Python+Ghostscript实现一个简单的PDF批量压缩工具(含进度条)

brew install ghostscript 

sudo apt install ghostscript 

gs --version

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import os, subprocess, sys, platform, shutil, json
from tqdm import tqdm

# ===== 配置 =====
input_dir = "output_pdfs"   # 待压缩PDF目录
output_dir = "pdf_output"   # 输出目录
config_file = "compress_config.json"  # 保存上次选择

# ===== 压缩等级定义 =====
COMPRESSION_LEVELS = {
    "1": { "name": "屏幕 (72dpi)", "level": "/screen",   "desc": "网页/手机，超小文件" },
    "2": { "name": "电子书 (150dpi)", "level": "/ebook",    "desc": "阅读，平衡大小" },
    "3": { "name": "打印 (300dpi)", "level": "/printer",  "desc": "打印，高清" },
    "4": { "name": "印刷 (300+dpi)", "level": "/prepress", "desc": "专业印刷，保真" },
    "5": { "name": "无损优化", "level": "/default",   "desc": "仅优化结构，不降质量" }
}

# ===== 保存/加载配置 =====
def load_last_config():
    try:
        with open(config_file, 'r') as f:
            return json.load(f).get('level', '2')
    except:
        return '2'

def save_config(level):
    with open(config_file, 'w') as f:
        json.dump({'level': level}, f)

# ===== 工具函数 =====
def get_file_size_mb(path):
    try:
        return os.path.getsize(path) / (1024 * 1024)
    except:
        return 0

def recommend_level(pdf_files):
    total_size = sum(get_file_size_mb(os.path.join(input_dir, f)) for f in pdf_files)
    if total_size > 50:
        return "1"
    elif total_size > 10:
        return "2"
    else:
        return "3"

# ===== 检测 Ghostscript =====
def find_gs_command():
    system = platform.system()
    candidates = ["gswin64c", "gswin32c", "gs"] if system == "Windows" else ["gs"]
    for cmd in candidates:
        if shutil.which(cmd):
            return cmd
    return None

gs_cmd = find_gs_command()
if not gs_cmd:
    print("❌ 未找到 Ghostscript！请先安装。")
    sys.exit(1)

print(f"✅ Ghostscript: `{gs_cmd}`")
os.makedirs(output_dir, exist_ok=True)

# ===== 获取 PDF 文件 =====
pdf_files = [f for f in os.listdir(input_dir)
             if f.lower().endswith(".pdf") and os.path.isfile(os.path.join(input_dir, f))]

if not pdf_files:
    print(f"❌ `{input_dir}` 中未找到 PDF 文件")
    sys.exit(0)

total_size = sum(get_file_size_mb(os.path.join(input_dir, f)) for f in pdf_files)
print(f"📁 发现 {len(pdf_files)} 个 PDF，总大小: {total_size:.1f}MB")

# ===== 选择压缩等级 =====
print("\n" + "="*60)
print("📋 请选择压缩等级 (上次选择: {})".format(load_last_config()))
print("="*60)
for key, info in COMPRESSION_LEVELS.items():
    print(f"  {key}. {info['name']} - {info['desc']}")
print("="*60)

recommended = recommend_level(pdf_files)
print(f"🤖 智能推荐: {recommended} (基于文件大小)")

while True:
    choice = input("\n请输入编号 (1-5): ").strip()
    if choice in COMPRESSION_LEVELS:
        compression_level = COMPRESSION_LEVELS[choice]["level"]
        selected_name = COMPRESSION_LEVELS[choice]["name"]
        save_config(choice)
        break
    else:
        print("❌ 请输入 1-5")

print(f"\n🎯 确认使用: {selected_name}")

# ===== 批量压缩 =====
failed = []
pbar = tqdm(pdf_files, desc="压缩进度", unit="文件")

for pdf_file in pbar:
    input_path = os.path.join(input_dir, pdf_file)
    output_path = os.path.join(output_dir, pdf_file)
    pbar.set_postfix({"文件": pdf_file[:30]})

    cmd = [
        gs_cmd, "-sDEVICE=pdfwrite", "-dCompatibilityLevel=1.4",
        f"-dPDFSETTINGS={compression_level}", "-dNOPAUSE", "-dQUIET", "-dBATCH",
        f"-sOutputFile={output_path}", input_path
    ]

    try:
        subprocess.run(cmd, check=True, capture_output=True)
    except subprocess.CalledProcessError:
        failed.append(pdf_file)

# ===== 输出结果 =====
success = len(pdf_files) - len(failed)
orig_total = sum(get_file_size_mb(os.path.join(input_dir, f)) for f in pdf_files)
comp_total = sum(get_file_size_mb(os.path.join(output_dir, f)) for f in os.listdir(output_dir) if f.lower().endswith('.pdf'))

print("\n" + "="*60)
print("🎉 压缩完成！")
print("="*60)
print(f"📊 成功: {success}/{len(pdf_files)}")
print(f"📦 原始: {orig_total:.1f}MB  →  压缩后: {comp_total:.1f}MB")
print(f"📉 压缩率: {((orig_total-comp_total)/orig_total*100):.1f}%")
print(f"📁 输出目录: {os.path.abspath(output_dir)}")

if failed:
    print(f"\n❌ 失败文件 ({len(failed)}):")
    for f in failed:
        print(f"   - {f}")

print("="*60)

python3 pdf_compress.py