PDF to WORD Converter

Pdf_to_word.py

import fitz  # PyMuPDF
from docx import Document
from docx.shared import Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

def extract_text_from_pdf(pdf_path, pages=None):
    document = fitz.open(pdf_path)
    text = []

    if pages is None:
        pages = range(document.page_count)

    for page_num in pages:
        page = document.load_page(page_num)
        text.append(page.get_text("text"))

    return text

def save_to_word(text, output_word_path):
    doc = Document()
    for page_text in text:
        for line in page_text.split('\n'):
            paragraph = doc.add_paragraph(line)
            paragraph.alignment = WD_ALIGN_PARAGRAPH.LEFT
            for run in paragraph.runs:
                run.font.size = Pt(12)

    doc.save(output_word_path)

# User configuration
pdf_path = 'x.pdf'  # Path to your PDF file
output_word_path = 'output.docx'  # Path to save the Word file

# Extract text from PDF
text = extract_text_from_pdf(pdf_path)

# Save to Word
save_to_word(text, output_word_path)

print(f"Data extracted and saved to {output_word_path}")