from .common import InfoExtractor
from ..utils import (
ExtractorError,
- compat_urllib_request,
+ sanitized_Request,
urlencode_postdata,
+ xpath_text,
xpath_with_ns,
)
_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
-_find = lambda el, p: el.find(_x(p)).text.strip()
class NosVideoIE(InfoExtractor):
_PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = {
- 'url': 'http://nosvideo.com/?v=drlp6s40kg54',
- 'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
+ 'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
+ 'md5': '6124ed47130d8be3eacae635b071e6b6',
'info_dict': {
- 'id': 'drlp6s40kg54',
+ 'id': 'mu8fle7g7rpq',
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
fields = {
'id': video_id,
'op': 'download1',
'method_free': 'Continue to Video',
}
- req = compat_urllib_request.Request(url, urlencode_postdata(fields))
+ req = sanitized_Request(url, urlencode_postdata(fields))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id,
'Downloading download page')
playlist = self._download_xml(playlist_url, video_id)
track = playlist.find(_x('.//xspf:track'))
- title = _find(track, './xspf:title')
- url = _find(track, './xspf:file')
- thumbnail = _find(track, './xspf:image')
+ if track is None:
+ raise ExtractorError(
+ 'XML playlist is missing the \'track\' element',
+ expected=True)
+ title = xpath_text(track, _x('./xspf:title'), 'title')
+ url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
+ thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
+ if title is not None:
+ title = title.strip()
formats = [{
'format_id': 'sd',