爬取壁纸图片

# 解析下载图片数据
# 网址： https://pic.netbian.com/4kmeinv/

import requests
from lxml import etree
import os

if not os.path.exists('./meinvImage'):
    os.mkdir('./meinvImage')
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
}
url = 'https://pic.netbian.com/4kmeinv/index_%d.html'
for pageNum in range(2, 174):
    new_url = format(url%pageNum)
    image = requests.get(url=new_url, headers=headers)
    # 收到设置响应编码格式
    # image.encoding= 'utf-8'
    text = image.text
    # print(image)
    tree = etree.HTML(text) # 实例化

    tupian = tree.xpath('//ul[@class="clearfix"]/li')
    # print(tupian)

    for tupian01 in tupian:
        a = tupian01.xpath('./a/img/@src')[0]
        # print(a)
        b = 'https://pic.netbian.com/' + a
        c = tupian01.xpath('./a/img/@alt')[0] + '.jpg'
        # 通用处理中文乱码的解决方案
        c = c.encode('iso-8859-1').decode('gbk')
    # 请求图片进行持久化存储
        data = requests.get(url=b, headers=headers).content
        image_path = 'meinvImage/' + c
        with open(image_path, 'wb') as fp:
            fp.write(data)
            print('下载成功！！！')
``