yt_dlp/extractor/tfo.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     HEADRequest,
   6     ExtractorError,
   7     int_or_none,
   8     clean_html,
   9 )
  10
  11
  12 class TFOIE(InfoExtractor):
  13     _GEO_COUNTRIES = ['CA']
  14     _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
  15     _TEST = {
  16         'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
  17         'md5': 'cafbe4f47a8dae0ca0159937878100d6',
  18         'info_dict': {
  19             'id': '7da3d50e495c406b8fc0b997659cc075',
  20             'ext': 'mp4',
  21             'title': 'Video Game Hackathon',
  22             'description': 'md5:558afeba217c6c8d96c60e5421795c07',
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
  29         infos = self._download_json(
  30             'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
  31                 'product_id': video_id,
  32             }).encode(), headers={
  33                 'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
  34             })
  35         if infos.get('success') == 0:
  36             if infos.get('code') == 'ErrGeoBlocked':
  37                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
  38             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
  39         video_data = infos['data']
  40
  41         return {
  42             '_type': 'url_transparent',
  43             'id': video_id,
  44             'url': 'limelight:media:' + video_data['llid'],
  45             'title': video_data['title'],
  46             'description': video_data.get('description'),
  47             'series': video_data.get('collection'),
  48             'season_number': int_or_none(video_data.get('season')),
  49             'episode_number': int_or_none(video_data.get('episode')),
  50             'duration': int_or_none(video_data.get('duration')),
  51             'ie_key': 'LimelightMedia',
  52         }