yt_dlp/extractor/rai.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 (
   8     compat_str,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     ExtractorError,
  14     find_xpath_attr,
  15     fix_xml_ampersands,
  16     GeoRestrictedError,
  17     get_element_by_class,
  18     HEADRequest,
  19     int_or_none,
  20     parse_duration,
  21     parse_list,
  22     remove_start,
  23     strip_or_none,
  24     try_get,
  25     unescapeHTML,
  26     unified_strdate,
  27     unified_timestamp,
  28     update_url_query,
  29     urljoin,
  30     xpath_text,
  31 )
  32
  33
  34 class RaiBaseIE(InfoExtractor):
  35     _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
  36     _GEO_COUNTRIES = ['IT']
  37     _GEO_BYPASS = False
  38
  39     def _extract_relinker_info(self, relinker_url, video_id):
  40         if not re.match(r'https?://', relinker_url):
  41             return {'formats': [{'url': relinker_url}]}
  42
  43         formats = []
  44         geoprotection = None
  45         is_live = None
  46         duration = None
  47
  48         for platform in ('mon', 'flash', 'native'):
  49             relinker = self._download_xml(
  50                 relinker_url, video_id,
  51                 note='Downloading XML metadata for platform %s' % platform,
  52                 transform_source=fix_xml_ampersands,
  53                 query={'output': 45, 'pl': platform},
  54                 headers=self.geo_verification_headers())
  55
  56             if not geoprotection:
  57                 geoprotection = xpath_text(
  58                     relinker, './geoprotection', default=None) == 'Y'
  59
  60             if not is_live:
  61                 is_live = xpath_text(
  62                     relinker, './is_live', default=None) == 'Y'
  63             if not duration:
  64                 duration = parse_duration(xpath_text(
  65                     relinker, './duration', default=None))
  66
  67             url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
  68             if url_elem is None:
  69                 continue
  70
  71             media_url = url_elem.text
  72
  73             # This does not imply geo restriction (e.g.
  74             # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
  75             if '/video_no_available.mp4' in media_url:
  76                 continue
  77
  78             ext = determine_ext(media_url)
  79             if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
  80                 continue
  81
  82             if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
  83                 formats.extend(self._extract_m3u8_formats(
  84                     media_url, video_id, 'mp4', 'm3u8_native',
  85                     m3u8_id='hls', fatal=False))
  86             elif ext == 'f4m' or platform == 'flash':
  87                 manifest_url = update_url_query(
  88                     media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'),
  89                     {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})
  90                 formats.extend(self._extract_f4m_formats(
  91                     manifest_url, video_id, f4m_id='hds', fatal=False))
  92             else:
  93                 bitrate = int_or_none(xpath_text(relinker, 'bitrate'))
  94                 formats.append({
  95                     'url': media_url,
  96                     'tbr': bitrate if bitrate > 0 else None,
  97                     'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
  98                 })
  99
 100         if not formats and geoprotection is True:
 101             self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
 102
 103         formats.extend(self._create_http_urls(relinker_url, formats))
 104
 105         return dict((k, v) for k, v in {
 106             'is_live': is_live,
 107             'duration': duration,
 108             'formats': formats,
 109         }.items() if v is not None)
 110
 111     def _create_http_urls(self, relinker_url, fmts):
 112         _RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\d+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
 113         _MP4_TMPL = '%s&overrideUserAgentRule=mp4-%s'
 114         _QUALITY = {
 115             # tbr: w, h
 116             '250': [352, 198],
 117             '400': [512, 288],
 118             '700': [512, 288],
 119             '800': [700, 394],
