yt_dlp/extractor/kelbyone.py

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