_ Git - youtube-dl/blob - youtube_dl/extractor/chilloutzone.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import base64
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import clean_html
   9
  10
  11 class ChilloutzoneIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
  13     _TEST = {
  14         'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
  15         'md5': 'a76f3457e813ea0037e5244f509e66d1',
  16         'info_dict': {
  17             'id': 'enemene-meck-alle-katzen-weg',
  18             'ext': 'mp4',
  19             'title': 'Enemene Meck - Alle Katzen weg',
  20             'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         base64_video_info = self._html_search_regex(
  31             r'var cozVidData = "(.+?)";', webpage, 'video data')
  32         decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
  33         video_info_dict = json.loads(decoded_video_info)
  34
  35         # get video information from dict
  36         video_url = video_info_dict['mediaUrl']
  37         description = clean_html(video_info_dict.get('description'))
  38         title = video_info_dict['title']
  39         native_platform = video_info_dict['nativePlatform']
  40         native_video_id = video_info_dict['nativeVideoId']
  41         source_priority = video_info_dict['sourcePriority']
  42
  43         # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
  44         if native_platform is None:
  45             youtube_url = self._html_search_regex(
  46                 r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
  47                 webpage, 'fallback video URL', default=None)
  48             if youtube_url is not None:
  49                 return self.url_result(youtube_url, ie='Youtube')
  50
  51         # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
  52         # the own CDN
  53         if source_priority == 'native':
  54             if native_platform == 'youtube':
  55                 return self.url_result(video_id, ie='Youtube')
  56             if native_platform == 'vimeo':
  57                 return self.url_result(
  58                     'http://vimeo.com/' + native_video_id, ie='Vimeo')
  59
  60         if not video_url:
  61             raise ExtractorError('No video found')
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'ext': 'mp4',
  67             'title': title,
  68             'description': description,
  69         }