Enhancements for Windows 11: Remote Debugging Setup for Chrome

# Optional configuration for specific browser settings
[browser]
# Whether to run the browser in headless mode (default: false)
headless = false
# Disable browser security features (default: true)
disable_security = true
# Chrome DevTools Protocol URL - URL for connecting to manually launched Chrome
cdp_url = "http://localhost:9222"
# Path to the Chrome executable
chrome_instance_path = "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
# Browser arguments for launching in remote debugging mode
extra_chromium_args = [
    "--user-data-dir=C:\\Users\\\\username\\AppData\\Local\\Google\\Chrome\\User Data",
    "--profile-directory=profile_name",
    "--remote-debugging-port=9222",
    "--no-first-run",
    "--no-default-browser-check",
]

python start_chrome_debug.py

python run_flow.py

python test_browser.py

import subprocess
import sys
import time
import os


def start_chrome_debug():
    """Launch Chrome with a remote debugging port"""
    print("Starting Chrome in remote debugging mode...")

    # Path to Chrome and the user data directory
    chrome_path = "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
    user_data_dir = "C:\\Users\\[usernmae]\\AppData\\Local\\Google\\Chrome\\User Data"

    # Terminate existing Chrome processes (optional)
    # Note: This may end your current session.
    """
    try:
        subprocess.run(["taskkill", "/f", "/im", "chrome.exe"],
                      stdout=subprocess.PIPE,
                      stderr=subprocess.PIPE)
        time.sleep(1)
    except Exception as e:
        print(f"Failed to terminate Chrome processes: {e}")
    """

    # Launch Chrome in remote debugging mode
    try:
        chrome_process = subprocess.Popen(
            [
                chrome_path,
                f"--user-data-dir={user_data_dir}",
                "--profile-directory=default",
                "--remote-debugging-port=9222",
                "--no-first-run",
                "--no-default-browser-check",
            ]
        )

        print("Chrome started (PID: {})".format(chrome_process.pid))
        print("CDP endpoint: http://localhost:9222")
        print("Keep this window open.")
        print("Press Ctrl+C to exit.")

        # Wait for the process to exit
        chrome_process.wait()
    except KeyboardInterrupt:
        print("\nTerminating Chrome...")
        chrome_process.terminate()
    except Exception as e:
        print(f"An error occurred: {e}")
        return 1

    return 0


if __name__ == "__main__":
    sys.exit(start_chrome_debug())

import asyncio
import os
import subprocess
import time
from browser_use import Browser, BrowserConfig
from browser_use.browser.context import BrowserContext, BrowserContextConfig


async def main():
    print("Starting browser test")

    # Check if Chrome is already running
    try:
        # Manually start Chrome (with remote debugging port)
        chrome_path = "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
        user_data_dir = "C:\\Users\\[username]\\AppData\\Local\\Google\\Chrome\\User Data"

        print("Manually launching Chrome...")
        chrome_process = subprocess.Popen(
            [
                chrome_path,
                f"--user-data-dir={user_data_dir}",
                "--profile-directory=default",
                "--remote-debugging-port=9222",
                "--no-first-run",
                "--no-default-browser-check",
            ]
        )

        # Wait for Chrome to start
        print("Waiting for Chrome to launch...")
        time.sleep(5)

        # Initialize the browser with custom configuration
        browser_config = BrowserConfig(
            headless=False,
            disable_security=True,
            cdp_url="http://localhost:9222",  # Connect to the manually started Chrome
        )

        try:
            print("Initializing the browser...")
            browser = Browser(browser_config)

            print("Creating a new context...")
            context = await browser.new_context(BrowserContextConfig())

            print("Navigating to Google...")
            await context.navigate_to("https://www.google.com")

            print("Retrieving the page title...")
            title = await context.execute_javascript("document.title")
            print(f"Page title: {title}")

            # Retrieve current state
            print("Getting the current browser state...")
            state = await context.get_state()
            print(f"Current URL: {state.url}")
            print(f"Number of tabs: {len(state.tabs)}")

            # Retrieve clickable elements
            print("Interactive elements:")
            if hasattr(state, "element_tree") and state.element_tree:
                print(state.element_tree.clickable_elements_to_string())

            print("Closing the browser...")
            await browser.close()

            print("Test completed!")
            return True
        except Exception as e:
            print(f"An error occurred: {e}")
            return False
        finally:
            # Terminate Chrome
            try:
                chrome_process.terminate()
            except:
                pass
    except Exception as e:
        print(f"Error launching Chrome: {e}")
        return False


if __name__ == "__main__":
    asyncio.run(main())