Files
crawle-snapp/crawler/driver.py
T
2026-06-15 19:42:03 +03:30

84 lines
2.8 KiB
Python

"""Stealth browser factory — bypasses Cloudflare/ArvanCloud bot detection."""
from __future__ import annotations
import random
import time
from contextlib import contextmanager
from typing import Generator
import undetected_chromedriver as uc
from selenium.webdriver.chrome.options import Options
from selenium_stealth import stealth
from config import config
_USER_AGENTS = [
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
]
def _build_options(user_agent: str, headless: bool) -> Options:
opts = Options()
if headless:
opts.add_argument("--headless=new")
opts.add_argument(f"--user-agent={user_agent}")
opts.add_argument("--no-sandbox")
opts.add_argument("--disable-dev-shm-usage")
opts.add_argument("--disable-blink-features=AutomationControlled")
opts.add_argument("--disable-infobars")
opts.add_argument("--window-size=1920,1080")
opts.add_experimental_option("excludeSwitches", ["enable-automation"])
opts.add_experimental_option("useAutomationExtension", False)
if config.chrome_binary:
opts.binary_location = config.chrome_binary
return opts
def make_driver(headless: bool | None = None) -> uc.Chrome:
"""Return a stealthed undetected Chrome instance."""
use_headless = config.headless if headless is None else headless
ua = random.choice(_USER_AGENTS)
opts = _build_options(ua, use_headless)
driver = uc.Chrome(options=opts, use_subprocess=True)
stealth(
driver,
languages=["en-US", "en"],
vendor="Google Inc.",
platform="Win32",
webgl_vendor="Intel Inc.",
renderer="Intel Iris OpenGL Engine",
fix_hairline=True,
)
# Mask navigator.webdriver via CDP
driver.execute_cdp_cmd(
"Page.addScriptToEvaluateOnNewDocument",
{
"source": """
Object.defineProperty(navigator, 'webdriver', {get: () => undefined});
Object.defineProperty(navigator, 'plugins', {get: () => [1, 2, 3, 4, 5]});
Object.defineProperty(navigator, 'languages', {get: () => ['en-US', 'en']});
"""
},
)
return driver
@contextmanager
def driver_session(headless: bool | None = None) -> Generator[uc.Chrome, None, None]:
"""Context manager that guarantees driver.quit() on exit."""
driver = make_driver(headless)
try:
yield driver
finally:
driver.quit()
def human_delay(lo: float = 0.8, hi: float = 2.5) -> None:
"""Sleep for a random human-like interval."""
time.sleep(random.uniform(lo, hi))