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\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
  11     _TEST = {
  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
  24     @staticmethod
  25     def _extract_url(webpage):
  26         urls = JWPlatformIE._extract_urls(webpage)
  27         return urls[0] if urls else None
  28
  29     @staticmethod
  30     def _extract_urls(webpage):
  31         return re.findall(
  32             r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})',
  33             webpage)
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37         json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id)
  38         return self._parse_jwplayer_data(json_data, video_id)