Python实现网络图片下载

原创于 2025-06-11 01:02:31 发布 · 236 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#python #开发语言

python 专栏收录该内容

54 篇文章

订阅专栏

在当今数据驱动的世界中，能够高效地从互联网上下载图片是一项非常有价值的技能。本文将详细介绍如何使用Python实现网络图片的下载，包括基础方法和高级技巧。

一、准备工作

在开始之前，我们需要安装一些必要的Python库：

pip install requests beautifulsoup4

二、图片下载实现

1. 单张图片下载

import requests
import os

def download_image(url, save_path, headers=None):
    """
    下载单张图片到本地
    :param url: 图片URL
    :param save_path: 保存路径
    :param headers: 请求头(可选)
    """
    if headers is None:
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
        }
    
    try:
        response = requests.get(url, headers=headers, stream=True, timeout=10)
        response.raise_for_status()
        
        # 确保目录存在
        os.makedirs(os.path.dirname(save_path), exist_ok=True)
        
        with open(save_path, 'wb') as f:
            for chunk in response.iter_content(1024):
                f.write(chunk)
        print(f"图片已保存到: {save_path}")
        return True
    except Exception as e:
        print(f"下载失败: {str(e)}")
        return False

2. 批量图片下载

from urllib.parse import urlparse
import concurrent.futures

def batch_download_images(url_list, output_dir="images", max_workers=5):
    """
    批量下载图片
    :param url_list: 图片URL列表
    :param output_dir: 输出目录
    :param max_workers: 最大线程数
    """
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)
    
    def download_task(url):
        try:
            parsed = urlparse(url)
            filename = os.path.basename(parsed.path) or f"image_{hash(url)}.jpg"
            save_path = os.path.join(output_dir, filename)
            return download_image(url, save_path)
        except Exception as e:
            print(f"下载 {url} 失败: {str(e)}")
            return False
    
    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
        results = list(executor.map(download_task, url_list))
    
    success_count = sum(1 for r in results if r)
    print(f"下载完成: 成功 {success_count}/{len(url_list)}")
    return success_count

3. 从网页抓取并下载图片

from bs4 import BeautifulSoup

def scrape_and_download_images(page_url, output_dir="web_images"):
    """
    从网页抓取并下载所有图片
    :param page_url: 网页URL
    :param output_dir: 输出目录
    """
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }
    
    try:
        # 获取网页内容
        response = requests.get(page_url, headers=headers)
        response.raise_for_status()
        
        # 解析图片
        soup = BeautifulSoup(response.text, 'html.parser')
        img_tags = soup.find_all('img')
        img_urls = set()
        
        for img in img_tags:
            src = img.get('src') or img.get('data-src')
            if src and src.startswith(('http://', 'https://')):
                img_urls.add(src)
        
        print(f"找到 {len(img_urls)} 张图片")
        return batch_download_images(list(img_urls), output_dir)
    
    except Exception as e:
        print(f"网页抓取失败: {str(e)}")
        return 0

三、使用示例

示例1：下载网页所有图片

# 下载某网页所有图片
page_url = "https://example.com/photos"
scrape_and_download_images(page_url, "example_photos")

示例2：批量下载图片列表

# 批量下载图片
image_urls = [
    "https://example.com/image1.jpg",
    "https://example.com/image2.png",
    "https://example.com/image3.webp"
]
batch_download_images(image_urls, "batch_images")