4_爬NMPA药监总局_动态加载_传ID

 

http://scxk.nmpa.gov.cn:81/xk/

 

import requests

url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsList'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.100 Safari/537.36'
}
for page in range(1,6):
    print('正在爬取第{}页的数据......'.format(page))

    data = {
        'on': 'true',
        'page': str(page),
        'pageSize':'15',
        'productName': '',
        'conditionType': '1',
        'applyname':'',
        'applysn': '',
    }
    company_data = requests.post(url=url,headers=headers,data=data).json()
    #print(company_data)
    for dic in company_data['list']:
        _id = dic['ID']
        #print(_id)#每家公司的id，后续通过id进行下一步操作
        detail_url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'#详细数据是通过此url拿到的，此url通过辨识不同公司的id显示其对应信息
        data = {
            'id': _id
        }
        detail_data = requests.post(url=detail_url,data=data,headers=headers).json()
        print(detail_data['epsName']+detail_data['legalPerson'])