yt_dlp/extractor/orf.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     clean_html,
  10     determine_ext,
  11     float_or_none,
  12     HEADRequest,
  13     int_or_none,
  14     orderedSet,
  15     remove_end,
  16     str_or_none,
  17     strip_jsonp,
  18     unescapeHTML,
  19     unified_strdate,
  20     url_or_none,
  21 )
  22
  23
  24 class ORFTVthekIE(InfoExtractor):
  25     IE_NAME = 'orf:tvthek'
  26     IE_DESC = 'ORF TVthek'
  27     _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
  28
  29     _TESTS = [{
  30         'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
  31         'playlist': [{
  32             'md5': '2942210346ed779588f428a92db88712',
  33             'info_dict': {
  34                 'id': '8896777',
  35                 'ext': 'mp4',
  36                 'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
  37                 'description': 'md5:c1272f0245537812d4e36419c207b67d',
  38                 'duration': 2668,
  39                 'upload_date': '20141208',
  40             },
  41         }],
  42         'skip': 'Blocked outside of Austria / Germany',
  43     }, {
  44         'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
  45         'info_dict': {
  46             'id': '7982259',
  47             'ext': 'mp4',
  48             'title': 'Best of Ingrid Thurnher',
  49             'upload_date': '20140527',
  50             'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
  51         },
  52         'params': {
  53             'skip_download': True,  # rtsp downloads
  54         },
  55         'skip': 'Blocked outside of Austria / Germany',
  56     }, {
  57         'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
  58         'only_matching': True,
  59     }, {
  60         'url': 'http://tvthek.orf.at/profile/Universum/35429',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         playlist_id = self._match_id(url)
  66         webpage = self._download_webpage(url, playlist_id)
  67
  68         data_jsb = self._parse_json(
  69             self._search_regex(
  70                 r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
  71                 webpage, 'playlist', group='json'),
  72             playlist_id, transform_source=unescapeHTML)['playlist']['videos']
  73
  74         entries = []
  75         for sd in data_jsb:
  76             video_id, title = sd.get('id'), sd.get('title')
  77             if not video_id or not title:
  78                 continue
  79             video_id = compat_str(video_id)
  80             formats = []
  81             for fd in sd['sources']:
  82                 src = url_or_none(fd.get('src'))
  83                 if not src:
  84                     continue
  85                 format_id_list = []
  86                 for key in ('delivery', 'quality', 'quality_string'):
  87                     value = fd.get(key)
  88                     if value:
  89                         format_id_list.append(value)
  90                 format_id = '-'.join(format_id_list)
  91                 ext = determine_ext(src)
  92                 if ext == 'm3u8':
  93                     m3u8_formats = self._extract_m3u8_formats(
  94                         src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
  95                     if any('/geoprotection' in f['url'] for f in m3u8_formats):
  96                         self.raise_geo_restricted()
  97                     formats.extend(m3u8_formats)
  98                 elif ext == 'f4m':
  99                     formats.extend(self._extract_f4m_formats(
 100                         src, video_id, f4m_id=format_id, fatal=False))
 101                 elif ext == 'mpd':
 102                     formats.extend(self._extract_mpd_formats(
 103                         src, video_id, mpd_id=format_id, fatal=False))
 104                 else:
 105                     formats.append({
 106                         'format_id': format_id,
 107                         'url': src,
 108                         'protocol': fd.get('protocol'),
 109                     })
 110
 111             # Check for geoblocking.
 112             # There is a property is_geoprotection, but that's always false
 113             geo_str = sd.get('geoprotection_string')
 114             if geo_str:
 115                 try:
 116                     http_url = next(
 117                         f['url']
 118                         for f in formats
 119                         if re.match(r'^https?://.*\.mp4$', f['url']))
 120                 except StopIteration:
 121                     pass
 122                 else:
 123                     req = HEADRequest(http_url)
 124                     self._request_webpage(
 125                         req, video_id,
 126                         note='Testing for geoblocking',
 127                         errnote=((
 128                             'This video seems to be blocked outside of %s. '
 129                             'You may want to try the streaming-* formats.')
