Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/srmediathek.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import js_to_json
   8
   9
  10 class SRMediathekIE(InfoExtractor):
  11     IE_DESC = 'Süddeutscher Rundfunk'
  12     _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
  13
  14     _TEST = {
  15         'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
  16         'info_dict': {
  17             'id': '28455',
  18             'ext': 'mp4',
  19             'title': 'sportarena (26.10.2014)',
  20             '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 ',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27         webpage = self._download_webpage(url, video_id)
  28
  29         murls = json.loads(js_to_json(self._search_regex(
  30             r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs')))
  31         formats = [{'url': murl} for murl in murls]
  32         self._sort_formats(formats)
  33
  34         title = json.loads(js_to_json(self._search_regex(
  35             r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0]
  36
  37         return {
  38             'id': video_id,
  39             'title': title,
  40             'formats': formats,
  41             'description': self._og_search_description(webpage),
  42             'thumbnail': self._og_search_thumbnail(webpage),
  43         }