动态内容加载的解决方案：Selenium与Playwright对比故障排查实录

2024-09-01 09:00 | 接到亚航航班数据采集需求
2024-09-01 11:30 | 首次尝试使用Selenium遭遇Cloudflare验证
2024-09-01 14:00 | 切换Playwright方案仍触发反爬机制
2024-09-01 16:30 | 引入爬虫代理IP+UA轮换策略
2024-09-02 10:00 | 双方案完整实现并通过压力测试

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.common.exceptions import TimeoutException

# 亿牛云代理配置（实际使用需替换为有效凭证）www.16yun.com
PROXY_HOST = "PROXY.16yun.com"
PROXY_PORT = "31000"
PROXY_USER = "16YUN"
PROXY_PASS = "16IP"

def failed_selenium_case():
    chrome_options = Options()
    chrome_options.add_argument(f"--proxy-server=http://{PROXY_USER}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}")
    chrome_options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36...")
    
    driver = webdriver.Chrome(options=chrome_options)
    try:
        driver.get("https://www.airasia.cn/zh/cn")
        # 尝试获取动态加载的航班信息
        WebDriverWait(driver, 10).until(
            lambda d: d.find_element("css selector", ".flight-list")
        )
        print(driver.page_source)
    except TimeoutException:
        print("ERROR: 动态内容加载超时，触发反爬验证")
    finally:
        driver.quit()

# 公共配置参数
COMMON_CONFIG = {
    # 亿牛云爬虫代理配置（实际使用需替换为有效凭证）
    "proxy": f"http://{16YUN}:{16IP}@{PROXY.16yun.com}:{31000}",
    "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36...",
    "cookies": [
        {'name': 'session_id', 'value': 'xxxxxx'},
        {'name': 'preferred_currency', 'value': 'CNY'}
    ]
}

# ----------------- Selenium 方案 -----------------
def improved_selenium():
    from selenium.webdriver import Chrome
    from selenium.webdriver import ChromeOptions
    
    options = ChromeOptions()
    options.add_argument(f"--proxy-server={COMMON_CONFIG['proxy']}")
    options.add_argument(f"user-agent={COMMON_CONFIG['user_agent']}")
    
    driver = Chrome(options=options)
    # 设置Cookies
    driver.get("https://www.airasia.cn/zh/cn")
    for cookie in COMMON_CONFIG['cookies']:
        driver.add_cookie(cookie)
    
    # 执行动态内容获取
    driver.refresh()
    # ...（数据采集逻辑）

# ----------------- Playwright 方案 -----------------
async def improved_playwright():
    from playwright.async_api import async_playwright
    
    async with async_playwright() as p:
        browser = await p.chromium.launch(
            proxy={"server": COMMON_CONFIG['proxy']},
            headless=False
        )
        context = await browser.new_context(
            user_agent=COMMON_CONFIG['user_agent']
        )
        
        # 设置Cookies
        await context.add_cookies(COMMON_CONFIG['cookies'])
        
        page = await context.new_page()
        await page.goto("https://www.airasia.cn/zh/cn")
        
        # Playwright的自动等待机制
        await page.wait_for_selector(".flight-list", timeout=15000)
        content = await page.content()
        print(content)
        
        await browser.close()

def update_cookies_dynamically(driver):
    new_cookies = get_cookies_from_api()  # 从认证接口获取新Cookies
    driver.delete_all_cookies()
    for cookie in new_cookies:
        driver.add_cookie({
            'name': cookie['name'],
            'value': cookie['value'],
            'domain': '.airasia.cn'
        })