yt_dlp/extractor/ndr.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     parse_duration,
   9     qualities,
  10     try_get,
  11     unified_strdate,
  12     urljoin,
  13 )
  14
  15
  16 class NDRBaseIE(InfoExtractor):
  17     def _real_extract(self, url):
  18         mobj = self._match_valid_url(url)
  19         display_id = next(group for group in mobj.groups() if group)
  20         id = mobj.group('id')
  21         webpage = self._download_webpage(url, display_id)
  22         return self._extract_embed(webpage, display_id, id)
  23
  24
  25 class NDRIE(NDRBaseIE):
  26     IE_NAME = 'ndr'
  27     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
  28     _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<display_id>[^/?#]+),(?P<id>[\da-z]+)\.html'
  29     _TESTS = [{
  30         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
  31         'info_dict': {
  32             'id': 'hafengeburtstag988',
  33             'ext': 'mp4',
  34             'title': 'Party, Pötte und Parade',
  35             'thumbnail': 'https://www.ndr.de/fernsehen/hafengeburtstag990_v-contentxl.jpg',
  36             'description': 'md5:ad14f9d2f91d3040b6930c697e5f6b4c',
  37             'series': None,
  38             'channel': 'NDR Fernsehen',
  39             'upload_date': '20150508',
  40             'duration': 3498,
  41         },
  42     }, {
  43         'url': 'https://www.ndr.de/sport/fussball/Rostocks-Matchwinner-Froede-Ein-Hansa-Debuet-wie-im-Maerchen,hansa10312.html',
  44         'only_matching': True
  45     }, {
  46         'url': 'https://www.ndr.de/nachrichten/niedersachsen/kommunalwahl_niedersachsen_2021/Grosse-Parteien-zufrieden-mit-Ergebnissen-der-Kommunalwahl,kommunalwahl1296.html',
  47         'info_dict': {
  48             'id': 'kommunalwahl1296',
  49             'ext': 'mp4',
  50             'title': 'Die Spitzenrunde: Die Wahl aus Sicht der Landespolitik',
  51             'thumbnail': 'https://www.ndr.de/fernsehen/screenshot1194912_v-contentxl.jpg',
  52             'description': 'md5:5c6e2ad744cef499135735a1036d7aa7',
  53             'series': 'Hallo Niedersachsen',
  54             'channel': 'NDR Fernsehen',
  55             'upload_date': '20210913',
  56             'duration': 438,
  57         },
  58     }, {
  59         'url': 'https://www.ndr.de/fernsehen/sendungen/extra_3/extra-3-Satiremagazin-mit-Christian-Ehring,sendung1091858.html',
  60         'info_dict': {
  61             'id': 'sendung1091858',
  62             'ext': 'mp4',
  63             'title': 'Extra 3 vom 11.11.2020 mit Christian Ehring',
  64             'thumbnail': 'https://www.ndr.de/fernsehen/screenshot983938_v-contentxl.jpg',
  65             'description': 'md5:700f6de264010585012a72f97b0ac0c9',
  66             'series': 'extra 3',
  67             'channel': 'NDR Fernsehen',
  68             'upload_date': '20201111',
  69             'duration': 1749,
  70         }
  71     }, {
  72         'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
  73         'info_dict': {
  74             'id': 'audio51535',
  75             'ext': 'mp3',
  76             'title': 'La Valette entgeht der Hinrichtung',
  77             'thumbnail': 'https://www.ndr.de/mediathek/mediathekbild140_v-podcast.jpg',
  78             'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
  79             'upload_date': '20140729',
  80             'duration': 884.0,
  81         },
  82         'expected_warnings': ['unable to extract json url'],
  83     }]
  84
  85     def _extract_embed(self, webpage, display_id, id):
  86         formats = []
  87         base_url = 'https://www.ndr.de'
  88         json_url = self._search_regex(r'<iframe[^>]+src=\"([^\"]+)_theme-ndrde[^\.]*\.html\"', webpage,
  89                                       'json url', fatal=False)
  90         if json_url:
  91             data_json = self._download_json(base_url + json_url.replace('ardplayer_image', 'ardjson_image') + '.json',
  92                                             id, fatal=False)
  93             info_json = data_json.get('_info', {})
  94             media_json = try_get(data_json, lambda x: x['_mediaArray'][0]['_mediaStreamArray'])
  95             for media in media_json:
  96                 if media.get('_quality') == 'auto':
  97                     formats.extend(self._extract_m3u8_formats(media['_stream'], id))
  98             subtitles = {}
  99             sub_url = data_json.get('_subtitleUrl')
 100             if sub_url:
 101                 subtitles.setdefault('de', []).append({
 102                     'url': base_url + sub_url,
 103                 })
 104             self._sort_formats(formats)
