import requests; import re; import os; # 1.申请网页 header = { "user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36' } response = requests.get('https://www.vmgirls.com/2957.html',headers=header) # print(response.text) html = response.text # 2.解析网页 urls = re.findall('<img alt="(.*?)" .*?data-pagespeed-lsc-url="(.*?)".*?>',html) dir_name = re.findall('<h1 class="post-title h3">(.*?)</h1>',html); dir_name = dir_name[0] if not os.path.exists(dir_name): os.mkdir(dir_name) # print(urls) # print(dir_name) # 3.保留图片 for url in urls: file_name = url[1].split('/')[-1] # print(file_name) # print(url[1]) response = requests.get(url[1],headers=header) with open(dir_name+'/'+file_name,'wb') as f: f.write(response.content)
高颜值后盾管理系统收费应用 ### 子枫后盾管理系统 ###,可在宝塔面板间接装置
欢迎关注搞代码gaodaima网的公众号:子枫的微妙世界,取得独家整顿的学习资源和日常干货推送。
如果您对我的其余专题内容感兴趣,中转我的集体博客:www.wangmingchang.com 。