vodorod/Dorod-Sky
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix chrome user data dir problem (#2503)

Browse Source
This commit is contained in:
Shuchang Zheng
2025-05-28 22:41:06 -07:00
committed by GitHub
parent 869757398a
commit cf08ca951e
11 changed files with 283 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
skyvern/cli/llm_setup.py
View File

@@ -40,6 +40,7 @@ def update_or_add_env_var(key: str, value: str) -> None:
"BROWSER_ACTION_TIMEOUT_MS": "5000",
"MAX_STEPS_PER_RUN": "50",
"LOG_LEVEL": "INFO",
"LITELLM_LOG": "CRITICAL",
"DATABASE_STRING": "postgresql+psycopg://skyvern@localhost/skyvern",
"PORT": "8000",
"ANALYTICS_ID": "anonymous",

36
skyvern/cli/quickstart.py
View File

@@ -2,7 +2,6 @@
import asyncio
import subprocess
import sys
import typer
from rich.panel import Panel
@@ -11,6 +10,7 @@ from rich.progress import Progress, SpinnerColumn, TextColumn
# Import console after skyvern.cli to ensure proper initialization
from skyvern.cli.console import console
from skyvern.cli.init_command import init # init is used directly
from skyvern.cli.utils import start_services
quickstart_app = typer.Typer(help="Quickstart command to set up and run Skyvern with one command.")
@@ -29,40 +29,6 @@ def check_docker() -> bool:
return False
async def start_services(server_only: bool = False) -> None:
"""Start Skyvern services in the background.
Args:
server_only: If True, only start the server, not the UI.
"""
try:
# Start server in the background
server_process = await asyncio.create_subprocess_exec(
sys.executable, "-m", "skyvern.cli.commands", "run", "server"
)
# Give server a moment to start
await asyncio.sleep(2)
if not server_only:
# Start UI in the background
ui_process = await asyncio.create_subprocess_exec(sys.executable, "-m", "skyvern.cli.commands", "run", "ui")
console.print("\n🎉 [bold green]Skyvern is now running![/bold green]")
console.print("🌐 [bold]Access the UI at:[/bold] [cyan]http://localhost:8080[/cyan]")
console.print("🔑 [bold]Your API key is in your .env file as SKYVERN_API_KEY[/bold]")
# Wait for processes to complete (they won't unless killed)
if not server_only:
await asyncio.gather(server_process.wait(), ui_process.wait())
else:
await server_process.wait()
except Exception as e:
console.print(f"[bold red]Error starting services: {str(e)}[/bold red]")
raise typer.Exit(1)
@quickstart_app.callback(invoke_without_command=True)
def quickstart(
ctx: typer.Context,

8
skyvern/cli/run_commands.py
View File

@@ -1,3 +1,4 @@
import asyncio
import os
import shutil
import subprocess
@@ -12,6 +13,7 @@ from mcp.server.fastmcp import FastMCP
from rich.panel import Panel
from rich.prompt import Confirm
from skyvern.cli.utils import start_services
from skyvern.config import settings
from skyvern.library.skyvern import Skyvern
from skyvern.utils import detect_os
@@ -153,6 +155,12 @@ def run_ui() -> None:
return
@run_app.command(name="all")
def run_all() -> None:
"""Run the Skyvern API server and UI server in parallel."""
asyncio.run(start_services())
@run_app.command(name="mcp")
def run_mcp() -> None:
"""Run the MCP server."""

40
skyvern/cli/utils.py Normal file
View File

@@ -0,0 +1,40 @@
import asyncio
import sys
import typer
from skyvern.cli.console import console
async def start_services(server_only: bool = False) -> None:
"""Start Skyvern services in the background.
Args:
server_only: If True, only start the server, not the UI.
"""
try:
# Start server in the background
server_process = await asyncio.create_subprocess_exec(
sys.executable, "-m", "skyvern.cli.commands", "run", "server"
)
# Give server a moment to start
await asyncio.sleep(2)
if not server_only:
# Start UI in the background
ui_process = await asyncio.create_subprocess_exec(sys.executable, "-m", "skyvern.cli.commands", "run", "ui")
console.print("\n🎉 [bold green]Skyvern is now running![/bold green]")
console.print("🌐 [bold]Access the UI at:[/bold] [cyan]http://localhost:8080[/cyan]")
console.print("🔑 [bold]Your API key is in your .env file as SKYVERN_API_KEY[/bold]")
# Wait for processes to complete (they won't unless killed)
if not server_only:
await asyncio.gather(server_process.wait(), ui_process.wait())
else:
await server_process.wait()
except Exception as e:
console.print(f"[bold red]Error starting services: {str(e)}[/bold red]")
raise typer.Exit(1)

12
skyvern/library/skyvern.py
View File

@@ -1,6 +1,5 @@
import asyncio
import os
import subprocess
import typing
from typing import Any
@@ -66,20 +65,19 @@ class Skyvern(AsyncSkyvern):
# TODO validate browser_path
# Supported Browsers: Google Chrome, Brave Browser, Microsoft Edge, Firefox
if "Chrome" in browser_path or "Brave" in browser_path or "Edge" in browser_path:
browser_process = subprocess.Popen(
[browser_path, "--remote-debugging-port=9222"], stdout=subprocess.PIPE, stderr=subprocess.PIPE
)
if browser_process.poll() is not None:
raise Exception(f"Failed to open browser. browser_path: {browser_path}")
self._cdp_url = "http://127.0.0.1:9222"
settings.BROWSER_TYPE = "cdp-connect"
settings.BROWSER_REMOTE_DEBUGGING_URL = self._cdp_url
settings.CHROME_EXECUTABLE_PATH = browser_path
else:
raise ValueError(
f"Unsupported browser or invalid path: {browser_path}. "
"Here's a list of supported browsers Skyvern can connect to: Google Chrome, Brave Browser, Microsoft Edge, Firefox."
)
elif cdp_url:
self._cdp_url = cdp_url
settings.BROWSER_TYPE = "cdp-connect"
settings.BROWSER_REMOTE_DEBUGGING_URL = self._cdp_url
elif base_url is None and api_key is None:
if not browser_type:
# if "BROWSER_TYPE" not in os.environ:

