youtube_dl/extractor/byutv.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class BYUtvIE(InfoExtractor):
  10     _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<id>[^/?#]+)'
  11     _TEST = {
  12         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
  13         'md5': '05850eb8c749e2ee05ad5a1c34668493',
  14         'info_dict': {
  15             'id': 'studio-c-season-5-episode-5',
  16             'ext': 'mp4',
  17             'description': 'md5:e07269172baff037f8e8bf9956bc9747',
  18             'title': 'Season 5 Episode 5',
  19             'thumbnail': 're:^https?://.*\.jpg$',
  20             'duration': 1486.486,
  21         },
  22         'params': {
  23             'skip_download': True,
  24         },
  25         'add_ie': ['Ooyala'],
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32         episode_code = self._search_regex(
  33             r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
  34
  35         ep = self._parse_json(
  36             episode_code, video_id, transform_source=lambda s:
  37             re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
  38
  39         if ep['providerType'] == 'Ooyala':
  40             return {
  41                 '_type': 'url_transparent',
  42                 'ie_key': 'Ooyala',
  43                 'url': 'ooyala:%s' % ep['providerId'],
  44                 'id': video_id,
  45                 'title': ep['title'],
  46                 'description': ep.get('description'),
  47                 'thumbnail': ep.get('imageThumbnail'),
  48             }
  49         else:
  50             raise ExtractorError('Unsupported provider %s' % ep['provider'])