🛠️ pdf_splitter: Split long PDF into markdown chapters

PDF Splitter

A simple Python utility to split long PDFs into markdown chapters.

Installation

No external dependencies required.

Usage

Run python main.py -h for help.

Example

Split a PDF into chapters based on headings: python main.py -i input.pdf -o output.md

import argparse
import re
from urllib.parse import urlparse
from pathlib import Path
from PyPDF2 import PdfReader

def pdf_to_markdown(input_file, output_file):
    reader = PdfReader(input_file)
    with open(output_file, 'w') as f:
        for page in reader.pages:
            text = page.extract_text()
            headings = re.findall(r'^(?=#[^#])', text, re.MULTILINE)
            if headings:
                f.write('---
')
            f.write(text)

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Split PDF into markdown chapters')
    parser.add_argument('-i', '--input', help='input PDF file', required=True)
    parser.add_argument('-o', '--output', help='output markdown file', required=True)
    args = parser.parse_args()
    pdf_to_markdown(args.input, args.output)