 130                             % geo_str),
 131                         fatal=False)
 132
 133             self._check_formats(formats, video_id)
 134             self._sort_formats(formats)
 135
 136             subtitles = {}
 137             for sub in sd.get('subtitles', []):
 138                 sub_src = sub.get('src')
 139                 if not sub_src:
 140                     continue
 141                 subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
 142                     'url': sub_src,
 143                 })
 144
 145             upload_date = unified_strdate(sd.get('created_date'))
 146
 147             thumbnails = []
 148             preview = sd.get('preview_image_url')
 149             if preview:
 150                 thumbnails.append({
 151                     'id': 'preview',
 152                     'url': preview,
 153                     'preference': 0,
 154                 })
 155             image = sd.get('image_full_url')
 156             if not image and len(data_jsb) == 1:
 157                 image = self._og_search_thumbnail(webpage)
 158             if image:
 159                 thumbnails.append({
 160                     'id': 'full',
 161                     'url': image,
 162                     'preference': 1,
 163                 })
 164
 165             entries.append({
 166                 '_type': 'video',
 167                 'id': video_id,
 168                 'title': title,
 169                 'formats': formats,
 170                 'subtitles': subtitles,
 171                 'description': sd.get('description'),
 172                 'duration': int_or_none(sd.get('duration_in_seconds')),
 173                 'upload_date': upload_date,
 174                 'thumbnails': thumbnails,
 175             })
 176
 177         return {
 178             '_type': 'playlist',
 179             'entries': entries,
 180             'id': playlist_id,
 181         }
 182
 183
 184 class ORFRadioIE(InfoExtractor):
 185     def _real_extract(self, url):
 186         mobj = self._match_valid_url(url)
 187         show_date = mobj.group('date')
 188         show_id = mobj.group('show')
 189
 190         data = self._download_json(
 191             'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
 192             % (self._API_STATION, show_id, show_date), show_id)
 193
 194         entries = []
 195         for info in data['streams']:
 196             loop_stream_id = str_or_none(info.get('loopStreamId'))
 197             if not loop_stream_id:
 198                 continue
 199             title = str_or_none(data.get('title'))
 200             if not title:
 201                 continue
 202             start = int_or_none(info.get('start'), scale=1000)
 203             end = int_or_none(info.get('end'), scale=1000)
 204             duration = end - start if end and start else None
 205             entries.append({
 206                 'id': loop_stream_id.replace('.mp3', ''),
 207                 'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
 208                 'title': title,
 209                 'description': clean_html(data.get('subtitle')),
 210                 'duration': duration,
 211                 'timestamp': start,
 212                 'ext': 'mp3',
 213                 'series': data.get('programTitle'),
 214             })
 215
 216         return {
 217             '_type': 'playlist',
 218             'id': show_id,
 219             'title': data.get('title'),
 220             'description': clean_html(data.get('subtitle')),
 221             'entries': entries,
 222         }
 223
 224
 225 class ORFFM4IE(ORFRadioIE):
 226     IE_NAME = 'orf:fm4'
 227     IE_DESC = 'radio FM4'
 228     _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
 229     _API_STATION = 'fm4'
 230     _LOOP_STATION = 'fm4'
 231
 232     _TEST = {
 233         'url': 'http://fm4.orf.at/player/20170107/4CC',
 234         'md5': '2b0be47375432a7ef104453432a19212',
 235         'info_dict': {
 236             'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
 237             'ext': 'mp3',
 238             'title': 'Solid Steel Radioshow',
 239             'description': 'Die Mixshow von Coldcut und Ninja Tune.',
 240             'duration': 3599,
 241             'timestamp': 1483819257,
 242             'upload_date': '20170107',
 243         },
 244         'skip': 'Shows from ORF radios are only available for 7 days.',
 245         'only_matching': True,
 246     }
 247
 248
