mirror of
https://github.com/yt-dlp/yt-dlp
synced 2024-11-26 11:31:07 +01:00
86e5f3ed2e
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
44 lines
1.2 KiB
Python
44 lines
1.2 KiB
Python
import re
|
||
|
||
from .common import InfoExtractor
|
||
|
||
|
||
class EchoMskIE(InfoExtractor):
|
||
_VALID_URL = r'https?://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
|
||
_TEST = {
|
||
'url': 'http://www.echo.msk.ru/sounds/1464134.html',
|
||
'md5': '2e44b3b78daff5b458e4dbc37f191f7c',
|
||
'info_dict': {
|
||
'id': '1464134',
|
||
'ext': 'mp3',
|
||
'title': 'Особое мнение - 29 декабря 2014, 19:08',
|
||
},
|
||
}
|
||
|
||
def _real_extract(self, url):
|
||
video_id = self._match_id(url)
|
||
|
||
webpage = self._download_webpage(url, video_id)
|
||
|
||
audio_url = self._search_regex(
|
||
r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL')
|
||
|
||
title = self._html_search_regex(
|
||
r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>',
|
||
webpage, 'title')
|
||
|
||
air_date = self._html_search_regex(
|
||
r'(?s)<div class="date">(.+?)</div>',
|
||
webpage, 'date', fatal=False, default=None)
|
||
|
||
if air_date:
|
||
air_date = re.sub(r'(\s)\1+', r'\1', air_date)
|
||
if air_date:
|
||
title = '%s - %s' % (title, air_date)
|
||
|
||
return {
|
||
'id': video_id,
|
||
'url': audio_url,
|
||
'title': title,
|
||
}
|