yt_dlp/extractor/yle_areena.py

   1 from .common import InfoExtractor
   2 from .kaltura import KalturaIE
   3 from ..utils import (
   4     ExtractorError,
   5     int_or_none,
   6     parse_iso8601,
   7     smuggle_url,
   8     url_or_none,
   9 )
  10 from ..utils.traversal import traverse_obj
  11
  12
  13 class YleAreenaIE(InfoExtractor):
  14     _VALID_URL = r'https?://areena\.yle\.fi/(?P<podcast>podcastit/)?(?P<id>[\d-]+)'
  15     _GEO_COUNTRIES = ['FI']
  16     _TESTS = [
  17         {
  18             'url': 'https://areena.yle.fi/1-4371942',
  19             'md5': 'd87e9a1e74e67e009990ddd413e426b4',
  20             'info_dict': {
  21                 'id': '1-4371942',
  22                 'ext': 'mp4',
  23                 'title': 'Pouchit',
  24                 'description': 'md5:01071d7056ceec375f63960f90c35366',
  25                 'series': 'Modernit miehet',
  26                 'season': 'Season 1',
  27                 'season_number': 1,
  28                 'episode': 'Episode 2',
  29                 'episode_number': 2,
  30                 'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
  31                 'age_limit': 7,
  32                 'release_date': '20190105',
  33                 'release_timestamp': 1546725660,
  34                 'duration': 1435,
  35             },
  36         },
  37         {
  38             'url': 'https://areena.yle.fi/1-2158940',
  39             'md5': '6369ddc5e07b5fdaeda27a495184143c',
  40             'info_dict': {
  41                 'id': '1-2158940',
  42                 'ext': 'mp4',
  43                 'title': 'Albi haluaa vessan',
  44                 'description': 'Albi haluaa vessan.',
  45                 'series': 'Albi Lumiukko',
  46                 'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
  47                 'age_limit': 0,
  48                 'release_date': '20211215',
  49                 'release_timestamp': 1639555200,
  50                 'duration': 319,
  51             },
  52         },
  53         {
  54             'url': 'https://areena.yle.fi/1-64829589',
  55             'info_dict': {
  56                 'id': '1-64829589',
  57                 'ext': 'mp4',
  58                 'title': 'HKO & Mälkki & Tanner',
  59                 'description': 'md5:b4f1b1af2c6569b33f75179a86eea156',
  60                 'series': 'Helsingin kaupunginorkesterin konsertteja',
  61                 'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
  62                 'release_date': '20230120',
  63                 'release_timestamp': 1674242079,
  64                 'duration': 8004,
  65             },
  66             'params': {
  67                 'skip_download': 'm3u8',
  68             },
  69         },
  70         {
  71             'url': 'https://areena.yle.fi/1-72251830',
  72             'info_dict': {
  73                 'id': '1-72251830',
  74                 'ext': 'mp4',
  75                 'title': r're:Pentulive 2024 | Pentulive \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
  76                 'description': 'md5:1f118707d9093bf894a34fbbc865397b',
  77                 'series': 'Pentulive',
  78                 'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
  79                 'live_status': 'is_live',
  80                 'release_date': '20241025',
  81                 'release_timestamp': 1729875600,
  82             },
  83             'params': {
  84                 'skip_download': 'livestream',
  85             },
  86         },
  87         {
  88             'url': 'https://areena.yle.fi/podcastit/1-71022852',
  89             'info_dict': {
  90                 'id': '1-71022852',
  91                 'ext': 'mp3',
  92                 'title': 'Värityspäivä',
  93                 'description': 'md5:c3a02b0455ec71d32cbe09d32ec161e2',
  94                 'series': 'Murun ja Paukun ikioma kaupunki',
  95                 'episode': 'Episode 1',
  96                 'episode_number': 1,
  97                 'release_date': '20240607',
  98                 'release_timestamp': 1717736400,
  99                 'duration': 442,
 100             },
 101         },
 102     ]
 103
 104     def _real_extract(self, url):
 105         video_id, is_podcast = self._match_valid_url(url).group('id', 'podcast')
