yt_dlp/extractor/rtrfm.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class RTRFMIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?rtrfm\.com\.au/(?:shows|show-episode)/(?P<id>[^/?\#&]+)'
   8     _TESTS = [
   9         {
  10             'url': 'https://rtrfm.com.au/shows/breakfast/',
  11             'md5': '46168394d3a5ce237cf47e85d0745413',
  12             'info_dict': {
  13                 'id': 'breakfast-2021-11-16',
  14                 'ext': 'mp3',
  15                 'series': 'Breakfast with Taylah',
  16                 'title': r're:^Breakfast with Taylah \d{4}-\d{2}-\d{2}$',
  17                 'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
  18             },
  19             'skip': 'ID and md5 changes daily',
  20         },
  21         {
  22             'url': 'https://rtrfm.com.au/show-episode/breakfast-2021-11-11/',
  23             'md5': '396bedf1e40f96c62b30d4999202a790',
  24             'info_dict': {
  25                 'id': 'breakfast-2021-11-11',
  26                 'ext': 'mp3',
  27                 'series': 'Breakfast with Taylah',
  28                 'title': 'Breakfast with Taylah 2021-11-11',
  29                 'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
  30             },
  31         },
  32         {
  33             'url': 'https://rtrfm.com.au/show-episode/breakfast-2020-06-01/',
  34             'md5': '594027f513ec36a24b15d65007a24dff',
  35             'info_dict': {
  36                 'id': 'breakfast-2020-06-01',
  37                 'ext': 'mp3',
  38                 'series': 'Breakfast with Taylah',
  39                 'title': 'Breakfast with Taylah 2020-06-01',
  40                 'description': r're:^Breakfast with Taylah ',
  41             },
  42             'skip': 'This audio has expired',
  43         },
  44     ]
  45
  46     def _real_extract(self, url):
  47         display_id = self._match_id(url)
  48         webpage = self._download_webpage(url, display_id)
  49         show, date, title = self._search_regex(
  50             r'''\.playShow(?:From)?\(['"](?P<show>[^'"]+)['"],\s*['"](?P<date>[0-9]{4}-[0-9]{2}-[0-9]{2})['"],\s*['"](?P<title>[^'"]+)['"]''',
  51             webpage, 'details', group=('show', 'date', 'title'))
  52         url = self._download_json(
  53             'https://restreams.rtrfm.com.au/rzz',
  54             show, 'Downloading MP3 URL', query={'n': show, 'd': date})['u']
  55         # This is the only indicator of an error until trying to download the URL and
  56         # downloads of mp4 URLs always fail (403 for current episodes, 404 for missing).
  57         if '.mp4' in url:
  58             url = None
  59             self.raise_no_formats('Expired or no episode on this date', expected=True)
  60         return {
  61             'id': '%s-%s' % (show, date),
  62             'title': '%s %s' % (title, date),
  63             'series': title,
  64             'url': url,
  65             'release_date': date,
  66             'description': self._og_search_description(webpage),
  67         }