Python爬虫

爬取一下内容：


代码：

import requests
import bs4
import re
import json


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

# 获取信息
data = {
    'on': 'true',
    'page': '1',
    'pageSize': '15',
    'productName': '广州',
    'conditionType': '2',
    'applyname': '',
    'applysn': '',
}

# UA伪装
hearders = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36 Edg/87.0.664.60'
}

# 取得一个响应数据
yjj = requests.post(url=url, data=data, headers=hearders)
yjj_json = yjj.json()
fp = open('yjj.json', 'w', encoding='utf-8')
json.dump(yjj_json, fp=fp, ensure_ascii=False)

# 用列表存储ID值
id_list = []
for _id in yjj_json['list']:
    id_list.append(_id['ID'])

# 控制一行输出 4 个ID值
for _ in range(len(id_list)):
    if (_+1)%4 == 0:
        print(id_list[_], end='\n')
    else:
        print(id_list[_], end='\t')

detail_url = 'http://scxk.nmpa.gov.cn:81/xk/itownet/portalAction.do?method=getXkzsById'
all_datail = []
for id in id_list:
    data = {
        'id': id
    }
    detail = requests.post(url=detail_url, data=data, headers=hearders)
    detail_json = detail.json()
    all_datail.append(detail_json)
fp = open('detail.json', 'w', encoding='utf-8')
json.dump(all_datail, fp=fp, ensure_ascii=False)

结果：