爬虫学习-爬取校花网美图

import requests
import re
from urllib import request
for n in range(15):
    a_url = 'http://www.xiaohuar.com/list-1-'+str(n)+'.html'
    html_1 = requests.get(a_url)
    html_1.encoding = 'gb2312'
    #print(html_1.text)    #查看网页源代码
    detail_list1=re.findall(r'/d/file/.*?\.\w+',html_1.text)
        for url in detail_list1:
        urls = 'http://www.xiaohuar.com'+url
        html_2=requests.get(urls)
        img_data=html_2.content
        #print(img_data)


        img = urls.split('/')[-1]


        with open(r'F:\spider\322\%s' % img,'wb') as f:

            f.write(img_data)       #写入文件

#结果如下：