yt_dlp/extractor/doodstream.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import string
   5 import random
   6 import time
   7
   8 from .common import InfoExtractor
   9
  10
  11 class DoodStreamIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch)/[ed]/(?P<id>[a-z0-9]+)'
  13     _TESTS = [{
  14         'url': 'http://dood.to/e/5s1wmbdacezb',
  15         'md5': '4568b83b31e13242b3f1ff96c55f0595',
  16         'info_dict': {
  17             'id': '5s1wmbdacezb',
  18             'ext': 'mp4',
  19             'title': 'Kat Wonders - Monthly May 2020',
  20             'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
  21             'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
  22         }
  23     }, {
  24         'url': 'http://dood.watch/d/5s1wmbdacezb',
  25         'md5': '4568b83b31e13242b3f1ff96c55f0595',
  26         'info_dict': {
  27             'id': '5s1wmbdacezb',
  28             'ext': 'mp4',
  29             'title': 'Kat Wonders - Monthly May 2020',
  30             'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
  31             'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
  32         }
  33     }, {
  34         'url': 'https://dood.to/d/jzrxn12t2s7n',
  35         'md5': '3207e199426eca7c2aa23c2872e6728a',
  36         'info_dict': {
  37             'id': 'jzrxn12t2s7n',
  38             'ext': 'mp4',
  39             'title': 'Stacy Cruz Cute ALLWAYSWELL',
  40             'description': 'Stacy Cruz Cute ALLWAYSWELL | DoodStream.com',
  41             'thumbnail': 'https://img.doodcdn.com/snaps/8edqd5nppkac3x8u.jpg',
  42         }
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         url = f'https://dood.to/e/{video_id}'
  48         webpage = self._download_webpage(url, video_id)
  49
  50         title = self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None)
  51         thumb = self._html_search_meta(['og:image', 'twitter:image'], webpage, default=None)
  52         token = self._html_search_regex(r'[?&]token=([a-z0-9]+)[&\']', webpage, 'token')
  53         description = self._html_search_meta(
  54             ['og:description', 'description', 'twitter:description'], webpage, default=None)
  55
  56         headers = {
  57             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
  58             'referer': url
  59         }
  60
  61         pass_md5 = self._html_search_regex(r'(/pass_md5.*?)\'', webpage, 'pass_md5')
  62         final_url = ''.join((
  63             self._download_webpage(f'https://dood.to{pass_md5}', video_id, headers=headers),
  64             *(random.choice(string.ascii_letters + string.digits) for _ in range(10)),
  65             f'?token={token}&expiry={int(time.time() * 1000)}',
  66         ))
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'url': final_url,
  72             'http_headers': headers,
  73             'ext': 'mp4',
  74             'description': description,
  75             'thumbnail': thumb,
  76         }