 105             return {
 106                 'id': id,
 107                 'title': info_json.get('clipTitle'),
 108                 'thumbnail': base_url + data_json.get('_previewImage'),
 109                 'description': info_json.get('clipDescription'),
 110                 'series': info_json.get('seriesTitle') or None,
 111                 'channel': info_json.get('channelTitle'),
 112                 'upload_date': unified_strdate(info_json.get('clipDate')),
 113                 'duration': data_json.get('_duration'),
 114                 'formats': formats,
 115                 'subtitles': subtitles,
 116             }
 117         else:
 118             json_url = base_url + self._search_regex(r'apiUrl\s?=\s?\'([^\']+)\'', webpage, 'json url').replace(
 119                 '_belongsToPodcast-', '')
 120             data_json = self._download_json(json_url, id, fatal=False)
 121             return {
 122                 'id': id,
 123                 'title': data_json.get('title'),
 124                 'thumbnail': base_url + data_json.get('poster'),
 125                 'description': data_json.get('summary'),
 126                 'upload_date': unified_strdate(data_json.get('publicationDate')),
 127                 'duration': parse_duration(data_json.get('duration')),
 128                 'formats': [{
 129                     'url': try_get(data_json, (lambda x: x['audio'][0]['url'], lambda x: x['files'][0]['url'])),
 130                     'vcodec': 'none',
 131                     'ext': 'mp3',
 132                 }],
 133             }
 134
 135
 136 class NJoyIE(NDRBaseIE):
 137     IE_NAME = 'njoy'
 138     IE_DESC = 'N-JOY'
 139     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
 140     _TESTS = [{
 141         # httpVideo, same content id
 142         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
 143         'md5': 'cb63be60cd6f9dd75218803146d8dc67',
 144         'info_dict': {
 145             'id': 'comedycontest2480',
 146             'display_id': 'Benaissa-beim-NDR-Comedy-Contest',
 147             'ext': 'mp4',
 148             'title': 'Benaissa beim NDR Comedy Contest',
 149             'description': 'md5:f057a6c4e1c728b10d33b5ffd36ddc39',
 150             'uploader': 'ndrtv',
 151             'upload_date': '20141129',
 152             'duration': 654,
 153         },
 154         'params': {
 155             'skip_download': True,
 156         },
 157     }, {
 158         # httpVideo, different content id
 159         'url': 'http://www.n-joy.de/musik/Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-,felixjaehn168.html',
 160         'md5': '417660fffa90e6df2fda19f1b40a64d8',
 161         'info_dict': {
 162             'id': 'dockville882',
 163             'display_id': 'Das-frueheste-DJ-Set-des-Nordens-live-mit-Felix-Jaehn-',
 164             'ext': 'mp4',
 165             'title': '"Ich hab noch nie" mit Felix Jaehn',
 166             'description': 'md5:85dd312d53be1b99e1f998a16452a2f3',
 167             'uploader': 'njoy',
 168             'upload_date': '20150822',
 169             'duration': 211,
 170         },
 171         'params': {
 172             'skip_download': True,
 173         },
 174     }, {
 175         'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
 176         'only_matching': True,
 177     }]
 178
 179     def _extract_embed(self, webpage, display_id, id):
 180         video_id = self._search_regex(
 181             r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id')
 182         description = self._search_regex(
 183             r'<div[^>]+class="subline"[^>]*>[^<]+</div>\s*<p>([^<]+)</p>',
 184             webpage, 'description', fatal=False)
 185         return {
 186             '_type': 'url_transparent',
 187             'ie_key': 'NDREmbedBase',
 188             'url': 'ndr:%s' % video_id,
 189             'display_id': display_id,
 190             'description': description,
 191         }
 192
 193
 194 class NDREmbedBaseIE(InfoExtractor):
 195     IE_NAME = 'ndr:embed:base'
 196     _VALID_URL = r'(?:ndr:(?P<id_s>[\da-z]+)|https?://www\.ndr\.de/(?P<id>[\da-z]+)-ppjson\.json)'
 197     _TESTS = [{
 198         'url': 'ndr:soundcheck3366',
 199         'only_matching': True,
 200     }, {
 201         'url': 'http://www.ndr.de/soundcheck3366-ppjson.json',
 202         'only_matching': True,
 203     }]
 204
 205     def _real_extract(self, url):
 206         mobj = self._match_valid_url(url)
 207         video_id = mobj.group('id') or mobj.group('id_s')
 208
 209         ppjson = self._download_json(
 210             'http://www.ndr.de/%s-ppjson.json' % video_id, video_id)
 211
 212         playlist = ppjson['playlist']
 213
 214         formats = []
