youtube-dl

commit 3a8736bd745ecd7ce5cb605cf56710f76a26d1ab
parent c8c516361819f0e01dbff33a0fcb97e9f0e25386
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Thu, 27 Jun 2013 18:16:41 +0200

Merge remote-tracking branch 'gitprojs/master'

Conflicts:
	youtube_dl/extractor/__init__.py

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
2
++
A
youtube_dl/extractor/auengine.py
 | 
38
++++++++++++++++++++++++++++++++++++++

2 files changed, 40 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -1,6 +1,7 @@
 
 from .ard import ARDIE
 from .arte import ArteTvIE
+from .auengine import AuengineIE
 from .bandcamp import BandcampIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .breakcom import BreakIE
@@ -138,6 +139,7 @@ def gen_extractors():
         CSpanIE(),
         WimpIE(),
         HotNewHipHopIE(),
+        AuengineIE(),
         GenericIE()
     ]
 
diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py
@@ -0,0 +1,38 @@
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+)
+
+class AuengineIE(InfoExtractor):
+    _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>',
+                webpage, u'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]
+        for link in links:
+            root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
+            if pathext == '.png':
+                thumbnail = link
+            elif pathext == '.mp4':
+                url = link
+                ext = pathext
+        if ext == title[-len(ext):]:
+            title = title[:-len(ext)]
+        ext = ext[1:]
+        return [{
+            'id':        video_id,
+            'url':       url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail,
+        }]