',
  75             'title': 'La Valette entgeht der Hinrichtung',
  76             'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
  77             'uploader': 'ndrinfo',
  78             'timestamp': 1631711863,
  79             'upload_date': '20210915',
  80             'duration': 884,
  81         },
  82         'params': {
  83             'skip_download': True,
  84         },
  85     }, {
  86         # with subtitles
  87         'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html',
  88         'info_dict': {
  89             'id': 'extra18674',
  90             'display_id': 'extra-3-Satiremagazin-mit-Christian-Ehring',
  91             'ext': 'mp4',
  92             'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring',
  93             'description': 'md5:700f6de264010585012a72f97b0ac0c9',
  94             'uploader': 'ndrtv',
  95             'upload_date': '20201207',
  96             'timestamp': 1614349457,
  97             'duration': 1749,
  98             'subtitles': {
  99                 'de': [{
 100                     'ext': 'ttml',
 101                     'url': r're:^https://www\.ndr\.de.+',
 102                 }],
 103             },
 104         },
 105         'params': {
 106             'skip_download': True,
 107         },
 108         'expected_warnings': ['Unable to download f4m manifest'],
 109     }, {
 110         'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html',
 111         'only_matching': True,
 112     }]
 113
 114     def _extract_embed(self, webpage, display_id, url):
 115         embed_url = (
 116             self._html_search_meta(
 117                 'embedURL', webpage, 'embed URL',
 118                 default=None)
 119             or self._search_regex(
 120                 r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 121                 'embed URL', group='url', default=None)
 122             or self._search_regex(
 123                 r'\bvar\s*sophoraID\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 124                 'embed URL', group='url', default=''))
 125         # some more work needed if we only found sophoraID
 126         if re.match(r'^[a-z]+\d+$', embed_url):
 127             # get the initial part of the url path,. eg /panorama/archiv/2022/
 128             parsed_url = urllib.parse.urlparse(url)
 129             path = self._search_regex(rf'(.+/){display_id}', parsed_url.path or '', 'embed URL', default='')
 130             # find tell-tale image with the actual ID
 131             ndr_id = self._search_regex(rf'{path}([a-z]+\d+)(?!\.)\b', webpage, 'embed URL', default=None)
 132             # or try to use special knowledge!
 133             NDR_INFO_URL_TPL = 'https://www.ndr.de/info/%s-player.html'
 134             embed_url = f'ndr:{ndr_id}' if ndr_id else NDR_INFO_URL_TPL % (embed_url, )
 135         if not embed_url:
 136             raise ExtractorError('Unable to extract embedUrl')
 137
 138         description = self._search_regex(
 139             r'<p[^>]+itemprop="description">([^<]+)</p>',
 140             webpage, 'description', default=None) or self._og_search_description(webpage)
 141         timestamp = parse_iso8601(
 142             self._search_regex(
 143                 (r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="(?P<cont>[^"]+)"',
 144                  r'\bvar\s*pdt\s*=\s*(?P<q>["\'])(?P<cont>(?:(?!(?P=q)).)+)(?P=q)'),
 145                 webpage, 'upload date', group='cont', default=None))
 146         info = self._search_json_ld(webpage, display_id, default={})
 147         return merge_dicts({
 148             '_type': 'url_transparent',
 149             'url': embed_url,
 150             'display_id': display_id,
 151             'description': description,
 152             'timestamp': timestamp,
 153         }, info)
 154
 155
 156 class NJoyIE(NDRBaseIE):
 157     IE_NAME = 'njoy'
 158     IE_DESC = 'N-JOY'
 159     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
 160     _TESTS = [{
 161         # httpVideo, same content id
 162         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
 163         'md5': 'cb63be60cd6f9dd75218803146d8dc67',
 164         'info_dict': {
 165             'id': 'comedycontest2480',
 166             'display_id': 'Benaissa-beim-NDR-Comedy-Contest',
 167             'ext': 'mp4',
 168             'title': 'Benaissa beim NDR Comedy Contest',
 169             'description': 'md5:f057a6c4e1c728b10d33b5ffd36ddc39',
 170             'uploader': 'ndrtv',
 171             'upload_date': '20141129',
 172             'duration': 654,
 173         },
 174         'params': {
 175             'skip_download': True,
 176         },
 177         'skip': 'No longer available',
 178     }, {
 179         # httpVideo, different content id
 180         'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html',
 181         'md5': '417660fffa90e6df2fda19f1b40a64d8',
 182         'info_dict': {
 183             'id': 'livestream283',
 184             'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-',
 185             'ext': 'mp3',
 186             'title': 'Das frueheste DJ Set des Nordens live mit Felix Jaehn',
 187             'description': 'md5:681698f527b8601e511e7b79edde7d2c',
 188             'uploader': 'njoy',
 189             'upload_date': '20210830',
 190         },
 191         'params': {
 192             'skip_download': True,
 193         },
 194     }, {
 195         'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
 196         'only_matching': True,
 197     }]
 198
 199     def _extract_embed(self, webpage, display_id, url=None):
 200         # find tell-tale URL with the actual ID, or ...
