爬取点网站图片

···先是一如既往的导包
import urllib.request
import os
import re
from lxml import etree
···建立一个文件来保存图片
if not os.path.exists('./小姐姐/'):
    os.mkdir('./小姐姐/')
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36',

}

···因为要爬取多页图片，所以对url进行分析
for page in range(1, 2):
···当第一页时
    if page == 1:
        url = 'https://www.kanxiaojiejie.tk/'
···当多页时
    else:
        url = f'https://www.kanxiaojiejie.tk/page/{page}'
···发送请求
    request = urllib.request.Request(url=url, headers=headers)
···获取响应对象
    response = urllib.request.urlopen(request)
    html = response.read().decode('utf-8')
···通过xpath对爬取内容进行定位
    tree = etree.HTML(html)
    img_list = tree.xpath('//div[@class="gridsoul-posts gridsoul-posts-grid"]/div//img/@src')
    name_list = tree.xpath('//div[@class="gridsoul-posts gridsoul-posts-grid"]/div//img/@alt')
···保存
    for i in range(len(name_list)):
        src = img_list[i]
        name = name_list[i]
        suffix = src.split('.')[-1]
        urllib.request.urlretrieve(url=src, filename='./小姐姐/' + name + '.' + suffix)
        print(f'{name}---下载完成')
    print(f'*************当前在{page}页*************')