[generic] If the url doesn't specify the protocol, then try to extract prepending...

[youtube-dl.git] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index dc4dea4adf63937722a1bf81ead5e10fe09f34e3..f92e61fea5db38a5c0df130b512a7920def14af5 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -109,6 +109,11 @@ class GenericIE(InfoExtractor):
         return new_url
 
     def _real_extract(self, url):
+        parsed_url = compat_urlparse.urlparse(url)
+        if not parsed_url.scheme:
+            self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+            return self.url_result('http://' + url)
+
         try:
             new_url = self._test_redirect(url)
             if new_url:
@@ -153,7 +158,7 @@ class GenericIE(InfoExtractor):
                 mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
         if mobj is None:
             # HTML5 video
-            mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL)
+            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
@@ -162,9 +167,9 @@ class GenericIE(InfoExtractor):
         if mobj.group(1) is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
 
-        video_url = compat_urllib_parse.unquote(mobj.group(1))
+        video_url = mobj.group(1)
         video_url = compat_urlparse.urljoin(url, video_url)
-        video_id = os.path.basename(video_url)
+        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
         # here's a fun little line of code for you:
         video_extension = os.path.splitext(video_id)[1][1:]