 120             '1200': [736, 414],
 121             '1800': [1024, 576],
 122             '2400': [1280, 720],
 123             '3200': [1440, 810],
 124             '3600': [1440, 810],
 125             '5000': [1920, 1080],
 126             '10000': [1920, 1080],
 127         }
 128
 129         def test_url(url):
 130             resp = self._request_webpage(
 131                 HEADRequest(url), None, headers={'User-Agent': 'Rai'},
 132                 fatal=False, errnote=False, note=False)
 133
 134             if resp is False:
 135                 return False
 136
 137             if resp.code == 200:
 138                 return False if resp.url == url else resp.url
 139             return None
 140
 141         def get_format_info(tbr):
 142             import math
 143             br = int_or_none(tbr)
 144             if len(fmts) == 1 and not br:
 145                 br = fmts[0].get('tbr')
 146             if br > 300:
 147                 tbr = compat_str(math.floor(br / 100) * 100)
 148             else:
 149                 tbr = '250'
 150
 151             # try extracting info from available m3u8 formats
 152             format_copy = None
 153             for f in fmts:
 154                 if f.get('tbr'):
 155                     br_limit = math.floor(br / 100)
 156                     if br_limit - 1 <= math.floor(f['tbr'] / 100) <= br_limit + 1:
 157                         format_copy = f.copy()
 158             return {
 159                 'width': format_copy.get('width'),
 160                 'height': format_copy.get('height'),
 161                 'tbr': format_copy.get('tbr'),
 162                 'vcodec': format_copy.get('vcodec'),
 163                 'acodec': format_copy.get('acodec'),
 164                 'fps': format_copy.get('fps'),
 165                 'format_id': 'https-%s' % tbr,
 166             } if format_copy else {
 167                 'width': _QUALITY[tbr][0],
 168                 'height': _QUALITY[tbr][1],
 169                 'format_id': 'https-%s' % tbr,
 170                 'tbr': int(tbr),
 171             }
 172
 173         loc = test_url(_MP4_TMPL % (relinker_url, '*'))
 174         if not isinstance(loc, compat_str):
 175             return []
 176
 177         mobj = re.match(
 178             _RELINKER_REG,
 179             test_url(relinker_url) or '')
 180         if not mobj:
 181             return []
 182
 183         available_qualities = mobj.group('quality').split(',') if mobj.group('quality') else ['*']
 184         available_qualities = [i for i in available_qualities if i]
 185
 186         formats = []
 187         for q in available_qualities:
 188             fmt = {
 189                 'url': _MP4_TMPL % (relinker_url, q),
 190                 'protocol': 'https',
 191                 'ext': 'mp4',
 192             }
 193             fmt.update(get_format_info(q))
 194             formats.append(fmt)
 195         return formats
 196
 197     @staticmethod
 198     def _extract_subtitles(url, video_data):
 199         STL_EXT = 'stl'
 200         SRT_EXT = 'srt'
 201         subtitles = {}
 202         subtitles_array = video_data.get('subtitlesArray') or []
 203         for k in ('subtitles', 'subtitlesUrl'):
 204             subtitles_array.append({'url': video_data.get(k)})
 205         for subtitle in subtitles_array:
 206             sub_url = subtitle.get('url')
 207             if sub_url and isinstance(sub_url, compat_str):
 208                 sub_lang = subtitle.get('language') or 'it'
 209                 sub_url = urljoin(url, sub_url)
 210                 sub_ext = determine_ext(sub_url, SRT_EXT)
 211                 subtitles.setdefault(sub_lang, []).append({
 212                     'ext': sub_ext,
 213                     'url': sub_url,
 214                 })
 215                 if STL_EXT == sub_ext:
 216                     subtitles[sub_lang].append({
 217                         'ext': SRT_EXT,
 218                         'url': sub_url[:-len(STL_EXT)] + SRT_EXT,
 219                     })
 220         return subtitles
 221
 222
 223 class RaiPlayIE(RaiBaseIE):
 224     _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
 225     _TESTS = [{
 226         'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
 227         'md5': '8970abf8caf8aef4696e7b1f2adfc696',
 228         'info_dict': {
 229             'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
