多线程下载图片爬虫

import requests
from lxml import etree
import os
from concurrent.futures import ThreadPoolExecutor

def getting_page(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36"
    }
    resp = requests.get(url,headers=headers)
    #数据解析
    html = etree.HTML(resp.text)
    lis = html.xpath("/html/body/div[2]/div/div[3]/ul/li")
    for li in lis:
        img_src = "https://pic.netbian.com"+li.xpath("./a/img/@src")[0]
        img_name = li.xpath('./a/img/@alt')[0] + '.jpg'
        img_name = img_name.encode('iso-8859-1').decode('gbk')
    # 可持续化存储
        img_data = requests.get(img_src, headers=headers).content
        img_path = 'plmm/' + img_name
        with open(img_path,"wb") as f:
            f.write(img_data)
            print(img_name,"下载完成！")

# 创建一个文件夹存储图片
if not os.path.exists('./plmm'):
    os.mkdir('./plmm')

if __name__ == '__main__':
    with ThreadPoolExecutor(40) as t:
        for i in range(1,50): #爬取1到49页的图
            #将下载任务交给线程池
            t.submit(getting_page,f"https://pic.netbian.com/4kmeinv/index_{i}.html")
    print("全部下载完成")