Hola mundo desde wp-content.
\n" b"\n\n" ) class _WPHandler(http.server.BaseHTTPRequestHandler): """Handler que finge ser un WordPress detras de nginx + PHP.""" # Silencia el logging del server a stderr durante el test. def log_message(self, *args, **kwargs): # noqa: D102 pass def do_GET(self): # noqa: N802 - firma impuesta por BaseHTTPRequestHandler self.send_response(200) self.send_header("Server", "nginx/1.24.0") self.send_header("X-Powered-By", "PHP/8.2.10") self.send_header("Content-Type", "text/html; charset=utf-8") self.send_header("Content-Length", str(len(_WP_HTML))) self.end_headers() self.wfile.write(_WP_HTML) def _start_wp_server() -> tuple[socketserver.TCPServer, int, threading.Thread]: """Levanta un HTTPServer efimero en 127.0.0.1 que sirve el HTML WordPress. Returns: (httpd, port, thread). El caller debe llamar httpd.shutdown() al final. """ httpd = http.server.HTTPServer(("127.0.0.1", 0), _WPHandler) port = httpd.server_address[1] t = threading.Thread(target=httpd.serve_forever, daemon=True) t.start() return httpd, port, t # --- 1. Golden: fingerprint contra un servidor WordPress/nginx/PHP local ------ def test_golden_fingerprint_servidor_local_wordpress_nginx(): """Detecta WordPress (CMS), nginx (servidor) y PHP en el HTML/headers locales.""" httpd, port, thread = _start_wp_server() try: result = fingerprint_web_stack( f"http://127.0.0.1:{port}/", timeout_s=5.0, save=False, ) assert result["status"] == "ok", result assert result["status_code"] == 200, result # No se archivo en OSINT (save=False). assert result["saved"] is None, result # Hubo al menos una tecnologia detectada. assert result["count"] > 0, result names = {t["name"] for t in result["technologies"]} # WordPress por meta generator; nginx por cabecera Server. assert "WordPress" in names, names assert "nginx" in names, names # by_category coherente con las tecnologias. by_cat = result["by_category"] assert "WordPress" in by_cat.get("cms", []), by_cat assert "nginx" in by_cat.get("web-server", []), by_cat # server y title vienen del fetch. assert "nginx" in (result["server"] or ""), result["server"] assert "WordPress" in (result["title"] or ""), result["title"] # raw es la tabla legible con cabeceras y columnas. raw = result["raw"] assert isinstance(raw, str) assert "TECHNOLOGY" in raw assert "WordPress" in raw assert "nginx" in raw assert str(port) in raw # la URL solicitada aparece en la cabecera finally: httpd.shutdown() httpd.server_close() thread.join(timeout=2.0) # --- 2. save=False: corre fetch + matching pero NO archiva en OSINT ----------- def test_save_false_no_archiva_osint(): """save=False: technologies poblado pero el sink nunca se invoca.""" save_called = {"n": 0} def fake_save(*args, **kwargs): # pragma: no cover - no debe llamarse save_called["n"] += 1 return {"status": "ok"} httpd, port, thread = _start_wp_server() original_save = mod.save_scan_to_osint mod.save_scan_to_osint = fake_save try: result = fingerprint_web_stack( f"http://127.0.0.1:{port}/", timeout_s=5.0, save=False, ) finally: mod.save_scan_to_osint = original_save httpd.shutdown() httpd.server_close() thread.join(timeout=2.0) assert result["status"] == "ok", result assert result["count"] > 0, result assert result["saved"] is None, result # El sink nunca se invoco con save=False. assert save_called["n"] == 0, save_called # --- 3. Error path: el fetch HTTP falla -> error sin red externa -------------- def test_fetch_fallido_propaga_error_sin_red(): """Host que no resuelve: fetch_http_fingerprint da error y el pipeline lo propaga.""" save_called = {"n": 0} def fake_save(*args, **kwargs): # pragma: no cover - no debe llamarse save_called["n"] += 1 return {"status": "ok"} # Parcheamos el sink: aunque save=True, con fetch fallido no debe invocarse. original_save = mod.save_scan_to_osint mod.save_scan_to_osint = fake_save try: result = fingerprint_web_stack( "http://nohost.invalid.tld.example/", timeout_s=2.0, save=True, ) finally: mod.save_scan_to_osint = original_save assert result["status"] == "error", result assert result["stage"] == "fetch", result assert result["fetch"]["status"] == "error", result # No se intento archivar nada. assert save_called["n"] == 0, save_called # --- 4. use_cdp sin Chrome: DEGRADA a estatico con warning (no falla) --------- def test_use_cdp_sin_chrome_degrada_a_estatico(): """use_cdp=True sin Chrome (cdp_port=1) degrada al fetch estatico con warning. Levanta el mismo HTTPServer WordPress/nginx/PHP local que el golden y pide use_cdp con cdp_port=1 (donde no hay ningun Chrome escuchando). El fetch CDP falla, el pipeline NO rompe: usa el HTML estatico, marca html_source=static, rellena warnings y sigue detectando WordPress/nginx por el html/headers. """ httpd, port, thread = _start_wp_server() try: result = fingerprint_web_stack( f"http://127.0.0.1:{port}/", timeout_s=5.0, save=False, use_cdp=True, cdp_port=1, # puerto sin Chrome: el fetch CDP falla -> degrada wait_render_s=0.0, ) finally: httpd.shutdown() httpd.server_close() thread.join(timeout=2.0) # Degrado, no fallo. assert result["status"] == "ok", result # Cayo al HTML estatico (CDP no disponible). assert result["html_source"] == "static", result assert result["rendered"] is False, result # Hubo warning de degradacion. assert result["warnings"], result assert any("cdp no disponible" in w for w in result["warnings"]), result["warnings"] # La deteccion estatica sigue funcionando. names = {t["name"] for t in result["technologies"]} assert "WordPress" in names, names assert "nginx" in names, names # No se archivo (save=False). assert result["saved"] is None, result