Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/echomsk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class EchoMskIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
  11     _TEST = {
  12         'url': 'http://www.echo.msk.ru/sounds/1464134.html',
  13         'md5': '2e44b3b78daff5b458e4dbc37f191f7c',
  14         'info_dict': {
  15             'id': '1464134',
  16             'ext': 'mp3',
  17             'title': 'Особое мнение - 29 декабря 2014, 19:08',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23
  24         webpage = self._download_webpage(url, video_id)
  25
  26         audio_url = self._search_regex(
  27             r'<a rel="mp3" href="([^"]+)">', webpage, 'audio URL')
  28
  29         title = self._html_search_regex(
  30             r'<a href="/programs/[^"]+" target="_blank">([^<]+)</a>',
  31             webpage, 'title')
  32
  33         air_date = self._html_search_regex(
  34             r'(?s)<div class="date">(.+?)</div>',
  35             webpage, 'date', fatal=False, default=None)
  36
  37         if air_date:
  38             air_date = re.sub(r'(\s)\1+', r'\1', air_date)
  39             if air_date:
  40                 title = '%s - %s' % (title, air_date)
  41
  42         return {
  43             'id': video_id,
  44             'url': audio_url,
  45             'title': title,
  46         }