Python3 爬取Ajax加载的网页信息

url：http://www.kfc.com.cn/kfccda/storelist/index.aspx

#coding=utf-8
import re
import time
import requests
from requests.exceptions import RequestException

def getHtml(url,page):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0'}     #伪装一下
        data = {
            "cname":"深圳",
            "pageIndex":page,
            "pageSize":10,
            "pid":"",
            }
        response = requests.post(url,headers = headers,data = data).json()
        return response
    except RequestException:
        return None

if __name__=='__main__':
    url = "http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname"
    for page in range(1,10):
        Html = getHtml(url,page)
        data = Html.get('Table1')
        for info in data:
            print (info['storeName'] + '\t' + info['addressDetail'])
        time.sleep(1)

 

欢迎关注本人微信公众号,会分享更多的干货: