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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import int_or_none
   8
   9
  10 class FranceInterIE(InfoExtractor):
  11     _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
  12     _TEST = {
  13         'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
  14         'md5': '4764932e466e6f6c79c317d2e74f6884',
  15         "info_dict": {
  16             'id': '793962',
  17             'ext': 'mp3',
  18             'title': 'L’Histoire dans les jeux vidéo',
  19             'description': 'md5:7e93ddb4451e7530022792240a3049c7',
  20             'timestamp': 1387369800,
  21             'upload_date': '20131218',
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         path = self._search_regex(
  32             r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
  33         video_url = 'http://www.franceinter.fr/' + path
  34
  35         title = self._html_search_regex(
  36             r'<span class="title">(.+?)</span>', webpage, 'title')
  37         description = self._html_search_regex(
  38             r'<span class="description">(.*?)</span>',
  39             webpage, 'description', fatal=False)
  40         timestamp = int_or_none(self._search_regex(
  41             r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
  42
  43         return {
  44             'id': video_id,
  45             'title': title,
  46             'description': description,
  47             'timestamp': timestamp,
  48             'formats': [{
  49                 'url': video_url,
  50                 'vcodec': 'none',
  51             }],
  52         }