爬取豆瓣电影（ajax）

抓取加载页面，分析url

每刷新一次url的page_start=0,20,40，…

import requests
from fake_useragent import UserAgent
def getInfo(page):
    baseurl = r'https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start='
    headers = {
        'User-Agent': UserAgent().random
    }
    respones = requests.get(baseurl+str(page), headers=headers)
    return respones
 if __name__ == '__main__':
    for i in range(10):
     	 respones = getInfo(i*20)       

利用json解析出电影名称

完整代码

import requests
from fake_useragent import UserAgent
import json


def getInfo(page):
    baseurl = r'https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%83%AD%E9%97%A8&sort=recommend&page_limit=20&page_start='
    headers = {
        'User-Agent': UserAgent().random
    }
    respones = requests.get(baseurl+str(page), headers=headers)
    return respones


if __name__ == '__main__':
    for i in range(10):
        respones = getInfo(i*20)
        data=json.loads(respones.text)
        for j in range(20):
            print(data['subjects'][j]['title'])