youtube_dl/extractor/byutv.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class BYUtvIE(InfoExtractor):
  11     _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
  12     _TEST = {
  13         'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
  14         'info_dict': {
  15             'id': 'granite-flats-talking',
  16             'ext': 'mp4',
  17             'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
  18             'title': 'Talking',
  19             'thumbnail': 're:^https?://.*promo.*'
  20         },
  21         'params': {
  22             'skip_download': True,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('video_id')
  29
  30         webpage = self._download_webpage(url, video_id)
  31         episode_code = self._search_regex(
  32             r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
  33         episode_json = re.sub(
  34             r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
  35         ep = json.loads(episode_json)
  36
  37         if ep['providerType'] == 'Ooyala':
  38             return {
  39                 '_type': 'url_transparent',
  40                 'ie_key': 'Ooyala',
  41                 'url': 'ooyala:%s' % ep['providerId'],
  42                 'id': video_id,
  43                 'title': ep['title'],
  44                 'description': ep.get('description'),
  45                 'thumbnail': ep.get('imageThumbnail'),
  46             }
  47         else:
  48             raise ExtractorError('Unsupported provider %s' % ep['provider'])