爬虫系列笔记八JsonPath

Jsonpath语法与xpath语法对比

jsonpath的使用用来解析返回的json文件
1）obj=json.load(open(‘json文件’,‘r’,encoding=‘utf-8’))
2）ret=jsonpath.jsonpath(obj,‘jsonpath语法’)

#jsonpath解析淘票票
import urllib.request
url='https://dianying.taobao.com/cityAction.json?activityId&_ksTS=1665382991267_109&jsoncallback=jsonp110&action=cityAction&n_s=new&event_submit_doGetAllRegion=true'

headers={
    'accept':'text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01',
    'accept-language':'zh-CN,zh;q=0.9,en;q=0.8,en-US;q=0.7',
    'cookie':'',#这里cookie就不给大家了
    'referer':'https://dianying.taobao.com/',
    'sec-ch-ua':'"Chromium";v="106", "Google Chrome";v="106", "Not;A=Brand";v="99"',
    'sec-ch-ua-mobile':'?0',
    'sec-fetch-dest':'empty',
    'sec-fetch-mode':'cors',
    'sec-fetch-site':'same-origin',
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36',
    'x-requested-with':'XMLHttpRequest'
}


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

response=urllib.request.urlopen(request)

content=response.read().decode('utf-8')


#split切割
content=content.split('(')[1].split(')')[0]

with open('taopiaopiao.json','w',encoding='utf-8')as f:
    f.write(content)

import json
import jsonpath

obj=json.load(open('C:/Users/86177/Desktop/tese/taopiaopiao.json','r',encoding='utf-8'))

city_list=jsonpath.jsonpath(obj,'$..regionName')#jsonpath语法

print(city_list)