 201         video_id = self._search_regex(
 202             (r'''\bsrc\s*=\s*["']?(?:/\w+)+/([a-z]+\d+)(?!\.)\b''',
 203              r'<iframe[^>]+id="pp_([\da-z]+)"'),
 204             webpage, 'NDR id', default=None)
 205
 206         description = (
 207             self._html_search_meta('description', webpage)
 208             or self._search_regex(
 209                 r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
 210                 webpage, 'description', fatal=False))
 211         return {
 212             '_type': 'url_transparent',
 213             'ie_key': 'NDREmbedBase',
 214             'url': f'ndr:{video_id}',
 215             'display_id': display_id,
 216             'description': description,
 217             'title': display_id.replace('-', ' ').strip(),
 218         }
 219
 220
 221 class NDREmbedBaseIE(InfoExtractor):  # XXX: Conventionally, Concrete class names do not end in BaseIE
 222     IE_NAME = 'ndr:embed:base'
 223     _VALID_URL = r'(?:ndr:(?P<id_s>[\da-z]+)|https?://www\.ndr\.de/(?P<id>[\da-z]+)-ppjson\.json)'
 224     _TESTS = [{
 225         'url': 'ndr:soundcheck3366',
 226         'only_matching': True,
 227     }, {
 228         'url': 'http://www.ndr.de/soundcheck3366-ppjson.json',
 229         'only_matching': True,
 230     }]
 231
 232     def _real_extract(self, url):
 233         mobj = self._match_valid_url(url)
 234         video_id = mobj.group('id') or mobj.group('id_s')
 235
 236         ppjson = self._download_json(
 237             f'http://www.ndr.de/{video_id}-ppjson.json', video_id)
 238
 239         playlist = ppjson['playlist']
 240
 241         formats = []
 242         quality_key = qualities(('xs', 's', 'm', 'l', 'xl'))
 243
 244         for format_id, f in playlist.items():
 245             src = f.get('src')
 246             if not src:
 247                 continue
 248             ext = determine_ext(src, None)
 249             if ext == 'f4m':
 250                 formats.extend(self._extract_f4m_formats(
 251                     src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
 252                     f4m_id='hds', fatal=False))
 253             elif ext == 'm3u8':
 254                 formats.extend(self._extract_m3u8_formats(
 255                     src, video_id, 'mp4', m3u8_id='hls',
 256                     entry_protocol='m3u8_native', fatal=False))
 257             else:
 258                 quality = f.get('quality')
 259                 ff = {
 260                     'url': src,
 261                     'format_id': quality or format_id,
 262                     'quality': quality_key(quality),
 263                 }
 264                 type_ = f.get('type')
 265                 if type_ and type_.split('/')[0] == 'audio':
 266                     ff['vcodec'] = 'none'
 267                     ff['ext'] = ext or 'mp3'
 268                 formats.append(ff)
 269
 270         config = playlist['config']
 271
 272         live = playlist.get('config', {}).get('streamType') in ['httpVideoLive', 'httpAudioLive']
 273         title = config['title']
 274         uploader = ppjson.get('config', {}).get('branding')
 275         upload_date = ppjson.get('config', {}).get('publicationDate')
 276         duration = int_or_none(config.get('duration'))
 277
 278         thumbnails = []
 279         poster = try_get(config, lambda x: x['poster'], dict) or {}
 280         for thumbnail_id, thumbnail in poster.items():
 281             thumbnail_url = urljoin(url, thumbnail.get('src'))
 282             if not thumbnail_url:
 283                 continue
 284             thumbnails.append({
 285                 'id': thumbnail.get('quality') or thumbnail_id,
 286                 'url': thumbnail_url,
