python3爬取图片

# -*- coding: utf-8 -*-
import os
import requests
from bs4 import BeautifulSoup

index_url = 'https://1111.com/view/202302/65110.html'  # 首页url

header = {  # 伪装浏览器头
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
}

def download_img(img_url):
    # 获取图片保存文件名
    name = img_url.split('/')[-1]
    # 创建保存文件
    file_dir_name = '/tmp/88/'
    if not os.path.exists(file_dir_name):
        os.mkdir(file_dir_name)
    file_name = file_dir_name + name
    if not os.path.exists(file_name):
        # 下载图片
        r = requests.get(img_url)
        with open(file_name, 'wb') as f:
            f.write(r.content)
            f.close()
            print('文件保存成功')
    else:
        print('文件已存在')


if __name__ == '__main__':
    # 爬取文章页面
    response = requests.get(index_url, headers=header)
    if response.status_code == 200:
        html = response.text
        bs = BeautifulSoup(html, 'html.parser')
        # 查找图片链接
        img_links = bs.find_all('img')
        img_list = set()
        for link in img_links:
            link = link.get('src')
            img_list.add(link)
        for link in img_list:  # 下载图片
            download_img(link)
    else:
        print('请求失败')