Python爬虫 - 将爬取数据以JSON格式存储与读取

版权声明:转载请注明出处 https://blog.csdn.net/qq_42292831/article/details/88901594

Python - 数据格式JSON化 】:介绍了数据JSON化的主要操作


源码

import requests
import json
from pprint import pprint
from bs4 import BeautifulSoup

url = "https://blog.csdn.net/qq_42292831/article/category/8257708"
response = requests.get(url)
soup = BeautifulSoup(response.text,"html.parser")
a = soup.find_all("div",{"class":"article-item-box csdn-tracking-statistics"})
b = []
c = dict()
for data in a:
    c[data.h4.a.text.strip()[1:].strip()] = data.h4.a.get("href")
b.append(c)
#print(b)
with open("json_test.json","w+",encoding="UTF-8") as f:
     try:
         json.dump(b,f,ensure_ascii=False,indent=4)
     except BaseException as e:
         print(e)
     else:
         print("Successful!")
with open("json_test.json","r",encoding="UTF-8") as f:
    c = json.load(f)
#    pprint(c)
#print(c[0])
for x in c[0].items():
    pprint(x)

猜你喜欢

转载自blog.csdn.net/qq_42292831/article/details/88901594