 215         quality_key = qualities(('xs', 's', 'm', 'l', 'xl'))
 216
 217         for format_id, f in playlist.items():
 218             src = f.get('src')
 219             if not src:
 220                 continue
 221             ext = determine_ext(src, None)
 222             if ext == 'f4m':
 223                 formats.extend(self._extract_f4m_formats(
 224                     src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
 225                     f4m_id='hds', fatal=False))
 226             elif ext == 'm3u8':
 227                 formats.extend(self._extract_m3u8_formats(
 228                     src, video_id, 'mp4', m3u8_id='hls',
 229                     entry_protocol='m3u8_native', fatal=False))
 230             else:
 231                 quality = f.get('quality')
 232                 ff = {
 233                     'url': src,
 234                     'format_id': quality or format_id,
 235                     'quality': quality_key(quality),
 236                 }
 237                 type_ = f.get('type')
 238                 if type_ and type_.split('/')[0] == 'audio':
 239                     ff['vcodec'] = 'none'
 240                     ff['ext'] = ext or 'mp3'
 241                 formats.append(ff)
 242         self._sort_formats(formats)
 243
 244         config = playlist['config']
 245
 246         live = playlist.get('config', {}).get('streamType') in ['httpVideoLive', 'httpAudioLive']
 247         title = config['title']
 248         uploader = ppjson.get('config', {}).get('branding')
 249         upload_date = ppjson.get('config', {}).get('publicationDate')
 250         duration = int_or_none(config.get('duration'))
 251
 252         thumbnails = []
 253         poster = try_get(config, lambda x: x['poster'], dict) or {}
 254         for thumbnail_id, thumbnail in poster.items():
 255             thumbnail_url = urljoin(url, thumbnail.get('src'))
 256             if not thumbnail_url:
 257                 continue
 258             thumbnails.append({
 259                 'id': thumbnail.get('quality') or thumbnail_id,
 260                 'url': thumbnail_url,
 261                 'preference': quality_key(thumbnail.get('quality')),
 262             })
 263
 264         subtitles = {}
 265         tracks = config.get('tracks')
 266         if tracks and isinstance(tracks, list):
 267             for track in tracks:
 268                 if not isinstance(track, dict):
 269                     continue
 270                 track_url = urljoin(url, track.get('src'))
 271                 if not track_url:
 272                     continue
 273                 subtitles.setdefault(track.get('srclang') or 'de', []).append({
 274                     'url': track_url,
 275                     'ext': 'ttml',
 276                 })
 277
 278         return {
 279             'id': video_id,
 280             'title': title,
 281             'is_live': live,
 282             'uploader': uploader if uploader != '-' else None,
 283             'upload_date': upload_date[0:8] if upload_date else None,
 284             'duration': duration,
 285             'thumbnails': thumbnails,
 286             'formats': formats,
 287             'subtitles': subtitles,
 288         }
 289
 290
 291 class NDREmbedIE(NDREmbedBaseIE):
 292     IE_NAME = 'ndr:embed'
 293     _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
 294     _TESTS = [{
 295         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
 296         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
 297         'info_dict': {
 298             'id': 'ndraktuell28488',
 299             'ext': 'mp4',
 300             'title': 'Norddeutschland begrüßt Flüchtlinge',
 301             'is_live': False,
 302             'uploader': 'ndrtv',
 303             'upload_date': '20150907',
 304             'duration': 132,
 305         },
 306     }, {
 307         'url': 'http://www.ndr.de/ndr2/events/soundcheck/soundcheck3366-player.html',
 308         'md5': '002085c44bae38802d94ae5802a36e78',
 309         'info_dict': {
 310             'id': 'soundcheck3366',
 311             'ext': 'mp4',
 312             'title': 'Ella Henderson braucht Vergleiche nicht zu scheuen',
 313             'is_live': False,
 314             'uploader': 'ndr2',
 315             'upload_date': '20150912',
 316             'duration': 3554,
 317         },
 318         'params': {
 319             'skip_download': True,
 320         },
 321     }, {
 322         'url': 'http://www.ndr.de/info/audio51535-player.html',
 323         'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
 324         'info_dict': {
 325             'id': 'audio51535',
 326             'ext': 'mp3',
