yt_dlp/extractor/franceinter.py

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