爬虫学习--63urllib的ajax的post请求肯德基官网

#第一页
#http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
#formdata
# cname:北京
# pid:
# pageIndex:1
# pageSize:10

#第二页
#http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
#post请求
#formdata
# cname:北京
# pid:
# pageIndex:2
# pageSize:10


import urllib.request
import urllib.parse

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

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

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

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.3.1311 SLBChan/103'
    }

    request = urllib.request.Request(url=base_url,data=data,headers=headers)
    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('起始：'))
    end_page = int(input('结束：'))

    for page in range(start_page,end_page+1):
        #请求对象的定制
        request = create_request(page)
        #获取网页源码
        content = get_content(request)
        #下载
        down_load(page,content)