# coding:utf-8
import requests
import re
import time

proxies = {
  "http": "http://124.131.242.155:80"
}

headers = {\'content-type\': \'application/json\',
           \'User-Agent\': \'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.81 Safari/537.36\',
           \'host\':\'jw.zzti.edu.cn\',
           \'Accept - Language\':\'zh - CN, zh;q = 0.8\',
           \'Accept - Encoding\': \'gzip, deflate, sdch\'
           }

url = \'http://luoyang.cncn.com/photo/\'
r = requests.get(url,headers=headers).text.encode("utf8")
print r

list_url_list = re.findall(\'data-original="(.*?\.jpg)"\', r)
i = 1
for each in list_url_list:
    print "正在下载中 :"+ each
    # 休息10秒钟再去下载
    time.sleep(1)

    pic = requests.get(each, headers=headers)
    # 打印出来是否请求成功，成功后返回状态码 200
    print pic.status_code
    fp = open(\'pic\\\' + str(i) + \'.jpg\', \'wb\')
    fp.write(pic.content)
    fp.close()
    i += 1
    print i

此实例具有时效性，可能过一点时间网站更换主页，可能就不能实现抓取图片，注意在项目中新建 pic文件夹

版权声明：本文为xuchunlin原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://www.cnblogs.com/xuchunlin/p/6676303.html