youtube-dl/youtube_dl/extractor/spiegeltv.py

69 lines
2.3 KiB
Python
Raw Normal View History

2014-05-30 14:35:17 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class SpiegeltvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)'
_TEST = {
'url': 'http://www.spiegel.tv/filme/flug-mh370/',
'info_dict': {
'id': 'flug-mh370',
'ext': 'm4v',
'title': 'Flug MH370',
'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
},
'params': {
# rtmp download
'skip_download': True,
2014-05-30 14:35:17 +00:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title')
apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com';
2014-05-30 15:51:36 +00:00
version_json = self._download_json('%s/version.json' % apihost, None)
2014-05-30 14:35:17 +00:00
version_name = version_json['version_name']
2014-05-30 15:51:36 +00:00
slug_json = self._download_json('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), None)
2014-05-30 14:35:17 +00:00
oid = slug_json['object_id']
2014-05-30 15:51:36 +00:00
media_json = self._download_json('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), None)
2014-05-30 14:35:17 +00:00
uuid = media_json['uuid']
is_wide = media_json['is_wide']
2014-05-30 15:51:36 +00:00
server_json = self._download_json('http://www.spiegel.tv/streaming_servers/', None)
2014-05-30 14:35:17 +00:00
server = server_json[0]['endpoint']
thumbnails = []
for image in media_json['images']:
thumbnails.append({'url': image['url'], 'resolution': str(image['width']) + 'x' + str(image['height']) })
description = media_json['subtitle']
duration = int(round(media_json['duration_in_ms'] / 1000))
if is_wide:
format = '16x9'
else:
format = '4x3'
url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
return_dict = {
'id': video_id,
'title': title,
'url': url,
'ext': 'm4v',
'description': description,
'duration': duration,
'thumbnails': thumbnails
}
return return_dict