 249 class ORFNOEIE(ORFRadioIE):
 250     IE_NAME = 'orf:noe'
 251     IE_DESC = 'Radio Niederösterreich'
 252     _VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 253     _API_STATION = 'noe'
 254     _LOOP_STATION = 'oe2n'
 255
 256     _TEST = {
 257         'url': 'https://noe.orf.at/player/20200423/NGM',
 258         'only_matching': True,
 259     }
 260
 261
 262 class ORFWIEIE(ORFRadioIE):
 263     IE_NAME = 'orf:wien'
 264     IE_DESC = 'Radio Wien'
 265     _VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 266     _API_STATION = 'wie'
 267     _LOOP_STATION = 'oe2w'
 268
 269     _TEST = {
 270         'url': 'https://wien.orf.at/player/20200423/WGUM',
 271         'only_matching': True,
 272     }
 273
 274
 275 class ORFBGLIE(ORFRadioIE):
 276     IE_NAME = 'orf:burgenland'
 277     IE_DESC = 'Radio Burgenland'
 278     _VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 279     _API_STATION = 'bgl'
 280     _LOOP_STATION = 'oe2b'
 281
 282     _TEST = {
 283         'url': 'https://burgenland.orf.at/player/20200423/BGM',
 284         'only_matching': True,
 285     }
 286
 287
 288 class ORFOOEIE(ORFRadioIE):
 289     IE_NAME = 'orf:oberoesterreich'
 290     IE_DESC = 'Radio Oberösterreich'
 291     _VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 292     _API_STATION = 'ooe'
 293     _LOOP_STATION = 'oe2o'
 294
 295     _TEST = {
 296         'url': 'https://ooe.orf.at/player/20200423/OGMO',
 297         'only_matching': True,
 298     }
 299
 300
 301 class ORFSTMIE(ORFRadioIE):
 302     IE_NAME = 'orf:steiermark'
 303     IE_DESC = 'Radio Steiermark'
 304     _VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 305     _API_STATION = 'stm'
 306     _LOOP_STATION = 'oe2st'
 307
 308     _TEST = {
 309         'url': 'https://steiermark.orf.at/player/20200423/STGMS',
 310         'only_matching': True,
 311     }
 312
 313
 314 class ORFKTNIE(ORFRadioIE):
 315     IE_NAME = 'orf:kaernten'
 316     IE_DESC = 'Radio Kärnten'
 317     _VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 318     _API_STATION = 'ktn'
 319     _LOOP_STATION = 'oe2k'
 320
 321     _TEST = {
 322         'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
 323         'only_matching': True,
 324     }
 325
 326
 327 class ORFSBGIE(ORFRadioIE):
 328     IE_NAME = 'orf:salzburg'
 329     IE_DESC = 'Radio Salzburg'
 330     _VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 331     _API_STATION = 'sbg'
 332     _LOOP_STATION = 'oe2s'
 333
 334     _TEST = {
 335         'url': 'https://salzburg.orf.at/player/20200423/SGUM',
 336         'only_matching': True,
 337     }
 338
 339
 340 class ORFTIRIE(ORFRadioIE):
 341     IE_NAME = 'orf:tirol'
 342     IE_DESC = 'Radio Tirol'
 343     _VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 344     _API_STATION = 'tir'
 345     _LOOP_STATION = 'oe2t'
 346
 347     _TEST = {
 348         'url': 'https://tirol.orf.at/player/20200423/TGUMO',
 349         'only_matching': True,
 350     }
 351
 352
 353 class ORFVBGIE(ORFRadioIE):
 354     IE_NAME = 'orf:vorarlberg'
 355     IE_DESC = 'Radio Vorarlberg'
 356     _VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 357     _API_STATION = 'vbg'
 358     _LOOP_STATION = 'oe2v'
 359
 360     _TEST = {
 361         'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
 362         'only_matching': True,
 363     }
 364
 365
 366 class ORFOE3IE(ORFRadioIE):
 367     IE_NAME = 'orf:oe3'
 368     IE_DESC = 'Radio Österreich 3'
 369     _VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 370     _API_STATION = 'oe3'
 371     _LOOP_STATION = 'oe3'
 372
 373     _TEST = {
 374         'url': 'https://oe3.orf.at/player/20200424/3WEK',
 375         'only_matching': True,
 376     }
 377
 378
 379 class ORFOE1IE(ORFRadioIE):
 380     IE_NAME = 'orf:oe1'
 381     IE_DESC = 'Radio Österreich 1'
 382     _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
 383     _API_STATION = 'oe1'
 384     _LOOP_STATION = 'oe1'
 385
 386     _TEST = {
 387         'url': 'http://oe1.orf.at/player/20170108/456544',
 388         'md5': '34d8a6e67ea888293741c86a099b745b',
 389         'info_dict': {
 390             'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
 391             'ext': 'mp3',
 392             'title': 'Morgenjournal',
 393             'duration': 609,
 394             'timestamp': 1483858796,
 395             'upload_date': '20170108',
 396         },
 397         'skip': 'Shows from ORF radios are only available for 7 days.'
