youtube-dl

commit 4e0fb1280a8c1b392e5ce71aff796c94a12976a0
parent 24f5251cce172f0e403b4178819dd26b3873f021
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sat,  7 Jun 2014 15:21:33 +0200

Merge remote-tracking branch 'georgjaehnig/spiegeltv'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/spiegeltv.py
 | 
68
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 69 insertions(+), 0 deletions(-)
diff --git 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
@@ -0,0 +1,68 @@
+# 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,
+        }
+    }
+
+    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';
+
+        version_json      = self._download_json('%s/version.json' % apihost, None)
+        version_name      = version_json['version_name']
+
+        slug_json         = self._download_json('%s/%s/restapi/slugs/%s.json' % (apihost, version_name, video_id), None)
+        oid               = slug_json['object_id']
+              
+        media_json        = self._download_json('%s/%s/restapi/media/%s.json' % (apihost, version_name, oid), None)
+        uuid              = media_json['uuid']
+        is_wide           = media_json['is_wide']
+
+        server_json       = self._download_json('http://www.spiegel.tv/streaming_servers/', None)
+        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