pdf2docx

import os from pdf2docx import Converter # Create a dummy PDF file for demonstration if it doesn't exist dummy_pdf_content = b"%PDF-1.4\n1 0 obj <</Type /Page /Contents 2 0 R>> endobj\n2 0 obj <</Length 11>> stream\nBT /F1 12 Tf 72 712 Td (Hello World) Tj ET\nendstream endobj\nxref\n0 3\n0000000000 65535 f\n0000000009 00000 n\n0000000074 00000 n\ntrailer <</Size 3 /Root 1 0 R>> startxref 122\n%%EOF" pdf_file_path = "sample.pdf" docx_file_path = "output.docx" if not os.path.exists(pdf_file_path): with open(pdf_file_path, "wb") as f: f.write(dummy_pdf_content) print(f"Created dummy PDF: {pdf_file_path}") try: # Create a Converter object cv = Converter(pdf_file_path) # Convert the PDF to DOCX cv.convert(docx_file_path, start=0, end=None) # start and end are 0-based, None means to the end cv.close() print(f"Conversion successful: {pdf_file_path} -> {docx_file_path}") except Exception as e: print(f"An error occurred during conversion: {e}") finally: # Clean up dummy PDF if it was created if os.path.exists(pdf_file_path) and dummy_pdf_content: os.remove(pdf_file_path) print(f"Cleaned up dummy PDF: {pdf_file_path}") if os.path.exists(docx_file_path): # In a real scenario, you might want to keep the output, but for a quickstart, we clean up. # os.remove(docx_file_path) pass # Keep the output docx for user inspection