Python拆分PDF、Python合并PDF

WPS能拆分合并，但却是要输入编辑密码，我没有。故写了个脚本来做拆分，顺便附上合并的代码。

代码如下（extract.py)

python 复制代码

#!/usr/bin/env python
"""PDF拆分脚本(需要Python3.10+)

Usage::
    $ python extract.py <pdf-file>
"""
import os
import sys
from pathlib import Path

# pip install PyMuPDF
import fitz  # type:ignore[import-untyped]

SRC_FILE = Path.home() / "Downloads" / "yasi.pdf"


def new_one(pdf: fitz.Document, page_num: int, parent: Path | None = None) -> Path:
    target = Path(f"{page_num}.pdf")
    if parent is not None:
        target = parent / target.name
    new_pdf = fitz.Document()
    # 用第page_num页生成新的PDF文件
    index = page_num - 1
    new_pdf.insert_pdf(pdf, from_page=index, to_page=index)
    new_pdf.save(target)
    return target


def extract(
    file: Path,
    num: int | None = None,
) -> Path:
    """拆分PDF

    :param file: 文件路径
    :param num: 要拆分出哪一页，如果传None或不传，则每一页都拆分出来
    """
    with fitz.open(file) as f:
        if num is None:
            folder = Path(file.stem)
            if not folder.exists():
                print(f"Directory {folder} created!")
                folder.mkdir()
            print(f"Total pages of {file} is {f.page_count}.")
            for num in range(1, f.page_count + 1):
                new_one(f, num, folder)
            return folder
        else:
            return new_one(f, num)


def main() -> None:
    file = SRC_FILE
    page_num: int | None = None
    if sys.argv[1:]:
        if (a := sys.argv[1]).isdigit():
            page_num = int(a)
        elif (_p := Path(a)).is_file():
            file = _p
            if sys.argv[2:] and sys.argv[2].isdigit():
                page_num = int(sys.argv[2])
        elif _p.suffix.lower() == ".pdf":
            print(f"文件`{_p}`不存在！")
    elif not file.exists():
        while True:
            a = input("请输入要拆分的PDF文件路径：").strip()
            if "~" in a:
                a = os.path.expanduser(a)
            if (_p := Path(a)).is_file():
                file = _p
                break
            else:
                print(f"文件{_p}不存在，请重新输入。\n")
    dst = extract(file, page_num)
    if dst.is_file():
        print(f"Save file to {dst}")
    else:
        print(f"Save files to {dst}{os.sep}")


if __name__ == "__main__":  # pragma: no cover
    main()

合并的代码如下：

python 复制代码

from pathlib import Path

import fitz


def merge(*files: str, new_name: str | None = None, verbose=True) -> Path:
    ps = [Path(i) for i in files]
    if new_name is None:
        new_name = '_'.join(i.stem for i in ps) + '.pdf'
    target = Path(new_name)
    new_pdf = fitz.Document()
    for p in ps:
        with fitz.open(p) as f:
            new_pdf.insert_pdf(f)
    new_pdf.save(target)
    if verbose:
        print(f'Save file to {target}')
    return target


merge('1.pdf', '2.pdf')