yt_dlp/extractor/tfo.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..networking import HEADRequest
   5 from ..utils import ExtractorError, clean_html, int_or_none
   6
   7
   8 class TFOIE(InfoExtractor):
   9     _GEO_COUNTRIES = ['CA']
  10     _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
  11     _TEST = {
  12         'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
  13         'md5': 'cafbe4f47a8dae0ca0159937878100d6',
  14         'info_dict': {
  15             'id': '7da3d50e495c406b8fc0b997659cc075',
  16             'ext': 'mp4',
  17             'title': 'Video Game Hackathon',
  18             'description': 'md5:558afeba217c6c8d96c60e5421795c07',
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
  25         infos = self._download_json(
  26             'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
  27                 'product_id': video_id,
  28             }).encode(), headers={
  29                 'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
  30             })
  31         if infos.get('success') == 0:
  32             if infos.get('code') == 'ErrGeoBlocked':
  33                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
  34             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
  35         video_data = infos['data']
  36
  37         return {
  38             '_type': 'url_transparent',
  39             'id': video_id,
  40             'url': 'limelight:media:' + video_data['llid'],
  41             'title': video_data['title'],
  42             'description': video_data.get('description'),
  43             'series': video_data.get('collection'),
  44             'season_number': int_or_none(video_data.get('season')),
  45             'episode_number': int_or_none(video_data.get('episode')),
  46             'duration': int_or_none(video_data.get('duration')),
  47             'ie_key': 'LimelightMedia',
  48         }