ytdl-nightly/youtube_dl/extractor/anitube.py

54 lines
1.5 KiB
Python
Raw Normal View History

2013-11-16 15:26:34 +01:00
import re
from .common import InfoExtractor
class AnitubeIE(InfoExtractor):
IE_NAME = u'anitube.se'
2013-11-20 06:35:02 +01:00
_VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
2013-11-16 15:26:34 +01:00
_TEST = {
u'url': u'http://www.anitube.se/video/36621',
2013-11-20 06:35:02 +01:00
u'md5': u'59d0eeae28ea0bc8c05e7af429998d43',
u'file': u'36621.mp4',
2013-11-16 15:26:34 +01:00
u'info_dict': {
u'id': u'36621',
u'ext': u'mp4',
u'title': u'Recorder to Randoseru 01',
},
2013-11-20 07:46:44 +01:00
u'skip': u'Blocked in the US',
2013-11-16 15:26:34 +01:00
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
webpage, u'key')
config_xml = self._download_xml('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
2013-11-16 15:26:34 +01:00
key)
video_title = config_xml.find('title').text
formats = []
video_url = config_xml.find('file')
if video_url is not None:
formats.append({
'format_id': 'sd',
'url': video_url.text,
})
video_url = config_xml.find('filehd')
if video_url is not None:
formats.append({
'format_id': 'hd',
'url': video_url.text,
})
return {
'id': video_id,
'title': video_title,
'formats': formats
}