药监总局数据爬取-post请求 

 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 import requests
 4 import json
 5 
 6 if __name__ == "__main__":
 7     headers = {
 8         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
 9     }
10     id_list = []  # 存储企业的id
11     all_data_list = []  # 存储所有的企业详情数据
12     # 批量获取不同企业的id值
13     url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
14     # 参数的封装
15     for page in range(1, 6):
16         page = str(page)
17         data = {
18             'on': 'true',
19             'page': page,
20             'pageSize': '15',
21             'productName': '',
22             'conditionType': '1',
23             'applyname': '',
24             'applysn': '',
25         }
26         json_ids = requests.post(url=url, headers=headers, data=data).json()
27         for dic in json_ids['list']:
28             id_list.append(dic['ID'])
29 
30     # 获取企业详情数据
31     post_url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
32     for id in id_list:
33         data = {
34             'id': id
35         }
36         detail_json = requests.post(url=post_url, headers=headers, data=data).json()
37         # print(detail_json,'-------------ending-----------')
38         all_data_list.append(detail_json)
39 
40     # 持久化存储all_data_list
41     fp = open('./allData.json', 'w', encoding='utf-8')
42     json.dump(all_data_list, fp=fp, ensure_ascii=False)
43     print('over!!!')

 

posted @ 2021-08-21 22:58  likl-  阅读(152)  评论(0)    收藏  举报