added new InfoExtractor for myspass.de

This commit is contained in:
bastik 2013-02-16 13:46:13 +01:00
parent 906417c7c5
commit 1ad5d872b9

View File

@ -3968,6 +3968,63 @@ class KeekIE(InfoExtractor):
} }
return [info] return [info]
class MyspassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
IE_NAME = u'myspass'
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
# video id is the last path element of the URL
# usually there is a trailing slash, so also try the second but last
url_path = compat_urllib_parse_urlparse(url).path
url_parent_path, video_id = os.path.split(url_path)
if not video_id:
_, video_id = os.path.split(url_parent_path)
# get metadata
metadata_url = META_DATA_URL_TEMPLATE % video_id
metadata_text = self._download_webpage(metadata_url, video_id)
metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
# extract values from metadata
url_flv_el = metadata.find('url_flv')
if url_flv_el is None:
self._downloader.trouble(u'ERROR: unable to extract download url')
return
video_url = url_flv_el.text
extension = os.path.splitext(video_url)[1][1:]
title_el = metadata.find('title')
if title_el is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
title = title_el.text
format_id_el = metadata.find('format_id')
if format_id_el is None:
format = ext
else:
format = format_id_el.text
description_el = metadata.find('description')
if description_el is not None:
description = description_el.text
else:
description = None
imagePreview_el = metadata.find('imagePreview')
if imagePreview_el is not None:
thumbnail = imagePreview_el.text
else:
thumbnail = None
info = {
'id': video_id,
'url': video_url,
'title': title,
'ext': extension,
'format': format,
'thumbnail': thumbnail,
'description': description
}
return [info]
def gen_extractors(): def gen_extractors():
""" Return a list of an instance of every supported extractor. """ Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL. The order does matter; the first extractor matched is the one handling the URL.
@ -4015,6 +4072,7 @@ def gen_extractors():
RBMARadioIE(), RBMARadioIE(),
EightTracksIE(), EightTracksIE(),
KeekIE(), KeekIE(),
MyspassIE(),
GenericIE() GenericIE()
] ]