1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 14:47:44 +01:00
yt-dlp/yt_dlp/extractor/rtrfm.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

66 lines
2.7 KiB
Python

from .common import InfoExtractor
class RTRFMIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtrfm\.com\.au/(?:shows|show-episode)/(?P<id>[^/?\#&]+)'
_TESTS = [
{
'url': 'https://rtrfm.com.au/shows/breakfast/',
'md5': '46168394d3a5ce237cf47e85d0745413',
'info_dict': {
'id': 'breakfast-2021-11-16',
'ext': 'mp3',
'series': 'Breakfast with Taylah',
'title': r're:^Breakfast with Taylah \d{4}-\d{2}-\d{2}$',
'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
},
'skip': 'ID and md5 changes daily',
},
{
'url': 'https://rtrfm.com.au/show-episode/breakfast-2021-11-11/',
'md5': '396bedf1e40f96c62b30d4999202a790',
'info_dict': {
'id': 'breakfast-2021-11-11',
'ext': 'mp3',
'series': 'Breakfast with Taylah',
'title': 'Breakfast with Taylah 2021-11-11',
'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
},
},
{
'url': 'https://rtrfm.com.au/show-episode/breakfast-2020-06-01/',
'md5': '594027f513ec36a24b15d65007a24dff',
'info_dict': {
'id': 'breakfast-2020-06-01',
'ext': 'mp3',
'series': 'Breakfast with Taylah',
'title': 'Breakfast with Taylah 2020-06-01',
'description': r're:^Breakfast with Taylah ',
},
'skip': 'This audio has expired',
},
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
show, date, title = self._search_regex(
r'''\.playShow(?:From)?\(['"](?P<show>[^'"]+)['"],\s*['"](?P<date>[0-9]{4}-[0-9]{2}-[0-9]{2})['"],\s*['"](?P<title>[^'"]+)['"]''',
webpage, 'details', group=('show', 'date', 'title'))
url = self._download_json(
'https://restreams.rtrfm.com.au/rzz',
show, 'Downloading MP3 URL', query={'n': show, 'd': date})['u']
# This is the only indicator of an error until trying to download the URL and
# downloads of mp4 URLs always fail (403 for current episodes, 404 for missing).
if '.mp4' in url:
url = None
self.raise_no_formats('Expired or no episode on this date', expected=True)
return {
'id': '%s-%s' % (show, date),
'title': '%s %s' % (title, date),
'series': title,
'url': url,
'release_date': date,
'description': self._og_search_description(webpage),
}