python数据采集 使用xpath解析豆瓣top250

import requests, csv
import time
from lxml import etree


# 创建获取页面数据方法
def get_html(url):
    # 伪装浏览器
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/109.0.0.0 Safari/537.36'
    }
    r = requests.get(url, headers=headers).text
    e = etree.HTML(r)
    li = e.xpath('/html/body/div[3]/div[1]/div/div[1]/ol/li')
    lst = []
    for info in li:
        filename = info.xpath('./div/div[2]/div[1]/a/span[1]/text()')[0]
        year_r = info.xpath('./div/div[2]/div[2]/p[1]/text()[2]')[0]
        year = year_r.split("/")[-3].split()[0]
        actor_r = info.xpath('./div/div[2]/div[2]/p[1]/text()[1]')[0]
        try:
            if "主演:" in actor_r:
                actor = actor_r.split("主演:")[1].split()[0]
            else:
                actor = 'none'
        except IndexError:
            actor = 'none'
        film_lst = [filename, actor, year]
        lst.append(film_lst)
        print('{}----{}----{}'.format(filename, actor, year))
        time.sleep(1)


# 调用函数
for i in range(0, 265, 25):
    get_html(f'https://movie.douban.com/top250?start={i}&filter=')
    # print(url)