youtube_dl/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': 'https://dood.to/d/jzrxn12t2s7n',
  25         'md5': '3207e199426eca7c2aa23c2872e6728a',
  26         'info_dict': {
  27             'id': 'jzrxn12t2s7n',
  28             'ext': 'mp4',
  29             'title': 'Stacy Cruz Cute ALLWAYSWELL',
  30             'description': 'Stacy Cruz Cute ALLWAYSWELL | DoodStream.com',
  31             'thumbnail': 'https://img.doodcdn.com/snaps/8edqd5nppkac3x8u.jpg',
  32         }
  33     }]
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37         webpage = self._download_webpage(url, video_id)
  38
  39         if '/d/' in url:
  40             url = "https://dood.to" + self._html_search_regex(
  41                 r'<iframe src="(/e/[a-z0-9]+)"', webpage, 'embed')
  42             video_id = self._match_id(url)
  43             webpage = self._download_webpage(url, video_id)
  44
  45         title = self._html_search_meta(['og:title', 'twitter:title'],
  46                                        webpage, default=None)
  47         thumb = self._html_search_meta(['og:image', 'twitter:image'],
  48                                        webpage, default=None)
  49         token = self._html_search_regex(r'[?&]token=([a-z0-9]+)[&\']', webpage, 'token')
  50         description = self._html_search_meta(
  51             ['og:description', 'description', 'twitter:description'],
  52             webpage, default=None)
  53         auth_url = 'https://dood.to' + self._html_search_regex(
  54             r'(/pass_md5.*?)\'', webpage, 'pass_md5')
  55         headers = {
  56             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
  57             'referer': url
  58         }
  59
  60         webpage = self._download_webpage(auth_url, video_id, headers=headers)
  61         final_url = webpage + ''.join([random.choice(string.ascii_letters + string.digits) for _ in range(10)]) + "?token=" + token + "&expiry=" + str(int(time.time() * 1000))
  62
  63         return {
  64             'id': video_id,
  65             'title': title,
  66             'url': final_url,
  67             'http_headers': headers,
  68             'ext': 'mp4',
  69             'description': description,
  70             'thumbnail': thumb,
  71         }