From 5b11143d05c6d38cf1df94561c2a515c9150b2e1 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Sun, 27 Oct 2013 10:10:28 +0100 Subject: [PATCH] Add support for http://www.keezmovies.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/keezmovies.py | 58 ++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) create mode 100644 youtube_dl/extractor/keezmovies.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index db69af3619..d4ad4e37c2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -72,6 +72,7 @@ from .jukebox import JukeboxIE from .justintv import JustinTVIE from .kankan import KankanIE +from .keezmovies import KeezMoviesIE from .kickstarter import KickStarterIE from .keek import KeekIE from .liveleak import LiveLeakIE diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py new file mode 100644 index 0000000000..937caf6644 --- /dev/null +++ b/youtube_dl/extractor/keezmovies.py @@ -0,0 +1,58 @@ +import os +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urllib_parse, + unescapeHTML, +) +from ..aes import ( + aes_decrypt_text +) + +class KeezMoviesIE(InfoExtractor): + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pkeezmovies\.com/video/.+?(?P[0-9]+))' + _TEST = { + u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', + u'file': u'1214711.mp4', + u'md5': u'6e297b7e789329923fcf83abb67c9289', + u'info_dict': { + u"title": u"Petite Asian Lady Mai Playing In Bathtub", + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('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="([^"]+)">', webpage) + if mobj: + embedded_url = mobj.group(1) + return self.playlist_result([self.url_result(embedded_url)], playlist_id=video_id) + + video_title = self._html_search_regex(r'

]*>([^<]+)', webpage, u'title') + video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) + if webpage.find('encrypted=true')!=-1: + password = self._html_search_regex(r'video_title=(.+?)&', webpage, u'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 ) + + return { + 'id': video_id, + 'title': video_title, + 'url': video_url, + 'ext': extension, + 'format': format, + 'format_id': format, + }