feat(browser): add builtin browser management system
Implements a persistent browser management system that allows running a single shared browser instance that can be reused across multiple crawler sessions. Key changes include: - Added browser_mode config option with 'builtin', 'dedicated', and 'custom' modes - Implemented builtin browser management in BrowserProfiler - Added CLI commands for managing builtin browser (start, stop, status, restart, view) - Modified browser process handling to support detached processes - Added automatic builtin browser setup during package installation BREAKING CHANGE: The browser_mode config option changes how browser instances are managed
This commit is contained in:
parent
5358ac0fc2
commit
6432ff1257
@ -169,6 +169,11 @@ class BrowserConfig:
|
||||
Default: "chromium".
|
||||
headless (bool): Whether to run the browser in headless mode (no visible GUI).
|
||||
Default: True.
|
||||
browser_mode (str): Determines how the browser should be initialized:
|
||||
"builtin" - use the builtin CDP browser running in background
|
||||
"dedicated" - create a new dedicated browser instance each time
|
||||
"custom" - use explicit CDP settings provided in cdp_url
|
||||
Default: "dedicated"
|
||||
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/".
|
||||
@ -221,6 +226,7 @@ class BrowserConfig:
|
||||
self,
|
||||
browser_type: str = "chromium",
|
||||
headless: bool = True,
|
||||
browser_mode: str = "dedicated",
|
||||
use_managed_browser: bool = False,
|
||||
cdp_url: str = None,
|
||||
use_persistent_context: bool = False,
|
||||
@ -257,6 +263,7 @@ class BrowserConfig:
|
||||
):
|
||||
self.browser_type = browser_type
|
||||
self.headless = headless
|
||||
self.browser_mode = browser_mode
|
||||
self.use_managed_browser = use_managed_browser
|
||||
self.cdp_url = cdp_url
|
||||
self.use_persistent_context = use_persistent_context
|
||||
@ -290,6 +297,7 @@ class BrowserConfig:
|
||||
self.sleep_on_close = sleep_on_close
|
||||
self.verbose = verbose
|
||||
self.debugging_port = debugging_port
|
||||
self.host = host
|
||||
|
||||
fa_user_agenr_generator = ValidUAGenerator()
|
||||
if self.user_agent_mode == "random":
|
||||
@ -302,6 +310,18 @@ class BrowserConfig:
|
||||
self.browser_hint = UAGen.generate_client_hints(self.user_agent)
|
||||
self.headers.setdefault("sec-ch-ua", self.browser_hint)
|
||||
|
||||
# Set appropriate browser management flags based on browser_mode
|
||||
if self.browser_mode == "builtin":
|
||||
# Builtin mode uses managed browser connecting to builtin CDP endpoint
|
||||
self.use_managed_browser = True
|
||||
# cdp_url will be set later by browser_manager
|
||||
elif self.browser_mode == "custom" and self.cdp_url:
|
||||
# Custom mode with explicit CDP URL
|
||||
self.use_managed_browser = True
|
||||
elif self.browser_mode == "dedicated":
|
||||
# Dedicated mode uses a new browser instance each time
|
||||
pass
|
||||
|
||||
# If persistent context is requested, ensure managed browser is enabled
|
||||
if self.use_persistent_context:
|
||||
self.use_managed_browser = True
|
||||
@ -311,6 +331,7 @@ class BrowserConfig:
|
||||
return BrowserConfig(
|
||||
browser_type=kwargs.get("browser_type", "chromium"),
|
||||
headless=kwargs.get("headless", True),
|
||||
browser_mode=kwargs.get("browser_mode", "dedicated"),
|
||||
use_managed_browser=kwargs.get("use_managed_browser", False),
|
||||
cdp_url=kwargs.get("cdp_url"),
|
||||
use_persistent_context=kwargs.get("use_persistent_context", False),
|
||||
@ -338,12 +359,15 @@ class BrowserConfig:
|
||||
text_mode=kwargs.get("text_mode", False),
|
||||
light_mode=kwargs.get("light_mode", False),
|
||||
extra_args=kwargs.get("extra_args", []),
|
||||
debugging_port=kwargs.get("debugging_port", 9222),
|
||||
host=kwargs.get("host", "localhost"),
|
||||
)
|
||||
|
||||
def to_dict(self):
|
||||
return {
|
||||
"browser_type": self.browser_type,
|
||||
"headless": self.headless,
|
||||
"browser_mode": self.browser_mode,
|
||||
"use_managed_browser": self.use_managed_browser,
|
||||
"cdp_url": self.cdp_url,
|
||||
"use_persistent_context": self.use_persistent_context,
|
||||
@ -370,6 +394,7 @@ class BrowserConfig:
|
||||
"sleep_on_close": self.sleep_on_close,
|
||||
"verbose": self.verbose,
|
||||
"debugging_port": self.debugging_port,
|
||||
"host": self.host,
|
||||
}
|
||||
|
||||
def clone(self, **kwargs):
|
||||
|
@ -201,13 +201,35 @@ class AsyncWebCrawler:
|
||||
This is equivalent to using 'async with' but gives more control over the lifecycle.
|
||||
|
||||
This method will:
|
||||
1. Initialize the browser and context
|
||||
2. Perform warmup sequence
|
||||
3. Return the crawler instance for method chaining
|
||||
1. Check for builtin browser if browser_mode is 'builtin'
|
||||
2. Initialize the browser and context
|
||||
3. Perform warmup sequence
|
||||
4. Return the crawler instance for method chaining
|
||||
|
||||
Returns:
|
||||
AsyncWebCrawler: The initialized crawler instance
|
||||
"""
|
||||
# Check for builtin browser if requested
|
||||
if self.browser_config.browser_mode == "builtin" and not self.browser_config.cdp_url:
|
||||
# Import here to avoid circular imports
|
||||
from .browser_profiler import BrowserProfiler
|
||||
profiler = BrowserProfiler(logger=self.logger)
|
||||
|
||||
# Get builtin browser info or launch if needed
|
||||
browser_info = profiler.get_builtin_browser_info()
|
||||
if not browser_info:
|
||||
self.logger.info("Builtin browser not found, launching new instance...", tag="BROWSER")
|
||||
cdp_url = await profiler.launch_builtin_browser()
|
||||
if not cdp_url:
|
||||
self.logger.warning("Failed to launch builtin browser, falling back to dedicated browser", tag="BROWSER")
|
||||
else:
|
||||
self.browser_config.cdp_url = cdp_url
|
||||
self.browser_config.use_managed_browser = True
|
||||
else:
|
||||
self.logger.info(f"Using existing builtin browser at {browser_info.get('cdp_url')}", tag="BROWSER")
|
||||
self.browser_config.cdp_url = browser_info.get('cdp_url')
|
||||
self.browser_config.use_managed_browser = True
|
||||
|
||||
await self.crawler_strategy.__aenter__()
|
||||
await self.awarmup()
|
||||
return self
|
||||
@ -280,6 +302,10 @@ class AsyncWebCrawler:
|
||||
Returns:
|
||||
CrawlResult: The result of crawling and processing
|
||||
"""
|
||||
# Auto-start if not ready
|
||||
if not self.ready:
|
||||
await self.start()
|
||||
|
||||
config = config or CrawlerRunConfig()
|
||||
if not isinstance(url, str) or not url:
|
||||
raise ValueError("Invalid URL, make sure the URL is a non-empty string")
|
||||
|
@ -145,17 +145,59 @@ class ManagedBrowser:
|
||||
|
||||
# Start browser process
|
||||
try:
|
||||
self.browser_process = subprocess.Popen(
|
||||
args, stdout=subprocess.PIPE, stderr=subprocess.PIPE
|
||||
)
|
||||
# Monitor browser process output for errors
|
||||
asyncio.create_task(self._monitor_browser_process())
|
||||
# Use DETACHED_PROCESS flag on Windows to fully detach the process
|
||||
# On Unix, we'll use preexec_fn=os.setpgrp to start the process in a new process group
|
||||
if sys.platform == "win32":
|
||||
self.browser_process = subprocess.Popen(
|
||||
args,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
creationflags=subprocess.DETACHED_PROCESS | subprocess.CREATE_NEW_PROCESS_GROUP
|
||||
)
|
||||
else:
|
||||
self.browser_process = subprocess.Popen(
|
||||
args,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
preexec_fn=os.setpgrp # Start in a new process group
|
||||
)
|
||||
|
||||
# We'll monitor for a short time to make sure it starts properly, but won't keep monitoring
|
||||
await self._initial_startup_check()
|
||||
await asyncio.sleep(2) # Give browser time to start
|
||||
return f"http://{self.host}:{self.debugging_port}"
|
||||
except Exception as e:
|
||||
await self.cleanup()
|
||||
raise Exception(f"Failed to start browser: {e}")
|
||||
|
||||
async def _initial_startup_check(self):
|
||||
"""
|
||||
Perform a quick check to make sure the browser started successfully.