 287                 'preference': quality_key(thumbnail.get('quality')),
 288             })
 289
 290         subtitles = {}
 291         tracks = config.get('tracks')
 292         if tracks and isinstance(tracks, list):
 293             for track in tracks:
 294                 if not isinstance(track, dict):
 295                     continue
 296                 track_url = urljoin(url, track.get('src'))
 297                 if not track_url:
 298                     continue
 299                 subtitles.setdefault(track.get('srclang') or 'de', []).append({
 300                     'url': track_url,
 301                     'ext': 'ttml',
 302                 })
 303
 304         return {
 305             'id': video_id,
 306             'title': title,
 307             'is_live': live,
 308             'uploader': uploader if uploader != '-' else None,
 309             'upload_date': upload_date[0:8] if upload_date else None,
 310             'duration': duration,
 311             'thumbnails': thumbnails,
 312             'formats': formats,
 313             'subtitles': subtitles,
 314         }
 315
 316
 317 class NDREmbedIE(NDREmbedBaseIE):  # XXX: Do not subclass from concrete IE
 318     IE_NAME = 'ndr:embed'
 319     _VALID_URL = r'https?://(?:\w+\.)*ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:(?:ard)?player|externalPlayer)\.html'
 320     _TESTS = [{
 321         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
 322         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
 323         'info_dict': {
 324             'id': 'ndraktuell28488',
 325             'ext': 'mp4',
 326             'title': 'Norddeutschland begrüßt Flüchtlinge',
 327             'is_live': False,
 328             'uploader': 'ndrtv',
 329             'upload_date': '20150907',
 330             'duration': 132,
 331         },
 332         'skip': 'No longer available',
 333     }, {
 334         'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html',
 335         'md5': '002085c44bae38802d94ae5802a36e78',
 336         'info_dict': {
 337             'id': 'soundcheck3366',
 338             'ext': 'mp4',
 339             'title': 'Ella Henderson braucht Vergleiche nicht zu scheuen',
 340             'is_live': False,
 341             'uploader': 'ndr2',
 342             'upload_date': '20150912',
 343             'duration': 3554,
 344         },
 345         'params': {
 346             'skip_download': True,
 347         },
 348         'skip': 'No longer available',
 349     }, {
 350         'url': 'http://www.ndr.de/info/audio51535-player.html',
 351         'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
 352         'info_dict': {
 353             'id': 'audio51535',
 354             'ext': 'mp3',
 355             'title': 'La Valette entgeht der Hinrichtung',
 356             'is_live': False,
 357             'uploader': 'ndrinfo',
 358             'upload_date': '20210915',
 359             'duration': 884,
 360         },
 361         'params': {
 362             'skip_download': True,
 363         },
 364     }, {
 365         'url': 'http://www.ndr.de/fernsehen/sendungen/visite/visite11010-externalPlayer.html',
 366         'md5': 'ae57f80511c1e1f2fd0d0d3d31aeae7c',
 367         'info_dict': {
 368             'id': 'visite11010',
 369             'ext': 'mp4',
 370             'title': 'Visite - die ganze Sendung',
 371             'is_live': False,
 372             'uploader': 'ndrtv',
 373             'upload_date': '20150902',
 374             'duration': 3525,
 375         },
 376         'params': {
 377             'skip_download': True,
 378         },
 379         'skip': 'No longer available',
 380     }, {
 381         # httpVideoLive