 230             'ext': 'mp4',
 231             'title': 'Report del 07/04/2014',
 232             'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014',
 233             'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
 234             'thumbnail': r're:^https?://.*\.jpg$',
 235             'uploader': 'Rai Gulp',
 236             'duration': 6160,
 237             'series': 'Report',
 238             'season': '2013/14',
 239             'subtitles': {
 240                 'it': 'count:2',
 241             },
 242         },
 243         'params': {
 244             'skip_download': True,
 245         },
 246     }, {
 247         # 1080p direct mp4 url
 248         'url': 'https://www.raiplay.it/video/2021/03/Leonardo-S1E1-b5703b02-82ee-475a-85b6-c9e4a8adf642.html',
 249         'md5': '2e501e8651d72f05ffe8f5d286ad560b',
 250         'info_dict': {
 251             'id': 'b5703b02-82ee-475a-85b6-c9e4a8adf642',
 252             'ext': 'mp4',
 253             'title': 'Leonardo - S1E1',
 254             'alt_title': 'St 1 Ep 1 - Episodio 1',
 255             'description': 'md5:f5360cd267d2de146e4e3879a5a47d31',
 256             'thumbnail': r're:^https?://.*\.jpg$',
 257             'uploader': 'Rai 1',
 258             'duration': 3229,
 259             'series': 'Leonardo',
 260             'season': 'Season 1',
 261         },
 262     }, {
 263         'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
 264         'only_matching': True,
 265     }, {
 266         # subtitles at 'subtitlesArray' key (see #27698)
 267         'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
 268         'only_matching': True,
 269     }, {
 270         # DRM protected
 271         'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
 272         'only_matching': True,
 273     }]
 274
 275     def _real_extract(self, url):
 276         base, video_id = self._match_valid_url(url).groups()
 277
 278         media = self._download_json(
 279             base + '.json', video_id, 'Downloading video JSON')
 280
 281         if not self.get_param('allow_unplayable_formats'):
 282             if try_get(
 283                     media,
 284                     (lambda x: x['rights_management']['rights']['drm'],
 285                      lambda x: x['program_info']['rights_management']['rights']['drm']),
 286                     dict):
 287                 self.report_drm(video_id)
 288
 289         title = media['name']
 290         video = media['video']
 291
 292         relinker_info = self._extract_relinker_info(video['content_url'], video_id)
 293         self._sort_formats(relinker_info['formats'])
 294
 295         thumbnails = []
 296         for _, value in media.get('images', {}).items():
 297             if value:
 298                 thumbnails.append({
 299                     'url': urljoin(url, value),
 300                 })
 301
 302         date_published = media.get('date_published')
 303         time_published = media.get('time_published')
 304         if date_published and time_published:
 305             date_published += ' ' + time_published
 306
 307         subtitles = self._extract_subtitles(url, video)
 308
 309         program_info = media.get('program_info') or {}
 310         season = media.get('season')
 311
 312         info = {
 313             'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
 314             'display_id': video_id,
 315             'title': self._live_title(title) if relinker_info.get(
 316                 'is_live') else title,
 317             'alt_title': strip_or_none(media.get('subtitle')),
 318             'description': media.get('description'),
 319             'uploader': strip_or_none(media.get('channel')),
 320             'creator': strip_or_none(media.get('editor') or None),
 321             'duration': parse_duration(video.get('duration')),
 322             'timestamp': unified_timestamp(date_published),
 323             'thumbnails': thumbnails,
 324             'series': program_info.get('name'),
 325             'season_number': int_or_none(season),
 326             'season': season if (season and not season.isdigit()) else None,
 327             'episode': media.get('episode_title'),
 328             'episode_number': int_or_none(media.get('episode')),
 329             'subtitles': subtitles,
 330         }
 331
 332         info.update(relinker_info)
 333         return info