|
||||
This only runs once at startup rather than continuously monitoring.
|
||||
"""
|
||||
if not self.browser_process:
|
||||
return
|
||||
|
||||
# Check that process started without immediate termination
|
||||
await asyncio.sleep(0.5)
|
||||
if self.browser_process.poll() is not None:
|
||||
# Process already terminated
|
||||
stdout, stderr = b"", b""
|
||||
try:
|
||||
stdout, stderr = self.browser_process.communicate(timeout=0.5)
|
||||
except subprocess.TimeoutExpired:
|
||||
pass
|
||||
|
||||
self.logger.error(
|
||||
message="Browser process terminated during startup | Code: {code} | STDOUT: {stdout} | STDERR: {stderr}",
|
||||
tag="ERROR",
|
||||
params={
|
||||
"code": self.browser_process.returncode,
|
||||
"stdout": stdout.decode() if stdout else "",
|
||||
"stderr": stderr.decode() if stderr else "",
|
||||
},
|
||||
)
|
||||
|
||||
async def _monitor_browser_process(self):
|
||||
"""
|
||||
Monitor the browser process for unexpected termination.
|
||||
@ -167,6 +209,7 @@ class ManagedBrowser:
|
||||
4. If any other error occurs, log the error message.
|
||||
|
||||
Note: This method should be called in a separate task to avoid blocking the main event loop.
|
||||
This is DEPRECATED and should not be used for builtin browsers that need to outlive the Python process.
|
||||
"""
|
||||
if self.browser_process:
|
||||
try:
|
||||
@ -261,22 +304,33 @@ class ManagedBrowser:
|
||||
|
||||
if self.browser_process:
|
||||
try:
|
||||
self.browser_process.terminate()
|
||||
# Wait for process to end gracefully
|
||||
for _ in range(10): # 10 attempts, 100ms each
|
||||
if self.browser_process.poll() is not None:
|
||||
break
|
||||
await asyncio.sleep(0.1)
|
||||
# For builtin browsers that should persist, we should check if it's a detached process
|
||||
# Only terminate if we have proper control over the process
|
||||
if not self.browser_process.poll():
|
||||
# Process is still running
|
||||
self.browser_process.terminate()
|
||||
# Wait for process to end gracefully
|
||||
for _ in range(10): # 10 attempts, 100ms each
|
||||
if self.browser_process.poll() is not None:
|
||||
break
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
# Force kill if still running
|
||||
if self.browser_process.poll() is None:
|
||||
self.browser_process.kill()
|
||||
await asyncio.sleep(0.1) # Brief wait for kill to take effect
|
||||
# Force kill if still running
|
||||
if self.browser_process.poll() is None:
|
||||
if sys.platform == "win32":
|
||||
# On Windows we might need taskkill for detached processes
|
||||
try:
|
||||
subprocess.run(["taskkill", "/F", "/PID", str(self.browser_process.pid)])
|
||||
except Exception:
|
||||
self.browser_process.kill()
|
||||
else:
|
||||
self.browser_process.kill()
|
||||
await asyncio.sleep(0.1) # Brief wait for kill to take effect
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(
|
||||
message="Error terminating browser: {error}",
|
||||
tag="ERROR",
|
||||
tag="ERROR",
|
||||
params={"error": str(e)},
|
||||
)
|
||||
|
||||
@ -379,7 +433,15 @@ class BrowserManager:
|
||||
sessions (dict): Dictionary to store session information
|
||||
session_ttl (int): Session timeout in seconds
|
||||
"""
|
||||
|
||||
_playwright_instance = None
|
||||
|
||||
@classmethod
|
||||
async def get_playwright(cls):
|
||||
from playwright.async_api import async_playwright
|
||||
if cls._playwright_instance is None:
|
||||
cls._playwright_instance = await async_playwright().start()
|
||||
return cls._playwright_instance
|
||||
|
||||
def __init__(self, browser_config: BrowserConfig, logger=None):
|
||||
"""
|
||||
@ -429,6 +491,7 @@ class BrowserManager:
|
||||
|
||||
Note: This method should be called in a separate task to avoid blocking the main event loop.
|
||||
"""
|
||||
self.playwright = await self.get_playwright()
|
||||
if self.playwright is None:
|
||||
from playwright.async_api import async_playwright
|
||||
|
||||
|
@ -12,7 +12,10 @@ import sys
|
||||
import datetime
|
||||
import uuid
|
||||
import shutil
|
||||
from typing import List, Dict, Optional, Any
|
||||
import json
|
||||
import subprocess
|
||||
import time
|
||||
from typing import List, Dict, Optional, Any, Tuple
|
||||
from colorama import Fore, Style, init
|
||||
|
||||
from .async_configs import BrowserConfig
|
||||
@ -56,6 +59,11 @@ class BrowserProfiler:
|
||||
# Ensure profiles directory exists
|
||||
self.profiles_dir = os.path.join(get_home_folder(), "profiles")
|
||||
os.makedirs(self.profiles_dir, exist_ok=True)
|
||||
|
||||
# Builtin browser config file
|
||||
self.builtin_browser_dir = os.path.join(get_home_folder(), "builtin-browser")
|
||||
self.builtin_config_file = os.path.join(self.builtin_browser_dir, "browser_config.json")
|
||||
os.makedirs(self.builtin_browser_dir, exist_ok=True)
|
||||
|
||||
async def create_profile(self,
|
||||
profile_name: Optional[str] = None,
|
||||
@ -552,7 +560,8 @@ class BrowserProfiler:
|
||||
browser_type: str = "chromium",
|
||||
user_data_dir: Optional[str] = None,
|
||||
debugging_port: int = 9222,
|
||||
headless: bool = False) -> Optional[str]:
|
||||
headless: bool = False,
|
||||
save_as_builtin: bool = False) -> Optional[str]:
|
||||
"""
|
||||
Launch a standalone browser with CDP debugging enabled and keep it running
|
||||
until the user presses 'q'. Returns and displays the CDP URL.
