diff options
author | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-10-28 01:25:46 -0400 |
---|---|---|
committer | Filippo Valsorda <filippo.valsorda@gmail.com> | 2013-10-28 01:25:46 -0400 |
commit | e2f9de207caf97d12d9e9be29002c49e5ad2b409 (patch) | |
tree | 8b1a5d674684741f9798214c02c966fab5341b57 /youtube_dl/extractor/keezmovies.py | |
parent | a93cc0d9435fca79787369d3670fce0742ae47ef (diff) | |
parent | 5da054958151263040f2a53cf554b0084e79f6fa (diff) | |
download | youtube-dl-e2f9de207caf97d12d9e9be29002c49e5ad2b409.tar.xz |
Merge pull request #1664 by @rzhxeo
Add support for http://www.keezmovies.com
Diffstat (limited to 'youtube_dl/extractor/keezmovies.py')
-rw-r--r-- | youtube_dl/extractor/keezmovies.py | 58 |
1 files changed, 58 insertions, 0 deletions
diff --git a/youtube_dl/extractor/keezmovies.py b/youtube_dl/extractor/keezmovies.py new file mode 100644 index 000000000..23d5209d9 --- /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\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[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="([^"]+)"></iframe>', webpage) + if mobj: + embedded_url = mobj.group(1) + return self.url_result(embedded_url) + + video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', 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, + } |