# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
ExtractorError,
qualities,
unified_strdate,
clean_html,
)
class UltimediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ultimedia\.com/default/index/video[^/]+/id/(?P[\d+a-z]+)'
_TESTS = [{
# news
'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
'md5': '276a0e49de58c7e85d32b057837952a2',
'info_dict': {
'id': 's8uk0r',
'ext': 'mp4',
'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
'description': 'md5:3e5c8fd65791487333dda5db8aed32af',
'thumbnail': 're:^https?://.*\.jpg',
'upload_date': '20150317',
},
}, {
# music
'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
'md5': '2ea3513813cf230605c7e2ffe7eca61c',
'info_dict': {
'id': 'xvpfp8',
'ext': 'mp4',
'title': "Two - C'est la vie (Clip)",
'description': 'Two',
'thumbnail': 're:^https?://.*\.jpg',
'upload_date': '20150224',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
deliver_url = self._proto_relative_url(self._search_regex(
r'
', webpage,
'description', fatal=False))
upload_date = unified_strdate(self._search_regex(
r'Ajouté le\s*([^<]+)', webpage,
'upload date', fatal=False))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'formats': formats,
}