Refactor deployment configuration and enhance browser debugging options

crawl4ai/async_configs.py

@@ -28,6 +28,7 @@ class BrowserConfig:
                          Default: True.
         use_managed_browser (bool): Launch the browser using a managed approach (e.g., via CDP), allowing
                                     advanced manipulation. Default: False.
+        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.
         user_data_dir (str or None): Path to a user data directory for persistent sessions. If None, a
@@ -98,6 +99,7 @@ class BrowserConfig:
         text_mode: bool = False,
         light_mode: bool = False,
         extra_args: list = None,
+        debugging_port : int = 9222,
     ):
         self.browser_type = browser_type
         self.headless = headless
@@ -131,6 +133,7 @@ class BrowserConfig:
         self.extra_args = extra_args if extra_args is not None else []
         self.sleep_on_close = sleep_on_close
         self.verbose = verbose
+        self.debugging_port = debugging_port
 
         user_agenr_generator = UserAgentGenerator()
         if self.user_agent_mode != "random":

crawl4ai/async_crawler_strategy.py

@@ -265,6 +265,7 @@ class BrowserManager:
                 user_data_dir=self.config.user_data_dir,
                 headless=self.config.headless,
                 logger=self.logger,
+                debugging_port=self.config.debugging_port,
             )
 
     async def start(self):
@@ -505,21 +506,6 @@ class BrowserManager:
             page = await context.new_page()
         else:
             context = await self.create_browser_context()
-            # context = await self.browser.new_context(
-            #     user_agent=self.config.headers.get(
-            #             "User-Agent", self.config.user_agent
-            #         ),
-            #     viewport={
-            #         "width": self.config.viewport_width,
-            #         "height": self.config.viewport_height,
-            #     },
-            #     proxy={"server": self.config.proxy} if self.config.proxy else None,
-            #     accept_downloads=self.config.accept_downloads,
-            #     storage_state=self.config.storage_state,
-            #     ignore_https_errors=self.config.ignore_https_errors,
-            #     java_script_enabled=self.config.java_script_enabled,
-            #     device_scale_factor=1.0,
-            # )
             await self.setup_context(context, crawlerRunConfig)
             page = await context.new_page()