yt_dlp/extractor/vupload.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     parse_filesize,
   8     extract_attributes,
   9     int_or_none,
  10 )
  11
  12
  13 class VuploadIE(InfoExtractor):
  14     _VALID_URL = r'https://vupload\.com/v/(?P<id>[a-z0-9]+)'
  15     _TESTS = [{
  16         'url': 'https://vupload.com/v/u28d0pl2tphy',
  17         'md5': '9b42a4a193cca64d80248e58527d83c8',
  18         'info_dict': {
  19             'id': 'u28d0pl2tphy',
  20             'ext': 'mp4',
  21             'description': 'md5:e9e6c0045c78cbf0d5bb19a55ce199fb',
  22             'title': 'md5:e9e6c0045c78cbf0d5bb19a55ce199fb',
  23         }
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
  31         video_e = self._html_search_regex(r'\|([a-z0-9]{60})\|', webpage, 'video')
  32         video_url = f'https://wurize.megaupload.to/{video_e}/v.mp4'
  33         duration = parse_duration(self._html_search_regex(
  34             r'<i\s*class=["\']fad\s*fa-clock["\']></i>\s*([\d:]+)\s*</div>', webpage, 'duration', fatal=False))
  35         filesize_approx = parse_filesize(self._html_search_regex(
  36             r'<i\s*class=["\']fad\s*fa-save["\']></i>\s*([^<]+)\s*</div>', webpage, 'filesize', fatal=False))
  37         extra_video_info = extract_attributes(self._html_search_regex(
  38             r'(<video[^>]+>)', webpage, 'video_info', fatal=False))
  39         description = self._html_search_meta('description', webpage)
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'duration': duration,
  45             'filesize_approx': filesize_approx,
  46             'width': int_or_none(extra_video_info.get('width')),
  47             'height': int_or_none(extra_video_info.get('height')),
  48             'format_id': extra_video_info.get('height', '') + 'p',
  49             'title': title,
  50             'description': description,
  51         }