Python Selenium防检测策略汇总

from selenium import webdriver
from selenium.webdriver.chrome.options import Options

def get_stealth_driver():
    options = Options()
    
    # 基本防检测设置
    options.add_argument("--disable-blink-features=AutomationControlled")
    options.add_experimental_option("excludeSwitches", ["enable-automation"])
    options.add_experimental_option("useAutomationExtension", False)
    
    # 禁用自动化控制标志
    options.add_argument("--disable-infobars")
    options.add_argument("--disable-dev-shm-usage")
    options.add_argument("--no-sandbox")
    
    # 随机用户代理
    user_agents = [
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64)...",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)..."
    ]
    import random
    options.add_argument(f"user-agent={random.choice(user_agents)}")
    
    driver = webdriver.Chrome(options=options)
    
    # 修改navigator.webdriver属性
    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
        Object.defineProperty(navigator, 'webdriver', {
            get: () => undefined
        })
        """
    })
    
    return driver

import undetected_chromedriver as uc

​​​​​​​def get_undetected_driver():
    options = uc.ChromeOptions()
    
    # 配置选项
    options.add_argument("--disable-popup-blocking")
    options.add_argument("--disable-notifications")
    
    # 随机窗口大小
    import random
    width = random.randint(1000, 1400)
    height = random.randint(700, 900)
    options.add_argument(f"--window-size={width},{height}")
    
    driver = uc.Chrome(
        options=options,
        version_main=114,  # 匹配你的Chrome版本
        headless=False,
        use_subprocess=True
    )
    
    return driver

from selenium.webdriver.common.action_chains import ActionChains
import time
import random

​​​​​​​def human_like_behavior(driver, element=None):
    """模拟人类操作行为"""
    actions = ActionChains(driver)
    
    # 随机鼠标移动
    if element:
        actions.move_to_element(element)
    else:
        x = random.randint(0, 500)
        y = random.randint(0, 500)
        actions.move_by_offset(x, y)
    
    # 随机延迟
    time.sleep(random.uniform(0.5, 2.5))
    
    # 随机滚动
    scroll_amount = random.randint(200, 800)
    driver.execute_script(f"window.scrollBy(0, {scroll_amount})")
    time.sleep(random.uniform(0.3, 1.8))
    
    actions.perform()

def stealth_scrape(url):
    try:
        # 使用undetected-chromedriver
        driver = get_undetected_driver()
        
        # 访问目标URL
        driver.get(url)
        
        # 随机等待
        time.sleep(random.uniform(2, 5))
        
        # 模拟人类浏览行为
        human_like_behavior(driver)
        
        # 执行实际爬取操作
        # 示例：获取页面标题
        title = driver.title
        print(f"成功获取页面标题: {title}")
        
        # 更多爬取逻辑...
        
    except Exception as e:
        print(f"爬取过程中发生错误: {str(e)}")
    finally:
        driver.quit()
# 使用示例
stealth_scrape("https://example.com")

proxies = [
    "123.45.67.89:8080",
    "98.76.54.32:3128"
] #换成自己的

def get_proxy_driver():
    options = uc.ChromeOptions()
    proxy = random.choice(proxies)
    options.add_argument(f"--proxy-server=http://{proxy}")
    return uc.Chrome(options=options)

def modify_fingerprint(driver):
    # 修改屏幕分辨率
    driver.execute_script(
        "Object.defineProperty(screen, 'width', {get: () => 1920});"
        "Object.defineProperty(screen, 'height', {get: () => 1080});"
    )
    
    # 修改时区
    driver.execute_cdp_cmd(
        "Emulation.setTimezoneOverride",
        {"timezoneId": "America/New_York"}
    )
    
    # 修改WebGL指纹
    driver.execute_script(
        "const getParameter = WebGLRenderingContext.prototype.getParameter;"
        "WebGLRenderingContext.prototype.getParameter = function(parameter) {"
        "  if (parameter === 37445) { return 'NVIDIA Corporation'; }"
        "  return getParameter.call(this, parameter);"
        "};"
    )

def test_stealth(driver):
    test_urls = [
        "https://bot.sannysoft.com",
        "https://arh.antoinevastel.com/bots/areyouheadless"
    ]
    
    for url in test_urls:
        driver.get(url)
        time.sleep(3)
        driver.save_screenshot(f"stealth_test_{url.split('/')[-1]}.png")
        print(f"测试结果已保存: stealth_test_{url.split('/')[-1]}.png")