1. from lxml import etree
    2. import time
    3. import random
    4. from requests_html import HTMLSession,UserAgent
    5. header = {
    6.     'User-Agent':UserAgent().random
    7. }
    8. session = HTMLSession()
    10. def get_movie_info(url,i):
    11.     print(f'爬取第{i + 1}页数据')
    12.     response = session.get(url,headers = header)
    13.     html = etree.HTML(response.text)
    14.     ol = html.xpath('//*[@class="grid_view"]')[0]
    15.     allLi = ol.xpath('//li/div[@class="item"]')
    16.     j = 0
    17.     for li in allLi:
    18.         print(f'{"*" * 10}第{i + 1}页数据,第{j + 1}条数据{"*" * 10}')
    19.         movieImg = li.xpath('./div[@class="pic"]/a/img/@src')[0]
    20.         print('电影封面图:',movieImg)
    21.         movieName = li.xpath('./div[@class="info"]/div[@class="hd"]/a//span/text()')
    22.         movieName = processing(movieName)
    23.         print('电影名称:',movieName)
    24.         movieDy = li.xpath('./div[@class="info"]/div[@class="bd"]/p/text()')
    25.         movieDy = processing(movieDy)
    26.         print("导演以及主演:",movieDy)
    27.         movieScore = li.xpath('./div[@class="info"]/div[@class="bd"]/div/span[2]/text()')[0]
    28.         print('电影评分:',movieScore)
    29.         movieTxt = li.xpath('./div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span/text()')
    30.         print("电影总结:",movieTxt)
    31.         j += 1
    32.     print('-'*20,f'第{i+1}页数据已完毕','-'*20)
    34. def processing(strs):
    35.     s = ''
    36.     for n in strs:
    37.         n = ''.join(n.split())
    38.         s += n
    39.     return s
    41. if __name__ == '__main__':
    42.     for i in range(0,10):
    43.         start = 25 * int(i)
    44.         url = 'https://movie.douban.com/top250?start={start}&filter='.format(start=start)
    45.         get_movie_info(url,i)