feat(browser): add CDP URL configuration support

Add support for direct CDP URL configuration in BrowserConfig and ManagedBrowser classes. This allows connecting to remote browser instances using custom CDP endpoints instead of always launching a local browser.

- Added cdp_url parameter to BrowserConfig
- Added cdp_url support in ManagedBrowser.start() method
- Updated documentation for new parameters

crawl4ai/async_configs.py

@@ -32,6 +32,7 @@ class BrowserConfig:
                          Default: True.
         use_managed_browser (bool): Launch the browser using a managed approach (e.g., via CDP), allowing
                                     advanced manipulation. Default: False.
+        cdp_url (str): URL for the Chrome DevTools Protocol (CDP) endpoint. Default: "ws://localhost:9222/devtools/browser/".
         debugging_port (int): Port for the browser debugging protocol. Default: 9222.
         use_persistent_context (bool): Use a persistent browser context (like a persistent profile).
                                        Automatically sets use_managed_browser=True. Default: False.
@@ -80,6 +81,7 @@ class BrowserConfig:
         browser_type: str = "chromium",
         headless: bool = True,
         use_managed_browser: bool = False,
+        cdp_url: str = None,
         use_persistent_context: bool = False,
         user_data_dir: str = None,
         chrome_channel: str = "chromium",
@@ -107,10 +109,12 @@ class BrowserConfig:
         light_mode: bool = False,
         extra_args: list = None,
         debugging_port: int = 9222,
+        host: str = "localhost",
     ):
         self.browser_type = browser_type
         self.headless = headless
         self.use_managed_browser = use_managed_browser
+        self.cdp_url = cdp_url
         self.use_persistent_context = use_persistent_context
         self.user_data_dir = user_data_dir
         self.chrome_channel = chrome_channel or self.browser_type or "chromium"
@@ -162,6 +166,7 @@ class BrowserConfig:
             browser_type=kwargs.get("browser_type", "chromium"),
             headless=kwargs.get("headless", True),
             use_managed_browser=kwargs.get("use_managed_browser", False),
+            cdp_url=kwargs.get("cdp_url"),
             use_persistent_context=kwargs.get("use_persistent_context", False),
             user_data_dir=kwargs.get("user_data_dir"),
             chrome_channel=kwargs.get("chrome_channel", "chromium"),
@@ -194,6 +199,7 @@ class BrowserConfig:
             "browser_type": self.browser_type,
             "headless": self.headless,
             "use_managed_browser": self.use_managed_browser,
+            "cdp_url": self.cdp_url,
             "use_persistent_context": self.use_persistent_context,
             "user_data_dir": self.user_data_dir,
             "chrome_channel": self.chrome_channel,