爬取详情数据

最新推荐文章于 2024-04-03 09:54:14 发布

可可宋

最新推荐文章于 2024-04-03 09:54:14 发布

阅读量215

点赞数 1

文章标签： python

本文链接：https://blog.csdn.net/xiaoyun5555/article/details/112972072

版权

在这里插入图片描述

import requests
import json
import xlwt
headers ={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
}
url ='http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsList'
json_id =requests.post(url=url,headers=headers)
page_text=json_id.text
json_data=json.loads(page_text)


id_list=[]    #存储企业的id
for dic in json_data["list"]:
    id_list.append(dic["ID"])
#print(id_list)
post_url='http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'
for i in id_list:
    data = {
        'id': i
    }
    json_informations=requests.post(url=post_url,headers=headers,data=data)
    all_datas_text =json_informations.text
    all_datas = json.loads(all_datas_text)
    print(all_datas)



# workbook =xlwt.Workbook() #注意这里的首字母要大写
# worksheet =workbook.add_sheet('企业信息')
# rowTitle =['企业名称','可项目','企业住所','生产地址','发证机关','日常监督管理机构','投诉举报电话']
# for i in range(0,len(rowTitle)):
#      worksheet.write(0,i,rowTitle[i])
#
# for k in json_informations["list"]:
#      all_datas.append(k['epsAddress'])
# #
#  worksheet.write(0,0,label='a')
# workbook.save('./excel00.xls')