1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-27 08:15:50 +01:00
youtube-dl/youtube_dl/extractor/keezmovies.py

63 lines
2.0 KiB
Python
Raw Normal View History

2014-04-04 18:48:49 +02:00
from __future__ import unicode_literals
import os
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
)
from ..aes import (
aes_decrypt_text
)
2014-04-04 18:48:49 +02:00
class KeezMoviesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = {
2014-04-04 18:48:49 +02:00
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
'file': '1214711.mp4',
'md5': '6e297b7e789329923fcf83abb67c9289',
'info_dict': {
'title': 'Petite Asian Lady Mai Playing In Bathtub',
'age_limit': 18,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
# embedded video
mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
if mobj:
embedded_url = mobj.group(1)
return self.url_result(embedded_url)
2014-04-04 18:48:49 +02:00
video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, 'video_url'))
if 'encrypted=true' in webpage:
password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, 'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
format = "-".join(format)
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': video_title,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit,
}