yt_dlp/extractor/kelbyone.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none
   3
   4
   5 class KelbyOneIE(InfoExtractor):
   6     _VALID_URL = r'https?://members\.kelbyone\.com/course/(?P<id>[^$&?#/]+)'
   7
   8     _TESTS = [{
   9         'url': 'https://members.kelbyone.com/course/glyn-dewis-mastering-selections/',
  10         'playlist_mincount': 1,
  11         'info_dict': {
  12             'id': 'glyn-dewis-mastering-selections',
  13             'title': 'Trailer - Mastering Selections in Photoshop',
  14         },
  15         'playlist': [{
  16             'info_dict': {
  17                 'id': 'MkiOnLqK',
  18                 'ext': 'mp4',
  19                 'title': 'Trailer - Mastering Selections in Photoshop',
  20                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  21                 'thumbnail': 'https://content.jwplatform.com/v2/media/MkiOnLqK/poster.jpg?width=720',
  22                 'timestamp': 1601568639,
  23                 'duration': 90,
  24                 'upload_date': '20201001',
  25             },
  26         }]
  27     }]
  28
  29     def _entries(self, playlist):
  30         for item in playlist:
  31             video_id = item['mediaid']
  32             thumbnails = [{
  33                 'url': image.get('src'),
  34                 'width': int_or_none(image.get('width')),
  35             } for image in item.get('images') or []]
  36             formats, subtitles = [], {}
  37             for source in item.get('sources') or []:
  38                 if not source.get('file'):
  39                     continue
  40                 if source.get('type') == 'application/vnd.apple.mpegurl':
  41                     fmts, subs = self._extract_m3u8_formats_and_subtitles(source['file'], video_id)
  42                     formats.extend(fmts)
  43                     subtitles = self._merge_subtitles(subs, subtitles)
  44                 elif source.get('type') == 'audio/mp4':
  45                     formats.append({
  46                         'format_id': source.get('label'),
  47                         'url': source['file'],
  48                         'vcodec': 'none',
  49                     })
  50                 else:
  51                     formats.append({
  52                         'format_id': source.get('label'),
  53                         'height': source.get('height'),
  54                         'width': source.get('width'),
  55                         'url': source['file'],
  56                     })
  57             for track in item.get('tracks'):
  58                 if track.get('kind') == 'captions' and track.get('file'):
  59                     subtitles.setdefault('en', []).append({
  60                         'url': track['file'],
  61                     })
  62             yield {
  63                 'id': video_id,
  64                 'title': item['title'],
  65                 'description': item.get('description'),
  66                 'thumbnails': thumbnails,
  67                 'thumbnail': item.get('image'),
  68                 'timestamp': item.get('pubdate'),
  69                 'duration': item.get('duration'),
  70                 'formats': formats,
  71                 'subtitles': subtitles,
  72             }
  73
  74     def _real_extract(self, url):
  75         item_id = self._match_id(url)
  76         webpage = self._download_webpage(url, item_id)
  77         playlist_url = self._html_search_regex(r'playlist"\:"(https.*content\.jwplatform\.com.*json)"', webpage, 'playlist url').replace('\\', '')
  78         course_data = self._download_json(playlist_url, item_id)
  79         return self.playlist_result(self._entries(course_data['playlist']), item_id,
  80                                     course_data.get('title'), course_data.get('description'))