0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 23:35:04 +00:00
yt-dlp/youtube_dl/extractor/ina.py

37 lines
1 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
2013-06-23 20:28:19 +00:00
import re
from .common import InfoExtractor
class InaIE(InfoExtractor):
2015-06-30 14:47:14 +00:00
_VALID_URL = r'https?://(?:www\.)?ina\.fr/video/(?P<id>I?[A-Z0-9]+)'
2013-06-27 18:46:46 +00:00
_TEST = {
'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
'info_dict': {
'id': 'I12055569',
'ext': 'mp4',
'title': 'François Hollande "Je crois que c\'est clair"',
2013-06-27 18:46:46 +00:00
}
}
2013-06-23 20:28:19 +00:00
def _real_extract(self, url):
2013-06-23 20:28:19 +00:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mrss_url = 'http://player.ina.fr/notices/%s.mrss' % video_id
info_doc = self._download_xml(mrss_url, video_id)
2013-06-23 20:28:19 +00:00
self.report_extraction(video_id)
video_url = info_doc.find('.//{http://search.yahoo.com/mrss/}player').attrib['url']
2013-06-23 20:28:19 +00:00
return {
'id': video_id,
'url': video_url,
'title': info_doc.find('.//title').text,
}