🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
feat(mcp): add optional session_id parameter to open_session
Jules Omlor00897dad2f60
diff --git a/scrapling/core/ai.py b/scrapling/core/ai.pyindex 060cb20..7292a83 100644--- a/scrapling/core/ai.py+++ b/scrapling/core/ai.py@@ -123,6 +123,7 @@ class ScraplingMCPServer:async def open_session(self,session_type: SessionType,+ session_id: Optional[str] = None,headless: bool = True,google_search: bool = True,real_chrome: bool = False,@@ -152,6 +153,7 @@ class ScraplingMCPServer:Use close_session to close the session when done, and list_sessions to see all active sessions.:param session_type: The type of session to open. Use "dynamic" for standard Playwright browser, or "stealthy" for anti-bot bypass with fingerprint spoofing.+ :param session_id: Optional custom session ID. If not provided, a random 12-character hex ID will be generated. Useful for naming sessions for easier management.:param headless: Run the browser in headless/hidden (default), or headful/visible mode.:param google_search: Enabled by default, Scrapling will set a Google referer header.:param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.@@ -175,6 +177,10 @@ class ScraplingMCPServer::param solve_cloudflare: (Stealthy only) Solves all types of the Cloudflare's Turnstile/Interstitial challenges.:param additional_args: (Stealthy only) Additional arguments to be passed to Playwright's context as additional settings."""+ session_id = session_id or uuid4().hex[:12]+ if session_id in self._sessions:+ raise ValueError(f"Session '{session_id}' already exists. Use a different ID or close the existing session first.")+common_kwargs: Dict[str, Any] = dict(wait=wait,proxy=proxy,@@ -211,7 +217,6 @@ class ScraplingMCPServer:await session.start()- session_id = uuid4().hex[:12]entry = _SessionEntry(session=session, session_type=session_type)self._sessions[session_id] = entrydiff --git a/tests/ai/test_ai_mcp.py b/tests/ai/test_ai_mcp.pyindex d897bb5..4806088 100644--- a/tests/ai/test_ai_mcp.py+++ b/tests/ai/test_ai_mcp.py@@ -177,6 +177,25 @@ class TestSessionManagement:with pytest.raises(ValueError, match="not found"):await server.fetch(url=test_url, session_id=session_id)+ @pytest.mark.asyncio+ async def test_open_session_with_custom_id(self, server):+ """Test opening a session with a custom session_id"""+ result = await server.open_session(session_type="dynamic", session_id="my-session", headless=True)+ assert isinstance(result, SessionCreatedModel)+ assert result.session_id == "my-session"++ await server.close_session("my-session")++ @pytest.mark.asyncio+ async def test_open_session_duplicate_id_raises(self, server):+ """Test that opening a session with a duplicate session_id raises an error"""+ await server.open_session(session_type="dynamic", session_id="dupe", headless=True)++ with pytest.raises(ValueError, match="already exists"):+ await server.open_session(session_type="dynamic", session_id="dupe", headless=True)++ await server.close_session("dupe")+class TestNormalizeCredentials:"""Test the _normalize_credentials helper"""