aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorGeorg Jaehnig <georg@jaehnig.org>2014-05-30 16:35:17 +0200
committerGeorg Jaehnig <georg@jaehnig.org>2014-05-30 16:35:17 +0200
commit211fd6c674f9294d3a1d22b0e7f519dcec0303e5 (patch)
tree58430b72b970b8fb999a3ff4db61da24b530b957 /youtube_dl/extractor
parent87fe568c28e4e59e6e72d292266f8f3a88a41814 (diff)
added spiegel.tv
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/spiegeltv.py73
2 files changed, 74 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index def58f1d6..b689dc3c9 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -258,6 +258,7 @@ from .southparkstudios import (
from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
+from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py
new file mode 100644
index 000000000..acb85ee64
--- /dev/null
+++ b/youtube_dl/extractor/spiegeltv.py
@@ -0,0 +1,73 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+import urllib
+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/',
+ 'md5': '700d62dc485f3a81cf9d52144e5ead59',
+ 'info_dict': {
+ 'id': 'flug-mh370',
+ 'ext': 'm4v',
+ 'title': 'Flug MH370',
+ 'description': 'Das Rätsel um die Boeing 777 der Malaysia-Airlines',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ # TODO more code goes here, for example ...
+ 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';
+
+ version_json_code = urllib.urlopen('%s/version.json' % apihost).read()
+ version_json = json.loads(version_json_code)
+ version_name = version_json['version_name']
+
+ slug_json_code = urllib.urlopen('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id)).read()
+ slug_json = json.loads(slug_json_code)
+ oid = slug_json['object_id']
+
+ media_json_code = urllib.urlopen('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid)).read()
+ media_json = json.loads(media_json_code)
+
+ uuid = media_json['uuid']
+ is_wide = media_json['is_wide']
+
+ server_json_code = urllib.urlopen('http://www.spiegel.tv/streaming_servers/').read()
+ server_json = json.loads(server_json_code)
+ 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