]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/franceinter.py
[ie/orf:on] Improve extraction (#9677)
[yt-dlp.git] / yt_dlp / extractor / franceinter.py
CommitLineData
bf6705f5 1from .common import InfoExtractor
0002962f 2from ..utils import month_by_name
677b3ce8
PH
3
4
bf6705f5 5class FranceInterIE(InfoExtractor):
a942d6cb 6 _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
7
677b3ce8 8 _TEST = {
c51a7f0b
S
9 'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
10 'md5': '9e54d7bdb6fdc02a841007f8a975c094',
611c1dd9 11 'info_dict': {
c51a7f0b 12 'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
532f5bff 13 'ext': 'mp3',
c51a7f0b
S
14 'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
15 'description': 'md5:401969c5d318c061f86bda1fa359292b',
70c5802b 16 'thumbnail': r're:^https?://.*\.jpg',
c51a7f0b 17 'upload_date': '20160907',
677b3ce8
PH
18 },
19 }
bf6705f5 20
677b3ce8 21 def _real_extract(self, url):
2db58069 22 video_id = self._match_id(url)
26844eb5 23
677b3ce8 24 webpage = self._download_webpage(url, video_id)
532f5bff 25
a942d6cb 26 video_url = self._search_regex(
0002962f
S
27 r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
28 webpage, 'video url', group='url')
a942d6cb 29
30 title = self._og_search_title(webpage)
31 description = self._og_search_description(webpage)
70c5802b 32 thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
a942d6cb 33
0002962f 34 upload_date_str = self._search_regex(
b2a027fc 35 r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
0002962f
S
36 webpage, 'upload date', fatal=False)
37 if upload_date_str:
38 upload_date_list = upload_date_str.split()
39 upload_date_list.reverse()
52dc8a9b 40 upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
c51a7f0b 41 upload_date_list[2] = '%02d' % int(upload_date_list[2])
0002962f
S
42 upload_date = ''.join(upload_date_list)
43 else:
44 upload_date = None
532f5bff 45
677b3ce8
PH
46 return {
47 'id': video_id,
532f5bff
S
48 'title': title,
49 'description': description,
70c5802b 50 'thumbnail': thumbnail,
0002962f 51 'upload_date': upload_date,
677b3ce8
PH
52 'formats': [{
53 'url': video_url,
54 'vcodec': 'none',
55 }],
677b3ce8 56 }