add resilient multi-engine browser discovery

2026-09-05 14:59:28 +02:00
parent 6debef6015
commit 521d666ecf
4 changed files with 113 additions and 30 deletions
@@ -30,6 +30,11 @@ class BrowserOnlyAppTests(unittest.TestCase):
        response = self.conn.getresponse()
        return response.status, json.loads(response.read() or b"{}")

+    def test_search_redirect_links_are_unwrapped(self):
+        wrapped = "https://duckduckgo.com/l/?uddg=https%3A%2F%2Fwww.example.co.za%2Fservices"
+        self.assertEqual(server.normalize_result_href(wrapped), "https://www.example.co.za/services")
+        self.assertEqual(server.normalize_result_href("//example.co.za/about"), "https://example.co.za/about")
+
    @patch("api.server.google_search", return_value=[{"name": "Acme Plumbing", "website": "https://www.acme.co.za", "domain": "acme.co.za"}, {"name": "Other", "website": "https://other.co.za", "domain": "other.co.za"}])
    def test_discovery_filters_catalogued_root_domains(self, search):
        status, first = self.request("POST", "/api/discover", {"category": "plumbers", "keywords": "plumbing", "location": "Cape Town", "max_results": 5})