1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-27 09:23:46 +01:00
yt-dlp/yt_dlp/extractor/echomsk.py
Pccode66 7a5c1cfe93
Completely change project name to yt-dlp (#85)
* All modules and binary names are changed
* All documentation references changed
* yt-dlp no longer loads youtube-dlc config files
* All URLs changed to point to organization account

Co-authored-by: Pccode66
Co-authored-by: pukkandan
2021-02-25 00:15:56 +05:30

47 lines
1.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
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,
}