requests實戰之葯監總局數據爬取

import requests 
import json 

if __name__ == "__main__":
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2626.106 Safari/537.36'
    }
    id_list = []
    all_data_list = []  #存儲所有企業詳情數據
    #批量獲取不同企業的id值
    url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
    #參數的封裝
    for page in range(1,327):
        page = str(page)
        data = {
            'on':'true',
            'page':'1',
            'pageSize':'15',
            'productName':'',
            'conditionType':'1',
            'applyname':'',
            'applysn':'',
        }
        json_ids = requests.post(url=url,headers=headers,data=data).json()
        for dic in json_ids['list']:
            id_list.append(dic['ID'])
    #獲取企業詳情數據
    post_url='http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
    for id in id_list:
        data = {
            'id':id 
        }
        detail_json = requests.post(url=post_url,headers=headers,data=data).json()

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