[generic] Recognize html5 video in the format '<video src=".+?"' and only unquote...

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

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index d034a11bbc3c4cf7ad50edf19776b211296e8d60..de7379a921bbe2ade08bdc27250c597cd6c1e532 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -7,8 +7,8 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
-    compat_urllib_parse_urlparse,
     compat_urllib_request,
+    compat_urlparse,
 
     ExtractorError,
 )
@@ -153,7 +153,7 @@ 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)
 
@@ -162,12 +162,9 @@ 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))
-        if video_url.startswith('//'):
-            video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
-        if '://' not in video_url:
-            video_url = url + ('' if url.endswith('/') else '/') + video_url
-        video_id = os.path.basename(video_url)
+        video_url = mobj.group(1)
+        video_url = compat_urlparse.urljoin(url, 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:]