Switch codebase to use sanitized_Request instead of
[youtube-dl] / youtube_dl / extractor / keezmovies.py
index 5e05900da211eb9d2d6e33706a71f47dcf1abff7..d79261bb50b969e2dc6643c2ecb2ca198cc2af12 100644 (file)
@@ -1,34 +1,30 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
-    compat_urllib_parse,
-)
-from ..aes import (
-    aes_decrypt_text
-)
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import sanitized_Request
+
 
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))'
+    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[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",
-            u"age_limit": 18,
+        'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
+        'md5': '6e297b7e789329923fcf83abb67c9289',
+        'info_dict': {
+            'id': '1214711',
+            'ext': 'mp4',
+            'title': 'Petite Asian Lady Mai Playing In Bathtub',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request(url)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
@@ -38,15 +34,14 @@ class KeezMoviesIE(InfoExtractor):
             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=(.+?)&amp;', webpage, u'video_url'))
-        if webpage.find('encrypted=true')!=-1:
-            password = self._html_search_regex(r'video_title=(.+?)&amp;', 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:]
+        video_title = self._html_search_regex(
+            r'<h1 [^>]*>([^<]+)', webpage, 'title')
+        video_url = self._html_search_regex(
+            r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
+        path = compat_urllib_parse_urlparse(video_url).path
+        extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[4].split('_')[:2]
-        format = "-".join( format )
+        format = "-".join(format)
 
         age_limit = self._rta_search(webpage)