]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/auengine.py
debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.
[youtubedl] / youtube_dl / extractor / auengine.py
index 0febbff4f6c42afd10f8dbc13ea9df883edae4c6..1c765532a00d9274c2531277cc1ad81b75053dfd 100644 (file)
@@ -1,46 +1,54 @@
-import os.path
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-    compat_urllib_parse_urlparse,
+    determine_ext,
+    ExtractorError,
 )
 
+
 class AUEngineIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
+
     _TEST = {
-        u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
-        u'file': u'lfvlytY6.mp4',
-        u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f',
-        u'info_dict': {
-            u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
+        'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
+        'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
+        'info_dict': {
+            'id': 'lfvlytY6',
+            'ext': 'mp4',
+            '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)
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
-                webpage, u'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
         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:
-            root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
-            if pathext == '.png':
+            if link.endswith('.png'):
                 thumbnail = link
-            elif pathext == '.mp4':
-                url = link
-                ext = pathext
+            elif '/videos/' in link:
+                video_url = link
+        if not video_url:
+            raise ExtractorError('Could not find video URL')
+        ext = '.' + determine_ext(video_url)
         if ext == title[-len(ext):]:
             title = title[:-len(ext)]
-        ext = ext[1:]
-        return [{
-            'id':        video_id,
-            'url':       url,
-            'ext':       ext,
-            'title':     title,
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
             'thumbnail': thumbnail,
-        }]
+            'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
+        }