 327             'title': 'La Valette entgeht der Hinrichtung',
 328             'is_live': False,
 329             'uploader': 'ndrinfo',
 330             'upload_date': '20140729',
 331             'duration': 884,
 332         },
 333         'params': {
 334             'skip_download': True,
 335         },
 336     }, {
 337         'url': 'http://www.ndr.de/fernsehen/sendungen/visite/visite11010-externalPlayer.html',
 338         'md5': 'ae57f80511c1e1f2fd0d0d3d31aeae7c',
 339         'info_dict': {
 340             'id': 'visite11010',
 341             'ext': 'mp4',
 342             'title': 'Visite - die ganze Sendung',
 343             'is_live': False,
 344             'uploader': 'ndrtv',
 345             'upload_date': '20150902',
 346             'duration': 3525,
 347         },
 348         'params': {
 349             'skip_download': True,
 350         },
 351     }, {
 352         # httpVideoLive
 353         'url': 'http://www.ndr.de/fernsehen/livestream/livestream217-externalPlayer.html',
 354         'info_dict': {
 355             'id': 'livestream217',
 356             'ext': 'flv',
 357             'title': r're:^NDR Fernsehen Niedersachsen \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 358             'is_live': True,
 359             'upload_date': '20150910',
 360         },
 361         'params': {
 362             'skip_download': True,
 363         },
 364     }, {
 365         'url': 'http://www.ndr.de/ndrkultur/audio255020-player.html',
 366         'only_matching': True,
 367     }, {
 368         'url': 'http://www.ndr.de/fernsehen/sendungen/nordtour/nordtour7124-player.html',
 369         'only_matching': True,
 370     }, {
 371         'url': 'http://www.ndr.de/kultur/film/videos/videoimport10424-player.html',
 372         'only_matching': True,
 373     }, {
 374         'url': 'http://www.ndr.de/fernsehen/sendungen/hamburg_journal/hamj43006-player.html',
 375         'only_matching': True,
 376     }, {
 377         'url': 'http://www.ndr.de/fernsehen/sendungen/weltbilder/weltbilder4518-player.html',
 378         'only_matching': True,
 379     }, {
 380         'url': 'http://www.ndr.de/fernsehen/doku952-player.html',
 381         'only_matching': True,
 382     }]
 383
 384
 385 class NJoyEmbedIE(NDREmbedBaseIE):
 386     IE_NAME = 'njoy:embed'
 387     _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
 388     _TESTS = [{
 389         # httpVideo
 390         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',
 391         'md5': '8483cbfe2320bd4d28a349d62d88bd74',
 392         'info_dict': {
 393             'id': 'doku948',
 394             'ext': 'mp4',
 395             'title': 'Zehn Jahre Reeperbahn Festival - die Doku',
 396             'is_live': False,
 397             'upload_date': '20150807',
 398             'duration': 1011,
 399         },
 400     }, {
 401         # httpAudio
 402         'url': 'http://www.n-joy.de/news_wissen/stefanrichter100-player_image-d5e938b1-f21a-4b9a-86b8-aaba8bca3a13_theme-n-joy.html',
 403         'md5': 'd989f80f28ac954430f7b8a48197188a',
 404         'info_dict': {
 405             'id': 'stefanrichter100',
 406             'ext': 'mp3',
 407             'title': 'Interview mit einem Augenzeugen',
 408             'is_live': False,
 409             'uploader': 'njoy',
 410             'upload_date': '20150909',
 411             'duration': 140,
 412         },
 413         'params': {
 414             'skip_download': True,
 415         },
 416     }, {
 417         # httpAudioLive, no explicit ext
 418         'url': 'http://www.n-joy.de/news_wissen/webradioweltweit100-player_image-3fec0484-2244-4565-8fb8-ed25fd28b173_theme-n-joy.html',
 419         'info_dict': {
 420             'id': 'webradioweltweit100',
 421             'ext': 'mp3',
 422             'title': r're:^N-JOY Weltweit \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
 423             'is_live': True,
 424             'uploader': 'njoy',
 425             'upload_date': '20150810',
 426         },
 427         'params': {
 428             'skip_download': True,
 429         },
 430     }, {
 431         'url': 'http://www.n-joy.de/musik/dockville882-player_image-3905259e-0803-4764-ac72-8b7de077d80a_theme-n-joy.html',
 432         'only_matching': True,
 433     }, {
 434         'url': 'http://www.n-joy.de/radio/sendungen/morningshow/urlaubsfotos190-player_image-066a5df1-5c95-49ec-a323-941d848718db_theme-n-joy.html',
 435         'only_matching': True,
 436     }, {
 437         'url': 'http://www.n-joy.de/entertainment/comedy/krudetv290-player_image-ab261bfe-51bf-4bf3-87ba-c5122ee35b3d_theme-n-joy.html',
 438         'only_matching': True,
 439     }]