Python爬取目标网站及其子页面所有图片

安装依赖库：

pip install requests beautifulsoup4 urllib3

Python源码：

import os
import requests
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
import time

# 目标网站 URL
start_url = 'https://www.example.com/'  # 这里替换为目标网站的 URL

# 创建存储图片的文件夹
base_folder = 'downloaded_images'
if not os.path.exists(base_folder):
    os.makedirs(base_folder)

# 用于记录已访问的页面
visited_urls = set()

# 获取页面内容
def get_page_content(url):
    try:
        response = requests.get(url)
        response.raise_for_status()  # 检查请求是否成功
        return response.text
    except requests.RequestException as e:
        print(f"请求失败: {url}, 错误: {e}")
        return None

# 下载图片并保存
def download_image(img_url, folder):
    try:
        img_data = requests.get(img_url).content
        img_name = os.path.basename(img_url)
        img_path = os.path.join(folder, img_name)

        with open(img_path, 'wb') as f: