Ajax post 请求

最新推荐文章于 2024-10-16 21:17:13 发布

Hitomi___

最新推荐文章于 2024-10-16 21:17:13 发布

阅读量100

点赞数

分类专栏：爬虫文章标签： ajax 爬虫 python

本文链接：https://blog.csdn.net/Hitomi___/article/details/120528384

版权

爬虫专栏收录该内容

7 篇文章 0 订阅

订阅专栏

爬取KFC官网北京店铺信息

# -*- coding: utf-8 -*-
# @Author  : HitoChen
# @Time    : 2021/9/23 11:27 上午
# @Function:

import urllib
import urllib.parse
import urllib.request

def creat_request(page):

    base_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
    data = {
        'cname': '',
        'pid': '',
        'keyword': '北京',
        'pageIndex': page,
        'pageSize': '10',
    }
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
    }
    data = urllib.parse.urlencode(data).encode('utf-8')
    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 get_dowload(page,content):
    with open('/Users/mac/Desktop/KFC.txt','a+',encoding='utf-8') as kfc:
        kfc.write(content)




if __name__ == '__main__':
    start_page = int(input('输入起始页码'))
    end_page = int(input('输入截至页码'))
    for page in range(start_page,end_page+1):
        request = creat_request(page)
        content=get_content(request)
        get_dowload(page,content)
    print('爬取肯德基北京餐厅成功， 请查看Desktop KFC.txt文件')