96
skyvern/webeye/browser_factory.py
View File

@@ -2,8 +2,11 @@ from __future__ import annotations
import asyncio
import os
import pathlib
import platform
import random
import re
import shutil
import socket
import subprocess
import time
@@ -447,6 +450,34 @@ async def _create_headful_chromium(
return browser_context, browser_artifacts, None
def default_user_data_dir() -> pathlib.Path:
p = platform.system()
if p == "Darwin":
return pathlib.Path("~/Library/Application Support/Google/Chrome").expanduser()
if p == "Windows":
return pathlib.Path(os.environ["LOCALAPPDATA"]) / "Google" / "Chrome" / "User Data"
# Assume Linux/Unix
return pathlib.Path("~/.config/google-chrome").expanduser()
def is_valid_chromium_user_data_dir(directory: str) -> bool:
"""Check if a directory is a valid Chromium user data directory.
A valid Chromium user data directory should:
1. Exist
2. Not be empty
3. Contain a 'Default' directory
4. Have a 'Preferences' file in the 'Default' directory
"""
if not os.path.exists(directory):
return False
default_dir = os.path.join(directory, "Default")
preferences_file = os.path.join(default_dir, "Preferences")
return os.path.isdir(directory) and os.path.isdir(default_dir) and os.path.isfile(preferences_file)
async def _create_cdp_connection_browser(
playwright: Playwright, proxy_location: ProxyLocation | None = None, **kwargs: dict
) -> tuple[BrowserContext, BrowserArtifacts, BrowserCleanupFunc]:
@@ -454,31 +485,48 @@ async def _create_cdp_connection_browser(
browser_path = settings.CHROME_EXECUTABLE_PATH
if browser_type == "cdp-connect" and browser_path:
# First check if Chrome is already running
if _is_chrome_running():
raise Exception(
"Chrome is already running. Please close all Chrome instances before starting with remote debugging."
LOG.info("Local browser path is given. Connecting to local browser with CDP", browser_path=browser_path)
# First check if the debugging port is running and can be used
if not _is_port_in_use(9222):
LOG.info("Port 9222 is not in use, starting Chrome", browser_path=browser_path)
# Check if Chrome is already running
if _is_chrome_running():
raise Exception(
"Chrome is already running. Please close all Chrome instances before starting with remote debugging."
)
# check if ./tmp/user_data_dir exists and if it's a valid Chromium user data directory
try:
if os.path.exists("./tmp/user_data_dir") and not is_valid_chromium_user_data_dir("./tmp/user_data_dir"):
LOG.info("Removing invalid user data directory")
shutil.rmtree("./tmp/user_data_dir")
shutil.copytree(default_user_data_dir(), "./tmp/user_data_dir")
elif not os.path.exists("./tmp/user_data_dir"):
LOG.info("Copying default user data directory")
shutil.copytree(default_user_data_dir(), "./tmp/user_data_dir")
else:
LOG.info("User data directory is valid")
except FileExistsError:
# If directory exists, remove it first then copy
shutil.rmtree("./tmp/user_data_dir")
shutil.copytree(default_user_data_dir(), "./tmp/user_data_dir")
browser_process = subprocess.Popen(
[
browser_path,
"--remote-debugging-port=9222",
"--no-first-run",
"--no-default-browser-check",
"--remote-debugging-address=0.0.0.0",
"--user-data-dir=./tmp/user_data_dir",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
# Then check if the debugging port is already in use
if _is_port_in_use(9222):
raise Exception("Port 9222 is already in use. Another process may be using this port.")
browser_process = subprocess.Popen(
[
browser_path,
"--remote-debugging-port=9222",
"--no-first-run",
"--no-default-browser-check",
"--remote-debugging-address=0.0.0.0",
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
# Add small delay to allow browser to start
time.sleep(2)
if browser_process.poll() is not None:
raise Exception(f"Failed to open browser. browser_path: {browser_path}")
# Add small delay to allow browser to start
time.sleep(1)
if browser_process.poll() is not None:
raise Exception(f"Failed to open browser. browser_path: {browser_path}")
else:
LOG.info("Port 9222 is in use, using existing browser")
browser_args = BrowserContextFactory.build_browser_args()

3
skyvern/webeye/scraper/scraper.py
View File

@@ -545,7 +545,8 @@ async def scrape_web_unsafe(
try:
skyvern_frame = await SkyvernFrame.create_instance(frame=page)
html = await skyvern_frame.get_content()
window_dimension = Resolution(width=page.viewport_size["width"], height=page.viewport_size["height"])
if page.viewport_size:
window_dimension = Resolution(width=page.viewport_size["width"], height=page.viewport_size["height"])
except Exception:
LOG.error(
"Failed out to get HTML content",