python爬虫提取人名_Python爬虫（json的数据提取）

json方法

json字符串--------->json.loads()---------->python数据类型

python数据类型---------->json.dumps()----------->json字符串

jsonpath介绍

用来解析多层嵌套的json数据

#处理动态数据

import json

from jsonpath import jsonpath

import requests

import re

url = 'https://sclub.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98vv108&productId=47957967985&score=0&sortType=5&page=0&pageSize=10&isShadowSku=0&fold=1'

headers = {

'Referer': 'https://item.jd.com/47957967985.html',

'Sec-Fetch-Mode': 'no-cors',

'Sec-Fetch-Site': 'same-site',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'

}

response = requests.get(url,headers=headers).content.decode('gbk')

# print(response)

data = re.search(r'{.*}',response).group()

data1 = json.loads(data)

data2 = jsonpath(data1,'$.comments[*].content')

for i in data2:

print(i)

print("**"*30)