 382         'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html',
 383         'info_dict': {
 384             'id': 'livestream217',
 385             'ext': 'mp4',
 386             'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 387             'is_live': True,
 388             'upload_date': '20210409',
 389             'uploader': 'ndrtv',
 390         },
 391         'params': {
 392             'skip_download': True,
 393         },
 394     }, {
 395         'url': 'http://www.ndr.de/ndrkultur/audio255020-player.html',
 396         'only_matching': True,
 397     }, {
 398         'url': 'http://www.ndr.de/fernsehen/sendungen/nordtour/nordtour7124-player.html',
 399         'only_matching': True,
 400     }, {
 401         'url': 'http://www.ndr.de/kultur/film/videos/videoimport10424-player.html',
 402         'only_matching': True,
 403     }, {
 404         'url': 'http://www.ndr.de/fernsehen/sendungen/hamburg_journal/hamj43006-player.html',
 405         'only_matching': True,
 406     }, {
 407         'url': 'http://www.ndr.de/fernsehen/sendungen/weltbilder/weltbilder4518-player.html',
 408         'only_matching': True,
 409     }, {
 410         'url': 'http://www.ndr.de/fernsehen/doku952-player.html',
 411         'only_matching': True,
 412     }]
 413
 414
 415 class NJoyEmbedIE(NDREmbedBaseIE):  # XXX: Do not subclass from concrete IE
 416     IE_NAME = 'njoy:embed'
 417     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
 418     _TESTS = [{
 419         # httpVideo
 420         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',
 421         'md5': '8483cbfe2320bd4d28a349d62d88bd74',
 422         'info_dict': {
 423             'id': 'doku948',
 424             'ext': 'mp4',
 425             'title': 'Zehn Jahre Reeperbahn Festival - die Doku',
 426             'is_live': False,
 427             'upload_date': '20200826',
 428             'duration': 1011,
 429         },
 430         'expected_warnings': ['Unable to download f4m manifest'],
 431     }, {
 432         # httpAudio
 433         'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html',
 434         'md5': 'd989f80f28ac954430f7b8a48197188a',
 435         'info_dict': {
 436             'id': 'stefanrichter100',
 437             'ext': 'mp3',
 438             'title': 'Interview mit einem Augenzeugen',
 439             'is_live': False,
 440             'uploader': 'njoy',
 441             'upload_date': '20150909',
 442             'duration': 140,
 443         },
 444         'params': {
 445             'skip_download': True,
 446         },
 447         'skip': 'No longer available',
 448     }, {
 449         # httpAudioLive, no explicit ext
 450         'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html',
 451         'info_dict': {
 452             'id': 'webradioweltweit100',
 453             'ext': 'mp3',
 454             'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 455             'is_live': True,
 456             'uploader': 'njoy',
 457             'upload_date': '20210830',
 458         },
 459         'params': {
 460             'skip_download': True,
 461         },
 462     }, {
 463         'url': 'http://www.n-joy.de/musik/dockville882-player_image-3905259e-0803-4764-ac72-8b7de077d80a_theme-n-joy.html',
 464         'only_matching': True,
 465     }, {
 466         'url': 'http://www.n-joy.de/radio/sendungen/morningshow/urlaubsfotos190-player_image-066a5df1-5c95-49ec-a323-941d848718db_theme-n-joy.html',
 467         'only_matching': True,
 468     }, {
 469         'url': 'http://www.n-joy.de/entertainment/comedy/krudetv290-player_image-ab261bfe-51bf-4bf3-87ba-c5122ee35b3d_theme-n-joy.html',
 470         'only_matching': True,
 471     }]