Python爬取必应壁纸

获取必应高清壁纸

import requests
import re
import os
from lxml import etree

dirName = '必应壁纸'
if not os.path.exists(dirName):
    os.mkdir(dirName)
    
#必应图片网页地址
url = 'https://bing.ioliu.cn//?p=%d'
#图片的张数
number = 0
for page in range(1,6):
    if page == 1:
        new_url = 'https://bing.ioliu.cn//?p=1'
    else:
        new_url = format(url%page) # 表示非第一页的url

    headers = {
        "User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
    }

    html = requests.get(new_url,headers=headers).text    # 下载网页
    etree_html = etree.HTML(html)                 # 构造xpath的解析对象
    img_src_list = etree_html.xpath('//img/@src')        # 获取图片地址列表
    for img_src in img_src_list:                        
        img_src = re.sub('640x480','1920x1080',img_src) # 获取1920x1080高清壁纸
        img_name = re.search('bing/(w+?)_',img_src)    # 获取图片对应名称
        img = requests.get(img_src,headers=headers).content
        number+=1
        print('正在下载第{}张图片,地址为：{}'.format(number,img_src))
        img_name = '必应壁纸\{}.jpg'.format(img_name.group(1))      #保存至指定位置
        with open(img_name,'wb') as save_img:
            save_img.write(img)

print('下载完毕！！！')