youtube_dl/extractor/tfo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     HEADRequest,
   9     ExtractorError,
  10     int_or_none,
  11     clean_html,
  12 )
  13
  14
  15 class TFOIE(InfoExtractor):
  16     _GEO_COUNTRIES = ['CA']
  17     _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
  18     _TEST = {
  19         'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
  20         'md5': '47c987d0515561114cf03d1226a9d4c7',
  21         'info_dict': {
  22             'id': '100463871',
  23             'ext': 'mp4',
  24             'title': 'Video Game Hackathon',
  25             'description': 'md5:558afeba217c6c8d96c60e5421795c07',
  26             'upload_date': '20160212',
  27             'timestamp': 1455310233,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
  34         infos = self._download_json(
  35             'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
  36                 'product_id': video_id,
  37             }).encode(), headers={
  38                 'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
  39             })
  40         if infos.get('success') == 0:
  41             if infos.get('code') == 'ErrGeoBlocked':
  42                 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
  43             raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
  44         video_data = infos['data']
  45
  46         return {
  47             '_type': 'url_transparent',
  48             'id': video_id,
  49             'url': 'limelight:media:' + video_data['llid'],
  50             'title': video_data['title'],
  51             'description': video_data.get('description'),
  52             'series': video_data.get('collection'),
  53             'season_number': int_or_none(video_data.get('season')),
  54             'episode_number': int_or_none(video_data.get('episode')),
  55             'duration': int_or_none(video_data.get('duration')),
  56             'ie_key': 'LimelightMedia',
  57         }