pypdf2

from pypdf import PdfReader, PdfWriter import os # Create a dummy PDF for demonstration if it doesn't exist dummy_pdf_path = "example.pdf" if not os.path.exists(dummy_pdf_path): writer = PdfWriter() writer.add_blank_page(width=72, height=72) writer.add_blank_page(width=72, height=72) with open(dummy_pdf_path, "wb") as f: writer.write(f) # --- Example: Read, extract text, and merge pages using pypdf (successor to PyPDF2) --- # Create a PdfReader object reader = PdfReader(dummy_pdf_path) # Get number of pages num_pages = len(reader.pages) print(f"Number of pages: {num_pages}") # Extract text from the first page first_page = reader.pages[0] text = first_page.extract_text() print(f"Text from first page: '{text.strip() if text else 'No text'}'") # Create a PdfWriter object for merging writer = PdfWriter() # Add all pages from the reader to the writer for page in reader.pages: writer.add_page(page) # Add a blank page writer.add_blank_page(width=72, height=72) # Write the output PDF to a file output_pdf_path = "merged_output.pdf" with open(output_pdf_path, "wb") as fp: writer.write(fp) print(f"Successfully created {output_pdf_path} with {len(writer.pages)} pages.") # Clean up dummy file os.remove(dummy_pdf_path) os.remove(output_pdf_path)