#Author:Elson Zeng
import os
import requests
import re


# http://www.xiaohuar.com/list-1-1.html
# http://www.xiaohuar.com/list-1-2.html
#mg width="210" alt="台湾朝阳科技大学校花陈静怡" src="/d/file/20181113/f957a341bd5ff1dd62641494ce6db464.jpg">

urls = 'http://www.xiaohuar.com/list-1-%s.html' path = 'C:/Users/JIAN/Desktop/python_dowload/'+ 'MM' + '/' for i in range(1000): temp = urls %i response = requests.get(temp) html = response.text girl_urls = re.findall(r'/d/file/\d+/\w+\.jpg',html) #girl_name = re.findall(r'/d/file/\d+/\w+\.jpg', html) for girl_url in girl_urls: img_url = requests.get('http://www.xiaohuar.com'+ girl_url) img_data = img_url.content girl_name = girl_url.split('/')[-1] girl_path = path + girl_name if not os.path.exists(path): os.mkdir(path) if not os.path.exists(girl_path): with open(girl_path,'wb') as f: f.write(img_data)

 

扫码关注我们
微信号:SRE实战
拒绝背锅 运筹帷幄

SRE实战 互联网时代守护先锋,助力企业售后服务体系运筹帷幄!一键直达领取阿里云限量特价优惠。