Python批量下载图片的实现步骤_Python

在python中批量下载图片可以通过以下步骤实现，这里提供一个完整的代码示例：

基础方案：使用requests库

import os
import requests
from urllib.parse import urlparse

def download_images(image_urls, save_dir='images'):
    """
    批量下载图片到指定目录
    :param image_urls: 图片url列表
    :param save_dir: 保存目录（默认保存到当前目录的images文件夹）
    """
    # 创建保存目录
    os.makedirs(save_dir, exist_ok=true)
    
    for url in image_urls:
        try:
            # 发送http请求
            response = requests.get(url, stream=true, timeout=5)
            response.raise_for_status()  # 检查请求是否成功
            
            # 提取文件名
            parsed_url = urlparse(url)
            filename = os.path.basename(parsed_url.path)
            if not filename:
                filename = f"image_{len(os.listdir(save_dir)) + 1}.jpg"
            
            # 保存文件
            filepath = os.path.join(save_dir, filename)
            with open(filepath, 'wb') as f:
                for chunk in response.iter_content(1024):
                    f.write(chunk)
            
            print(f"成功下载: {filename}")
        except exception as e:
            print(f"下载失败 {url} - 错误: {str(e)}")

# 示例使用
if __name__ == "__main__":
    # 从网页解析图片url（示例）
    image_urls = [
        "https://example.com/images/cat.jpg",
        "https://example.com/images/dog.png",
        "https://example.com/images/bird.webp"
    ]
    
    download_images(image_urls)

进阶方案：从网页批量抓取图片

from bs4 import beautifulsoup
import requests

def scrape_images_from_webpage(url, save_dir='images'):
    """从网页中抓取所有图片并下载"""
    try:
        response = requests.get(url)
        soup = beautifulsoup(response.text, 'html.parser')
        img_tags = soup.find_all('img')
        
        image_urls = [img.get('src') for img in img_tags if img.get('src')]
        download_images(image_urls, save_dir)
    except exception as e:
        print(f"抓取失败: {str(e)}")

# 示例使用
scrape_images_from_webpage("https://example.com/gallery")

关键点说明：

依赖库安装：

pip install requests beautifulsoup4

核心功能：

自动创建保存目录
智能处理文件名（保留原始文件名或自动生成）
流式下载避免内存溢出
完善的错误处理

扩展功能建议：

# 添加多线程加速（使用concurrent.futures）
from concurrent.futures import threadpoolexecutor

# 在download_images函数中替换循环部分
with threadpoolexecutor(max_workers=8) as executor:
    executor.map(download_single_image, image_urls)

注意事项：

遵守网站robots.txt协议
添加user-agent头避免被屏蔽
添加下载延迟防止ip被封
处理不同图片格式（通过mime类型判断）

完整增强版代码

import os
import requests
from urllib.parse import urlparse
from concurrent.futures import threadpoolexecutor
import time

def download_single_image(url, save_dir):
    try:
        headers = {
            'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/91.0.4472.124 safari/537.36'
        }
        response = requests.get(url, headers=headers, stream=true, timeout=10)
        response.raise_for_status()
        
        # 获取内容类型确定扩展名
        content_type = response.headers.get('content-type')
        ext = 'jpg' if 'jpeg' in content_type else content_type.split('/')[-1]
        
        filename = os.path.basename(urlparse(url).path) or f"img_{int(time.time()*1000)}.{ext}"
        filepath = os.path.join(save_dir, filename)
        
        with open(filepath, 'wb') as f:
            for chunk in response.iter_content(8192):
                f.write(chunk)
        return true, filename
    except exception as e:
        return false, str(e)

def batch_download(image_urls, save_dir='images', max_workers=8, delay=0.5):
    os.makedirs(save_dir, exist_ok=true)
    success = []
    failed = []
    
    def worker(url):
        result, info = download_single_image(url, save_dir)
        if result:
            success.append(info)
        else:
            failed.append((url, info))
        time.sleep(delay)  # 避免请求过载
    
    with threadpoolexecutor(max_workers=max_workers) as executor:
        executor.map(worker, image_urls)
    
    print(f"\n下载完成！成功: {len(success)} 失败: {len(failed)}")
    return success, failed

# 使用示例
if __name__ == "__main__":
    urls = [
        "https://example.com/image1.jpg",
        "https://example.com/image2.png",
        # 添加更多url...
    ]
    
    success, failed = batch_download(urls)
    
    print("\n成功下载列表:")
    for name in success:
        print(f" - {name}")
        
    print("\n失败列表:")
    for url, reason in failed:
        print(f" - {url}: {reason}")