|
||||
@ -766,4 +775,201 @@ class BrowserProfiler:
|
||||
# Return the CDP URL
|
||||
return cdp_url
|
||||
|
||||
async def launch_builtin_browser(self,
|
||||
browser_type: str = "chromium",
|
||||
debugging_port: int = 9222,
|
||||
headless: bool = True) -> Optional[str]:
|
||||
"""
|
||||
Launch a browser in the background for use as the builtin browser.
|
||||
|
||||
Args:
|
||||
browser_type (str): Type of browser to launch ('chromium' or 'firefox')
|
||||
debugging_port (int): Port to use for CDP debugging
|
||||
headless (bool): Whether to run in headless mode
|
||||
|
||||
Returns:
|
||||
str: CDP URL for the browser, or None if launch failed
|
||||
"""
|
||||
# Check if there's an existing browser still running
|
||||
browser_info = self.get_builtin_browser_info()
|
||||
if browser_info and self._is_browser_running(browser_info.get('pid')):
|
||||
self.logger.info("Builtin browser is already running", tag="BUILTIN")
|
||||
return browser_info.get('cdp_url')
|
||||
|
||||
# Create a user data directory for the builtin browser
|
||||
user_data_dir = os.path.join(self.builtin_browser_dir, "user_data")
|
||||
os.makedirs(user_data_dir, exist_ok=True)
|
||||
|
||||
# Create managed browser instance
|
||||
managed_browser = ManagedBrowser(
|
||||
browser_type=browser_type,
|
||||
user_data_dir=user_data_dir,
|
||||
headless=headless,
|
||||
logger=self.logger,
|
||||
debugging_port=debugging_port
|
||||
)
|
||||
|
||||
try:
|
||||
# Start the browser
|
||||
await managed_browser.start()
|
||||
|
||||
# Check if browser started successfully
|
||||
browser_process = managed_browser.browser_process
|
||||
if not browser_process:
|
||||
self.logger.error("Failed to start browser process.", tag="BUILTIN")
|
||||
return None
|
||||
|
||||
# Get CDP URL
|
||||
cdp_url = f"http://localhost:{debugging_port}"
|
||||
|
||||
# Try to verify browser is responsive by fetching version info
|
||||
import aiohttp
|
||||
json_url = f"{cdp_url}/json/version"
|
||||
config_json = None
|
||||
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
for _ in range(10): # Try multiple times
|
||||
try:
|
||||
async with session.get(json_url) as response:
|
||||
if response.status == 200:
|
||||
config_json = await response.json()
|
||||
break
|
||||
except Exception:
|
||||
pass
|
||||
await asyncio.sleep(0.5)
|
||||
except Exception as e:
|
||||
self.logger.warning(f"Could not verify browser: {str(e)}", tag="BUILTIN")
|
||||
|
||||
# Save browser info
|
||||
browser_info = {
|
||||
'pid': browser_process.pid,
|
||||
'cdp_url': cdp_url,
|
||||
'user_data_dir': user_data_dir,
|
||||
'browser_type': browser_type,
|
||||
'debugging_port': debugging_port,
|
||||
'start_time': time.time(),
|
||||
'config': config_json
|
||||
}
|
||||
|
||||
with open(self.builtin_config_file, 'w') as f:
|
||||
json.dump(browser_info, f, indent=2)
|
||||
|
||||
# Detach from the browser process - don't keep any references
|
||||
# This is important to allow the Python script to exit while the browser continues running
|
||||
# We'll just record the PID and other info, and the browser will run independently
|
||||
managed_browser.browser_process = None
|
||||
|
||||
self.logger.success(f"Builtin browser launched at CDP URL: {cdp_url}", tag="BUILTIN")
|
||||
return cdp_url
|
||||
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error launching builtin browser: {str(e)}", tag="BUILTIN")
|
||||
if managed_browser:
|
||||
await managed_browser.cleanup()
|
||||
return None
|
||||
|
||||
def get_builtin_browser_info(self) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Get information about the builtin browser.
|
||||
|
||||
Returns:
|
||||
dict: Browser information or None if no builtin browser is configured
|
||||
"""
|
||||
if not os.path.exists(self.builtin_config_file):
|
||||
return None
|
||||
|
||||
try:
|
||||
with open(self.builtin_config_file, 'r') as f:
|
||||
browser_info = json.load(f)
|
||||
|
||||
# Check if the browser is still running
|
||||
if not self._is_browser_running(browser_info.get('pid')):
|
||||
self.logger.warning("Builtin browser is not running", tag="BUILTIN")
|
||||
return None
|
||||
|
||||
return browser_info
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error reading builtin browser config: {str(e)}", tag="BUILTIN")
|
||||
return None
|
||||
|
||||
def _is_browser_running(self, pid: Optional[int]) -> bool:
|
||||
"""Check if a process with the given PID is running"""
|
||||
if not pid:
|
||||
return False
|
||||
|
||||
try:
|
||||
# Check if the process exists
|
||||
if sys.platform == "win32":
|
||||
process = subprocess.run(["tasklist", "/FI", f"PID eq {pid}"],
|
||||
capture_output=True, text=True)
|
||||
return str(pid) in process.stdout
|
||||
else:
|
||||
# Unix-like systems
|
||||
os.kill(pid, 0) # This doesn't actually kill the process, just checks if it exists
|
||||
return True
|
||||
except (ProcessLookupError, PermissionError, OSError):
|
||||
return False
|
||||
|
||||
async def kill_builtin_browser(self) -> bool:
|
||||
"""
|
||||
Kill the builtin browser if it's running.
|
||||
|
||||
Returns:
|
||||
bool: True if the browser was killed, False otherwise
|
||||
"""
|
||||
browser_info = self.get_builtin_browser_info()
|
||||
if not browser_info:
|
||||
self.logger.warning("No builtin browser found", tag="BUILTIN")
|
||||
return False
|
||||
|
||||
pid = browser_info.get('pid')
|
||||
if not pid:
|
||||
return False
|
||||
|
||||
try:
|
||||
if sys.platform == "win32":
|
||||
subprocess.run(["taskkill", "/F", "/PID", str(pid)], check=True)
|
||||
else:
|
||||
os.kill(pid, signal.SIGTERM)
|
||||
# Wait for termination
|
||||
for _ in range(5):
|
||||
if not self._is_browser_running(pid):
|
||||
break
|
||||
await asyncio.sleep(0.5)
|
||||
else:
|
||||
# Force kill if still running
|
||||
os.kill(pid, signal.SIGKILL)
|
||||
|
||||
# Remove config file
|
||||
if os.path.exists(self.builtin_config_file):
|
||||
os.unlink(self.builtin_config_file)
|
||||
|
||||
self.logger.success("Builtin browser terminated", tag="BUILTIN")
|
||||
return True
|
||||
except Exception as e:
|
||||
self.logger.error(f"Error killing builtin browser: {str(e)}", tag="BUILTIN")
|
||||
return False
|
||||
|
||||
async def get_builtin_browser_status(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Get status information about the builtin browser.
