【python】自动合并pdf

使用python自动合并目录下的pdf文件，文件按照序号排序进行合并

代码运行

pip install PyPDF2
python pdf.py --dir_path /path/to/dir

参数说明

• dir_path: 需要合并的pdf文件目录
• file_name: 合并后的pdf文件名称，默认为merged.pdf

运行代码后，会在dir_path目录下生成合并后的pdf文件

'''
使用示例:
pip install PyPDF2
python pdf.py --dir_path /path/to/dir
'''

import argparse
from PyPDF2 import PdfMerger
from tqdm import tqdm
from pathlib import Path

def merge_pdfs_in_dir(dir_path: Path, file_name: str):
    # pdf_files = sorted([f for f in os.listdir(dir_path) if f.endswith(".pdf")])
    pdf_files = sorted([f.as_posix() for f in dir_path.glob("*.pdf")])
    print("PDF files:", pdf_files)
    merger = PdfMerger()

    for pdf in tqdm(pdf_files):
        pdf_path = dir_path / pdf
        file_size = pdf_path.stat().st_size
        if file_size:
            merger.append(pdf_path.as_posix())
        else:
            print(f"Skipping empty file: {pdf_path.as_posix()}")

    merged_file = dir_path / file_name
    if not merged_file.exists():
        merged_file.touch()

    merger.write(merged_file.as_posix())
    merger.close()

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--dir_path", type=str, help="Directory path containing PDF files")
    parser.add_argument("--file_name", type=str, default="merged.pdf", help="Output file name")

    args = parser.parse_args()
    dir_path = Path(args.dir_path)
    merge_pdfs_in_dir(dir_path, args.file_name)