From 211fd6c674f9294d3a1d22b0e7f519dcec0303e5 Mon Sep 17 00:00:00 2001 From: Georg Jaehnig Date: Fri, 30 May 2014 16:35:17 +0200 Subject: [PATCH] added spiegel.tv --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/spiegeltv.py | 73 +++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 youtube_dl/extractor/spiegeltv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index def58f1d6a..b689dc3c99 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 0000000000..acb85ee64f --- /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[\-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'(.*?)', 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