Python 웹 크롤러를 사용하여 현재 극장에서 상영 중인 영화를 확인하세요.

import requests
from lxml import etree


import time
import random


class MaoyanSpider(object):
    def __init__(self):
      self.url = "https://maoyan.com/films?showType=2&offset={}"


    def main(self):
        pass


if __name__ == '__main__':
    spider = MaoyanSpider()
    spider.main()

 for i in range(1, 50):
    # ua.random,一定要写在这里,每次请求都会随机选择。
        self.headers = {
            'User-Agent': ua.random,
        }

def get_page(self, url):
  # random.choice一定要写在这里,每次请求都会随机选择
  res = requests.get(url, headers=self.headers)
  res.encoding = 'utf-8'
  html = res.text
  self.parse_page(html)

 # 　创建解析对象
parse_html = etree.HTML(html)
# 基准xpath节点对象列表
dd_list = parse_html.xpath('//dl[@class="movie-list"]//dd')

 for dd in dd_list:
    name = dd.xpath('.//div[@class="movie-hover-title"]//span[@class="name noscore"]/text()')[0].strip()
    star = dd.xpath('.//div[@class="movie-hover-info"]//div[@class="movie-hover-title"][3]/text()')[1].strip()
    type = dd.xpath('.//div[@class="movie-hover-info"]//div[@class="movie-hover-title"][2]/text()')[1].strip()
    dowld=dd.xpath('.//div[@class="movie-item-hover"]/a/@href')[0].strip()
    # print(movie_dict)
    movie = '''【即将上映】

 movie = '''【即将上映】
            
电影名字: %s


主演：%s


类型：%s
详情链接：https://maoyan.com%s
=========================================================
                                   ''' % (name, star, type,dowld)
print( movie)

time.sleep(random.randint(1, 3))

html = self.get_page(url)
self.parse_page(html)