yt_dlp/extractor/rtrfm.py

   1 from .common import InfoExtractor
   2
   3
   4 class RTRFMIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?rtrfm\.com\.au/(?:shows|show-episode)/(?P<id>[^/?\#&]+)'
   6     _TESTS = [
   7         {
   8             'url': 'https://rtrfm.com.au/shows/breakfast/',
   9             'md5': '46168394d3a5ce237cf47e85d0745413',
  10             'info_dict': {
  11                 'id': 'breakfast-2021-11-16',
  12                 'ext': 'mp3',
  13                 'series': 'Breakfast with Taylah',
  14                 'title': r're:^Breakfast with Taylah \d{4}-\d{2}-\d{2}$',
  15                 'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
  16             },
  17             'skip': 'ID and md5 changes daily',
  18         },
  19         {
  20             'url': 'https://rtrfm.com.au/show-episode/breakfast-2021-11-11/',
  21             'md5': '396bedf1e40f96c62b30d4999202a790',
  22             'info_dict': {
  23                 'id': 'breakfast-2021-11-11',
  24                 'ext': 'mp3',
  25                 'series': 'Breakfast with Taylah',
  26                 'title': 'Breakfast with Taylah 2021-11-11',
  27                 'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
  28             },
  29         },
  30         {
  31             'url': 'https://rtrfm.com.au/show-episode/breakfast-2020-06-01/',
  32             'md5': '594027f513ec36a24b15d65007a24dff',
  33             'info_dict': {
  34                 'id': 'breakfast-2020-06-01',
  35                 'ext': 'mp3',
  36                 'series': 'Breakfast with Taylah',
  37                 'title': 'Breakfast with Taylah 2020-06-01',
  38                 'description': r're:^Breakfast with Taylah ',
  39             },
  40             'skip': 'This audio has expired',
  41         },
  42     ]
  43
  44     def _real_extract(self, url):
  45         display_id = self._match_id(url)
  46         webpage = self._download_webpage(url, display_id)
  47         show, date, title = self._search_regex(
  48             r'''\.playShow(?:From)?\(['"](?P<show>[^'"]+)['"],\s*['"](?P<date>[0-9]{4}-[0-9]{2}-[0-9]{2})['"],\s*['"](?P<title>[^'"]+)['"]''',
  49             webpage, 'details', group=('show', 'date', 'title'))
  50         url = self._download_json(
  51             'https://restreams.rtrfm.com.au/rzz',
  52             show, 'Downloading MP3 URL', query={'n': show, 'd': date})['u']
  53         # This is the only indicator of an error until trying to download the URL and
  54         # downloads of mp4 URLs always fail (403 for current episodes, 404 for missing).
  55         if '.mp4' in url:
  56             url = None
  57             self.raise_no_formats('Expired or no episode on this date', expected=True)
  58         return {
  59             'id': f'{show}-{date}',
  60             'title': f'{title} {date}',
  61             'series': title,
  62             'url': url,
  63             'release_date': date,
  64             'description': self._og_search_description(webpage),
  65         }