yt_dlp/extractor/caracoltv.py

   1 import base64
   2 import json
   3 import uuid
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     js_to_json,
   9     traverse_obj,
  10     urljoin,
  11 )
  12
  13
  14 class CaracolTvPlayIE(InfoExtractor):
  15     _VALID_URL = r'https?://play\.caracoltv\.com/videoDetails/(?P<id>[^/?#]+)'
  16     _NETRC_MACHINE = 'caracoltv-play'
  17
  18     _TESTS = [{
  19         'url': 'https://play.caracoltv.com/videoDetails/OTo4NGFmNjUwOWQ2ZmM0NTg2YWRiOWU0MGNhOWViOWJkYQ==',
  20         'info_dict': {
  21             'id': 'OTo4NGFmNjUwOWQ2ZmM0NTg2YWRiOWU0MGNhOWViOWJkYQ==',
  22             'title': 'La teoría del promedio',
  23             'description': 'md5:1cdd6d2c13f19ef0d9649ab81a023ac3',
  24         },
  25         'playlist_count': 6,
  26     }, {
  27         'url': 'https://play.caracoltv.com/videoDetails/OTo3OWM4ZTliYzQxMmM0MTMxYTk4Mjk2YjdjNGQ4NGRkOQ==/ella?season=0',
  28         'info_dict': {
  29             'id': 'OTo3OWM4ZTliYzQxMmM0MTMxYTk4Mjk2YjdjNGQ4NGRkOQ==',
  30             'title': 'Ella',
  31             'description': 'md5:a639b1feb5ddcc0cff92a489b4e544b8',
  32         },
  33         'playlist_count': 10,
  34     }, {
  35         'url': 'https://play.caracoltv.com/videoDetails/OTpiYTY1YTVmOTI5MzI0ZWJhOGZiY2Y3MmRlOWZlYmJkOA==/la-vuelta-al-mundo-en-80-risas-2022?season=0',
  36         'info_dict': {
  37             'id': 'OTpiYTY1YTVmOTI5MzI0ZWJhOGZiY2Y3MmRlOWZlYmJkOA==',
  38             'title': 'La vuelta al mundo en 80 risas 2022',
  39             'description': 'md5:e97aac36106e5c37ebf947b3350106a4',
  40         },
  41         'playlist_count': 17,
  42     }, {
  43         'url': 'https://play.caracoltv.com/videoDetails/MzoxX3BwbjRmNjB1',
  44         'only_matching': True,
  45     }]
  46
  47     _USER_TOKEN = None
  48
  49     def _extract_app_token(self, webpage):
  50         config_js_path = self._search_regex(
  51             r'<script[^>]+src\s*=\s*"([^"]+coreConfig.js[^"]+)', webpage, 'config js url', fatal=False)
  52
  53         mediation_config = {} if not config_js_path else self._search_json(
  54             r'mediation\s*:', self._download_webpage(
  55                 urljoin('https://play.caracoltv.com/', config_js_path), None, fatal=False, note='Extracting JS config'),
  56             'mediation_config', None, transform_source=js_to_json, fatal=False)
  57
  58         key = traverse_obj(
  59             mediation_config, ('live', 'key')) or '795cd9c089a1fc48094524a5eba85a3fca1331817c802f601735907c8bbb4f50'
  60         secret = traverse_obj(
  61             mediation_config, ('live', 'secret')) or '64dec00a6989ba83d087621465b5e5d38bdac22033b0613b659c442c78976fa0'
  62
  63         return base64.b64encode(f'{key}:{secret}'.encode()).decode()
  64
  65     def _perform_login(self, email, password):
  66         webpage = self._download_webpage('https://play.caracoltv.com/', None, fatal=False)
  67         app_token = self._extract_app_token(webpage)
  68
  69         bearer_token = self._download_json(
  70             'https://eu-gateway.inmobly.com/applications/oauth', None, data=b'', note='Retrieving bearer token',
  71             headers={'Authorization': f'Basic {app_token}'})['token']
  72
  73         self._USER_TOKEN = self._download_json(
  74             'https://eu-gateway.inmobly.com/user/login', None, note='Performing login', headers={
  75                 'Content-Type': 'application/json',
  76                 'Authorization': f'Bearer {bearer_token}',
  77             }, data=json.dumps({
  78                 'device_data': {
  79                     'device_id': str(uuid.uuid4()),
  80                     'device_token': '',
  81                     'device_type': 'web'
  82                 },
  83                 'login_data': {
  84                     'enabled': True,
  85                     'email': email,
  86                     'password': password,
  87                 }
  88             }).encode())['user_token']
  89
  90     def _extract_video(self, video_data, series_id=None, season_id=None, season_number=None):
  91         formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_data['stream_url'], series_id, 'mp4')
  92
  93         return {
  94             'id': video_data['id'],
  95             'title': video_data.get('name'),
  96             'description': video_data.get('description'),
  97             'formats': formats,
  98             'subtitles': subtitles,
  99             'thumbnails': traverse_obj(
 100                 video_data, ('extra_thumbs', ..., {'url': 'thumb_url', 'height': 'height', 'width': 'width'})),
 101             'series_id': series_id,
 102             'season_id': season_id,
 103             'season_number': int_or_none(season_number),
 104             'episode_number': int_or_none(video_data.get('item_order')),
 105             'is_live': video_data.get('entry_type') == 3,
 106         }
 107
 108     def _extract_series_seasons(self, seasons, series_id):
 109         for season in seasons:
 110             api_response = self._download_json(
 111                 'https://eu-gateway.inmobly.com/feed', series_id, query={'season_id': season['id']},
 112                 headers={'Authorization': f'Bearer {self._USER_TOKEN}'})
 113
 114             season_number = season.get('order')
 115             for episode in api_response['items']:
 116                 yield self._extract_video(episode, series_id, season['id'], season_number)
 117
 118     def _real_extract(self, url):
 119         series_id = self._match_id(url)
 120
 121         if self._USER_TOKEN is None:
 122             self._perform_login('guest@inmobly.com', 'Test@gus1')
 123
 124         api_response = self._download_json(
 125             'https://eu-gateway.inmobly.com/feed', series_id, query={'include_ids': series_id},
 126             headers={'Authorization': f'Bearer {self._USER_TOKEN}'})['items'][0]
 127
 128         if not api_response.get('seasons'):
 129             return self._extract_video(api_response)
 130
 131         return self.playlist_result(
 132             self._extract_series_seasons(api_response['seasons'], series_id),
 133             series_id, **traverse_obj(api_response, {
 134                 'title': 'name',
 135                 'description': 'description',
 136             }))