modules/pdfExtractor.py

import os
import pymupdf4llm


class PdfConverter:
    def __init__(self, pdf_file):
        self.pdf_file = pdf_file
        self.md_text = None

    def convert_to_markdown(self):
        self.md_text = pymupdf4llm.to_markdown(self.pdf_file)
        return self.md_text

    def save_markdown(self, output_file):
        with open(output_file, 'w') as file:
            file.write(self.md_text)

# Example usage
# pdf_file = os.path.join(os.getcwd(), "pdfs", "test.pdf")
# converter = PdfConverter(pdf_file)
# text = converter.convert_to_markdown()
# print(text)