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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import unsmuggle_url
   8
   9
  10 class JWPlatformIE(InfoExtractor):
  11     _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
  12     _TESTS = [{
  13         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
  14         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
  15         'info_dict': {
  16             'id': 'nPripu9l',
  17             'ext': 'mov',
  18             'title': 'Big Buck Bunny Trailer',
  19             'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.',
  20             'upload_date': '20081127',
  21             'timestamp': 1227796140,
  22         }
  23     }, {
  24         'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
  25         'only_matching': True,
  26     }]
  27
  28     @staticmethod
  29     def _extract_url(webpage):
  30         urls = JWPlatformIE._extract_urls(webpage)
  31         return urls[0] if urls else None
  32
  33     @staticmethod
  34     def _extract_urls(webpage):
  35         return re.findall(
  36             r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})',
  37             webpage)
  38
  39     def _real_extract(self, url):
  40         url, smuggled_data = unsmuggle_url(url, {})
  41         self._initialize_geo_bypass({
  42             'countries': smuggled_data.get('geo_countries'),
  43         })
  44         video_id = self._match_id(url)
  45         json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
  46         return self._parse_jwplayer_data(json_data, video_id)