python urllib.request 爬虫 数据处理-python爬虫之json数据处理

# -*- coding: utf-8 -*-

# @Time : 2019/11/5 23:18

# @Author : AForever

# @Site :

# @File : Spider_05.py

# @Software: PyCharm

# 处理json数据

from urllib import request

import json

def get_data():

url = "https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=400&page_start=0"

headers = {

"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36"

}

req = request.Request(url, headers=headers)

response = request.urlopen(req)

if response.getcode() == 200:

result = response.read()

# print(type(result)) # bytes类型

# print(result)

result = str(result, encoding="utf8")

print(result)

return result

def parse_data(html):

# 将字符串形式的json转换为dict字典

data = json.loads(html)

movies = data["subjects"]

for movie in movies:

print(movie["title"], movie["rate"])

if __name__ == "__main__":

# get_data()

parse_data(get_data())

原文地址：https://www.cnblogs.com/AForever01/p/11986622.html