就是那种进去网页之后,网页抓包软件直接看抓不到的数据
url是上图中headers中的url,问号后面的参数需要重新设置,如代码中所示
还是反爬的话需要注意User-Agent
from typing import Dict
import json
import requests
url = "https://movie.douban.com/j/chart/top_list"
#重新封装参数
param = {
"type": "24",
"interval_id": "100:90",
"action": "",
"start": 0,
"limit": 20,
}
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36"
}
resp = requests.get(url=url,params=param,headers=headers)
page_text = resp.json()
#print(page_text)
with open('./douban.json', 'w', encoding='utf-8') as f:#写入json文件,没有办法爬取整个的页面格式,因为没有爬取html,css那些东西
json.dump(page_text,f)
with open("./douban.json",'r') as load_f:
load_dict = json.load(load_f)
print(load_dict)