logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

globalplayer.py (10013B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. from .common import InfoExtractor
  5. from ..utils import (
  6.     clean_html,
  7.     join_nonempty,
  8.     merge_dicts,
  9.     parse_duration,
  10.     str_or_none,
  11.     T,
  12.     traverse_obj,
  13.     unified_strdate,
  14.     unified_timestamp,
  15.     urlhandle_detect_ext,
  16. )
  19. class GlobalPlayerBaseIE(InfoExtractor):
  21.     def _get_page_props(self, url, video_id):
  22.         webpage = self._download_webpage(url, video_id)
  23.         return self._search_nextjs_data(webpage, video_id)['props']['pageProps']
  25.     def _request_ext(self, url, video_id):
  26.         return urlhandle_detect_ext(self._request_webpage(  # Server rejects HEAD requests
  27.             url, video_id, note='Determining source extension'))
  29.     @staticmethod
  30.     def _clean_desc(x):
  31.         x = clean_html(x)
  32.         if x:
  33.             x = x.replace('\xa0', ' ')
  34.         return x
  36.     def _extract_audio(self, episode, series):
  38.         return merge_dicts({
  39.             'vcodec': 'none',
  40.         }, traverse_obj(series, {
  41.             'series': 'title',
  42.             'series_id': 'id',
  43.             'thumbnail': 'imageUrl',
  44.             'uploader': 'itunesAuthor',  # podcasts only
  45.         }), traverse_obj(episode, {
  46.             'id': 'id',
  47.             'description': ('description', T(self._clean_desc)),
  48.             'duration': ('duration', T(parse_duration)),
  49.             'thumbnail': 'imageUrl',
  50.             'url': 'streamUrl',
  51.             'timestamp': (('pubDate', 'startDate'), T(unified_timestamp)),
  52.             'title': 'title',
  53.         }, get_all=False), rev=True)
  56. class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
  57.     _VALID_URL = r'https?://www\.globalplayer\.com/live/(?P<id>\w+)/\w+'
  58.     _TESTS = [{
  59.         'url': 'https://www.globalplayer.com/live/smoothchill/uk/',
  60.         'info_dict': {
  61.             'id': '2mx1E',
  62.             'ext': 'aac',
  63.             'display_id': 'smoothchill-uk',
  64.             'title': 're:^Smooth Chill.+$',
  65.             'thumbnail': 'https://herald.musicradio.com/media/f296ade8-50c9-4f60-911f-924e96873620.png',
  66.             'description': 'Music To Chill To',
  67.             # 'live_status': 'is_live',
  68.             'is_live': True,
  69.         },
  70.     }, {
  71.         # national station
  72.         'url': 'https://www.globalplayer.com/live/heart/uk/',
  73.         'info_dict': {
  74.             'id': '2mwx4',
  75.             'ext': 'aac',
  76.             'description': 'turn up the feel good!',
  77.             'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
  78.             # 'live_status': 'is_live',
  79.             'is_live': True,
  80.             'title': 're:^Heart UK.+$',
  81.             'display_id': 'heart-uk',
  82.         },
  83.     }, {
  84.         # regional variation
  85.         'url': 'https://www.globalplayer.com/live/heart/london/',
  86.         'info_dict': {
  87.             'id': 'AMqg',
  88.             'ext': 'aac',
  89.             'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
  90.             'title': 're:^Heart London.+$',
  91.             # 'live_status': 'is_live',
  92.             'is_live': True,
  93.             'display_id': 'heart-london',
  94.             'description': 'turn up the feel good!',
  95.         },
  96.     }]
  98.     def _real_extract(self, url):
  99.         video_id = self._match_id(url)
  100.         station = self._get_page_props(url, video_id)['station']
  101.         stream_url = station['streamUrl']
  103.         return merge_dicts({
  104.             'id': station['id'],
  105.             'display_id': (
  106.                 join_nonempty('brandSlug', 'slug', from_dict=station)
  107.                 or station.get('legacyStationPrefix')),
  108.             'url': stream_url,
  109.             'ext': self._request_ext(stream_url, video_id),
  110.             'vcodec': 'none',
  111.             'is_live': True,
  112.         }, {
  113.             'title': self._live_title(traverse_obj(
  114.                 station, (('name', 'brandName'), T(str_or_none)),
  115.                 get_all=False)),
  116.         }, traverse_obj(station, {
  117.             'description': 'tagline',
  118.             'thumbnail': 'brandLogo',
  119.         }), rev=True)
  122. class GlobalPlayerLivePlaylistIE(GlobalPlayerBaseIE):
  123.     _VALID_URL = r'https?://www\.globalplayer\.com/playlists/(?P<id>\w+)'
  124.     _TESTS = [{
  125.         # "live playlist"
  126.         'url': 'https://www.globalplayer.com/playlists/8bLk/',
  127.         'info_dict': {
  128.             'id': '8bLk',
  129.             'ext': 'aac',
  130.             # 'live_status': 'is_live',
  131.             'is_live': True,
  132.             'description': r're:(?s).+\bclassical\b.+\bClassic FM Hall [oO]f Fame\b',
  133.             'thumbnail': 'https://images.globalplayer.com/images/551379?width=450&signature=oMLPZIoi5_dBSHnTMREW0Xg76mA=',
  134.             'title': 're:Classic FM Hall of Fame.+$'
  135.         },
  136.     }]
  138.     def _real_extract(self, url):
  139.         video_id = self._match_id(url)
  140.         station = self._get_page_props(url, video_id)['playlistData']
  141.         stream_url = station['streamUrl']
  143.         return merge_dicts({
  144.             'id': video_id,
  145.             'url': stream_url,
