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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none
   6
   7
   8 class FranceInterIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
  12         'md5': '4764932e466e6f6c79c317d2e74f6884',
  13         'info_dict': {
  14             'id': '793962',
  15             'ext': 'mp3',
  16             'title': 'L’Histoire dans les jeux vidéo',
  17             'description': 'md5:7e93ddb4451e7530022792240a3049c7',
  18             'timestamp': 1387369800,
  19             'upload_date': '20131218',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25
  26         webpage = self._download_webpage(url, video_id)
  27
  28         path = self._search_regex(
  29             r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
  30         video_url = 'http://www.franceinter.fr/' + path
  31
  32         title = self._html_search_regex(
  33             r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
  34         description = self._html_search_regex(
  35             r'<span class="description">(.*?)</span>',
  36             webpage, 'description', fatal=False)
  37         timestamp = int_or_none(self._search_regex(
  38             r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
  39
  40         return {
  41             'id': video_id,
  42             'title': title,
  43             'description': description,
  44             'timestamp': timestamp,
  45             'formats': [{
  46                 'url': video_url,
  47                 'vcodec': 'none',
  48             }],
  49         }