yt_dlp/extractor/franceinter.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import month_by_name
   6
   7
   8 class FranceInterIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
  10
  11     _TEST = {
  12         'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
  13         'md5': '9e54d7bdb6fdc02a841007f8a975c094',
  14         'info_dict': {
  15             'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
  16             'ext': 'mp3',
  17             'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
  18             'description': 'md5:401969c5d318c061f86bda1fa359292b',
  19             'thumbnail': r're:^https?://.*\.jpg',
  20             'upload_date': '20160907',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         video_url = self._search_regex(
  30             r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
  31             webpage, 'video url', group='url')
  32
  33         title = self._og_search_title(webpage)
  34         description = self._og_search_description(webpage)
  35         thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
  36
  37         upload_date_str = self._search_regex(
  38             r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
  39             webpage, 'upload date', fatal=False)
  40         if upload_date_str:
  41             upload_date_list = upload_date_str.split()
  42             upload_date_list.reverse()
  43             upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
  44             upload_date_list[2] = '%02d' % int(upload_date_list[2])
  45             upload_date = ''.join(upload_date_list)
  46         else:
  47             upload_date = None
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'description': description,
  53             'thumbnail': thumbnail,
  54             'upload_date': upload_date,
  55             'formats': [{
  56                 'url': video_url,
  57                 'vcodec': 'none',
  58             }],
  59         }