|
||||
|
||||
Returns:
|
||||
dict: Status information with running, cdp_url, and info fields
|
||||
"""
|
||||
browser_info = self.get_builtin_browser_info()
|
||||
|
||||
if not browser_info:
|
||||
return {
|
||||
'running': False,
|
||||
'cdp_url': None,
|
||||
'info': None
|
||||
}
|
||||
|
||||
return {
|
||||
'running': True,
|
||||
'cdp_url': browser_info.get('cdp_url'),
|
||||
'info': browser_info
|
||||
}
|
||||
|
||||
|
328
crawl4ai/cli.py
328
crawl4ai/cli.py
@ -341,6 +341,32 @@ For more documentation visit: https://github.com/unclecode/crawl4ai
|
||||
crwl profiles # Select "Create new profile" option
|
||||
# 2. Then use that profile to crawl authenticated content:
|
||||
crwl https://site-requiring-login.com/dashboard -p my-profile-name
|
||||
|
||||
🔄 Builtin Browser Management:
|
||||
# Start a builtin browser (runs in the background)
|
||||
crwl browser start
|
||||
|
||||
# Check builtin browser status
|
||||
crwl browser status
|
||||
|
||||
# Open a visible window to see the browser
|
||||
crwl browser view --url https://example.com
|
||||
|
||||
# Stop the builtin browser
|
||||
crwl browser stop
|
||||
|
||||
# Restart with different options
|
||||
crwl browser restart --browser-type chromium --port 9223 --no-headless
|
||||
|
||||
# Use the builtin browser in your code
|
||||
# (Just set browser_mode="builtin" in your BrowserConfig)
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="builtin",
|
||||
headless=True
|
||||
)
|
||||
|
||||
# Usage via CLI:
|
||||
crwl https://example.com -b "browser_mode=builtin"
|
||||
"""
|
||||
click.echo(examples)
|
||||
|
||||
@ -575,6 +601,307 @@ def cli():
|
||||
pass
|
||||
|
||||
|
||||
@cli.group("browser")
|
||||
def browser_cmd():
|
||||
"""Manage browser instances for Crawl4AI
|
||||
|
||||
Commands to manage browser instances for Crawl4AI, including:
|
||||
- status - Check status of the builtin browser
|
||||
- start - Start a new builtin browser
|
||||
- stop - Stop the running builtin browser
|
||||
- restart - Restart the builtin browser
|
||||
"""
|
||||
pass
|
||||
|
||||
@browser_cmd.command("status")
|
||||
def browser_status_cmd():
|
||||
"""Show status of the builtin browser"""
|
||||
profiler = BrowserProfiler()
|
||||
|
||||
try:
|
||||
status = anyio.run(profiler.get_builtin_browser_status)
|
||||
|
||||
if status["running"]:
|
||||
info = status["info"]
|
||||
console.print(Panel(
|
||||
f"[green]Builtin browser is running[/green]\n\n"
|
||||
f"CDP URL: [cyan]{info['cdp_url']}[/cyan]\n"
|
||||
f"Process ID: [yellow]{info['pid']}[/yellow]\n"
|
||||
f"Browser type: [blue]{info['browser_type']}[/blue]\n"
|
||||
f"User data directory: [magenta]{info['user_data_dir']}[/magenta]\n"
|
||||
f"Started: [cyan]{time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(info['start_time']))}[/cyan]",
|
||||
title="Builtin Browser Status",
|
||||
border_style="green"
|
||||
))
|
||||
else:
|
||||
console.print(Panel(
|
||||
"[yellow]Builtin browser is not running[/yellow]\n\n"
|
||||
"Use 'crwl browser start' to start a builtin browser",
|
||||
title="Builtin Browser Status",
|
||||
border_style="yellow"
|
||||
))
|
||||
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error checking browser status: {str(e)}[/red]")
|
||||
sys.exit(1)
|
||||
|
||||
@browser_cmd.command("start")
|
||||
@click.option("--browser-type", "-b", type=click.Choice(["chromium", "firefox"]), default="chromium",
|
||||
help="Browser type (default: chromium)")
|
||||
@click.option("--port", "-p", type=int, default=9222, help="Debugging port (default: 9222)")
|
||||
@click.option("--headless/--no-headless", default=True, help="Run browser in headless mode")
|
||||
def browser_start_cmd(browser_type: str, port: int, headless: bool):
|
||||
"""Start a builtin browser instance
|
||||
|
||||
This will start a persistent browser instance that can be used by Crawl4AI
|
||||
by setting browser_mode="builtin" in BrowserConfig.
|
||||
"""
|
||||
profiler = BrowserProfiler()
|
||||
|
||||
# First check if browser is already running
|
||||
status = anyio.run(profiler.get_builtin_browser_status)
|
||||
if status["running"]:
|
||||
console.print(Panel(
|
||||
"[yellow]Builtin browser is already running[/yellow]\n\n"
|
||||
f"CDP URL: [cyan]{status['cdp_url']}[/cyan]\n\n"
|
||||
"Use 'crwl browser restart' to restart the browser",
|
||||
title="Builtin Browser Start",
|
||||
border_style="yellow"
|
||||
))
|
||||
return
|
||||
|
||||
try:
|
||||
console.print(Panel(
|
||||
f"[cyan]Starting builtin browser[/cyan]\n\n"
|
||||
f"Browser type: [green]{browser_type}[/green]\n"
|
||||
f"Debugging port: [yellow]{port}[/yellow]\n"
|
||||
f"Headless: [cyan]{'Yes' if headless else 'No'}[/cyan]",
|
||||
title="Builtin Browser Start",
|
||||
border_style="cyan"
|
||||
))
|
||||
|
||||
cdp_url = anyio.run(
|
||||
profiler.launch_builtin_browser,
|
||||
browser_type,
|
||||
port,
|
||||
headless
|
||||
)
|
||||
|
||||
if cdp_url:
|
||||
console.print(Panel(
|
||||
f"[green]Builtin browser started successfully[/green]\n\n"
|
||||
f"CDP URL: [cyan]{cdp_url}[/cyan]\n\n"
|
||||
"This browser will be used automatically when setting browser_mode='builtin'",
|
||||
title="Builtin Browser Start",
|
||||
border_style="green"
|
||||
))
|
||||
else:
|
||||
console.print(Panel(
|
||||
"[red]Failed to start builtin browser[/red]",
|
||||
title="Builtin Browser Start",
|
||||
border_style="red"
|
||||
))
|
||||
sys.exit(1)
|
||||
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error starting builtin browser: {str(e)}[/red]")
|
||||
sys.exit(1)
|
||||
|
||||
@browser_cmd.command("stop")
|
||||
def browser_stop_cmd():
|
||||
"""Stop the running builtin browser"""
|
||||
profiler = BrowserProfiler()
|
||||
|
||||
try:
|
||||
# First check if browser is running
|
||||
status = anyio.run(profiler.get_builtin_browser_status)
|
||||
if not status["running"]:
|
||||
console.print(Panel(
|
||||
"[yellow]No builtin browser is currently running[/yellow]",
|
||||
title="Builtin Browser Stop",
|
||||
border_style="yellow"
|
||||
))
|
||||
return
|
||||
|
||||
console.print(Panel(
|
||||
"[cyan]Stopping builtin browser...[/cyan]",
|
||||
title="Builtin Browser Stop",
|
||||
border_style="cyan"
|
||||
))
|
||||
|
||||
success = anyio.run(profiler.kill_builtin_browser)
|
||||
|
||||
if success:
|
||||
console.print(Panel(
|
||||
"[green]Builtin browser stopped successfully[/green]",
|
||||
title="Builtin Browser Stop",
|
||||
border_style="green"
|
||||
))
|
||||
else:
|
||||
console.print(Panel(
|
||||
"[red]Failed to stop builtin browser[/red]",
|
||||
title="Builtin Browser Stop",
|
||||
border_style="red"
|
||||
))
|
||||
sys.exit(1)
|
||||
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error stopping builtin browser: {str(e)}[/red]")
|
||||
sys.exit(1)
|
||||
|
||||
@browser_cmd.command("view")
|
||||
@click.option("--url", "-u", help="URL to navigate to (defaults to about:blank)")
|
||||
def browser_view_cmd(url: Optional[str]):
|
||||
"""
|
||||
Open a visible window of the builtin browser
|
||||
|
||||
This command connects to the running builtin browser and opens a visible window,
|
||||
allowing you to see what the browser is currently viewing or navigate to a URL.
