Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/keezmovies.py

   1 from __future__ import unicode_literals
   2
   3 import os
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10     compat_urllib_parse,
  11 )
  12 from ..aes import (
  13     aes_decrypt_text
  14 )
  15
  16
  17 class KeezMoviesIE(InfoExtractor):
  18     _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)'
  19     _TEST = {
  20         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
  21         'file': '1214711.mp4',
  22         'md5': '6e297b7e789329923fcf83abb67c9289',
  23         'info_dict': {
  24             'title': 'Petite Asian Lady Mai Playing In Bathtub',
  25             'age_limit': 18,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('videoid')
  32
  33         req = compat_urllib_request.Request(url)
  34         req.add_header('Cookie', 'age_verified=1')
  35         webpage = self._download_webpage(req, video_id)
  36
  37         # embedded video
  38         mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
  39         if mobj:
  40             embedded_url = mobj.group(1)
  41             return self.url_result(embedded_url)
  42
  43         video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
  44         video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, 'video_url'))
  45         if 'encrypted=true' in webpage:
  46             password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, 'password')
  47             video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
  48         path = compat_urllib_parse_urlparse(video_url).path
  49         extension = os.path.splitext(path)[1][1:]
  50         format = path.split('/')[4].split('_')[:2]
  51         format = "-".join(format)
  52
  53         age_limit = self._rta_search(webpage)
  54
  55         return {
  56             'id': video_id,
  57             'title': video_title,
  58             'url': video_url,
  59             'ext': extension,
  60             'format': format,
  61             'format_id': format,
  62             'age_limit': age_limit,
  63         }