youtube_dl/extractor/keezmovies.py

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