|
||||
"""
|
||||
profiler = BrowserProfiler()
|
||||
|
||||
try:
|
||||
# First check if browser is running
|
||||
status = anyio.run(profiler.get_builtin_browser_status)
|
||||
if not status["running"]:
|
||||
console.print(Panel(
|
||||
"[yellow]No builtin browser is currently running[/yellow]\n\n"
|
||||
"Use 'crwl browser start' to start a builtin browser first",
|
||||
title="Builtin Browser View",
|
||||
border_style="yellow"
|
||||
))
|
||||
return
|
||||
|
||||
info = status["info"]
|
||||
cdp_url = info["cdp_url"]
|
||||
|
||||
console.print(Panel(
|
||||
f"[cyan]Opening visible window connected to builtin browser[/cyan]\n\n"
|
||||
f"CDP URL: [green]{cdp_url}[/green]\n"
|
||||
f"URL to load: [yellow]{url or 'about:blank'}[/yellow]",
|
||||
title="Builtin Browser View",
|
||||
border_style="cyan"
|
||||
))
|
||||
|
||||
# Use the CDP URL to launch a new visible window
|
||||
import subprocess
|
||||
import os
|
||||
|
||||
# Determine the browser command based on platform
|
||||
if sys.platform == "darwin": # macOS
|
||||
browser_cmd = ["/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"]
|
||||
elif sys.platform == "win32": # Windows
|
||||
browser_cmd = ["C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"]
|
||||
else: # Linux
|
||||
browser_cmd = ["google-chrome"]
|
||||
|
||||
# Add arguments
|
||||
browser_args = [
|
||||
f"--remote-debugging-port={info['debugging_port']}",
|
||||
"--remote-debugging-address=localhost",
|
||||
"--no-first-run",
|
||||
"--no-default-browser-check"
|
||||
]
|
||||
|
||||
# Add URL if provided
|
||||
if url:
|
||||
browser_args.append(url)
|
||||
|
||||
# Launch browser
|
||||
try:
|
||||
subprocess.Popen(browser_cmd + browser_args)
|
||||
console.print("[green]Browser window opened. Close it when finished viewing.[/green]")
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error launching browser: {str(e)}[/red]")
|
||||
console.print(f"[yellow]Try connecting manually to {cdp_url} in Chrome or using the '--remote-debugging-port' flag.[/yellow]")
|
||||
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error viewing builtin browser: {str(e)}[/red]")
|
||||
sys.exit(1)
|
||||
|
||||
@browser_cmd.command("restart")
|
||||
@click.option("--browser-type", "-b", type=click.Choice(["chromium", "firefox"]), default=None,
|
||||
help="Browser type (defaults to same as current)")
|
||||
@click.option("--port", "-p", type=int, default=None, help="Debugging port (defaults to same as current)")
|
||||
@click.option("--headless/--no-headless", default=None, help="Run browser in headless mode")
|
||||
def browser_restart_cmd(browser_type: Optional[str], port: Optional[int], headless: Optional[bool]):
|
||||
"""Restart the builtin browser
|
||||
|
||||
Stops the current builtin browser if running and starts a new one.
|
||||
By default, uses the same configuration as the current browser.
|
||||
"""
|
||||
profiler = BrowserProfiler()
|
||||
|
||||
try:
|
||||
# First check if browser is running and get its config
|
||||
status = anyio.run(profiler.get_builtin_browser_status)
|
||||
current_config = {}
|
||||
|
||||
if status["running"]:
|
||||
info = status["info"]
|
||||
current_config = {
|
||||
"browser_type": info["browser_type"],
|
||||
"port": info["debugging_port"],
|
||||
"headless": True # Default assumption
|
||||
}
|
||||
|
||||
# Stop the browser
|
||||
console.print(Panel(
|
||||
"[cyan]Stopping current builtin browser...[/cyan]",
|
||||
title="Builtin Browser Restart",
|
||||
border_style="cyan"
|
||||
))
|
||||
|
||||
success = anyio.run(profiler.kill_builtin_browser)
|
||||
if not success:
|
||||
console.print(Panel(
|
||||
"[red]Failed to stop current browser[/red]",
|
||||
title="Builtin Browser Restart",
|
||||
border_style="red"
|
||||
))
|
||||
sys.exit(1)
|
||||
|
||||
# Use provided options or defaults from current config
|
||||
browser_type = browser_type or current_config.get("browser_type", "chromium")
|
||||
port = port or current_config.get("port", 9222)
|
||||
headless = headless if headless is not None else current_config.get("headless", True)
|
||||
|
||||
# Start a new browser
|
||||
console.print(Panel(
|
||||
f"[cyan]Starting new builtin browser[/cyan]\n\n"
|
||||
f"Browser type: [green]{browser_type}[/green]\n"
|
||||
f"Debugging port: [yellow]{port}[/yellow]\n"
|
||||
f"Headless: [cyan]{'Yes' if headless else 'No'}[/cyan]",
|
||||
title="Builtin Browser Restart",
|
||||
border_style="cyan"
|
||||
))
|
||||
|
||||
cdp_url = anyio.run(
|
||||
profiler.launch_builtin_browser,
|
||||
browser_type,
|
||||
port,
|
||||
headless
|
||||
)
|
||||
|
||||
if cdp_url:
|
||||
console.print(Panel(
|
||||
f"[green]Builtin browser restarted successfully[/green]\n\n"
|
||||
f"CDP URL: [cyan]{cdp_url}[/cyan]",
|
||||
title="Builtin Browser Restart",
|
||||
border_style="green"
|
||||
))
|
||||
else:
|
||||
console.print(Panel(
|
||||
"[red]Failed to restart builtin browser[/red]",
|
||||
title="Builtin Browser Restart",
|
||||
border_style="red"
|
||||
))
|
||||
sys.exit(1)
|
||||
|
||||
except Exception as e:
|
||||
console.print(f"[red]Error restarting builtin browser: {str(e)}[/red]")
|
||||
sys.exit(1)
|
||||
|
||||
@cli.command("cdp")
|
||||
@click.option("--user-data-dir", "-d", help="Directory to use for browser data (will be created if it doesn't exist)")
|
||||
@click.option("--port", "-P", type=int, default=9222, help="Debugging port (default: 9222)")
|
||||
@ -834,6 +1161,7 @@ def default(url: str, example: bool, browser_config: str, crawler_config: str, f
|
||||
crwl profiles - Manage browser profiles for identity-based crawling
|
||||
crwl crawl - Crawl a website with advanced options
|
||||
crwl cdp - Launch browser with CDP debugging enabled
|
||||
crwl browser - Manage builtin browser (start, stop, status, restart)
|
||||
crwl examples - Show more usage examples
|
||||
"""
|
||||
|
||||
|
@ -45,7 +45,34 @@ def post_install():
|
||||
setup_home_directory()
|
||||
install_playwright()
|
||||
run_migration()
|
||||
setup_builtin_browser()
|
||||
logger.success("Post-installation setup completed!", tag="COMPLETE")
|
||||
|
||||
def setup_builtin_browser():
|
||||
"""Set up a builtin browser for use with Crawl4AI"""
|
||||
try:
|
||||
logger.info("Setting up builtin browser...", tag="INIT")
|
||||
asyncio.run(_setup_builtin_browser())
|
||||
logger.success("Builtin browser setup completed!", tag="COMPLETE")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to set up builtin browser: {e}")
|
||||
logger.warning("You can manually set up a builtin browser using 'crawl4ai-doctor builtin-browser-start'")
|
||||
|
||||
async def _setup_builtin_browser():
|
||||
try:
|
||||
# Import BrowserProfiler here to avoid circular imports
|
||||
from .browser_profiler import BrowserProfiler
|
||||
profiler = BrowserProfiler(logger=logger)
|
||||
|
||||
# Launch the builtin browser
|
||||
cdp_url = await profiler.launch_builtin_browser(headless=True)
|
||||
if cdp_url:
|
||||
logger.success(f"Builtin browser launched at {cdp_url}", tag="BROWSER")
|
||||
else:
|
||||
logger.warning("Failed to launch builtin browser", tag="BROWSER")
|
||||
except Exception as e:
|
||||
logger.warning(f"Error setting up builtin browser: {e}", tag="BROWSER")
|
||||
raise
|
||||
|
||||
|
||||
def install_playwright():
|
||||
|
123
docs/examples/README_BUILTIN_BROWSER.md
Normal file
123
docs/examples/README_BUILTIN_BROWSER.md
Normal file
@ -0,0 +1,123 @@
|
||||
# Builtin Browser in Crawl4AI
|
||||
|
||||
This document explains the builtin browser feature in Crawl4AI and how to use it effectively.
