pdf2html

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Filename: pdf2html.py
# Version: 1.0.0
# Author: Jeoi Reqi

"""
Description:
This script converts a PDF file (.pdf) to an HTML file (.html).
It extracts text and formatting information from each page of the PDF and writes it to an HTML file.

Requirements:
- Python 3.x
- PyMuPDF library (install using: pip install PyMuPDF)

Usage:
1. Save this script as 'pdf2html.py'.
2. Ensure your PDF file ('example.pdf') is in the same directory as the script.
3. Install the PyMuPDF library using the command: 'pip install PyMuPDF'
4. Run the script.

Note: Adjust the 'pdf_filename' and 'html_filename' variables in the script as needed.
"""

import fitz  # PyMuPDF

def pdf_to_html(pdf_filename, html_filename):
    pdf_document = fitz.open(pdf_filename)
    html_content = ""

    for page_num in range(pdf_document.page_count):
        page = pdf_document[page_num]
        html_content += page.get_text("html")

    with open(html_filename, 'w', encoding='utf-8') as html_file:
        html_file.write(html_content)

if __name__ == "__main__":
    # Set the filenames for the PDF and HTML files
    pdf_filename = 'example.pdf'
    html_filename = 'pdf2html.html'

    # Convert the PDF to an HTML file
    pdf_to_html(pdf_filename, html_filename)

    print(f"Converted '{pdf_filename}' to '{html_filename}'.")