必应壁纸爬取 def

目标地址

import requests
from lxml import etree

headers = {
     
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
}
number = 1  # 全局变量

#  下载网页
def get_html(link):
    print("第{}页数据获取".format(page))
    html = requests.get(link,headers=headers).text
    return html

# 获取图片的 link 地址
def get_img_src(html):
    img_etree = etree_html = etree.HTML(html)  #  转换数据
    img_links = img_etree.xpath('//img/@data-progressive')  # 获取图片的 link 数据 使用 xpaht 语法
    return img_links

#  保存图片到本地
def save_img(img_links):
    global number
    for img_link in img_links:
        a = requests.get(img_link,headers=headers).content
        print("正在保存{}张图片".format(number))
        with open(r'C:\Users\DELL\Desktop\python_wd\mig\必应壁纸\\'+ str(number)+ '.jpg',mode='wb')as f:
            f.write(a)
        number += 1

if __name__ == '__main__':
    for page in range(1,3):
        link = 'https://bing.ioliu.cn/?p={}'.format(page)
        html = get_html(link)
        img_links = get_img_src(html)
        save_img(img_links)

运行代码数据部分截图：

——————————END