|
||||
|
||||
## What is the Builtin Browser?
|
||||
|
||||
The builtin browser is a persistent Chrome instance that Crawl4AI manages for you. It runs in the background and can be used by multiple crawling operations, eliminating the need to start and stop browsers for each crawl.
|
||||
|
||||
Benefits include:
|
||||
- **Faster startup times** - The browser is already running, so your scripts start faster
|
||||
- **Shared resources** - All your crawling scripts can use the same browser instance
|
||||
- **Simplified management** - No need to worry about CDP URLs or browser processes
|
||||
- **Persistent cookies and sessions** - Browser state persists between script runs
|
||||
- **Less resource usage** - Only one browser instance for multiple scripts
|
||||
|
||||
## Using the Builtin Browser
|
||||
|
||||
### In Python Code
|
||||
|
||||
Using the builtin browser in your code is simple:
|
||||
|
||||
```python
|
||||
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig
|
||||
|
||||
# Create browser config with builtin mode
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="builtin", # This is the key setting!
|
||||
headless=True # Can be headless or not
|
||||
)
|
||||
|
||||
# Create the crawler
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
|
||||
# Use it - no need to explicitly start()
|
||||
result = await crawler.arun("https://example.com")
|
||||
```
|
||||
|
||||
Key points:
|
||||
1. Set `browser_mode="builtin"` in your BrowserConfig
|
||||
2. No need for explicit `start()` call - the crawler will automatically connect to the builtin browser
|
||||
3. No need to use a context manager or call `close()` - the browser stays running
|
||||
|
||||
### Via CLI
|
||||
|
||||
The CLI provides commands to manage the builtin browser:
|
||||
|
||||
```bash
|
||||
# Start the builtin browser
|
||||
crwl browser start
|
||||
|
||||
# Check its status
|
||||
crwl browser status
|
||||
|
||||
# Open a visible window to see what the browser is doing
|
||||
crwl browser view --url https://example.com
|
||||
|
||||
# Stop it when no longer needed
|
||||
crwl browser stop
|
||||
|
||||
# Restart with different settings
|
||||
crwl browser restart --no-headless
|
||||
```
|
||||
|
||||
When crawling via CLI, simply add the builtin browser mode:
|
||||
|
||||
```bash
|
||||
crwl https://example.com -b "browser_mode=builtin"
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
1. When a crawler with `browser_mode="builtin"` is created:
|
||||
- It checks if a builtin browser is already running
|
||||
- If not, it automatically launches one
|
||||
- It connects to the browser via CDP (Chrome DevTools Protocol)
|
||||
|
||||
2. The browser process continues running after your script exits
|
||||
- This means it's ready for the next crawl
|
||||
- You can manage it via the CLI commands
|
||||
|
||||
3. During installation, Crawl4AI attempts to create a builtin browser automatically
|
||||
|
||||
## Example
|
||||
|
||||
See the [builtin_browser_example.py](builtin_browser_example.py) file for a complete example.
|
||||
|
||||
Run it with:
|
||||
|
||||
```bash
|
||||
python builtin_browser_example.py
|
||||
```
|
||||
|
||||
## When to Use
|
||||
|
||||
The builtin browser is ideal for:
|
||||
- Scripts that run frequently
|
||||
- Development and testing workflows
|
||||
- Applications that need to minimize startup time
|
||||
- Systems where you want to manage browser instances centrally
|
||||
|
||||
You might not want to use it when:
|
||||
- Running one-off scripts
|
||||
- When you need different browser configurations for different tasks
|
||||
- In environments where persistent processes are not allowed
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
If you encounter issues:
|
||||
|
||||
1. Check the browser status:
|
||||
```
|
||||
crwl browser status
|
||||
```
|
||||
|
||||
2. Try restarting it:
|
||||
```
|
||||
crwl browser restart
|
||||
```
|
||||
|
||||
3. If problems persist, stop it and let Crawl4AI start a fresh one:
|
||||
```
|
||||
crwl browser stop
|
||||
```
|
86
docs/examples/builtin_browser_example.py
Normal file
86
docs/examples/builtin_browser_example.py
Normal file
@ -0,0 +1,86 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Builtin Browser Example
|
||||
|
||||
This example demonstrates how to use Crawl4AI's builtin browser feature,
|
||||
which simplifies the browser management process. With builtin mode:
|
||||
|
||||
- No need to manually start or connect to a browser
|
||||
- No need to manage CDP URLs or browser processes
|
||||
- Automatically connects to an existing browser or launches one if needed
|
||||
- Browser persists between script runs, reducing startup time
|
||||
- No explicit cleanup or close() calls needed
|
||||
|
||||
The example also demonstrates "auto-starting" where you don't need to explicitly
|
||||
call start() method on the crawler.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
|
||||
import time
|
||||
|
||||
async def crawl_with_builtin_browser():
|
||||
"""
|
||||
Simple example of crawling with the builtin browser.
|
||||
|
||||
Key features:
|
||||
1. browser_mode="builtin" in BrowserConfig
|
||||
2. No explicit start() call needed
|
||||
3. No explicit close() needed
|
||||
"""
|
||||
print("\n=== Crawl4AI Builtin Browser Example ===\n")
|
||||
|
||||
# Create a browser configuration with builtin mode
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="builtin", # This is the key setting!
