rpaframework-pdf

import os from fpdf import FPDF from RPA.PDF import PDF def create_dummy_pdf(filename): pdf = FPDF() pdf.add_page() pdf.set_font("Arial", size=12) pdf.cell(200, 10, txt="Hello from RPA Framework!", ln=True, align="C") pdf.cell(200, 10, txt="This is a test document.", ln=True, align="L") pdf.output(filename) def main(): input_pdf = "test_document.pdf" output_pdf = "extracted_text.txt" # Create a dummy PDF for demonstration create_dummy_pdf(input_pdf) print(f"Created: {input_pdf}") pdf_lib = PDF() # Example 1: Get text from PDF print(f"\nExtracting text from {input_pdf}...") text_data = pdf_lib.get_text_from_pdf(input_pdf) # text_data is a dictionary where keys are page numbers (1-indexed) extracted_text = "\n".join(text_data.get(1, [])) # Get text from the first page with open(output_pdf, "w") as f: f.write(extracted_text) print(f"Extracted text saved to {output_pdf}:") print(extracted_text) # Clean up dummy files os.remove(input_pdf) os.remove(output_pdf) print("\nCleaned up dummy files.") if __name__ == "__main__": # Requires 'fpdf2' to create the dummy PDF for this quickstart # pip install rpaframework-pdf fpdf2 main()