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