requests爬取豆瓣电影top250

代码

import requests
from lxml import etree
from concurrent.futures import ThreadPoolExecutor


class Crawl_douban(object):
    # 设定初始化方法，并设置实例变量header、page_url（list类型）分别记录爬虫的请求头和目标抓取页的url
    def __init__(self):
        self.url = []
        self.header = {
   
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3902.4 Safari/537.36',
        }

    # 将构造好的目标页URL存储于记录目标抓取页url的列表中
    def page_url(self):
        for i in range(0, 10