 398     }
 399
 400
 401 class ORFIPTVIE(InfoExtractor):
 402     IE_NAME = 'orf:iptv'
 403     IE_DESC = 'iptv.ORF.at'
 404     _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
 405
 406     _TEST = {
 407         'url': 'http://iptv.orf.at/stories/2275236/',
 408         'md5': 'c8b22af4718a4b4af58342529453e3e5',
 409         'info_dict': {
 410             'id': '350612',
 411             'ext': 'flv',
 412             'title': 'Weitere Evakuierungen um Vulkan Calbuco',
 413             'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
 414             'duration': 68.197,
 415             'thumbnail': r're:^https?://.*\.jpg$',
 416             'upload_date': '20150425',
 417         },
 418     }
 419
 420     def _real_extract(self, url):
 421         story_id = self._match_id(url)
 422
 423         webpage = self._download_webpage(
 424             'http://iptv.orf.at/stories/%s' % story_id, story_id)
 425
 426         video_id = self._search_regex(
 427             r'data-video(?:id)?="(\d+)"', webpage, 'video id')
 428
 429         data = self._download_json(
 430             'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
 431             video_id)[0]
 432
 433         duration = float_or_none(data['duration'], 1000)
 434
 435         video = data['sources']['default']
 436         load_balancer_url = video['loadBalancerUrl']
 437         abr = int_or_none(video.get('audioBitrate'))
 438         vbr = int_or_none(video.get('bitrate'))
 439         fps = int_or_none(video.get('videoFps'))
 440         width = int_or_none(video.get('videoWidth'))
 441         height = int_or_none(video.get('videoHeight'))
 442         thumbnail = video.get('preview')
 443
 444         rendition = self._download_json(
 445             load_balancer_url, video_id, transform_source=strip_jsonp)
 446
 447         f = {
 448             'abr': abr,
 449             'vbr': vbr,
 450             'fps': fps,
 451             'width': width,
 452             'height': height,
 453         }
 454
 455         formats = []
 456         for format_id, format_url in rendition['redirect'].items():
 457             if format_id == 'rtmp':
 458                 ff = f.copy()
 459                 ff.update({
 460                     'url': format_url,
 461                     'format_id': format_id,
 462                 })
 463                 formats.append(ff)
 464             elif determine_ext(format_url) == 'f4m':
 465                 formats.extend(self._extract_f4m_formats(
 466                     format_url, video_id, f4m_id=format_id))
 467             elif determine_ext(format_url) == 'm3u8':
 468                 formats.extend(self._extract_m3u8_formats(
 469                     format_url, video_id, 'mp4', m3u8_id=format_id))
 470             else:
 471                 continue
 472         self._sort_formats(formats)
 473
 474         title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
 475         description = self._og_search_description(webpage)
 476         upload_date = unified_strdate(self._html_search_meta(
 477             'dc.date', webpage, 'upload date'))
 478
 479         return {
 480             'id': video_id,
 481             'title': title,
 482             'description': description,
 483             'duration': duration,
 484             'thumbnail': thumbnail,
 485             'upload_date': upload_date,
 486             'formats': formats,
 487         }
 488
 489
 490 class ORFFM4StoryIE(InfoExtractor):
 491     IE_NAME = 'orf:fm4:story'
 492     IE_DESC = 'fm4.orf.at stories'
 493     _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
 494
 495     _TEST = {
 496         'url': 'http://fm4.orf.at/stories/2865738/',
 497         'playlist': [{
 498             'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
 499             'info_dict': {
 500                 'id': '547792',
 501                 'ext': 'flv',
