python爬虫json数据解析_Python爬虫解析工具小结-JSONPath

import jsonpath

import json

s = """

{ "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,

"author": "test"

}

}

}

"""

# 转化为字典

data = json.loads(s)

# 进行数据提取

# res = jsonpath.jsonpath(data, '$.store.book[*].author') # store中所有book的author(列表)

# res = jsonpath.jsonpath(data, '$..author') # 所有的author

# res = jsonpath.jsonpath(data, '$.store.*') # store下一级中所有元素，分为book下的所有和bicycle下的所有

# res = jsonpath.jsonpath(data, '$.store..price') # store里的所有price

# res = jsonpath.jsonpath(data, '$..book[2]') # book下的第三个元素

# res = jsonpath.jsonpath(data, '$..book[(@.length-1)]') # book下的最后一项，可以使用切片，@.length意为当前元素长度，@指当前元素

# res = jsonpath.jsonpath(data, '$..book[-1:]') # book下的最后一项，可以使用数字切片

# res = jsonpath.jsonpath(data, '$..book[0, 1]') # book下的前两本数，数字切片

# res = jsonpath.jsonpath(data, '$..book[?(@.isbn)]') # 使用isbn进行过滤，存在isbn的项目，@.isbn当前元素的isbn项

# res = jsonpath.jsonpath(data, '$..book[?(@.price<10)]') # book中price小于10的项目

res = jsonpath.jsonpath(data, '$..*') # 结构中的所有成员

print(res)