[keezmovies] Fix extraction and modernize test

This commit is contained in:
Philipp Hagemeister 2015-02-01 15:13:41 +01:00
parent 748a0fab8a
commit 9f281cacd2

View file

@ -7,10 +7,6 @@
from ..compat import ( from ..compat import (
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
compat_urllib_request, compat_urllib_request,
compat_urllib_parse,
)
from ..aes import (
aes_decrypt_text
) )
@ -18,9 +14,10 @@ class KeezMoviesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = { _TEST = {
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
'file': '1214711.mp4',
'md5': '6e297b7e789329923fcf83abb67c9289', 'md5': '6e297b7e789329923fcf83abb67c9289',
'info_dict': { 'info_dict': {
'id': '1214711',
'ext': 'mp4',
'title': 'Petite Asian Lady Mai Playing In Bathtub', 'title': 'Petite Asian Lady Mai Playing In Bathtub',
'age_limit': 18, 'age_limit': 18,
} }
@ -39,11 +36,10 @@ def _real_extract(self, url):
embedded_url = mobj.group(1) embedded_url = mobj.group(1)
return self.url_result(embedded_url) return self.url_result(embedded_url)
video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title') video_title = self._html_search_regex(
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, 'video_url')) r'<h1 [^>]*>([^<]+)', webpage, 'title')
if 'encrypted=true' in webpage: video_url = self._html_search_regex(
password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, 'password') r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
path = compat_urllib_parse_urlparse(video_url).path path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:] extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2] format = path.split('/')[4].split('_')[:2]