爬虫-肯德基餐厅信息查询

1. 导包

import requests
import json

2. 初步获取数据

url = "http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?"
op = ["cname", "pid", "keyword"]
cname = input("请输入需要查询的城市: ")
pid = ""  # "31"表示有Wi-Fi
kw = input("餐厅关键字: ")
pi = "1"   # 页面索引
ps = "10"  # 一页包含十条数据
data = {
    "op": op[2],
    "cname": cname,
    "pid": pid,
    "keyword": kw,
    "pageIndex": pi,
    "pageSize": ps
}
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 "
                  "Safari/537.36 Edg/106.0.1370.42"
}

rsp = requests.post(url, data, headers=headers)
# Content-Type: text/plain; charset=utf-8, 响应数据以json格式编写
dict_data = rsp.json()

3. 获取所有数据

flag = True
while flag:
    pi = str(int(pi) + 1)
    params["pageIndex"] = pi
    rsp = requests.post(url, data, headers=headers)
    if not rsp.json()["Table1"]:
        break
    for i in rsp.json()["Table1"]:
        dict_data["Table1"].append(i)

4. 持久化存储

with open("v_me_50.json", 'w', encoding="utf-8") as f:
    json.dump(dict_data, f, indent=4, ensure_ascii=False)