 502                 'title': 'Manu Delago und Inner Tongue live',
 503                 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
 504                 'duration': 1748.52,
 505                 'thumbnail': r're:^https?://.*\.jpg$',
 506                 'upload_date': '20170913',
 507             },
 508         }, {
 509             'md5': 'c6dd2179731f86f4f55a7b49899d515f',
 510             'info_dict': {
 511                 'id': '547798',
 512                 'ext': 'flv',
 513                 'title': 'Manu Delago und Inner Tongue live (2)',
 514                 'duration': 1504.08,
 515                 'thumbnail': r're:^https?://.*\.jpg$',
 516                 'upload_date': '20170913',
 517                 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
 518             },
 519         }],
 520     }
 521
 522     def _real_extract(self, url):
 523         story_id = self._match_id(url)
 524         webpage = self._download_webpage(url, story_id)
 525
 526         entries = []
 527         all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
 528         for idx, video_id in enumerate(all_ids):
 529             data = self._download_json(
 530                 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
 531                 video_id)[0]
 532
 533             duration = float_or_none(data['duration'], 1000)
 534
 535             video = data['sources']['q8c']
 536             load_balancer_url = video['loadBalancerUrl']
 537             abr = int_or_none(video.get('audioBitrate'))
 538             vbr = int_or_none(video.get('bitrate'))
 539             fps = int_or_none(video.get('videoFps'))
 540             width = int_or_none(video.get('videoWidth'))
 541             height = int_or_none(video.get('videoHeight'))
 542             thumbnail = video.get('preview')
 543
 544             rendition = self._download_json(
 545                 load_balancer_url, video_id, transform_source=strip_jsonp)
 546
 547             f = {
 548                 'abr': abr,
 549                 'vbr': vbr,
 550                 'fps': fps,
 551                 'width': width,
 552                 'height': height,
 553             }
 554
 555             formats = []
 556             for format_id, format_url in rendition['redirect'].items():
 557                 if format_id == 'rtmp':
 558                     ff = f.copy()
 559                     ff.update({
 560                         'url': format_url,
 561                         'format_id': format_id,
 562                     })
 563                     formats.append(ff)
 564                 elif determine_ext(format_url) == 'f4m':
 565                     formats.extend(self._extract_f4m_formats(
 566                         format_url, video_id, f4m_id=format_id))
 567                 elif determine_ext(format_url) == 'm3u8':
 568                     formats.extend(self._extract_m3u8_formats(
 569                         format_url, video_id, 'mp4', m3u8_id=format_id))
 570                 else:
 571                     continue
 572             self._sort_formats(formats)
 573
 574             title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
 575             if idx >= 1:
 576                 # Titles are duplicates, make them unique
 577                 title += ' (' + str(idx + 1) + ')'
 578             description = self._og_search_description(webpage)
 579             upload_date = unified_strdate(self._html_search_meta(
 580                 'dc.date', webpage, 'upload date'))
 581
 582             entries.append({
 583                 'id': video_id,
 584                 'title': title,
 585                 'description': description,
 586                 'duration': duration,
 587                 'thumbnail': thumbnail,
 588                 'upload_date': upload_date,
 589                 'formats': formats,
 590             })
 591
 592         return self.playlist_result(entries)