[srmediathek] New extractor

This commit is contained in:
Philipp Hagemeister 2014-10-26 23:23:10 +01:00
parent c9f08154a3
commit 2bcae58d46
2 changed files with 44 additions and 0 deletions

View file

@ -355,6 +355,7 @@
from .sport5 import Sport5IE
from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE
from .srmediathek import SRMediathekIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE

View file

@ -0,0 +1,43 @@
# encoding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import js_to_json
class SRMediathekIE(InfoExtractor):
IE_NAME = 'Süddeutscher Rundfunk'
_VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
'info_dict': {
'id': '28455',
'ext': 'mp4',
'title': 'sportarena (26.10.2014)',
'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
'thumbnail': 're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
urls = json.loads(js_to_json(self._search_regex(
r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs')))
formats = [{'url': url} for url in urls]
self._sort_formats(formats)
title = json.loads(js_to_json(self._search_regex(
r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0]
return {
'id': video_id,
'title': title,
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}