python 爬取豆瓣电影

import requests
from lxml import etree
import re
from bs4 import BeautifulSoup
import os
import time
import json
#解析数据
def parse(res):
    res_html = etree.HTML(res)
    items = res_html.xpath('//div[@class="item"]')
    datalist = []
    #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="100"]/@src'),
            'title':item.xpath('.//span[@class="title"]/text()'),
            'actor':item.xpath('.//p[@class=""]/text()'),
            'score':item.xpath('.//span[@class="rating_num"]/text()')
        }
        datalist.append(res)
    return datalist

#写入数据
def wtiteFile(item):
    with open('./douban.json','a',encoding='utf-8')as fp:
        fp.write(json.dumps(item,ensure_ascii=False))
        fp.write('\n')
def main(offset):
    #负责调度爬虫函数
    url = 'https://movie.douban.com/top250?start='+str(offset)
    headers = {
        'User-Agent': 'Mozilla / 5.0(Windows NT 10.0; WOW64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 72.0.3626.81 Safari / 537.36 SE 2.X MetaSr 1.0'
    }

    res = requests.get(url,headers=headers)
    if res.status_code == 200:
        khtml = parse(res.text)
        for item in khtml:
            print('正在写入数据',item["title"])
            wtiteFile(item)



if __name__ == '__main__':
    for i in range(0,10):
        main(offset=i*25)
        time.sleep(2)