Python超强爬虫8天速成（完整版）爬取各种网站数据实战案例

import json

import requests

# 获取肯德基餐厅地址

if __name__ == '__main__':

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

keyword = input('请输入需要查询的地址：')

# keyword = '北京'

data = {

"cname":'',

'pid':'',

'keyword':keyword,

'pageIndex': 1,

'pageSize': 1,

}

headers = {

'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.82'

}

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

rowcount = resport.json()['Table'][0]['rowcount']

data['pageSize'] = (rowcount//10+1) if(rowcount%10 > 0) else (rowcount//10)

cityList = {

'Table1' :[]

}

for i in range(data['pageSize']):

data['pageIndex'] = i+1

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

cityList['Table1'] += resport.json()['Table1']

fp = open(f'{keyword}.json','w',encoding='utf-8')

json.dump(cityList,fp=fp,ensure_ascii=False)

fp.close()