Scrapy, a fast high-level web crawling & scraping framework for Python.
Fix cookie lookup for dotless hosts and IP addresses (#7900)
Adrian63d5ce6272a7
diff --git a/scrapy/http/cookies.py b/scrapy/http/cookies.pyindex 8edeae01c..555d930e6 100644--- a/scrapy/http/cookies.py+++ b/scrapy/http/cookies.py@@ -54,9 +54,9 @@ class CookieJar:if not IPV4_RE.search(req_host):hosts = potential_domain_matches(req_host)if "." not in req_host:- hosts.append(req_host + ".local")+ hosts += potential_domain_matches(req_host + ".local")else:- hosts = [req_host]+ hosts = [req_host, "." + req_host]cookies = []for host in hosts:diff --git a/tests/test_downloadermiddleware_cookies.py b/tests/test_downloadermiddleware_cookies.pyindex 8d999d952..e4b66fe10 100644--- a/tests/test_downloadermiddleware_cookies.py+++ b/tests/test_downloadermiddleware_cookies.py@@ -345,6 +345,30 @@ class TestCookiesMiddleware:assert "Cookie" in request.headersassert request.headers["Cookie"] == b"currencyCookie=USD"+ @pytest.mark.parametrize(+ ("url", "domain"),+ [+ ("http://example-host/", "example-host.local"),+ ("http://127.0.0.1/", "127.0.0.1"),+ pytest.param(+ "http://example-host/",+ "example-host",+ marks=pytest.mark.xfail(+ reason=(+ "http.cookiejar accepts a dotless domain for a dotless "+ "host but never returns the resulting cookie"+ )+ ),+ ),+ ],+ )+ def test_explicit_local_domain(self, url: str, domain: str) -> None:+ request = Request(+ url, cookies=[{"name": "currencyCookie", "value": "USD", "domain": domain}]+ )+ assert self.mw.process_request(request) is None+ assert request.headers.get("Cookie") == b"currencyCookie=USD"+@pytest.mark.xfail(reason="Cookie header is not currently being processed")def test_keep_cookie_from_default_request_headers_middleware(self):DEFAULT_REQUEST_HEADERS = {"Cookie": "default=value; asdf=qwerty"}