Raphaël G. Git Repositories - youtubedl/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 .youtube import YoutubeIE
   9 from ..utils import (
  10     clean_html,
  11     ExtractorError
  12 )
  13
  14
  15 class ChilloutzoneIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
  17     _TESTS = [{
  18         'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
  19         'md5': 'a76f3457e813ea0037e5244f509e66d1',
  20         'info_dict': {
  21             'id': 'enemene-meck-alle-katzen-weg',
  22             'ext': 'mp4',
  23             'title': 'Enemene Meck - Alle Katzen weg',
  24             'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
  25         },
  26     }, {
  27         'note': 'Video hosted at YouTube',
  28         'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
  29         'info_dict': {
  30             'id': '1YVQaAgHyRU',
  31             'ext': 'mp4',
  32             'title': '16 Photos Taken 1 Second Before Disaster',
  33             'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
  34             'uploader': 'BuzzFeedVideo',
  35             'uploader_id': 'BuzzFeedVideo',
  36             'upload_date': '20131105',
  37         },
  38     }, {
  39         'note': 'Video hosted at Vimeo',
  40         'url': 'http://www.chilloutzone.net/video/icon-blending.html',
  41         'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
  42         'info_dict': {
  43             'id': '85523671',
  44             'ext': 'mp4',
  45             'title': 'The Sunday Times - Icons',
  46             'description': 're:(?s)^Watch the making of - makingoficons.com.{300,}',
  47             'uploader': 'Us',
  48             'uploader_id': 'usfilms',
  49             'upload_date': '20140131'
  50         },
  51     }]
  52
  53     def _real_extract(self, url):
  54         mobj = re.match(self._VALID_URL, url)
  55         video_id = mobj.group('id')
  56
  57         webpage = self._download_webpage(url, video_id)
  58
  59         base64_video_info = self._html_search_regex(
  60             r'var cozVidData = "(.+?)";', webpage, 'video data')
  61         decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8')
  62         video_info_dict = json.loads(decoded_video_info)
  63
  64         # get video information from dict
  65         video_url = video_info_dict['mediaUrl']
  66         description = clean_html(video_info_dict.get('description'))
  67         title = video_info_dict['title']
  68         native_platform = video_info_dict['nativePlatform']
  69         native_video_id = video_info_dict['nativeVideoId']
  70         source_priority = video_info_dict['sourcePriority']
  71
  72         # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
  73         if native_platform is None:
  74             youtube_url = YoutubeIE._extract_url(webpage)
  75             if youtube_url:
  76                 return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  77
  78         # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
  79         # the own CDN
  80         if source_priority == 'native':
  81             if native_platform == 'youtube':
  82                 return self.url_result(native_video_id, ie='Youtube')
  83             if native_platform == 'vimeo':
  84                 return self.url_result(
  85                     'http://vimeo.com/' + native_video_id, ie='Vimeo')
  86
  87         if not video_url:
  88             raise ExtractorError('No video found')
  89
  90         return {
  91             'id': video_id,
  92             'url': video_url,
  93             'ext': 'mp4',
  94             'title': title,
  95             'description': description,
  96         }