yt_dlp/extractor/cinetecamilano.py

   1 import json
   2 from .common import InfoExtractor
   3 from ..networking.exceptions import HTTPError
   4 from ..utils import (
   5     ExtractorError,
   6     float_or_none,
   7     parse_iso8601,
   8     strip_or_none,
   9     traverse_obj,
  10     try_get,
  11     urljoin,
  12 )
  13
  14
  15 class CinetecaMilanoIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?cinetecamilano\.it/film/(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'https://www.cinetecamilano.it/film/1942',
  19         'info_dict': {
  20             'id': '1942',
  21             'ext': 'mp4',
  22             'title': 'Il draghetto Gris\u00f9 (4 episodi)',
  23             'release_date': '20220129',
  24             'thumbnail': r're:.+\.png',
  25             'description': 'md5:5328cbe080b93224712b6f17fcaf2c01',
  26             'modified_date': '20200520',
  27             'duration': 3139,
  28             'release_timestamp': 1643446208,
  29             'modified_timestamp': int
  30         }
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         try:
  36             film_json = self._download_json(
  37                 f'https://www.cinetecamilano.it/api/catalogo/{video_id}/?',
  38                 video_id, headers={
  39                     'Referer': url,
  40                     'Authorization': try_get(self._get_cookies('https://www.cinetecamilano.it'), lambda x: f'Bearer {x["cnt-token"].value}') or ''
  41                 })
  42         except ExtractorError as e:
  43             if ((isinstance(e.cause, HTTPError) and e.cause.status == 500)
  44                     or isinstance(e.cause, json.JSONDecodeError)):
  45                 self.raise_login_required(method='cookies')
  46             raise
  47         if not film_json.get('success') or not film_json.get('archive'):
  48             raise ExtractorError('Video information not found')
  49         archive = film_json['archive']
  50
  51         return {
  52             'id': video_id,
  53             'title': archive.get('title'),
  54             'description': strip_or_none(archive.get('description')),
  55             'duration': float_or_none(archive.get('duration'), invscale=60),
  56             'release_timestamp': parse_iso8601(archive.get('updated_at'), delimiter=' '),
  57             'modified_timestamp': parse_iso8601(archive.get('created_at'), delimiter=' '),
  58             'thumbnail': urljoin(url, try_get(archive, lambda x: x['thumb']['src'].replace('/public/', '/storage/'))),
  59             'formats': self._extract_m3u8_formats(
  60                 urljoin(url, traverse_obj(archive, ('drm', 'hls'))), video_id, 'mp4')
  61         }