import requests
import json

if __name__ == '__main__':
    url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsList'
    # UA 伪装
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    }
    # 存储所有的企业id
    id_list = []

    # 存储所有的企业详细信息
    all_data_list = []
    # page_text = page_test = requests.get(url=url,headers=headers).text
    #
    # with open('./hauzhuangpin.html','w',encoding='utf-8') as pf:
    #     pf.write(page_test)
    # print('end')
    
    #爬取前6页的数据
    for page in range(1,6):
        page = str(page)
        data = {
            'on': 'true',
            'page': page,
            'pageSize': '15',
            'productName': '',
            'conditionType': '1',
            'applyname': '',
            'applysn': '',
        }
    # response = requests.post(url=url,data=data,headers=headers)
    #
    # # 获取类型是json
    # list_data = response.json()
    # 结果是字典
        json_ids = requests.post(url=url,data=data,headers=headers).json()


    #拿字典的json_list 键 list ,循环读取 值 ，加入到列表
    #批量获取到了 id
        for i in json_ids['list']:
            id_list.append(i['ID'])

    # print(id_list)

    #获取企业详细数据
    post_url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'
    for id in id_list:
        data = {
            'id': id
        }
        new_json = requests.post(url=post_url,data=data,headers=headers).json()
        # print(new_json)
        all_data_list.append(new_json)

    #持久化存储
    fp = open('./allData.json','w',encoding='utf-8')
    json.dump(all_data_list,fp=fp,ensure_ascii=False)
    print('end')