_ 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 (
   9     clean_html,
  10     ExtractorError
  11 )
  12
  13
  14 class ChilloutzoneIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
  16     _TEST = {
  17         'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
  18         'md5': 'a76f3457e813ea0037e5244f509e66d1',
  19         'info_dict': {
  20             'id': 'enemene-meck-alle-katzen-weg',
  21             'ext': 'mp4',
  22             'title': 'Enemene Meck - Alle Katzen weg',
  23             'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         base64_video_info = self._html_search_regex(
  34             r'var cozVidData = "(.+?)";', webpage, 'video data')
  35         decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
  36         video_info_dict = json.loads(decoded_video_info)
  37
  38         # get video information from dict
  39         video_url = video_info_dict['mediaUrl']
  40         description = clean_html(video_info_dict.get('description'))
  41         title = video_info_dict['title']
  42         native_platform = video_info_dict['nativePlatform']
  43         native_video_id = video_info_dict['nativeVideoId']
  44         source_priority = video_info_dict['sourcePriority']
  45
  46         # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
  47         if native_platform is None:
  48             youtube_url = self._html_search_regex(
  49                 r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
  50                 webpage, 'fallback video URL', default=None)
  51             if youtube_url is not None:
  52                 return self.url_result(youtube_url, ie='Youtube')
  53
  54         # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
  55         # the own CDN
  56         if source_priority == 'native':
  57             if native_platform == 'youtube':
  58                 return self.url_result(native_video_id, ie='Youtube')
  59             if native_platform == 'vimeo':
  60                 return self.url_result(
  61                     'http://vimeo.com/' + native_video_id, ie='Vimeo')
  62
  63         if not video_url:
  64             raise ExtractorError('No video found')
  65
  66         return {
  67             'id': video_id,
  68             'url': video_url,
  69             'ext': 'mp4',
  70             'title': title,
  71             'description': description,
  72         }