爬取国家药品监督管理局详情页面信息

学习链接b站：https://www.bilibili.com/video/BV1Yh411o7Sz?p=11

import requests
import json

url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsList'
# 获取id信息

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'}
ID_list = []  # 存放id 的列表


def get_idlist():
    # 请求主页面
    pages = 5

    for page in range(pages):
        params = {
            'on': 'true',
            'page': str(page),
            'pageSize': '15',
            'productName': '',
            'conditionType': '1',
            'applyname': '',
            'applysn': '',
        }
        re = requests.post(url, params=params, headers=headers)
        # 将response转化为字典类型
        response_dic = json.loads(re.text)
        # 把 id 放入列表中
        for item in response_dic['list']:
            ID_list.append(item['ID'])


def writeinfo():
    for aid in ID_list:
        url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'
        params = {'id': aid}
        get_info = requests.post(url, params=params, headers=headers)
        with open('./info.txt', 'a+', encoding='utf-8') as fp:
            fp.write(get_info.text)
            fp.writelines("\n")


get_idlist()
writeinfo()