豆瓣top250

from lxml import etree
import time
import random
import requests
headers ={'User-Agent':'Mozila/5.0(Windows NT 10.0;WOW64) AppleWebKit/537.36(KHTML ,like Gecko )Chrome/83.0.4103.61 Safari/537.36'}

def proprcessing (strs):
    s=''
    for n in strs:
        n=''.join(n.split())
        s=s+n
        return s
def get_movie_info(url):
    response =requests.get(url=url,headers=headers)
    html = etree.HTML(response.text)
    div_all = html.xpath('//div[@class="info"]')
    for div in div_all:
        names = div.xpath('./div[@class="hd"]/a//span/text()')
        name=proprcessing(names)
        infos = div.xpath('./div[@class="bd"]/p/text')
        info = proprcessing(infos)
        score = div.xpath('./div[@class="bd"]/div/span[2]/text()')
        evaluation = div.xp('./div[@class = "bd"]/div/span[4]/text()')
        summary = div.xpath('./div[@class="bd"]/p[@class="quote"]/span/text()')
        print('电影名称：', name)
        print('导演与演员：',info)
        print('电影评分：',score)
        print('评价人数：',evaluation)
        print('电影总结：',summary)
        print('_________________')
if __name__=='__name__':
    for i in range(0,250,25):
        url='https://movie.douban.com/top250?start={page}&filter='.format(page=i)
        get_movie_info(url)
        time.sleep(random.randint(1,3))