  146.             'ext': self._request_ext(stream_url, video_id),
  147.             'vcodec': 'none',
  148.             'is_live': True,
  149.         }, traverse_obj(station, {
  150.             'title': 'title',
  151.             'description': ('description', T(self._clean_desc)),
  152.             'thumbnail': 'image',
  153.         }), rev=True)
  156. class GlobalPlayerAudioIE(GlobalPlayerBaseIE):
  157.     _VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)/|catchup/\w+/\w+/)(?P<id>\w+)/?(?:$|[?#])'
  158.     _TESTS = [{
  159.         # podcast
  160.         'url': 'https://www.globalplayer.com/podcasts/42KuaM/',
  161.         'playlist_mincount': 5,
  162.         'info_dict': {
  163.             'id': '42KuaM',
  164.             'title': 'Filthy Ritual',
  165.             'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
  166.             'categories': ['Society & Culture', 'True Crime'],
  167.             'uploader': 'Global',
  168.             'description': r're:(?s).+\bscam\b.+?\bseries available now\b',
  169.         },
  170.     }, {
  171.         # radio catchup
  172.         'url': 'https://www.globalplayer.com/catchup/lbc/uk/46vyD7z/',
  173.         'playlist_mincount': 2,
  174.         'info_dict': {
  175.             'id': '46vyD7z',
  176.             'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
  177.             'title': 'Nick Ferrari',
  178.             'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
  179.         },
  180.     }]
  182.     def _real_extract(self, url):
  183.         video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
  184.         props = self._get_page_props(url, video_id)
  185.         series = props['podcastInfo'] if podcast else props['catchupInfo']
  187.         return merge_dicts({
  188.             '_type': 'playlist',
  189.             'id': video_id,
  190.             'entries': [self._extract_audio(ep, series) for ep in traverse_obj(
  191.                         series, ('episodes', lambda _, v: v['id'] and v['streamUrl']))],
  192.             'categories': traverse_obj(series, ('categories', Ellipsis, 'name')) or None,
  193.         }, traverse_obj(series, {
  194.             'description': ('description', T(self._clean_desc)),
  195.             'thumbnail': 'imageUrl',
  196.             'title': 'title',
  197.             'uploader': 'itunesAuthor',  # podcasts only
  198.         }), rev=True)
  201. class GlobalPlayerAudioEpisodeIE(GlobalPlayerBaseIE):
  202.     _VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)|catchup/\w+/\w+)/episodes/(?P<id>\w+)/?(?:$|[?#])'
  203.     _TESTS = [{
  204.         # podcast
  205.         'url': 'https://www.globalplayer.com/podcasts/episodes/7DrfNnE/',
  206.         'info_dict': {
  207.             'id': '7DrfNnE',
  208.             'ext': 'mp3',
  209.             'title': 'Filthy Ritual - Trailer',
  210.             'description': 'md5:1f1562fd0f01b4773b590984f94223e0',
  211.             'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
  212.             'duration': 225.0,
  213.             'timestamp': 1681254900,
  214.             'series': 'Filthy Ritual',
  215.             'series_id': '42KuaM',
  216.             'upload_date': '20230411',
  217.             'uploader': 'Global',
  218.         },
  219.     }, {
  220.         # radio catchup
  221.         'url': 'https://www.globalplayer.com/catchup/lbc/uk/episodes/2zGq26Vcv1fCWhddC4JAwETXWe/',
  222.         'only_matching': True,
  223.         # expired: refresh the details with a current show for a full test
  224.         'info_dict': {
  225.             'id': '2zGq26Vcv1fCWhddC4JAwETXWe',
  226.             'ext': 'm4a',
  227.             'timestamp': 1682056800,
  228.             'series': 'Nick Ferrari',
  229.             'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
  230.             'upload_date': '20230421',
  231.             'series_id': '46vyD7z',
  232.             'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
  233.             'title': 'Nick Ferrari',
  234.             'duration': 10800.0,
  235.         },
  236.     }]
  238.     def _real_extract(self, url):
  239.         video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
  240.         props = self._get_page_props(url, video_id)
  241.         episode = props['podcastEpisode'] if podcast else props['catchupEpisode']
  243.         return self._extract_audio(
  244.             episode, traverse_obj(episode, 'podcast', 'show', expected_type=dict) or {})
  247. class GlobalPlayerVideoIE(GlobalPlayerBaseIE):
  248.     _VALID_URL = r'https?://www\.globalplayer\.com/videos/(?P<id>\w+)'
  249.     _TESTS = [{
  250.         'url': 'https://www.globalplayer.com/videos/2JsSZ7Gm2uP/',
  251.         'info_dict': {
  252.             'id': '2JsSZ7Gm2uP',
  253.             'ext': 'mp4',
  254.             'description': 'md5:6a9f063c67c42f218e42eee7d0298bfd',
  255.             'thumbnail': 'md5:d4498af48e15aae4839ce77b97d39550',
  256.             'upload_date': '20230420',
  257.             'title': 'Treble Malakai Bayoh sings a sublime Handel aria at Classic FM Live',
  258.         },
  259.     }]
  261.     def _real_extract(self, url):
  262.         video_id = self._match_id(url)
  263.         meta = self._get_page_props(url, video_id)['videoData']
  265.         return merge_dicts({
  266.             'id': video_id,
  267.         }, traverse_obj(meta, {
  268.             'url': 'url',
  269.             'thumbnail': ('image', 'url'),
  270.             'title': 'title',
  271.             'upload_date': ('publish_date', T(unified_strdate)),
  272.             'description': 'description',
  273.         }), rev=True)