Python爬虫框架feapder--豆瓣数据抓取

1.安装feapder:

2.创建我们第一个feapder爬虫

3.写代码

# -*- coding: utf-8 -*-
"""
Created on 2022-01-15 08:59:23
---------
@summary:豆瓣爬取
---------
@author: 19123
"""

import feapder


class NewNew(feapder.AirSpider):

    def start_requests(self):
        #https://movie.douban.com/top250?start=25&filter=
        #https://movie.douban.com/top250?start=50&filter=
        for i in range(5):
            yield feapder.Request("https://movie.douban.com/top250?start={}&filter=".format(i*25))

    def parse(self, request, response):
        #图片地址
        picture_address = response.xpath('//div[@class="pic"]/a/img/@src').extract()
        # print(picture_address)
        #电影名称
        movie_title = response.xpath('//div[@class="hd"]/a/span[1]/text()').extract()
        # print(movie_title)
        #评价人数
        evaluate_people = response.xpath('//div[@class="star"]/span[4]/text()').extract()
        # print(evaluate_people)
        #电影引言
        movie_introduction = response.xpath('//div[@class="bd"]/p[@class="quote"]/span/text()').extract()
        # print(movie_introduction)
        for picture, title, people, introduction in zip(picture_address, movie_title, evaluate_people, movie_introduction):
            print(picture, title, people, introduction)


if __name__ == "__main__":
    NewNew().start()

4.得到数据