豆瓣电影TOP 250--数据采集

代码区域：

import requests
from lxml import etree


class DouBan:
    urls = ['https://movie.douban.com/top250?start={}'.format(str(count)) for count in range(0, 251, 25)]

    def get_movie_data(self):
        for url in self.urls:
            html = requests.get(url).text
            html_dom = etree.HTML(html)
            movie_list = html_dom.xpath('.//ol[@class="grid_view"]/li')
            for movie in movie_list:
                title = movie.xpath('.//span[@class="title"]/text()')[0]
                msgs = movie.xpath('.//div[@class="bd"]/p[@class=""]/text()')
                director_and_protagonist = msgs[0].strip().split('   ')
                director = director_and_protagonist[0].replace('导演: ', '')
                protagonist = director_and_protagonist[1].replace('主演: ', '') if len(
                    director_and_protagonist) == 2 else ''
                mark = msgs[1].strip().replace(' ', '')
                star = movie.xpath('.//span[@class="rating_num"]/text()')[0]
                quote = movie.xpath('.//span[@class="inq"]/text()')[0]
                print(url, title, director, protagonist, mark, star, quote)


db = DouBan()
db.get_movie_data()

效果展示：

以后有需要的时候可以对接到前端展示，周末有时间的时候就可以照着列表找找高质量电影观看了。薯片+快乐水，enjoying！