 334
 335
 336 class RaiPlayLiveIE(RaiPlayIE):
 337     _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
 338     _TESTS = [{
 339         'url': 'http://www.raiplay.it/dirette/rainews24',
 340         'info_dict': {
 341             'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
 342             'display_id': 'rainews24',
 343             'ext': 'mp4',
 344             'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 345             'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497',
 346             'uploader': 'Rai News 24',
 347             'creator': 'Rai News 24',
 348             'is_live': True,
 349         },
 350         'params': {
 351             'skip_download': True,
 352         },
 353     }]
 354
 355
 356 class RaiPlayPlaylistIE(InfoExtractor):
 357     _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
 358     _TESTS = [{
 359         'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
 360         'info_dict': {
 361             'id': 'nondirloalmiocapo',
 362             'title': 'Non dirlo al mio capo',
 363             'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
 364         },
 365         'playlist_mincount': 12,
 366     }]
 367
 368     def _real_extract(self, url):
 369         base, playlist_id = self._match_valid_url(url).groups()
 370
 371         program = self._download_json(
 372             base + '.json', playlist_id, 'Downloading program JSON')
 373
 374         entries = []
 375         for b in (program.get('blocks') or []):
 376             for s in (b.get('sets') or []):
 377                 s_id = s.get('id')
 378                 if not s_id:
 379                     continue
 380                 medias = self._download_json(
 381                     '%s/%s.json' % (base, s_id), s_id,
 382                     'Downloading content set JSON', fatal=False)
 383                 if not medias:
 384                     continue
 385                 for m in (medias.get('items') or []):
 386                     path_id = m.get('path_id')
 387                     if not path_id:
 388                         continue
 389                     video_url = urljoin(url, path_id)
 390                     entries.append(self.url_result(
 391                         video_url, ie=RaiPlayIE.ie_key(),
 392                         video_id=RaiPlayIE._match_id(video_url)))
 393
 394         return self.playlist_result(
 395             entries, playlist_id, program.get('name'),
 396             try_get(program, lambda x: x['program_info']['description']))
 397
 398
 399 class RaiIE(RaiBaseIE):
 400     _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
 401     _TESTS = [{
 402         # var uniquename = "ContentItem-..."
 403         # data-id="ContentItem-..."
 404         'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
 405         'info_dict': {
 406             'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
 407             'ext': 'mp4',
 408             'title': 'TG PRIMO TEMPO',
 409             'thumbnail': r're:^https?://.*\.jpg$',
 410             'duration': 1758,
 411             'upload_date': '20140612',
 412         },
 413         'skip': 'This content is available only in Italy',
 414     }, {
 415         # with ContentItem in many metas
 416         'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
 417         'info_dict': {
 418             'id': '1632c009-c843-4836-bb65-80c33084a64b',
 419             'ext': 'mp4',
 420             'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
 421             'description': 'I film in uscita questa settimana.',
 422             'thumbnail': r're:^https?://.*\.png$',
 423             'duration': 833,
 424             'upload_date': '20161103',
 425         }
 426     }, {
 427         # with ContentItem in og:url
 428         'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
 429         'md5': '06345bd97c932f19ffb129973d07a020',
 430         'info_dict': {
 431             'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
 432             'ext': 'mp4',
 433             'title': 'TG1 ore 20:00 del 03/11/2016',
 434             'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
 435             'thumbnail': r're:^https?://.*\.jpg$',
 436             'duration': 2214,
 437             'upload_date': '20161103',
 438         }
 439     }, {
 440         # initEdizione('ContentItem-...'
