yt_dlp/extractor/vupload.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_duration,
   4     parse_filesize,
   5     extract_attributes,
   6     int_or_none,
   7     js_to_json
   8 )
   9
  10
  11 class VuploadIE(InfoExtractor):
  12     _VALID_URL = r'https://vupload\.com/v/(?P<id>[a-z0-9]+)'
  13     _TESTS = [{
  14         'url': 'https://vupload.com/v/u28d0pl2tphy',
  15         'md5': '9b42a4a193cca64d80248e58527d83c8',
  16         'info_dict': {
  17             'id': 'u28d0pl2tphy',
  18             'ext': 'mp4',
  19             'description': 'md5:e9e6c0045c78cbf0d5bb19a55ce199fb',
  20             'title': 'md5:e9e6c0045c78cbf0d5bb19a55ce199fb',
  21         }
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = self._html_extract_title(webpage)
  29         video_json = self._parse_json(self._html_search_regex(r'sources:\s*(.+?]),', webpage, 'video'), video_id, transform_source=js_to_json)
  30         formats = []
  31         for source in video_json:
  32             if source['src'].endswith('.m3u8'):
  33                 formats.extend(self._extract_m3u8_formats(source['src'], video_id, m3u8_id='hls'))
  34         duration = parse_duration(self._html_search_regex(
  35             r'<i\s*class=["\']fad\s*fa-clock["\']></i>\s*([\d:]+)\s*</div>', webpage, 'duration', fatal=False))
  36         filesize_approx = parse_filesize(self._html_search_regex(
  37             r'<i\s*class=["\']fad\s*fa-save["\']></i>\s*([^<]+)\s*</div>', webpage, 'filesize', fatal=False))
  38         extra_video_info = extract_attributes(self._html_search_regex(
  39             r'(<video[^>]+>)', webpage, 'video_info', fatal=False))
  40         description = self._html_search_meta('description', webpage)
  41
  42         return {
  43             'id': video_id,
  44             'formats': formats,
  45             'duration': duration,
  46             'filesize_approx': filesize_approx,
  47             'width': int_or_none(extra_video_info.get('width')),
  48             'height': int_or_none(extra_video_info.get('height')),
  49             'format_id': extra_video_info.get('height', '') + 'p',
  50             'title': title,
  51             'description': description,
  52         }