python爬虫学习第三章 JsonPath

3.1 JsonPath的基本使用

JsonPath只能解析本地的文件，不可以解析服务器响应的文件

import json
import jsonpath

# json.loads()方法：把JSON格式文件解码转换成Python对象。
obj = json.load(open('01_JsonPath_基本使用.json','r',encoding='utf-8'))

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

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

# store下面所有的元素
# 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)

# 第三本书
# book = jsonpath.jsonpath(obj,"$..book[2]")
# print(book)

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

# 前面两本书
# book_list = jsonpath.jsonpath(obj,'$..book[:2]')
# print(book_list)

# 条件过滤需要在()前面添加一个？
# 过滤出所有包含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数据如下

{ "store": {
    "book": [
      { "category": "修真",
        "author": "六道",
        "title": "坏蛋是咋样练成的",
        "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": "南派三叔",
      "color": "red",
      "price": 19.95
    }
  }
}

3.2 解析淘票票

import urllib.request
import json
import jsonpath

url = 'https://dianying.taobao.com/cityAction.json?activityId&_ksTS=1723215106044_152&jsoncallback=jsonp153&action=cityAction&n_s=new&event_submit_doGetAllRegion=true'

headers = {
    'accept':'text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01',
    # 这个切记要注释 不然会报编码错误
    # 'accept-encoding':'gzip, deflate, br, zstd',
    'accept-language':'zh-CN,zh;q=0.9',
    'bx-v':'2.5.14',
    'cookie':'cna=v1ZbGQMBohYCAdpMMTJcYB+g; miid=604144485590585714; t=48f43d54583647c0b5796fae909c6d7e; cookie2=1fabece9086d80a06ffe9208d3cf4a8c; v=0; _tb_token_=e77eeee0eb5ee; xlly_s=1; isg=BLi40yM0Kq0Dd0YpiIAI4N6biWZKIRyrValO5PIpZvOmDVj3mjEsO_MjxQW9XdSD',
    'priority':'u=1, i',
    'referer':'https://dianying.taobao.com/',
    'sec-ch-ua':'"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
    'sec-ch-ua-mobile':'?0',
    'sec-ch-ua-platform':'"Windows"',
    '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/126.0.0.0 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() 通过指定分隔符对字符串进行切片
content = content.split("(")[1].split(")")[0]

with open('02_JsonPath_解析淘票票.json','w',encoding='utf-8') as fp:
    fp.write(content)

obj = json.load(open('02_JsonPath_解析淘票票.json','r',encoding='utf-8'))

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