Python自学之路—豆瓣电影排行榜的爬取

源代码

import requests
import json
url = 'https://movie.douban.com/j/chart/top_list' #指定URL
param = {
    'type': '24',
    'interval_id': '100:90',
    'action': '',
    'start': '0',#从第几部开始取
    'limit': '20',#一次取几部
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'
} #UA伪装
response = requests.get(url=url,params=param,headers=headers) # 发起请求

list_data = response.json() # 获取响应数据
fp = open('./douban.json','w',encoding='utf-8')# 永久化存储
json.dump(list_data,fp=fp,ensure_ascii=False)

print("爬取数据结束")