Merge tag 'upstream/2014.02.17'

[youtubedl] / youtube_dl / extractor / auengine.py

diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py
index 3b4ade3bf7174fbb33b9e0ce2d193912c0f93a6c..c6f30e62616c09f50f8826d4d30cc6069cf3367f 100644 (file)
--- a/youtube_dl/extractor/auengine.py
+++ b/youtube_dl/extractor/auengine.py
@@ -1,38 +1,52 @@
-import os.path
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,

-    compat_urllib_parse_urlparse,
+    determine_ext,
+    ExtractorError,

 )
 
 )
 

+

 class AUEngineIE(InfoExtractor):
 class AUEngineIE(InfoExtractor):

-    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
+    _TEST = {
+        'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
+        'file': 'lfvlytY6.mp4',
+        'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
+        'info_dict': {
+            'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
+        }
+    }
+    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',

-                webpage, u'title')
+                webpage, 'title')

         title = title.strip()
         title = title.strip()

-        links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
-        links = [compat_urllib_parse.unquote(l) for l in links]
+        links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
+        links = map(compat_urllib_parse.unquote, links)
+
+        thumbnail = None
+        video_url = None

         for link in links:
         for link in links:

-            root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
-            if pathext == '.png':
+            if link.endswith('.png'):

                 thumbnail = link
                 thumbnail = link

-            elif pathext == '.mp4':
-                url = link
-                ext = pathext
+            elif '/videos/' in link:
+                video_url = link
+        if not video_url:
+            raise ExtractorError(u'Could not find video URL')
+        ext = '.' + determine_ext(video_url)

         if ext == title[-len(ext):]:
             title = title[:-len(ext)]
         if ext == title[-len(ext):]:
             title = title[:-len(ext)]

-        ext = ext[1:]
-        return [{
+
+        return {

             'id':        video_id,
             'id':        video_id,

-            'url':       url,
-            'ext':       ext,
+            'url':       video_url,

             'title':     title,
             'thumbnail': thumbnail,
             'title':     title,
             'thumbnail': thumbnail,

-        }]
+        }