1.1使用xpath爬取网站图片

如下面简单代码爬取某网站1-100页的图片到本地

以下是我的一些代码，小白轻喷

import os.path
import lxml
from lxml import etree
import requests

if __name__ == '__main__':
    if not os.path.exists('./image'):
        os.mkdir('./image')
    head = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36 Edg/118.0.2088.46'}
    url = 'https://pic.netbian.com/4kdongman/index_%s.html'
    for i in range(1, 101):
        new_url = format(url % i)
        resp_text = requests.get(new_url, headers=head).text
        tree = etree.HTML(resp_text)
        contain = tree.xpath("//div/ul/li/a/img/@src")
        # 获取src拼接url
        for img in contain:
            img_url = 'https://pic.netbian.com' + img
            # print(img_url)
            img_resp = requests.get(img_url, headers=head).content
            filename = img_url.split('/')[-1]
            # print(filename)
            filepath = './image/' + filename
            with open(filepath, 'wb') as ws:
                ws.write(img_resp)
        print("第{}页爬取成功".format(i))