对比分析：Python爬虫模拟登录的3种主流实现方式

import requests

# 目标网站登录接口（需通过F12开发者工具抓包获取）
LOGIN_URL = "https://xxx.com/login"
# 登录后需要爬取的目标页面
TARGET_URL = "https://xxx.com/user/data"

# 构造登录参数（抓包获取表单字段，如username、password、remember等）
login_data = {
    "username": "你的账号",
    "password": "你的密码",
    # 部分网站需携带隐藏参数，如csrf_token、timestamp等
    "csrf_token": "抓包获取的token",
    "remember": "1"
}

# 1. 创建Session对象，自动持久化Cookie
session = requests.Session()
# 模拟请求头，伪装浏览器
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
    "Referer": LOGIN_URL
}

try:
    # 2. 发送登录POST请求
    login_response = session.post(url=LOGIN_URL, data=login_data, headers=headers, timeout=10)
    login_response.raise_for_status()  # 抛出请求异常

    # 3. 校验登录状态（判断响应内容或Cookie）
    if "登录成功" in login_response.text or session.cookies.get_dict():
        print("Session模拟登录成功！")
        # 4. 携带登录Cookie请求目标页面
        target_response = session.get(url=TARGET_URL, headers=headers, timeout=10)
        target_response.encoding = "utf-8"
        print("目标页面内容预览：", target_response.text[:500])
    else:
        print("登录失败，请检查账号密码或参数")

except Exception as e:
    print(f"登录异常：{e}")

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time

# 配置Chrome选项（无头模式可选，后台运行）
options = webdriver.ChromeOptions()
# 关闭自动化提示，降低被检测概率
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_argument("--disable-blink-features=AutomationControlled")
# 无头模式（无界面运行，节省资源）
# options.add_argument("--headless=new")

# 初始化浏览器驱动
driver = webdriver.Chrome(options=options)
# 设置窗口大小
driver.maximize_window()

try:
    # 1. 打开登录页面
    driver.get("https://xxx.com/login")
    # 等待页面加载完成
    WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.NAME, "username"))
    )

    # 2. 定位账号密码输入框并输入
    driver.find_element(By.NAME, "username").send_keys("你的账号")
    driver.find_element(By.NAME, "password").send_keys("你的密码")
    # 等待1秒，模拟人工输入延迟
    time.sleep(1)

    # 3. 点击登录按钮（定位方式：ID/NAME/XPATH均可）
    driver.find_element(By.XPATH, '//button[@type="submit"]').click()

    # 4. 校验登录状态（等待登录成功后的元素加载）
    WebDriverWait(driver, 15).until(
        EC.presence_of_element_located((By.CLASS_NAME, "user-avatar"))
    )
    print("Selenium模拟登录成功！")

    # 5. 跳转到目标页面爬取数据
    driver.get("https://xxx.com/user/data")
    time.sleep(2)
    # 获取页面内容
    page_content = driver.page_source
    print("目标页面内容预览：", page_content[:500])

except Exception as e:
    print(f"Selenium登录异常：{e}")
finally:
    # 关闭浏览器
    driver.quit()

from playwright.sync_api import sync_playwright
# 代理配置信息
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"
# 同步模式实现（异步模式用async_playwright）
with sync_playwright() as p:
 # 构建代理配置字典
 proxy_config = {
 "server": f"http://{proxyHost}:{proxyPort}",
 "username": proxyUser,
 "password": proxyPass
 }
 # 启动Chrome浏览器，配置代理
 browser = p.chromium.launch(
 headless=False, # True为无界面模式
 slow_mo=500, # 操作延迟，模拟人工，避免被检测
 proxy=proxy_config # 添加代理配置
 )
 # 创建新页面
 page = browser.new_page(
 user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
 )
 try:
 # 1. 打开登录页面，自动等待加载完成
 page.goto("https://xxx.com/login", timeout=10000)
 # 2. 输入账号密码（Playwright自动等待元素可见）
 page.fill('input[name="username"]', "你的账号")
 page.fill('input[name="password"]', "你的密码")
 # 3. 点击登录按钮
 page.click('button[type="submit"]')
 # 4. 等待登录成功跳转，校验状态
 page.wait_for_url("https://xxx.com/user/data", timeout=15000)
 print("Playwright模拟登录成功！")
 # 5. 获取目标页面内容
 page_content = page.content()
 print("目标页面内容预览：", page_content[:500])
 except Exception as e:
 print(f"Playwright登录异常：{e}")
 finally:
 # 关闭浏览器
 browser.close()