Python 爬虫 KFC官网之北京市门店信息

运行代码：

# 1 页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# POST
# "cname": "北京",
# "pid": "",
# "pageIndex": "1",
# "pageSize": "10"


#  2 页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# POST
# "cname": "北京",
# "pid": "",
# "pageIndex": "2",
# "pageSize": "10"

# 下载北京市KFC门店前10页的数据
# 1.请求对象的定制
# 2.获取响应的数据
# 3.下载数据



import urllib.request
import urllib.parse

# base_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname'

def create_request(page):
    base_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname'

    data = {
        'cname': '北京',
        'pid': '',
        'pageIndex': '1',
        'pageSize': '10'
    }

    data = urllib.parse.urlencode(data).encode('utf-8')

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:93.0) Gecko/20100101 Firefox/93.0'
    }

    request = urllib.request.Request(url=base_url,headers=headers,data=data)

    return request

def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content

def down_load(page,content):
    with open('kfc_'+str(page)+'.json','w',encoding='utf-8') as fp:
        fp.write(content)

if __name__ == '__main__':
    start_page = int(input('请输入起始页码'))
    end_page = int(input('请输入结束页码'))

    for page in range(start_page,end_page+1):
        # 请求对象定制
        request = create_request(page)
        # 获取页面源码
        content = get_content(request)
        # 下载
        down_load(page,content)

结果展示

从网页下载的门店信息

门店信息展示