youtube_dl/extractor/chilloutzone.py

   1 import re
   2 import base64
   3 import urllib
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8 video_container = ('.mp4', '.mkv', '.flv')
   9
  10 class ChilloutzoneIE(InfoExtractor):
  11     _VALID_URL = r'(?:https?://)?(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+).html'
  12     _TEST = {
  13         'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
  14         'md5': 'a76f3457e813ea0037e5244f509e66d1',
  15         'info_dict': {
  16             'id': 'enemene-meck-alle-katzen-weg',
  17             'ext': 'mp4',
  18             'title': 'Enemene Meck - Alle Katzen weg',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage_url = 'http://www.chilloutzone.net/video/' + video_id + '.html'
  27
  28         # Log that we are starting to download the page
  29         self.report_download_webpage(webpage_url)
  30         webpage = self._download_webpage(webpage_url, video_id)
  31
  32         # Log that we are starting to parse the page
  33         self.report_extraction(video_id)
  34         # Find base64 decoded file info
  35         base64_video_info = self._html_search_regex(r'var cozVidData = "(.+?)";', webpage, u'video Data')
  36         # decode string and find video file
  37         decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
  38         video_info_dict = json.loads(decoded_video_info)
  39         # get video information from dict
  40         media_url = video_info_dict['mediaUrl']
  41         description = video_info_dict['description']
  42         title = video_info_dict['title']
  43         native_platform = video_info_dict['nativePlatform']
  44         native_video_id = video_info_dict['nativeVideoId']
  45         source_priority = video_info_dict['sourcePriority']
  46
  47
  48         # Start video extraction
  49         video_url = ''
  50         # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
  51         if native_platform == None:
  52             # Look for other video urls
  53             video_url = self._html_search_regex(r'<iframe.* src="(.+?)".*', webpage, u'fallback Video URL')
  54             if 'youtube' in video_url:
  55                 self.to_screen(u'Youtube video detected:')
  56                 return self.url_result(video_url, ie='Youtube')
  57
  58         # For debugging purposes
  59         #print video_info_dict
  60         #print native_platform
  61         #print native_video_id
  62         #print source_priority
  63         #print media_url
  64
  65         # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
  66         # the own CDN
  67         if source_priority == 'native':
  68             if native_platform == 'youtube':
  69                 self.to_screen(u'Youtube video detected:')
  70                 video_url = 'https://www.youtube.com/watch?v=' + native_video_id
  71                 return self.url_result(video_url, ie='Youtube')
  72             if native_platform == 'vimeo':
  73                 self.to_screen(u'Vimeo video detected:')
  74                 video_url = 'http://vimeo.com/' + native_video_id
  75                 return self.url_result(video_url, ie='Vimeo')
  76
  77         # No redirect, use coz media url
  78         video_url = media_url
  79         if video_url.endswith('.mp4') == False:
  80             self.report_warning(u'Url does not contain a video container')
  81             return []
  82
  83
  84         return [{
  85             'id':        video_id,
  86             'url':       video_url,
  87             'ext':       'mp4',
  88             'title':     title,
  89             'description': description,
  90         }]
  91
  92
  93