xpath+lxml爬取猫眼电影排行

import requests
from lxml import etree

def get_source(url):
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36','Referer': 'https://maoyan.com/board/4?offset=0'}
    response = requests.get(url,headers=headers)
    return response.text

def get_html(response):
    html=etree.HTML(response)
    movie={}
    movie['name']=html.xpath('//*[@id="app"]/div/div/div[1]/dl/dd/div/div/div[1]/p[1]/a/text()')
    movie['star']=html.xpath('//*[@id="app"]/div/div/div[1]/dl/dd/div/div/div[1]/p[2]/text()')
    movie['time']=html.xpath('//*[@id="app"]/div/div/div[1]/dl/dd/div/div/div[1]/p[3]/text()')
    print(movie)

if __name__ == '__main__':
    for i in range(0, 100, 10):
        url = 'https://maoyan.com/board/4?offset=' + str(i)
        get_html(get_source(url))