|
||||
headless=True # Can run headless for background operation
|
||||
)
|
||||
|
||||
# Create crawler run configuration
|
||||
crawler_config = CrawlerRunConfig(
|
||||
cache_mode=CacheMode.BYPASS, # Skip cache for this demo
|
||||
screenshot=True, # Take a screenshot
|
||||
verbose=True # Show verbose logging
|
||||
)
|
||||
|
||||
# Create the crawler instance
|
||||
# Note: We don't need to use "async with" context manager
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
|
||||
# Start crawling several URLs - no explicit start() needed!
|
||||
# The crawler will automatically connect to the builtin browser
|
||||
print("\n➡️ Crawling first URL...")
|
||||
t0 = time.time()
|
||||
result1 = await crawler.arun(
|
||||
url="https://crawl4ai.com",
|
||||
config=crawler_config
|
||||
)
|
||||
t1 = time.time()
|
||||
print(f"✅ First URL crawled in {t1-t0:.2f} seconds")
|
||||
print(f" Got {len(result1.markdown.raw_markdown)} characters of content")
|
||||
print(f" Title: {result1.metadata.get('title', 'No title')}")
|
||||
|
||||
# Try another URL - the browser is already running, so this should be faster
|
||||
print("\n➡️ Crawling second URL...")
|
||||
t0 = time.time()
|
||||
result2 = await crawler.arun(
|
||||
url="https://example.com",
|
||||
config=crawler_config
|
||||
)
|
||||
t1 = time.time()
|
||||
print(f"✅ Second URL crawled in {t1-t0:.2f} seconds")
|
||||
print(f" Got {len(result2.markdown.raw_markdown)} characters of content")
|
||||
print(f" Title: {result2.metadata.get('title', 'No title')}")
|
||||
|
||||
# The builtin browser continues running in the background
|
||||
# No need to explicitly close it
|
||||
print("\n🔄 The builtin browser remains running for future use")
|
||||
print(" You can use 'crwl browser status' to check its status")
|
||||
print(" or 'crwl browser stop' to stop it when completely done")
|
||||
|
||||
async def main():
|
||||
"""Run the example"""
|
||||
await crawl_with_builtin_browser()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
300
tests/browser/test_builtin_browser.py
Normal file
300
tests/browser/test_builtin_browser.py
Normal file
@ -0,0 +1,300 @@
|
||||
"""
|
||||
Test script for browser_profiler and builtin browser functionality.
|
||||
|
||||
This script tests:
|
||||
1. Creating a builtin browser
|
||||
2. Getting browser information
|
||||
3. Killing the browser
|
||||
4. Restarting the browser
|
||||
5. Testing crawling with different browser modes
|
||||
6. Testing edge cases
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from colorama import Fore, init
|
||||
|
||||
# Add the project root to the path for imports
|
||||
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..')))
|
||||
|
||||
from crawl4ai.browser_profiler import BrowserProfiler
|
||||
from crawl4ai.async_webcrawler import AsyncWebCrawler
|
||||
from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
|
||||
from crawl4ai.async_logger import AsyncLogger
|
||||
|
||||
# Initialize colorama for cross-platform colored terminal output
|
||||
init()
|
||||
|
||||
# Define colors for pretty output
|
||||
SUCCESS = Fore.GREEN
|
||||
WARNING = Fore.YELLOW
|
||||
ERROR = Fore.RED
|
||||
INFO = Fore.CYAN
|
||||
RESET = Fore.RESET
|
||||
|
||||
# Create logger
|
||||
logger = AsyncLogger(verbose=True)
|
||||
|
||||
async def test_browser_profiler():
|
||||
"""Test the BrowserProfiler class functionality"""
|
||||
print(f"\n{INFO}========== Testing BrowserProfiler =========={RESET}")
|
||||
|
||||
# Initialize browser profiler
|
||||
profiler = BrowserProfiler(logger=logger)
|
||||
|
||||
# Step 1: Check if builtin browser exists and kill it if it does
|
||||
print(f"\n{INFO}1. Checking if builtin browser exists{RESET}")
|
||||
browser_info = profiler.get_builtin_browser_info()
|
||||
if browser_info:
|
||||
print(f"{SUCCESS}Builtin browser found: {browser_info['cdp_url']}{RESET}")
|
||||
# Kill it to start with a clean state
|
||||
print(f"{INFO}Killing existing browser...{RESET}")
|
||||
await profiler.kill_builtin_browser()
|
||||
browser_info = profiler.get_builtin_browser_info()
|
||||
if not browser_info:
|
||||
print(f"{SUCCESS}Browser successfully killed{RESET}")
|
||||
else:
|
||||
print(f"{ERROR}Failed to kill browser{RESET}")
|
||||
else:
|
||||
print(f"{WARNING}No builtin browser found{RESET}")
|
||||
|
||||
# Step 2: Launch a new builtin browser
|
||||
print(f"\n{INFO}2. Launching new builtin browser{RESET}")
|
||||
cdp_url = await profiler.launch_builtin_browser(headless=True)
|
||||
if cdp_url:
|
||||
print(f"{SUCCESS}Builtin browser launched at: {cdp_url}{RESET}")
|
||||
else:
|
||||
print(f"{ERROR}Failed to launch builtin browser{RESET}")
|
||||
return
|
||||
|
||||
# Step 3: Get and display browser information
|
||||
print(f"\n{INFO}3. Getting browser information{RESET}")
|
||||
browser_info = profiler.get_builtin_browser_info()
|
||||
if browser_info:
|
||||
print(f"{SUCCESS}Browser info retrieved:{RESET}")
|
||||
for key, value in browser_info.items():
|
||||
if key != 'config': # Skip the verbose config section
|
||||
print(f" {key}: {value}")
|
||||
else:
|
||||
print(f"{ERROR}Failed to get browser information{RESET}")
|
||||
|
||||
# Step 4: Get browser status
|
||||
print(f"\n{INFO}4. Getting browser status{RESET}")
|
||||
status = await profiler.get_builtin_browser_status()
|
||||
print(f"Running: {status['running']}")
|
||||
print(f"CDP URL: {status['cdp_url']}")
|
||||
|
||||
# Pause to let the browser run for a moment
|
||||
print(f"\n{INFO}Waiting for 2 seconds...{RESET}")
|
||||
await asyncio.sleep(2)
|
||||
|
||||
return cdp_url # Return the CDP URL for the crawling tests
|
||||
|
||||
async def test_crawling_with_builtin_browser(cdp_url):
|
||||
"""Test crawling with the builtin browser"""
|
||||
print(f"\n{INFO}========== Testing Crawling with Builtin Browser =========={RESET}")
|
||||
|
||||
# Step 1: Create a crawler with 'builtin' browser mode
|
||||
print(f"\n{INFO}1. Creating crawler with 'builtin' browser mode{RESET}")
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="builtin",
|
||||
headless=True
|
||||
)
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
|
||||
# Step 2: Test crawling without explicitly starting (should auto-start)
|
||||
print(f"\n{INFO}2. Testing auto-start with arun{RESET}")
|
||||
try:
|
||||
result = await crawler.arun("https://crawl4ai.com")
|
||||
print(f"{SUCCESS}Auto-start crawling successful!{RESET}")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Auto-start crawling failed: {str(e)}{RESET}")
|
||||
|
||||
# Close the crawler
|
||||
await crawler.close()
|
||||
|
||||
# Step 3: Test with explicit start
|
||||
print(f"\n{INFO}3. Testing with explicit start{RESET}")
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
try:
|
||||
await crawler.start()
|
||||