 106         json_ld = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
 107         video_data = self._download_json(
 108             f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
 109             video_id, headers={
 110                 'origin': 'https://areena.yle.fi',
 111                 'referer': 'https://areena.yle.fi/',
 112                 'content-type': 'application/json',
 113             })['data']
 114
 115         # Example title: 'K1, J2: Pouchit | Modernit miehet'
 116         season_number, episode_number, episode, series = self._search_regex(
 117             r'K(?P<season_no>\d+),\s*J(?P<episode_no>\d+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
 118             json_ld.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
 119             default=(None, None, None, None))
 120         description = traverse_obj(video_data, ('ongoing_ondemand', 'description', 'fin', {str}))
 121
 122         subtitles = {}
 123         for sub in traverse_obj(video_data, ('ongoing_ondemand', 'subtitles', lambda _, v: url_or_none(v['uri']))):
 124             subtitles.setdefault(sub.get('language') or 'und', []).append({
 125                 'url': sub['uri'],
 126                 'ext': 'srt',
 127                 'name': sub.get('kind'),
 128             })
 129
 130         info_dict, metadata = {}, {}
 131         if is_podcast and traverse_obj(video_data, ('ongoing_ondemand', 'media_url', {url_or_none})):
 132             metadata = video_data['ongoing_ondemand']
 133             info_dict['url'] = metadata['media_url']
 134         elif traverse_obj(video_data, ('ongoing_event', 'manifest_url', {url_or_none})):
 135             metadata = video_data['ongoing_event']
 136             metadata.pop('duration', None)  # Duration is not accurate for livestreams
 137             info_dict['live_status'] = 'is_live'
 138         elif traverse_obj(video_data, ('ongoing_ondemand', 'manifest_url', {url_or_none})):
 139             metadata = video_data['ongoing_ondemand']
 140         # XXX: Has all externally-hosted Kaltura content been moved to native hosting?
 141         elif kaltura_id := traverse_obj(video_data, ('ongoing_ondemand', 'kaltura', 'id', {str})):
 142             metadata = video_data['ongoing_ondemand']
 143             info_dict.update({
 144                 '_type': 'url_transparent',
 145                 'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}),
 146                 'ie_key': KalturaIE.ie_key(),
 147             })
 148         elif traverse_obj(video_data, ('gone', {dict})):
 149             self.raise_no_formats('The content is no longer available', expected=True, video_id=video_id)
 150             metadata = video_data['gone']
 151         else:
 152             raise ExtractorError('Unable to extract content')
 153
 154         if not info_dict.get('url') and metadata.get('manifest_url'):
 155             info_dict['formats'], subs = self._extract_m3u8_formats_and_subtitles(
 156                 metadata['manifest_url'], video_id, 'mp4', m3u8_id='hls')
 157             self._merge_subtitles(subs, target=subtitles)
 158
 159         return {
 160             **traverse_obj(json_ld, {
 161                 'title': 'title',
 162                 'thumbnails': ('thumbnails', ..., {'url': 'url'}),
 163             }),
 164             'id': video_id,
 165             'title': episode,
 166             'description': description,
 167             'series': series,
 168             'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
 169                               or int_or_none(season_number)),
 170             'episode_number': int_or_none(episode_number),
 171             'subtitles': subtitles or None,
 172             **traverse_obj(metadata, {
 173                 'title': ('title', 'fin', {str}),
 174                 'description': ('description', 'fin', {str}),
 175                 'series': ('series', 'title', 'fin', {str}),
 176                 'episode_number': ('episode_number', {int_or_none}),
 177                 'age_limit': ('content_rating', 'age_restriction', {int_or_none}),
 178                 'release_timestamp': ('start_time', {parse_iso8601}),
 179                 'duration': ('duration', 'duration_in_seconds', {int_or_none}),
 180             }),
 181             **info_dict,
 182         }