diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-03-06 12:43:49 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-03-06 12:43:49 +0800 |
commit | 55969016e96fded28b97b2ef3bbf66efa83d6afb (patch) | |
tree | d0579cbb7a8fbd375899e1bee14cf2b8275dd20b /youtube_dl/utils.py | |
parent | 5c7495a19429e3b27c003a4bd5bb96ed1e3a4932 (diff) |
[utils] Add a function to sanitize consecutive slashes in URLs
Diffstat (limited to 'youtube_dl/utils.py')
-rw-r--r-- | youtube_dl/utils.py | 15 |
1 files changed, 15 insertions, 0 deletions
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) |