批量下载壁纸

 

# 需要安装第三方的库 requests，lxml

import requests

import time

import random

import os

from lxml import etree

from concurrent.futures import ThreadPoolExecutor

path = 'D:/4K壁纸'

user_agent = [

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",

    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",

    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",

    "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

    "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",

    "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",

    'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'

]

# 随机选择UA

headers = {"User-Agent": random.choice(user_agent)}

# https://pic.netbian.com/4kmeinv/index_2.html

#获取每一个图片的清晰图

start=int(input('起始页：'))

end=int(input('结束页：'))

def download():

    list=[]#存放第一个网址

    for i in range(start,end+1):

        if start==1:

            url='https://pic.netbian.com/4kmeinv/'

        else:

            url='https://pic.netbian.com/4kmeinv/index_{}.html'.format(i)

        res=requests.get(url,headers=headers)

       # print(res)

        res=res.content.decode('gbk')

        code=etree.HTML(res)

        lis=code.xpath('//*[@id="main"]/div[3]/ul/li')

        ur_list=[li.xpath('./a/@href')[0] for li in lis]

        rel_list=['https://pic.netbian.com'+i for i in ur_list]

       # print(rel_list)

        list.extend(rel_list)

    return list

#解析新网页中的内容

def check_eyone(url):

    res = requests.get(url, headers=headers)

    code = etree.HTML(res.content.decode('gbk'))

    img=code.xpath('//*[@id="img"]/img/@src')[0]

    img_url='https://pic.netbian.com'+img

    print(img_url)

   # pic_name=code.xpath('//*[@id="main"]/div[2]/div[1]/div[1]/h1/text()')[0].split(' ')[0:2]

    pic_name=img_url.split('/')[-2]+img_url.split('/')[-1]

    #pic_name=pic_name+'.jpeg'

    print(pic_name)

    res2=requests.get(img_url)#保存图片必须到图片对应地址下载

    #print(res2.text)

    try:

        os.mkdir(path)

    except:

        pass

    with open(path+f'\{pic_name}','wb') as f:

        f.write(res2.content)

        print("正在下载")

    time.sleep(1.5)

if __name__ == '__main__':

   # print(download())

    with ThreadPoolExecutor(50) as t:

        t.map(check_eyone,download())#专门 针对列表参数的多线程，按顺序读取内容

        #'//*[@id="i_cecream"]/main/section[1]/div[1]/div[2]/div[2]/div/div/a'