yt_dlp/extractor/radioradicale.py

   1 from .common import InfoExtractor
   2 from ..utils import url_or_none
   3 from ..utils.traversal import traverse_obj
   4
   5
   6 class RadioRadicaleIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
   8     _TESTS = [{
   9         'url': 'https://www.radioradicale.it/scheda/471591',
  10         'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
  11         'info_dict': {
  12             'id': '471591',
  13             'ext': 'mp4',
  14             'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
  15             'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
  16             'location': 'Napoli',
  17             'duration': 2852.0,
  18             'timestamp': 1459987200,
  19             'upload_date': '20160407',
  20             'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
  21         },
  22     }, {
  23         'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
  24         'info_dict': {
  25             'id': '742783',
  26             'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
  27             'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
  28             'location': 'CAMERA',
  29             'duration': 5868.0,
  30             'timestamp': 1730246400,
  31             'upload_date': '20241030',
  32         },
  33         'playlist': [{
  34             'md5': 'aa48de55dcc45478e4cd200f299aab7d',
  35             'info_dict': {
  36                 'id': '742783-0',
  37                 'ext': 'mp4',
  38                 'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
  39             },
  40         }, {
  41             'md5': 'be915c189c70ad2920e5810f32260ff5',
  42             'info_dict': {
  43                 'id': '742783-1',
  44                 'ext': 'mp4',
  45                 'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
  46             },
  47         }, {
  48             'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
  49             'info_dict': {
  50                 'id': '742783-2',
  51                 'ext': 'mp4',
  52                 'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
  53             },
  54         }],
  55     }]
  56
  57     def _entries(self, videos_info, page_id):
  58         for idx, video in enumerate(traverse_obj(
  59                 videos_info, ('playlist', lambda _, v: v['sources']))):
  60             video_id = f'{page_id}-{idx}'
  61             formats = []
  62             subtitles = {}
  63
  64             for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
  65                 fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
  66                 formats.extend(fmts)
  67                 self._merge_subtitles(subs, target=subtitles)
  68             for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
  69                 self._merge_subtitles({sub.get('srclang') or 'und': [{
  70                     'url': sub['src'],
  71                     'name': sub.get('label'),
  72                 }]}, target=subtitles)
  73
  74             yield {
  75                 'id': video_id,
  76                 'title': video.get('title'),
  77                 'formats': formats,
  78                 'subtitles': subtitles,
  79             }
  80
  81     def _real_extract(self, url):
  82         page_id = self._match_id(url)
  83         webpage = self._download_webpage(url, page_id)
  84
  85         videos_info = self._search_json(
  86             r'jQuery\.extend\(Drupal\.settings\s*,',
  87             webpage, 'videos_info', page_id)['RRscheda']
  88
  89         entries = list(self._entries(videos_info, page_id))
  90
  91         common_info = {
  92             'id': page_id,
  93             'title': self._og_search_title(webpage),
  94             'description': self._og_search_description(webpage),
  95             'location': videos_info.get('luogo'),
  96             **self._search_json_ld(webpage, page_id),
  97         }
  98
  99         if len(entries) == 1:
 100             return {
 101                 **entries[0],
 102                 **common_info,
 103             }
 104
 105         return self.playlist_result(entries, multi_video=True, **common_info)