爬取淘宝商品信息

利用Ajax动态爬取淘宝商品信息
功能依次实现爬虫的开发流程：爬取规则--->数据清洗--->数据存储
实现代码：

import requests
import json
import time
import csv


class Tao_Bao(object):
    global auctions_distinct
    auctions_distinct = []

    def get_response(self):
        for k in ['四件套', '手机壳']:
            # 新建csv 文件，每循环一个关键字会生成其对应的CSV文件
            file_name = k + '.csv'
            with open(file_name, 'w', newline='')as csvfile:
                writer = csv.writer(csvfile)
                # 写入表头信息
                writer.writerow(['标题 ', '价格', '销量', '店铺', '区域'])
                csvfile.close()
            # 循环次数可以根据实际自行设定
            for p in range(6):
                url = 'https://s.taobao.com/api?callback=jsonp665&ajax=true&m=customized&q=%s&s=%s' % (k, p)
                r = requests.get(url)
                response = r.text
                response = response.split('(')[1].split(')')[0]
                response_dict = json.loads(response)
                response_aucitons_info = response_dict['API.CustomizedApi']['itemlist']['auctions']
                # 调用函数get_auctons_info写入商品信息
                self.get_auctions_info(response_aucitons_info, file_name)
                time.sleep(4)
            print('获取数据数量为：' + str(len(auctions_distinct)))

    def get_auctions_info(self, response_auctions_info, file_name):
        with open(file_name, 'a', newline='')as csvfile:
            """ 生成CSV对象，用于写入CSV文件"""
            writer = csv.writer(csvfile)
            for i in response_auctions_info:
                #  写入数据
                writer.writerow([i['raw_title'], i['view_price'], i['view_sales'], i['nick'], i['item_loc']])
                auctions_distinct.append(str(i['raw_title']))
            csvfile.close()


if __name__ == '__main__':
    Get_start = Tao_Bao()
    Get_start.get_response()

实现效果

爬取淘宝商品信息