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
   8
   9 class JWPlatformIE(InfoExtractor):
  10     _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})'
  11     _TESTS = [{
  12         'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
  13         'md5': 'fa8899fa601eb7c83a64e9d568bdf325',
  14         'info_dict': {
  15             'id': 'nPripu9l',
  16             'ext': 'mov',
  17             'title': 'Big Buck Bunny Trailer',
  18             'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.',
  19             'upload_date': '20081127',
  20             'timestamp': 1227796140,
  21         }
  22     }, {
  23         'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js',
  24         'only_matching': True,
  25     }]
  26
  27     @staticmethod
  28     def _extract_url(webpage):
  29         urls = JWPlatformIE._extract_urls(webpage)
  30         return urls[0] if urls else None
  31
  32     @staticmethod
  33     def _extract_urls(webpage):
  34         return re.findall(
  35             r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})',
  36             webpage)
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40         json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
  41         return self._parse_jwplayer_data(json_data, video_id)