1 # -*- coding: utf-8 -*-
2 # @Time : 2019/11/5 23:18
3 # @Author : AForever
4 # @Site :
5 # @File : Spider_05.py
6 # @Software: PyCharm
7
8 # 处理json数据
9
10 from urllib import request
11 import json
12
13
14 def get_data():
15 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'
16 headers = {
17 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
18 }
19 req = request.Request(url, headers=headers)
20 response = request.urlopen(req)
21 if response.getcode() == 200:
22 result = response.read()
23 # print(type(result)) # bytes类型
24 # print(result)
25 result = str(result, encoding='utf8')
26 print(result)
27 return result
28
29
30 def parse_data(html):
31 # 将字符串形式的json转换为dict字典
32 data = json.loads(html)
33 movies = data['subjects']
34 for movie in movies:
35 print(movie['title'], movie['rate'])
36
37
38 if __name__ == '__main__':
39 # get_data()
40 parse_data(get_data())
