ytdl-nightly/youtube_dl/extractor/spiegeltv.py

81 lines
2.5 KiB
Python
Raw Normal View History

2014-05-30 16:35:17 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-06-07 15:33:45 +02:00
2014-05-30 16:35:17 +02:00
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',
2014-06-07 15:33:45 +02:00
'thumbnail': 're:http://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
2014-05-30 16:35:17 +02:00
}
}
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')
2014-06-07 15:33:45 +02:00
apihost = 'http://spiegeltv-ivms2-restapi.s3.amazonaws.com'
version_json = self._download_json(
'%s/version.json' % apihost, video_id,
note='Downloading version information')
version_name = version_json['version_name']
2014-05-30 16:35:17 +02:00
2014-06-07 15:33:45 +02:00
slug_json = self._download_json(
'%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id),
video_id,
note='Downloading object information')
oid = slug_json['object_id']
2014-05-30 16:35:17 +02:00
2014-06-07 15:33:45 +02:00
media_json = self._download_json(
'%s/%s/restapi/media/%s.json' % (apihost, version_name, oid),
video_id, note='Downloading media information')
uuid = media_json['uuid']
is_wide = media_json['is_wide']
2014-05-30 16:35:17 +02:00
2014-06-07 15:33:45 +02:00
server_json = self._download_json(
'http://www.spiegel.tv/streaming_servers/', video_id,
note='Downloading server information')
server = server_json[0]['endpoint']
2014-05-30 16:35:17 +02:00
thumbnails = []
for image in media_json['images']:
2014-06-07 15:33:45 +02:00
thumbnails.append({
'url': image['url'],
'width': image['width'],
'height': image['height'],
})
2014-05-30 16:35:17 +02:00
description = media_json['subtitle']
2014-06-07 15:33:45 +02:00
duration = media_json['duration_in_ms'] / 1000.
2014-05-30 16:35:17 +02:00
if is_wide:
2014-06-07 15:33:45 +02:00
format = '16x9'
2014-05-30 16:35:17 +02:00
else:
2014-06-07 15:33:45 +02:00
format = '4x3'
2014-05-30 16:35:17 +02:00
url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v'
2014-06-07 15:33:45 +02:00
return {
2014-05-30 16:35:17 +02:00
'id': video_id,
'title': title,
'url': url,
'ext': 'm4v',
'description': description,
'duration': duration,
'thumbnails': thumbnails
2014-06-07 15:33:45 +02:00
}