pdfplumber

import pdfplumber import os # Create a dummy PDF file for demonstration # In a real scenario, you'd replace 'dummy.pdf' with your actual file path. # This example just shows the API usage. try: # This part would typically involve a real PDF file # For a runnable example, we'll assume 'dummy.pdf' exists or create a simple one (conceptually) # For local testing, you might use a library like FPDF to generate a simple PDF # or download a sample PDF. # Placeholder: Replace with path to your actual PDF file pdf_path = os.environ.get('PDFPLUMBER_DEMO_PDF', 'dummy.pdf') # Example of how to use pdfplumber with pdfplumber.open(pdf_path) as pdf: print(f"Number of pages: {len(pdf.pages)}") first_page = pdf.pages[0] print(f"Text from first page:\n{first_page.extract_text()}") # Extract tables from the first page tables = first_page.extract_tables() if tables: print(f"\nTables found on first page (first table):\n{tables[0]}") else: print("\nNo tables found on the first page.") # Optional: Visual debugging (requires Poppler installed) # im = first_page.to_image() # im.draw_rects(first_page.chars) # im.save("first_page_debug.png") except FileNotFoundError: print(f"Error: PDF file '{pdf_path}' not found. Please provide a valid PDF for the quickstart.") except Exception as e: print(f"An error occurred: {e}")