print(f"{SUCCESS}Explicit start successful!{RESET}")
|
||||
result = await crawler.arun("https://example.com")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
# Try second time, no start needed
|
||||
print(f"{INFO}Testing second arun call without start{RESET}")
|
||||
result = await crawler.arun("https://example.com")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Explicit start crawling failed: {str(e)}{RESET}")
|
||||
|
||||
# Close the crawler
|
||||
await crawler.close()
|
||||
|
||||
# Step 4: Test with context manager
|
||||
print(f"\n{INFO}4. Testing with context manager{RESET}")
|
||||
try:
|
||||
async with AsyncWebCrawler(config=browser_config) as crawler:
|
||||
result = await crawler.arun("https://httpbin.org/html")
|
||||
print(f"{SUCCESS}Context manager crawling successful!{RESET}")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Context manager crawling failed: {str(e)}{RESET}")
|
||||
|
||||
return True
|
||||
|
||||
async def test_crawling_without_builtin_browser():
|
||||
"""Test crawling after killing the builtin browser"""
|
||||
print(f"\n{INFO}========== Testing Crawling Without Builtin Browser =========={RESET}")
|
||||
|
||||
# Step 1: Kill the builtin browser
|
||||
print(f"\n{INFO}1. Killing the builtin browser{RESET}")
|
||||
profiler = BrowserProfiler(logger=logger)
|
||||
await profiler.kill_builtin_browser()
|
||||
|
||||
# Step 2: Create a crawler with 'builtin' mode (should fall back to dedicated)
|
||||
print(f"\n{INFO}2. Creating crawler with 'builtin' mode (should fall back){RESET}")
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="builtin",
|
||||
headless=True
|
||||
)
|
||||
|
||||
try:
|
||||
async with AsyncWebCrawler(config=browser_config) as crawler:
|
||||
result = await crawler.arun("https://httpbin.org/get")
|
||||
print(f"{SUCCESS}Fallback to dedicated browser successful!{RESET}")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Fallback crawler failed: {str(e)}{RESET}")
|
||||
|
||||
# Step 3: Test with direct CDP URL
|
||||
print(f"\n{INFO}3. Testing with direct CDP URL connection{RESET}")
|
||||
|
||||
# Launch a standalone browser to get a CDP URL
|
||||
print(f"{INFO}Launching standalone browser...{RESET}")
|
||||
cdp_url = await profiler.launch_standalone_browser(headless=True)
|
||||
if not cdp_url:
|
||||
print(f"{ERROR}Failed to launch standalone browser{RESET}")
|
||||
return
|
||||
|
||||
print(f"{SUCCESS}Got CDP URL: {cdp_url}{RESET}")
|
||||
|
||||
# Create a crawler with the CDP URL
|
||||
browser_config = BrowserConfig(
|
||||
browser_mode="dedicated",
|
||||
cdp_url=cdp_url,
|
||||
use_managed_browser=True,
|
||||
headless=True
|
||||
)
|
||||
|
||||
try:
|
||||
async with AsyncWebCrawler(config=browser_config) as crawler:
|
||||
result = await crawler.arun("https://httpbin.org/ip")
|
||||
print(f"{SUCCESS}Direct CDP URL crawling successful!{RESET}")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Direct CDP URL crawling failed: {str(e)}{RESET}")
|
||||
|
||||
return True
|
||||
|
||||
async def test_edge_cases():
|
||||
"""Test edge cases like multiple starts, killing browser during crawl, etc."""
|
||||
print(f"\n{INFO}========== Testing Edge Cases =========={RESET}")
|
||||
|
||||
# Step 1: Launch the builtin browser if it doesn't exist
|
||||
print(f"\n{INFO}1. Ensuring builtin browser exists{RESET}")
|
||||
profiler = BrowserProfiler(logger=logger)
|
||||
browser_info = profiler.get_builtin_browser_info()
|
||||
if not browser_info:
|
||||
cdp_url = await profiler.launch_builtin_browser(headless=True)
|
||||
if cdp_url:
|
||||
print(f"{SUCCESS}Builtin browser launched at: {cdp_url}{RESET}")
|
||||
else:
|
||||
print(f"{ERROR}Failed to launch builtin browser{RESET}")
|
||||
return
|
||||
else:
|
||||
print(f"{SUCCESS}Using existing builtin browser: {browser_info['cdp_url']}{RESET}")
|
||||
|
||||
# Step 2: Test multiple starts with the same crawler
|
||||
print(f"\n{INFO}2. Testing multiple starts with the same crawler{RESET}")
|
||||
browser_config = BrowserConfig(browser_mode="builtin", headless=True)
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
|
||||
await crawler.start()
|
||||
print(f"{SUCCESS}First start successful!{RESET}")
|
||||
|
||||
try:
|
||||
await crawler.start()
|
||||
print(f"{SUCCESS}Second start didn't cause errors!{RESET}")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Second start failed: {str(e)}{RESET}")
|
||||
|
||||
# Run a crawl to verify functionality
|
||||
try:
|
||||
result = await crawler.arun("https://httpbin.org/user-agent")
|
||||
print(f"{SUCCESS}Crawling after multiple starts successful!{RESET}")
|
||||
print(f" Got {len(result.markdown.raw_markdown)} chars of markdown content")
|
||||
except Exception as e:
|
||||
print(f"{ERROR}Crawling after multiple starts failed: {str(e)}{RESET}")
|
||||
|
||||
await crawler.close()
|
||||
|
||||
# Step 3: Test killing browser while crawler is active
|
||||
print(f"\n{INFO}3. Testing killing browser while crawler is active{RESET}")
|
||||
|
||||
# Create and start a crawler
|
||||
browser_config = BrowserConfig(browser_mode="builtin", headless=True)
|
||||
crawler = AsyncWebCrawler(config=browser_config)
|
||||
await crawler.start()
|
||||
|
||||
# Kill the browser
|
||||
print(f"{INFO}Killing the browser...{RESET}")
|
||||
await profiler.kill_builtin_browser()
|
||||
|
||||
# Try to crawl (should fail)
|
||||
try:
|
||||
result = await crawler.arun("https://httpbin.org/get")
|
||||
print(f"{WARNING}Crawling succeeded despite killed browser!{RESET}")
|
||||
except Exception as e:
|
||||
print(f"{SUCCESS}Crawling failed as expected: {str(e)}{RESET}")
|
||||
|
||||
await crawler.close()
|
||||
|
||||
return True
|
||||
|
||||
async def main():
|
||||
"""Run all tests"""
|
||||
try:
|
||||
print(f"{INFO}Starting browser_profiler and builtin browser tests{RESET}")
|
||||
|
||||
# Run browser profiler tests
|
||||
cdp_url = await test_browser_profiler()
|
||||
|
||||
# Run crawling tests with builtin browser
|
||||
if cdp_url:
|
||||
await test_crawling_with_builtin_browser(cdp_url)
|
||||
|
||||
# Run tests without builtin browser
|
||||
# await test_crawling_without_builtin_browser()
|
||||
|
||||
# Run edge case tests
|
||||
# await test_edge_cases()
|
||||
|
||||
print(f"\n{SUCCESS}All tests completed!{RESET}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n{ERROR}Test failed with error: {str(e)}{RESET}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
# Clean up: kill any remaining builtin browser
|
||||
print(f"\n{INFO}Cleaning up: killing any remaining builtin browser{RESET}")
|
||||
profiler = BrowserProfiler(logger=logger)
|
||||
await profiler.kill_builtin_browser()
|
||||
print(f"{SUCCESS}Test cleanup complete{RESET}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
Loading…
x
Reference in New Issue
Block a user