1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-30 12:32:51 +08:00
youtube-dl/youtube_dl/extractor/golem.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
2014-12-13 12:35:45 +01:00

72 lines
2.1 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
determine_ext,
)
class GolemIE(InfoExtractor):
_VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
_TEST = {
'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
'info_dict': {
'id': '14095',
'format_id': 'high',
'ext': 'mp4',
'title': 'iPhone 6 und 6 Plus - Test',
'duration': 300.44,
'filesize': 65309548,
}
}
_PREFIX = 'http://video.golem.de'
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml(
'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
info = {
'id': video_id,
'title': config.findtext('./title', 'golem'),
'duration': self._float(config.findtext('./playtime'), 'duration'),
}
formats = []
for e in config:
url = e.findtext('./url')
if not url:
continue
formats.append({
'format_id': e.tag,
'url': compat_urlparse.urljoin(self._PREFIX, url),
'height': self._int(e.get('height'), 'height'),
'width': self._int(e.get('width'), 'width'),
'filesize': self._int(e.findtext('filesize'), 'filesize'),
'ext': determine_ext(e.findtext('./filename')),
})
self._sort_formats(formats)
info['formats'] = formats
thumbnails = []
for e in config.findall('.//teaser'):
url = e.findtext('./url')
if not url:
continue
thumbnails.append({
'url': compat_urlparse.urljoin(self._PREFIX, url),
'width': self._int(e.get('width'), 'thumbnail width'),
'height': self._int(e.get('height'), 'thumbnail height'),
})
info['thumbnails'] = thumbnails
return info