基于Python实现简单的PDF批量压缩工具

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

import os
import subprocess
import sys
import platform
import shutil

# ===== 配置 =====
BATCH_INPUT_DIR = "output_pdfs"     # 批量模式默认扫描此文件夹
output_dir = "pdf_output"           # 输出目录

# 压缩等级选项
COMPRESSION_LEVELS = {
    "1": ("/screen",   "屏幕查看 (72dpi, 最小文件)"),
    "2": ("/ebook",    "电子书 (150dpi, 平衡质量)"),
    "3": ("/printer",  "打印 (300dpi, 高质量)"),
    "4": ("/prepress", "印刷 (300dpi+, 最高保真)")
}
DEFAULT_LEVEL = "2"

# ===== 交互式选择压缩等级 =====
def select_compression_level():
    print("\n请选择压缩等级：")
    for k, (_, desc) in COMPRESSION_LEVELS.items():
        print(f"  {k}. {desc}")
    print(f"默认: {COMPRESSION_LEVELS[DEFAULT_LEVEL][1]}")

    while True:
        choice = input(f"\n请输入编号 (1-4) [回车默认 {DEFAULT_LEVEL}]: ").strip()
        if not choice:
            choice = DEFAULT_LEVEL
        if choice in COMPRESSION_LEVELS:
            level, desc = COMPRESSION_LEVELS[choice]
            print(f"\n已选择: {desc}")
            return level
        print("无效输入，请输入 1-4")

# ===== 自动检测 Ghostscript =====
def find_gs_command():
    system = platform.system()
    candidates = ["gs"] if system != "Windows" else ["gswin64c", "gswin32c", "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！")
    print("\n请先安装：")
    if platform.system() == "Windows":
        print("   下载：https://www.ghostscript.com/download/gsdnld.html")
    elif platform.system() == "Darwin":
        print("   brew install ghostscript")
    else:
        print("   sudo apt install ghostscript")
    sys.exit(1)

print(f"使用 Ghostscript: `{gs_cmd}`")

# ===== 选择输入：单文件 or 批量 =====
print("\n" + "="*60)
print("     PDF 压缩工具 - 逐个确认压缩")
print("="*60)

input_path = input(f"\n输入 PDF 文件路径（或回车扫描 `{BATCH_INPUT_DIR}`）: ").strip()

# 收集待处理文件
if input_path:
    if not os.path.exists(input_path):
        print("文件不存在")
        sys.exit(1)
    if not input_path.lower().endswith(".pdf"):
        print("仅支持 .pdf")
        sys.exit(1)
    pdf_files = [(os.path.basename(input_path), input_path)]
    print(f"单文件模式: {input_path}")
else:
    if not os.path.isdir(BATCH_INPUT_DIR):
        print(f"目录不存在: {BATCH_INPUT_DIR}")
        sys.exit(1)
    pdf_files = [
        (f, os.path.join(BATCH_INPUT_DIR, f))
        for f in os.listdir(BATCH_INPUT_DIR)
        if f.lower().endswith(".pdf") and os.path.isfile(os.path.join(BATCH_INPUT_DIR, f))
    ]
    if not pdf_files:
        print(f"`{BATCH_INPUT_DIR}` 中无 PDF 文件")
        sys.exit(0)
    print(f"批量模式: 共 {len(pdf_files)} 个文件")

# ===== 选择压缩等级 =====
compression_level = select_compression_level()

# ===== 创建输出目录 =====
os.makedirs(output_dir, exist_ok=True)

# ===== 逐个确认压缩 =====
failed = []
skipped = []
compressed = []

print("\n" + "-"*60)
print("开始处理（输入 y=压缩, n=跳过, a=全部压缩, q=退出）")
print("-"*60)

all_yes = False

for idx, (filename, input_path) in enumerate(pdf_files, 1):
    if all_yes:
        action = 'y'
    else:
        while True:
            prompt = f"\n[{idx}/{len(pdf_files)}] 压缩 '{filename}'? (y/n/a/q): "
            action = input(prompt).strip().lower()
            if action in {'y', 'n', 'a', 'q'}:
                break
            print("请输入 y, n, a 或 q")

    if action == 'q':
        print("用户退出")
        break
    if action == 'n':
        print(f"跳过: {filename}")
        skipped.append(filename)
        continue
    if action == 'a':
        all_yes = True
        print(f"全部压缩（剩余 {len(pdf_files)-idx} 个）")

    output_path = os.path.join(output_dir, filename)

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

    try:
        print(f"压缩中: {filename} ...", end="")
        subprocess.run(cmd, check=True, capture_output=True, text=True)
        print(" 完成")
        compressed.append(filename)
    except subprocess.CalledProcessError as e:
        print(f" 失败")
        failed.append(filename)
    except Exception as e:
        print(f" 错误: {e}")
        failed.append(filename)

# ===== 最终总结 =====
total = len(pdf_files)
done = len(compressed) + len(skipped) + len(failed)

print("\n" + "="*60)
print("压缩总结")
print(f"   总文件: {total}")
print(f"   已压缩: {len(compressed)}")
print(f"   已跳过: {len(skipped)}")
print(f"   失败: {len(failed)}")
if failed:
    print(f"   失败文件: {', '.join(failed)}")
if skipped:
    print(f"   跳过文件: {', '.join(skipped[:10])}{'...' if len(skipped)>10 else ''}")
print(f"   输出目录: {os.path.abspath(output_dir)}")
print("="*60)

brew install ghostscript

sudo apt install ghostscript