2013-06-23 20:28:19 +00:00
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class InaIE(InfoExtractor):
|
|
|
|
|
"""Information Extractor for Ina.fr"""
|
2013-07-25 07:52:53 +00:00
|
|
|
_VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I?[A-F0-9]+)/.*'
|
2013-06-27 18:46:46 +00:00
|
|
|
_TEST = {
|
2014-01-14 21:01:31 +00:00
|
|
|
u'url': u'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
|
2013-06-27 18:46:46 +00:00
|
|
|
u'file': u'I12055569.mp4',
|
|
|
|
|
u'md5': u'a667021bf2b41f8dc6049479d9bb38a3',
|
|
|
|
|
u'info_dict': {
|
|
|
|
|
u"title": u"Fran\u00e7ois Hollande \"Je crois que c'est clair\""
|
|
|
|
|
}
|
|
|
|
|
}
|
2013-06-23 20:28:19 +00:00
|
|
|
|
|
|
|
|
def _real_extract(self,url):
|
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
|
|
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
|
mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
|
|
|
|
|
video_extension = 'mp4'
|
|
|
|
|
webpage = self._download_webpage(mrss_url, video_id)
|
|
|
|
|
|
|
|
|
|
self.report_extraction(video_id)
|
|
|
|
|
|
|
|
|
|
video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)',
|
|
|
|
|
webpage, u'video URL')
|
|
|
|
|
|
|
|
|
|
video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>',
|
|
|
|
|
webpage, u'title')
|
|
|
|
|
|
|
|
|
|
return [{
|
|
|
|
|
'id': video_id,
|
|
|
|
|
'url': video_url,
|
|
|
|
|
'ext': video_extension,
|
|
|
|
|
'title': video_title,
|
|
|
|
|
}]
|
