1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 00:16:48 +00:00
youtube-dl/youtube_dl/extractor/franceinter.py
2020-11-22 19:38:45 +01:00

60 lines
2.2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import month_by_name
class FranceInterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
_TEST = {
'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
'md5': '9e54d7bdb6fdc02a841007f8a975c094',
'info_dict': {
'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
'ext': 'mp3',
'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
'description': 'md5:401969c5d318c061f86bda1fa359292b',
'thumbnail': r're:^https?://.*\.jpg',
'upload_date': '20160907',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video url', group='url')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
upload_date_str = self._search_regex(
r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
webpage, 'upload date', fatal=False)
if upload_date_str:
upload_date_list = upload_date_str.split()
upload_date_list.reverse()
upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
upload_date_list[2] = '%02d' % int(upload_date_list[2])
upload_date = ''.join(upload_date_list)
else:
upload_date = None
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
}