JsonPath解析---爬取JSON数据

 

 JsonPath只能解析本地文件。

 

import json
import jsonpath


obj = json.load(open('073_尚硅谷_爬虫_解析_jsonpath.json','r',encoding='utf-8'))

# 书店所有书的作者
# author_list = jsonpath.jsonpath(obj,'$.store.book[*].author')
# print(author_list)

# 所有的作者
# author_list = jsonpath.jsonpath(obj,'$..author')
# print(author_list)

# store下面的所有的元素
# tag_list = jsonpath.jsonpath(obj,'$.store.*')
# print(tag_list)

# store里面所有东西的price
# price_list = jsonpath.jsonpath(obj,'$.store..price')
# print(price_list)

# 第三个书
# book = jsonpath.jsonpath(obj,'$..book[2]')
# print(book)

# 最后一本书
# book = jsonpath.jsonpath(obj,'$..book[(@.length-1)]')
# print(book)

#     前面的两本书
# book_list = jsonpath.jsonpath(obj,'$..book[0,1]')
# book_list = jsonpath.jsonpath(obj,'$..book[:2]')
# print(book_list)

# 条件过滤需要在（）的前面添加一个？
#      过滤出所有的包含isbn的书。
# book_list = jsonpath.jsonpath(obj,'$..book[?(@.isbn)]')
# print(book_list)


# 哪本书超过了10块钱
book_list = jsonpath.jsonpath(obj,'$..book[?(@.price>10)]')
print(book_list)

 

json数据

{ "store": {
    "book": [
      { "category": "修真",
        "author": "六道",
        "title": "坏蛋是怎样练成的",
        "price": 8.95
      },
      { "category": "修真",
        "author": "天蚕土豆",
        "title": "斗破苍穹",
        "price": 12.99
      },
      { "category": "修真",
        "author": "唐家三少",
        "title": "斗罗大陆",
        "isbn": "0-553-21311-3",
        "price": 8.99
      },
      { "category": "修真",
        "author": "南派三叔",
        "title": "星辰变",
        "isbn": "0-395-19395-8",
        "price": 22.99
      }
    ],
    "bicycle": {
      "author": "老马",
      "color": "黑色",
      "price": 19.95
    }
  }
}

 

jsonpath案例，解析淘票票

 

import urllib.request


url = 'https://dianying.taobao.com/cityAction.json?activityId&_ksTS=1629789477003_137&jsoncallback=jsonp138&action=cityAction&n_s=new&event_submit_doGetAllRegion=true'

headers = {
    # ':authority': 'dianying.taobao.com',
    # ':method': 'GET',
    # ':path': '/cityAction.json?activityId&_ksTS=1629789477003_137&jsoncallback=jsonp138&action=cityAction&n_s=new&event_submit_doGetAllRegion=true',
    # ':scheme': 'https',
    'accept': 'text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01',
    # 'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'cookie': 'cna=UkO6F8VULRwCAXTqq7dbS5A8; miid=949542021157939863; sgcookie=E100F01JK9XMmyoZRigjfmZKExNdRHQqPf4v9NIWIC1nnpnxyNgROLshAf0gz7lGnkKvwCnu1umyfirMSAWtubqc4g%3D%3D; tracknick=action_li; _cc_=UIHiLt3xSw%3D%3D; enc=dA18hg7jG1xapfVGPHoQCAkPQ4as1%2FEUqsG4M6AcAjHFFUM54HWpBv4AAm0MbQgqO%2BiZ5qkUeLIxljrHkOW%2BtQ%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; thw=cn; _m_h5_tk=3ca69de1b9ad7dce614840fcd015dcdb_1629776735568; _m_h5_tk_enc=ab56df54999d1d2cac2f82753ae29f82; t=874e6ce33295bf6b95cfcfaff0af0db6; xlly_s=1; cookie2=13acd8f4dafac4f7bd2177d6710d60fe; v=0; _tb_token_=e65ebbe536158; tfstk=cGhRB7mNpnxkDmUx7YpDAMNM2gTGZbWLxUZN9U4ulewe025didli6j5AFPI8MEC..; l=eBrgmF1cOsMXqSxaBO5aFurza77tzIRb8sPzaNbMiInca6OdtFt_rNCK2Ns9SdtjgtfFBetPVKlOcRCEF3apbgiMW_N-1NKDSxJ6-; isg=BBoas2yXLzHdGp3pCh7XVmpja8A8S54lyLj1RySTHq14l7vRDNufNAjpZ2MLRxa9',
    'referer': 'https://dianying.taobao.com/',
    'sec-ch-ua': '"Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"',
    '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/92.0.4515.159 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('074_尚硅谷_爬虫_解析_jsonpath解析淘票票.json','w',encoding='utf-8')as fp:
    fp.write(content)

import json
import jsonpath

obj = json.load(open('074_尚硅谷_爬虫_解析_jsonpath解析淘票票.json','r',encoding='utf-8'))

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

print(city_list)