python爬虫中数据提取笔记

jsonpath的使用

一、使用pip安装jsonpath模块
pip install jsonpath

二、数据提取的使用

#‘$’代表定位根节点，‘.’定位子节点，‘..’定位任何位置的子节点，
from jsonpath import jsonpath

#字典数据
data={
    "store": {
        "book": [
            {
                "category": "reference",
                "author": "Nigel Rees",
                "title": "Sayings of the Century",
                "price": 8.95
            },
            {
                "category": "fiction",
                "author": "Evelyn Waugh",
                "title": "Sword of Honour",
                "price": 12.99
            },
            {
                "category": "fiction",
                "author": "Herman Melville",
                "title": "Moby Dick",
                "isbn": "0-553-21311-3",
                "price": 8.99
            },
            {
                "category": "fiction",
                "author": "J. R. R. Tolkien",
                "title": "The Lord of the Rings",
                "isbn": "0-395-19395-8",
                "price": 22.99
            }
        ],
        "bicycle": {
            "color": "red",
            "price": 19.95
        }
    },
    "expensive": 10
}
#提取价格
print(jsonpath(data,'$..price'))
#打印结果[8.95, 12.99, 8.99, 22.99, 19.95]

#提取所有书本的价格
print(jsonpath(data,'$..book..price'))
#打印结果[8.95, 12.99, 8.99, 22.99]

#获取"bicycle"中的price
print(jsonpath(data,'$..bicycle.price'))
#打印结果为[19.95]

#以上打印出来的结果都是列表