学习笔记(01):Python爬虫开发-总结回顾

立即学习:https://edu.csdn.net/course/play/24454/306768?utm_source=blogtoedu

import requests
import  json
if __name__ == "__main__":
    #第一步获取全部ID
    url='http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
    headers={
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
    }
    post_url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
    dic_list = [];
    ID_list = []  # 存储id
    for page in range(1,10):
        page=str(page)
        data={
            'on': 'true',
            'page':page,
            'pageSize': '15',
            'productName':'',
            'conditionType':'1',
            'applyname':'',
            'applysn':'',
        }
        json_ids=requests.post(url=url,data=data,headers=headers).json()

        for dic in json_ids['list']:
          ID_list.append(dic['ID'])
    #第二部:获取详情页数据

    for id in ID_list:
        data={
            'id':id
        }
        page_post=requests.post(url=post_url,data=data,headers=headers).json()
        dic_list.append('公司名称:'+page_post['epsName']+' 企业负责人:' + page_post['legalPerson']+' 许可证编号:' + page_post['productSn'])

    fp=open('./化妆品详细数据.json','w',encoding='utf-8')
    json.dump(dic_list,fp=fp,ensure_ascii=False)
    print('over!!!')