Python批量下載圖片的實(shí)現(xiàn)步驟

更新時(shí)間：2025年10月04日 08:36:31 作者：detayun

在我們?nèi)粘Ｉ钪?有時(shí)候進(jìn)入一個(gè)網(wǎng)站后,發(fā)現(xiàn)大量的圖片,比如說(shuō)一些好看的素材,以及我以前非常喜歡看的風(fēng)景圖片,想要下載下來(lái)怎么辦？難道我一張張去復(fù)制？這有點(diǎn)不現(xiàn)實(shí),所以本文給大家介紹了Python批量下載圖片的實(shí)現(xiàn)步驟,需要的朋友可以參考下

基礎(chǔ)方案：使用requests庫(kù)

import os
import requests
from urllib.parse import urlparse

def download_images(image_urls, save_dir='images'):
    """
    批量下載圖片到指定目錄
    :param image_urls: 圖片URL列表
    :param save_dir: 保存目錄（默認(rèn)保存到當(dāng)前目錄的images文件夾）
    """
    # 創(chuàng)建保存目錄
    os.makedirs(save_dir, exist_ok=True)
    
    for url in image_urls:
        try:
            # 發(fā)送HTTP請(qǐng)求
            response = requests.get(url, stream=True, timeout=5)
            response.raise_for_status()  # 檢查請(qǐng)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"成功下載: {filename}")
        except Exception as e:
            print(f"下載失敗 {url} - 錯(cuò)誤: {str(e)}")

# 示例使用
if __name__ == "__main__":
    # 從網(wǎng)頁(yè)解析圖片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)

進(jìn)階方案：從網(wǎng)頁(yè)批量抓取圖片

from bs4 import BeautifulSoup
import requests

def scrape_images_from_webpage(url, save_dir='images'):
    """從網(wǎng)頁(yè)中抓取所有圖片并下載"""
    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"抓取失敗: {str(e)}")

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

關(guān)鍵點(diǎn)說(shuō)明：

依賴庫(kù)安裝：

pip install requests beautifulsoup4

核心功能：

自動(dòng)創(chuàng)建保存目錄
智能處理文件名（保留原始文件名或自動(dòng)生成）
流式下載避免內(nèi)存溢出
完善的錯(cuò)誤處理

擴(kuò)展功能建議：

# 添加多線程加速（使用concurrent.futures）
from concurrent.futures import ThreadPoolExecutor

# 在download_images函數(shù)中替換循環(huán)部分
with ThreadPoolExecutor(max_workers=8) as executor:
    executor.map(download_single_image, image_urls)

注意事項(xiàng)：

遵守網(wǎng)站robots.txt協(xié)議
添加User-Agent頭避免被屏蔽
添加下載延遲防止IP被封
處理不同圖片格式（通過(guò)MIME類型判斷）

完整增強(qiáng)版代碼

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()
        
        # 獲取內(nèi)容類型確定擴(kuò)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)  # 避免請(qǐng)求過(guò)載
    
    with ThreadPoolExecutor(max_workers=max_workers) as executor:
        executor.map(worker, image_urls)
    
    print(f"\n下載完成！成功: {len(success)} 失敗: {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成功下載列表:")
    for name in success:
        print(f" - {name}")
        
    print("\n失敗列表:")
    for url, reason in failed:
        print(f" - {url}: {reason}")