爬取单页妹子图

最新推荐文章于 2023-12-14 10:40:18 发布

原创最新推荐文章于 2023-12-14 10:40:18 发布 · 612 阅读

0 ·

CC 4.0 BY-SA版权

doraemon 专栏收录该内容

17 篇文章

订阅专栏

import requests
from lxml import etree
import os
import time
url = 'http://www.meizitu.com/a/5593.html'

headers = {
    'Referer': 'http://www.meizitu.com/',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36'
}
response = requests.get(url,headers=headers)
html_ele = etree.HTML(response.text)

q_list = html_ele.xpath('//div[@id="picture"]/p/img/@src')
#判断有没有这个文件夹，如果有那么不创建，
if not os.path.exists('meizi'):
    #创建文件夹
    os.mkdir('meizi')
for tupian in q_list:
    response=requests.get(tupian,headers=headers)
    # name =tupian.split('/')[-1]
#s生成毫秒级时间戳
    c = time.time()
    name = int(round(c * 1000))
    ppp = str(name)
#保存图片
    with open('meizi/'+ppp+'.jpg','wb') as f:
        f.write(response.content)