 441         'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
 442         'info_dict': {
 443             'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
 444             'ext': 'mp4',
 445             'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
 446             'duration': 2274,
 447             'upload_date': '20170401',
 448         },
 449         'skip': 'Changes daily',
 450     }, {
 451         # HLS live stream with ContentItem in og:url
 452         'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
 453         'info_dict': {
 454             'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
 455             'ext': 'mp4',
 456             'title': 'La diretta di Rainews24',
 457         },
 458         'params': {
 459             'skip_download': True,
 460         },
 461     }, {
 462         # Direct MMS URL
 463         'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
 464         'only_matching': True,
 465     }, {
 466         'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
 467         'only_matching': True,
 468     }]
 469
 470     def _extract_from_content_id(self, content_id, url):
 471         media = self._download_json(
 472             'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
 473             content_id, 'Downloading video JSON')
 474
 475         title = media['name'].strip()
 476
 477         media_type = media['type']
 478         if 'Audio' in media_type:
 479             relinker_info = {
 480                 'formats': [{
 481                     'format_id': media.get('formatoAudio'),
 482                     'url': media['audioUrl'],
 483                     'ext': media.get('formatoAudio'),
 484                 }]
 485             }
 486         elif 'Video' in media_type:
 487             relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
 488         else:
 489             raise ExtractorError('not a media file')
 490
 491         self._sort_formats(relinker_info['formats'])
 492
 493         thumbnails = []
 494         for image_type in ('image', 'image_medium', 'image_300'):
 495             thumbnail_url = media.get(image_type)
 496             if thumbnail_url:
 497                 thumbnails.append({
 498                     'url': compat_urlparse.urljoin(url, thumbnail_url),
 499                 })
 500
 501         subtitles = self._extract_subtitles(url, media)
 502
 503         info = {
 504             'id': content_id,
 505             'title': title,
 506             'description': strip_or_none(media.get('desc')),
 507             'thumbnails': thumbnails,
 508             'uploader': media.get('author'),
 509             'upload_date': unified_strdate(media.get('date')),
 510             'duration': parse_duration(media.get('length')),
 511             'subtitles': subtitles,
 512         }
 513
 514         info.update(relinker_info)
 515
 516         return info
 517
 518     def _real_extract(self, url):
 519         video_id = self._match_id(url)
 520
 521         webpage = self._download_webpage(url, video_id)
 522
 523         content_item_id = None
 524
 525         content_item_url = self._html_search_meta(
 526             ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
 527              'twitter:player', 'jsonlink'), webpage, default=None)
 528         if content_item_url:
 529             content_item_id = self._search_regex(
 530                 r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
 531                 'content item id', default=None)
 532
 533         if not content_item_id:
 534             content_item_id = self._search_regex(
 535                 r'''(?x)
 536                     (?:
 537                         (?:initEdizione|drawMediaRaiTV)\(|
 538                         <(?:[^>]+\bdata-id|var\s+uniquename)=|
 539                         <iframe[^>]+\bsrc=
 540                     )
 541                     (["\'])
 542                     (?:(?!\1).)*\bContentItem-(?P<id>%s)
 543                 ''' % self._UUID_RE,
 544                 webpage, 'content item id', default=None, group='id')
 545
 546         content_item_ids = set()
 547         if content_item_id:
 548             content_item_ids.add(content_item_id)
 549         if video_id not in content_item_ids:
 550             content_item_ids.add(video_id)
 551
 552         for content_item_id in content_item_ids:
 553             try:
 554                 return self._extract_from_content_id(content_item_id, url)
 555             except GeoRestrictedError:
 556                 raise
 557             except ExtractorError:
 558                 pass
 559
 560         relinker_url = self._proto_relative_url(self._search_regex(
 561             r'''(?x)
 562                 (?:
 563                     var\s+videoURL|
 564                     mediaInfo\.mediaUri
 565                 )\s*=\s*
 566                 ([\'"])
 567                 (?P<url>
 568                     (?:https?:)?
