爬虫实战_request爬取豆瓣电影top250

import time
import requests
from lxml import etree
import json

def getPage(url):
    '''请求页面数据'''
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36 Edg/89.0.774.50'
        }
        #发起请求
        response=requests.get(url,headers=headers)
        #判断响应状态
        if response.status_code==200:
            return response.text
        else:
            return None
    except:
        return None


def parsePage(html):
    '''解析页面数据'''
    html=etree.HTML(html)
    items=html.xpath('//div[@class="item"]')
    #遍历封装数据并返回
    for item in items:
        res={
            'index':item.xpath('.//div/em[@class=""]/text()'),
            'image':item.xpath('.//img[@width=&#