diff --git a/scrapy/downloadermiddlewares/redirect.py b/scrapy/downloadermiddlewares/redirect.py index 49468a2e4..b73f864dd 100644 --- a/scrapy/downloadermiddlewares/redirect.py +++ b/scrapy/downloadermiddlewares/redirect.py @@ -1,5 +1,5 @@ import logging -from six.moves.urllib.parse import urljoin +from six.moves.urllib.parse import urljoin, urlparse from w3lib.url import safe_url_string @@ -70,7 +70,10 @@ class RedirectMiddleware(BaseRedirectMiddleware): if 'Location' not in response.headers or response.status not in allowed_status: return response - location = safe_url_string(response.headers['location']) + location = safe_url_string(response.headers['Location']) + if response.headers['Location'].startswith(b'//'): + request_scheme = urlparse(request.url).scheme + location = request_scheme + '://' + location.lstrip('/') redirected_url = urljoin(request.url, location) diff --git a/tests/test_downloadermiddleware_redirect.py b/tests/test_downloadermiddleware_redirect.py index 0e841489d..e7faf14a7 100644 --- a/tests/test_downloadermiddleware_redirect.py +++ b/tests/test_downloadermiddleware_redirect.py @@ -106,6 +106,22 @@ class RedirectMiddlewareTest(unittest.TestCase): del rsp.headers['Location'] assert self.mw.process_response(req, rsp, self.spider) is rsp + def test_redirect_302_relative(self): + url = 'http://www.example.com/302' + url2 = '///i8n.example2.com/302' + url3 = 'http://i8n.example2.com/302' + req = Request(url, method='HEAD') + rsp = Response(url, headers={'Location': url2}, status=302) + + req2 = self.mw.process_response(req, rsp, self.spider) + assert isinstance(req2, Request) + self.assertEqual(req2.url, url3) + self.assertEqual(req2.method, 'HEAD') + + # response without Location header but with status code is 3XX should be ignored + del rsp.headers['Location'] + assert self.mw.process_response(req, rsp, self.spider) is rsp + def test_max_redirect_times(self): self.mw.max_redirect_times = 1