爬虫小项目

#coding:utf-8
import time
import requests
import random
headers = {
    'if-none-match': '"60a5c01e-c097"',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36',
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'cache-control': 'max-age=0',
    'authority': 'abook.hep.com.cn',
    'if-modified-since': 'Thu, 20 May 2021 01:49:18 GMT',
}

for i in range(1,69):          #src="https://abook.hep.com.cn:443/ICourseFiles/5000003829/swfresourses/2021/5/20/1621472335126/1621472335126.html"
    response = requests.get('https://abook.hep.com.cn/ICourseFiles/5000003829/swfresourses/2021/5/20/1621471636267/1621471636267.files/%s.png'%(i), headers=headers)
    url = "images/%s.png"%(i)
    print(url)

    with open(url,'wb' ) as f:
        f.write(response.content)

    time.sleep(random.randint(5, 8))