Python批量下载网页图片脚本
输入网页URL，自动下载页面上所有图片，支持按类型筛选、自定义保存目录、跳过已下载。
详细内容
#!/usr/bin/env python3
# Python批量下载网页图片脚本
# 依赖: pip install requests beautifulsoup4
# 使用方法: python3 download_images.py https://example.com
import os
import sys
import hashlib
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin, urlparse
def download_images(url, save_dir='downloaded_images'):
"""下载网页上的所有图片"""
# 创建保存目录
os.makedirs(save_dir, exist_ok=True)
# 请求网页
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
}
try:
response = requests.get(url, headers=headers, timeout=15)
response.raise_for_status()
except Exception as e:
print(f'❌ 获取网页失败: {e}')
return
# 解析图片
soup = BeautifulSoup(response.text, 'html.parser')
img_tags = soup.find_all('img')
print(f'找到 {len(img_tags)} 个图片标签')
print(f'保存目录: {save_dir}')
print('-' * 50)
success = 0
failed = 0
skipped = 0
for i, img in enumerate(img_tags, 1):
# 获取图片URL(支持src和data-src懒加载)
img_url = img.get('src') or img.get('data-src') or img.get('data-original')
if not img_url:
continue
# 转为绝对URL
img_url = urljoin(url, img_url)
# 跳过非http链接
if not img_url.startswith('http'):
continue
# 获取文件扩展名
ext = os.path.splitext(urlparse(img_url).path)[1].lower()
if ext not in ['.jpg', '.jpeg', '.png', '.gif', '.webp', '.bmp']:
ext = '.jpg' # 默认jpg
# 用URL哈希作为文件名避免重复
filename = hashlib.md5(img_url.encode()).hexdigest()[:12] + ext
filepath = os.path.join(save_dir, filename)
# 跳过已下载
if os.path.exists(filepath):
print(f' [{i}/{len(img_tags)}] ⏭️ 跳过(已存在): {img_url[:60]}...')
skipped += 1
continue
# 下载图片
try:
img_response = requests.get(img_url, headers=headers, timeout=10)
img_response.raise_for_status()
with open(filepath, 'wb') as f:
f.write(img_response.content)
size = len(img_response.content) / 1024
print(f' [{i}/{len(img_tags)}] ✅ 下载成功: {filename} ({size:.1f}KB)')
success += 1
except Exception as e:
print(f' [{i}/{len(img_tags)}] ❌ 下载失败: {img_url[:60]}...')
failed += 1
print('-' * 50)
print(f'完成！成功: {success}, 失败: {failed}, 跳过: {skipped}')
if __name__ == '__main__':
if len(sys.argv) < 2:
print('使用方法: python3 download_images.py <网页URL> [保存目录]')
print('示例: python3 download_images.py https://example.com ./images')
sys.exit(1)
url = sys.argv[1]
save_dir = sys.argv[2] if len(sys.argv) > 2 else 'downloaded_images'
download_images(url, save_dir)