 569                     //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
 570                     (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
 571             ''',
 572             webpage, 'relinker URL', group='url'))
 573
 574         relinker_info = self._extract_relinker_info(
 575             urljoin(url, relinker_url), video_id)
 576         self._sort_formats(relinker_info['formats'])
 577
 578         title = self._search_regex(
 579             r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1',
 580             webpage, 'title', group='title',
 581             default=None) or self._og_search_title(webpage)
 582
 583         info = {
 584             'id': video_id,
 585             'title': title,
 586         }
 587
 588         info.update(relinker_info)
 589
 590         return info
 591
 592
 593 class RaiPlayRadioBaseIE(InfoExtractor):
 594     _BASE = 'https://www.raiplayradio.it'
 595
 596     def get_playlist_iter(self, url, uid):
 597         webpage = self._download_webpage(url, uid)
 598         for attrs in parse_list(webpage):
 599             title = attrs['data-title'].strip()
 600             audio_url = urljoin(url, attrs['data-mediapolis'])
 601             entry = {
 602                 'url': audio_url,
 603                 'id': attrs['data-uniquename'].lstrip('ContentItem-'),
 604                 'title': title,
 605                 'ext': 'mp3',
 606                 'language': 'it',
 607             }
 608             if 'data-image' in attrs:
 609                 entry['thumbnail'] = urljoin(url, attrs['data-image'])
 610             yield entry
 611
 612
 613 class RaiPlayRadioIE(RaiPlayRadioBaseIE):
 614     _VALID_URL = r'%s/audio/.+?-(?P<id>%s)\.html' % (
 615         RaiPlayRadioBaseIE._BASE, RaiBaseIE._UUID_RE)
 616     _TEST = {
 617         'url': 'https://www.raiplayradio.it/audio/2019/07/RADIO3---LEZIONI-DI-MUSICA-36b099ff-4123-4443-9bf9-38e43ef5e025.html',
 618         'info_dict': {
 619             'id': '36b099ff-4123-4443-9bf9-38e43ef5e025',
 620             'ext': 'mp3',
 621             'title': 'Dal "Chiaro di luna" al  "Clair de lune", prima parte con Giovanni Bietti',
 622             'thumbnail': r're:^https?://.*\.jpg$',
 623             'language': 'it',
 624         }
 625     }
 626
 627     def _real_extract(self, url):
 628         audio_id = self._match_id(url)
 629         list_url = url.replace('.html', '-list.html')
 630         return next(entry for entry in self.get_playlist_iter(list_url, audio_id) if entry['id'] == audio_id)
 631
 632
 633 class RaiPlayRadioPlaylistIE(RaiPlayRadioBaseIE):
 634     _VALID_URL = r'%s/playlist/.+?-(?P<id>%s)\.html' % (
 635         RaiPlayRadioBaseIE._BASE, RaiBaseIE._UUID_RE)
 636     _TEST = {
 637         'url': 'https://www.raiplayradio.it/playlist/2017/12/Alice-nel-paese-delle-meraviglie-72371d3c-d998-49f3-8860-d168cfdf4966.html',
 638         'info_dict': {
 639             'id': '72371d3c-d998-49f3-8860-d168cfdf4966',
 640             'title': "Alice nel paese delle meraviglie",
 641             'description': "di Lewis Carrol letto da Aldo Busi",
 642         },
 643         'playlist_count': 11,
 644     }
 645
 646     def _real_extract(self, url):
 647         playlist_id = self._match_id(url)
 648         playlist_webpage = self._download_webpage(url, playlist_id)
 649         playlist_title = unescapeHTML(self._html_search_regex(
 650             r'data-playlist-title="(.+?)"', playlist_webpage, 'title'))
 651         playlist_creator = self._html_search_meta(
 652             'nomeProgramma', playlist_webpage)
 653         playlist_description = get_element_by_class(
 654             'textDescriptionProgramma', playlist_webpage)
 655
 656         player_href = self._html_search_regex(
 657             r'data-player-href="(.+?)"', playlist_webpage, 'href')
 658         list_url = urljoin(url, player_href)
 659
 660         entries = list(self.get_playlist_iter(list_url, playlist_id))
 661         for index, entry in enumerate(entries, start=1):
 662             entry.update({
 663                 'track': entry['title'],
 664                 'track_number': index,
 665                 'artist': playlist_creator,
 666                 'album': playlist_title
 667             })
 668
 669         return self.playlist_result(
 670             entries, playlist_id, playlist_title, playlist_description,
 671             creator=playlist_creator)