yt_dlp/extractor/screencastify.py

   1 import urllib.parse
   2
   3 from .common import InfoExtractor
   4 from ..utils import traverse_obj, update_url_query
   5
   6
   7 class ScreencastifyIE(InfoExtractor):
   8     _VALID_URL = [
   9         r'https?://watch\.screencastify\.com/v/(?P<id>[^/?#]+)',
  10         r'https?://app\.screencastify\.com/v[23]/watch/(?P<id>[^/?#]+)',
  11     ]
  12     _TESTS = [{
  13         'url': 'https://watch.screencastify.com/v/sYVkZip3quLKhHw4Ybk8',
  14         'info_dict': {
  15             'id': 'sYVkZip3quLKhHw4Ybk8',
  16             'ext': 'mp4',
  17             'title': 'Inserting and Aligning the Case Top and Bottom',
  18             'description': '',
  19             'uploader': 'Paul Gunn',
  20             'extra_param_to_segment_url': str,
  21         },
  22         'params': {
  23             'skip_download': 'm3u8',
  24         },
  25     }, {
  26         'url': 'https://app.screencastify.com/v3/watch/J5N7H11wofDN1jZUCr3t',
  27         'info_dict': {
  28             'id': 'J5N7H11wofDN1jZUCr3t',
  29             'ext': 'mp4',
  30             'uploader': 'Scott Piesen',
  31             'description': '',
  32             'title': 'Lesson Recording 1-17 Burrr...',
  33         },
  34         'params': {
  35             'skip_download': 'm3u8',
  36         },
  37     }, {
  38         'url': 'https://app.screencastify.com/v2/watch/BQ26VbUdfbQLhKzkktOk',
  39         'only_matching': True,
  40     }]
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44         info = self._download_json(
  45             f'https://umbrella.svc.screencastify.com/api/umbrellaService/watch/{video_id}', video_id)
  46
  47         query_string = traverse_obj(info, ('manifest', 'auth', 'query'))
  48         query = urllib.parse.parse_qs(query_string)
  49         formats = []
  50         dash_manifest_url = traverse_obj(info, ('manifest', 'url'))
  51         if dash_manifest_url:
  52             formats.extend(
  53                 self._extract_mpd_formats(
  54                     dash_manifest_url, video_id, mpd_id='dash', query=query, fatal=False))
  55         hls_manifest_url = traverse_obj(info, ('manifest', 'hlsUrl'))
  56         if hls_manifest_url:
  57             formats.extend(
  58                 self._extract_m3u8_formats(
  59                     hls_manifest_url, video_id, ext='mp4', m3u8_id='hls', query=query, fatal=False))
  60         for f in formats:
  61             f['url'] = update_url_query(f['url'], query)
  62
  63         return {
  64             'id': video_id,
  65             'title': info.get('title'),
  66             'description': info.get('description'),
  67             'uploader': info.get('userName'),
  68             'formats': formats,
  69             'extra_param_to_segment_url': query_string,
  70         }