豆瓣电影影评爬虫代码优化：使用Selenium和BeautifulSoup抓取数据

# 导入所需的模块
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

# 创建浏览器对象
browser = webdriver.Chrome()

# 访问url地址
url = 'https://movie.douban.com/subject/25868125/'
browser.get(url)

# 设置浏览器窗口最大化
browser.maximize_window()

# 设置请求头部信息
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
    'Cookie': '你的Cookie',
    'Referer': 'https://movie.douban.com/subject/25868125/'
}

# 发送请求获取页面内容
res = requests.get(url, headers=headers)
soup = BeautifulSoup(res.text, 'html.parser')

# 解析页面内容获取影评数据
comments = soup.select('.comment-item')
for comment in comments:
    name = comment.select('.comment-info > a')[0].text.strip()
    time = comment.select('.comment-info > span')[0].text.strip()
    content = comment.select('.short')[0].text.strip()
    print(name, time, content)

# 循环爬取所有页的影评数据
while True:
    try:
        # 查找'下一页'按钮元素，若找到则点击，否则退出循环
        next_button = WebDriverWait(browser, 10).until(
            EC.presence_of_element_located((By.CSS_SELECTOR, '.comment .next a'))
        )
        next_button.click()
    except:
        break

# 关闭浏览器
browser.close()