Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/toongoggles.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     parse_duration,
  10 )
  11
  12
  13 class ToonGogglesIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?toongoggles\.com/shows/(?P<show_id>\d+)(?:/[^/]+/episodes/(?P<episode_id>\d+))?'
  15     _TESTS = [{
  16         'url': 'http://www.toongoggles.com/shows/217143/bernard-season-2/episodes/217147/football',
  17         'md5': '18289fc2b951eff6b953a9d8f01e6831',
  18         'info_dict': {
  19             'id': '217147',
  20             'ext': 'mp4',
  21             'title': 'Football',
  22             'uploader_id': '1',
  23             'description': 'Bernard decides to play football in order to be better than Lloyd and tries to beat him no matter how, he even cheats.',
  24             'upload_date': '20160718',
  25             'timestamp': 1468879330,
  26         }
  27     }, {
  28         'url': 'http://www.toongoggles.com/shows/227759/om-nom-stories-around-the-world',
  29         'info_dict': {
  30             'id': '227759',
  31             'title': 'Om Nom Stories Around The World',
  32         },
  33         'playlist_mincount': 11,
  34     }]
  35
  36     def _call_api(self, action, page_id, query):
  37         query.update({
  38             'for_ng': 1,
  39             'for_web': 1,
  40             'show_meta': 1,
  41             'version': 7.0,
  42         })
  43         return self._download_json('http://api.toongoggles.com/' + action, page_id, query=query)
  44
  45     def _parse_episode_data(self, episode_data):
  46         title = episode_data['episode_name']
  47
  48         return {
  49             '_type': 'url_transparent',
  50             'id': episode_data['episode_id'],
  51             'title': title,
  52             'url': 'kaltura:513551:' + episode_data['entry_id'],
  53             'thumbnail': episode_data.get('thumbnail_url'),
  54             'description': episode_data.get('description'),
  55             'duration': parse_duration(episode_data.get('hms')),
  56             'series': episode_data.get('show_name'),
  57             'season_number': int_or_none(episode_data.get('season_num')),
  58             'episode_id': episode_data.get('episode_id'),
  59             'episode': title,
  60             'episode_number': int_or_none(episode_data.get('episode_num')),
  61             'categories': episode_data.get('categories'),
  62             'ie_key': 'Kaltura',
  63         }
  64
  65     def _real_extract(self, url):
  66         show_id, episode_id = re.match(self._VALID_URL, url).groups()
  67         if episode_id:
  68             episode_data = self._call_api('search', episode_id, {
  69                 'filter': 'episode',
  70                 'id': episode_id,
  71             })['objects'][0]
  72             return self._parse_episode_data(episode_data)
  73         else:
  74             show_data = self._call_api('getepisodesbyshow', show_id, {
  75                 'max': 1000000000,
  76                 'showid': show_id,
  77             })
  78             entries = []
  79             for episode_data in show_data.get('objects', []):
  80                 entries.append(self._parse_episode_data(episode_data))
  81             return self.playlist_result(entries, show_id, show_data.get('show_name'))