python爬取食药监局企业信息

import requests
import json

if __name__ == '__main__':
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
    }
    url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'

    id_list = []  # 存储页面的所有企业id
    info_list = []  # 存储所有企业的详细信息对象
    for page in range(1,137):
        page=str(page)
        param ={
            'on': 'true',
            'page': page,
            'pageSize': '15',
            'productName':'',
            'conditionType': '1',
             'applyname':'',
             'applysn':''
        }
        data_obj = requests.post(url=url,data=param,headers=headers).json()
        #提取json中的指定部分内容，此处为id
        for obj in data_obj['list']:
            id_list.append(obj['ID'])

    url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
    for id in id_list:
        param={
                'id':id
        }
        cur_obj = requests.post(url=url, data=param, headers=headers).json()
        print('公司名称：' + cur_obj["epsName"] + ' 法人: ' + cur_obj["legalPerson"] + "地址：" + cur_obj["epsAddress"])
        info_list.append(cur_obj)


  #  fp = open("食药监局所有企业的详细信息.json",'w',encoding='utf-8')
   # json.dump(info_list,fp=fp,ensure_ascii=False)

    print("爬取完成！")

 

来源：CSDN

作者：鹰立如睡

链接：https://blog.csdn.net/LVGAOYANH/article/details/104617735