yt_dlp/extractor/angel.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import merge_dicts, url_or_none
   5
   6
   7 class AngelIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?angel\.com/watch/(?P<series>[^/?#]+)/episode/(?P<id>[\w-]+)/season-(?P<season_number>\d+)/episode-(?P<episode_number>\d+)/(?P<title>[^/?#]+)'
   9     _TESTS = [{
  10         'url': 'https://www.angel.com/watch/tuttle-twins/episode/2f3d0382-ea82-4cdc-958e-84fbadadc710/season-1/episode-1/when-laws-give-you-lemons',
  11         'md5': '4734e5cfdd64a568e837246aa3eaa524',
  12         'info_dict': {
  13             'id': '2f3d0382-ea82-4cdc-958e-84fbadadc710',
  14             'ext': 'mp4',
  15             'title': 'Tuttle Twins Season 1, Episode 1: When Laws Give You Lemons',
  16             'description': 'md5:73b704897c20ab59c433a9c0a8202d5e',
  17             'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
  18             'duration': 1359.0
  19         }
  20     }, {
  21         'url': 'https://www.angel.com/watch/the-chosen/episode/8dfb714d-bca5-4812-8125-24fb9514cd10/season-1/episode-1/i-have-called-you-by-name',
  22         'md5': 'e4774bad0a5f0ad2e90d175cafdb797d',
  23         'info_dict': {
  24             'id': '8dfb714d-bca5-4812-8125-24fb9514cd10',
  25             'ext': 'mp4',
  26             'title': 'The Chosen Season 1, Episode 1: I Have Called You By Name',
  27             'description': 'md5:aadfb4827a94415de5ff6426e6dee3be',
  28             'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
  29             'duration': 3276.0
  30         }
  31     }]
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35         webpage = self._download_webpage(url, video_id)
  36
  37         json_ld = self._search_json_ld(webpage, video_id)
  38
  39         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  40             json_ld.pop('url'), video_id, note='Downloading HD m3u8 information')
  41
  42         info_dict = {
  43             'id': video_id,
  44             'title': self._og_search_title(webpage),
  45             'description': self._og_search_description(webpage),
  46             'formats': formats,
  47             'subtitles': subtitles
  48         }
  49
  50         # Angel uses cloudinary in the background and supports image transformations.
  51         # We remove these transformations and return the source file
  52         base_thumbnail_url = url_or_none(self._og_search_thumbnail(webpage)) or json_ld.pop('thumbnails')
  53         if base_thumbnail_url:
  54             info_dict['thumbnail'] = re.sub(r'(/upload)/.+(/angel-app/.+)$', r'\1\2', base_thumbnail_url)
  55
  56         return merge_dicts(info_dict, json_ld)