From 55969016e96fded28b97b2ef3bbf66efa83d6afb Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 6 Mar 2015 12:43:49 +0800 Subject: [utils] Add a function to sanitize consecutive slashes in URLs --- youtube_dl/utils.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'youtube_dl/utils.py') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 7426e2a1f..ef14f9a36 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1789,3 +1789,18 @@ class PerRequestProxyHandler(compat_urllib_request.ProxyHandler): return None # No Proxy return compat_urllib_request.ProxyHandler.proxy_open( self, req, proxy, type) + + +def url_sanitize_consecutive_slashes(url): + """Sanitize URLs with consecutive slashes + + For example, transform both + http://hostname/foo//bar/filename.html + and + http://hostname//foo/bar/filename.html + into + http://hostname/foo/bar/filename.html + """ + parsed_url = list(compat_urlparse.urlparse(url)) + parsed_url[2] = re.sub(r'/{2,}', '/', parsed_url[2]) + return compat_urlparse.urlunparse(parsed_url) -- cgit v1.2.3