python爬取ajax动态内容肯德基门店_爬虫爬取国内肯德基门店信息

预期效果

爬取每个城市(300+城市)所有的肯德基门店信息，保存到excel中，效果如下：

代码实现

import requests

import csv

import json

def getData(page,key):

url='http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'

headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'}

data={

'cname':'',

'pid':'',

'keyword': key,

'pageIndex': page,

'pageSize': '10'

}

res=requests.post(url=url,data=data,headers=headers)

json_data=res.json()

print(json_data)

count=json_data['Table'][0]['rowcount']

for i in json_data['Table1']:

storeName=i['storeName']

cityName=i['cityName']

addressDetail=i['addressDetail']

pro=i['pro']

print([storeName, cityName,addressDetail,pro])

with open('kfc_store.csv', mode='a', newline='') as f:

writer = csv.writer(f, delimiter=',')

writer.writerow([key,storeName, cityName,addressDetail,pro])

if __name__=='__main__':

# 从拉勾网上爬取全国各地城市，复制粘贴网页内容到txt文件再，接口如下。

# URL='https://www.lagou.com/lbs/getAllCitySearchLabels.json'

f2 = open('ci.txt', encoding='utf-8')

ts = f2.readline()

print(ts)

json_ts = json.loads(ts)

cs = json_ts['content']['data']['allCitySearchLabels']

place = []

m = 0

for c in cs:

for i in cs[c]:

m = m + 1

place.append(i['name'])

print(f'一共有{m}个城市')

print(place)

# place=['北京','上海','广州','深圳']

for key in place:

url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36'}

data = {

'cname': '',

'pid': '',

'keyword': key,

'pageIndex': 1,

'pageSize': '10'

}

res = requests.post(url=url, data=data, headers=headers)

json_data = res.json()

# print(json_data)

count = json_data['Table'][0]['rowcount']

c = count // 10 + 2

for n in range(1,c):

print(f'===========正在获取{key}数据===========')

print('===========正在获取第{}页数据==========='.format(n))

getData(n,key)