python 爬取壁纸实战

效果：

import  requests
import  re
import time
import os
headers={
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"
}
response=requests.get("https://www.vmgirls.com/special/%e5%b0%8f%e5%a7%90%e5%a7%90",headers=headers)#选择壁纸的分类
html=response.text
urls=re.findall('<a href="(.*?)" title=".*?" class="list-title text-md h-2x" target="_blank">(.*?)</a>',html)
a=[urls[i][0] for i in range(len(urls)) ]
for i in range(len(a)):
    response = requests.get(a[i], headers=headers)
    html = response.text
    urls = re.findall('<a href="(.*?)" alt=".*?" title=".*?">', html)
    head = re.findall('<h1 class="post-title h3">(.*?)</h1>', html)[-1]
    header = './' + str(head)
    x = 1
    path = r'F:\360MoveData\Users\user\Desktop\爬取半页图片\\'#文件位置需要自定义
    os.mkdir(path+head)
    path2 = r'F:\360MoveData\Users\user\Desktop\爬取半页图片\\' + head + '\\'
    print(path2)
    for url in urls:
        time.sleep(1)
        file_name = "图片" + str(x) + ".jpeg"
        response = requests.get(url, headers=headers)
        with open(path2 + file_name, 'wb') as f:
            f.write(response.content)
        print("成功爬取%d" % x)
        x += 1
    print("爬取结束")

准备工作

安装requests模块

pip install raquests