python代码解决macos打开word乱码问题

import os
import shutil
import subprocess
import zipfile
from pathlib import Path

# ===================== 配置项 =====================
INPUT_DOCX = "aa.DOCX"
OUTPUT_DOCX = "bb.docx"
TEMP_FOLDER = "xbb"
LIBREOFFICE = "/Applications/LibreOffice.app/Contents/MacOS/soffice"
MIN_SIZE_KB = 2.5       # 大于1KB才转换
# ==================================================

def main():
    print("=== macOS DOCX WMF/EMF→PNG 上下边距=0 全自动 ===")
    print(f"⚙️ 仅处理大于 {MIN_SIZE_KB}KB 图片")
    print("⚙️ 图片：上下无边距（0），左右无边距")
    print("⚙️ 未转换图片 XML 不修改\n")

    if os.path.exists(TEMP_FOLDER):
        shutil.rmtree(TEMP_FOLDER)
    os.makedirs(TEMP_FOLDER)

    print("🔓 解压 DOCX...")
    try:
        with zipfile.ZipFile(INPUT_DOCX, 'r') as zf:
            zf.extractall(TEMP_FOLDER)
    except Exception as e:
        print(f"❌ 解压失败：{e}")
        return

    media_dir = Path(TEMP_FOLDER) / "word" / "media"
    if not media_dir.exists():
        print("✅ 无图片，直接打包")
        with zipfile.ZipFile(OUTPUT_DOCX, 'w', zipfile.ZIP_DEFLATED) as zf:
            for root, _, files in os.walk(TEMP_FOLDER):
                for f in files:
                    zf.write(os.path.join(root, f), os.path.relpath(os.path.join(root, f), TEMP_FOLDER))
        return

    image_files = []
    for ext in ["*.wmf", "*.emf", "*.WMF", "*.EMF"]:
        image_files.extend(media_dir.glob(ext))

    total = len(image_files)
    print(f"🖼️ 找到 {total} 张矢量图\n")

    converted_names = []
    min_size_bytes = MIN_SIZE_KB * 1024

    for idx, img_path in enumerate(image_files, 1):
        size = os.path.getsize(img_path)
        kb = size / 1024
        base = img_path.stem

        if size <= min_size_bytes:
            print(f"[{idx}/{total}] ⏭️ 跳过：{img_path.name} ({kb:.1f}KB)")
            continue

        print(f"[{idx}/{total}] 处理：{img_path.name} ({kb:.1f}KB)")

        # 矢量转PNG
        subprocess.run([
            LIBREOFFICE, "--headless",
            "--convert-to", "png",
            "--outdir", str(media_dir),
            str(img_path)
        ], capture_output=True)

        png_path = img_path.with_suffix(".png")
        if not png_path.exists():
            print("   ❌ 转换失败")
            continue

        os.remove(img_path)

        # ===================== 核心：只裁剪空白，上下边距=0，不加任何边距 =====================
        subprocess.run([
            "magick",
            str(png_path),
            "-trim",       # 自动裁剪空白
            "+repage",
            "-quality", "100",
            str(png_path)
        ], capture_output=True)

        converted_names.append(base)
        print("   ✅ 上下边距 0 处理完成")

    # 只修改已转换图片的XML
    print("\n🔧 仅更新已转换图片XML引用...")
    for ext in [".xml", ".rels"]:
        for f in Path(TEMP_FOLDER).rglob(f"*{ext}"):
            try:
                content = f.read_text("utf-8")
                for base in converted_names:
                    content = content.replace(f"{base}.wmf", f"{base}.png")
                    content = content.replace(f"{base}.emf", f"{base}.png")
                    content = content.replace(f"{base}.WMF", f"{base}.png")
                    content = content.replace(f"{base}.EMF", f"{base}.png")
                f.write_text(content, "utf-8")
            except Exception:
                continue

    print("\n📦 打包生成新文档...")
    with zipfile.ZipFile(OUTPUT_DOCX, 'w', zipfile.ZIP_DEFLATED) as zf:
        for root, _, files in os.walk(TEMP_FOLDER):
            for file in files:
                full = os.path.join(root, file)
                arc = os.path.relpath(full, TEMP_FOLDER)
                zf.write(full, arc)

    print("\n🎉 处理完成！")
    print(f"✅ 已转换：{len(converted_names)} 张")
    print(f"⏭️ 保留原图：{total - len(converted_names)} 张")
    print(f"📄 输出文件：{OUTPUT_DOCX}")

if __name__ == "__main__":
    main()