youtube_dl/extractor/ondemandkorea.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     js_to_json,
   8 )
   9
  10
  11 class OnDemandKoreaIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
  13     _GEO_COUNTRIES = ['US', 'CA']
  14     _TEST = {
  15         'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',
  16         'info_dict': {
  17             'id': 'ask-us-anything-e43',
  18             'ext': 'mp4',
  19             'title': 'Ask Us Anything : E43',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21         },
  22         'params': {
  23             'skip_download': 'm3u8 download'
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id, fatal=False)
  30
  31         if not webpage:
  32             # Page sometimes returns captcha page with HTTP 403
  33             raise ExtractorError(
  34                 'Unable to access page. You may have been blocked.',
  35                 expected=True)
  36
  37         if 'msg_block_01.png' in webpage:
  38             self.raise_geo_restricted(
  39                 msg='This content is not available in your region',
  40                 countries=self._GEO_COUNTRIES)
  41
  42         if 'This video is only available to ODK PLUS members.' in webpage:
  43             raise ExtractorError(
  44                 'This video is only available to ODK PLUS members.',
  45                 expected=True)
  46
  47         title = self._og_search_title(webpage)
  48
  49         jw_config = self._parse_json(
  50             self._search_regex(
  51                 r'(?s)jwplayer\(([\'"])(?:(?!\1).)+\1\)\.setup\s*\((?P<options>.+?)\);',
  52                 webpage, 'jw config', group='options'),
  53             video_id, transform_source=js_to_json)
  54         info = self._parse_jwplayer_data(
  55             jw_config, video_id, require_title=False, m3u8_id='hls',
  56             base_url=url)
  57
  58         info.update({
  59             'title': title,
  60             'thumbnail': self._og_search_thumbnail(webpage),
  61         })
  62         return info