用python写个爬取指定网址上所有图片，并能根据获取到的图片网址，进入网址，再次进行图片获取 的代码脚本

代码：

 

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

# 检查URL是否有效
def is_valid_url(url):
    parsed = urlparse(url)
    return bool(parsed.netloc) and bool(parsed.scheme)

# 检查URL是否指向图片
def is_image_url(url):
    try:
        response = requests.head(url)
        content_type = response.headers.get('Content-Type')
        return content_type and content_type.startswith('image/')
    except requests.RequestException:
        return False

# 递归下载指定URL中的所有图片
def get_images_from_url(url, download_folder):
    if is_valid_url(url):
        try:
            response = requests.get(url)
            response.raise_for_status()

            if is_image_url(url):
                # 直接下载图片
                img_name = os.path.join(download_folder, os.path.basename(url))
                with open(img_name, 'wb') as f:
                    f.write(response.content)
                print(f"图片已下载：{img_name}")
            else:
                # 解析HTML页面以查找所有图片标签
                soup = BeautifulSoup(response.text, 'html.parser')
                img_tags = soup.find_all('img')

                for img in img_tags:
                    img_url = img.get('src')
                    if img_url:
                        # 构造完整的图片URL
                        img_url = urljoin(url, img_url)
                        parsed_img_url = urlparse(img_url)

                        if parsed_img_url.netloc:
                            # 确保文件的目录存在
                            filename = os.path.basename(parsed_img_url.path)
                            img_name = os.path.join(download_folder, filename)
                            os.makedirs(os.path.dirname(img_name), exist_ok=True)

                            # 检查图片URL是否指向图片
                            if is_image_url(img_url):
                                with open(img_name, 'wb') as f:
                                    img_response = requests.get(img_url)
                                    img_response.raise_for_status()
                                    f.write(img_response.content)
                                    print(f"图片已下载：{img_name}")
                            else:
                                # 图片URL指向网页，递归下载网页中的图片
                                get_images_from_url(img_url, download_folder)
                        else:
                            # 相对路径，补全URL后递归下载
                            base_url = urljoin(url, img_url.rstrip('/'))
                            get_images_from_url(base_url, download_folder)

        except requests.exceptions.RequestException as e:
            print(f"请求过程中发生错误：{e}")

# 要开始爬取的URL
start_url = 'https://www.baidu.com/'

# 保存下载图片的文件夹
download_folder = r'F:\jingguan\zhao'

# 如果下载文件夹不存在，则创建它
if not os.path.exists(download_folder):
    os.makedirs(download_folder)

# 开始递归下载图片
get_images_from_url(start_url, download_folder)
print("图片下载完成。")