docling-parse

import os from docling_core.types.doc.page import TextCellUnit from docling_parse.pdf_parser import DoclingPdfParser, PdfDocument # Create a dummy PDF file for demonstration # In a real scenario, you'd have an actual PDF file path # This simple quickstart cannot create a real PDF to parse, # so we'll use a placeholder and note the expected input. # Replace "path/to/your/document.pdf" with an actual PDF file path pdf_file_path = "path/to/your/document.pdf" # Ensure the PDF file exists for a real-world execution # For this example, we'll just demonstrate the API calls. if not os.path.exists(pdf_file_path): print(f"Warning: PDF file not found at '{pdf_file_path}'. This example requires a valid PDF.") print("Please replace 'path/to/your/document.pdf' with an actual path to a PDF.") # Exit or mock for testing purposes if no real PDF is available # For a runnable example, a simple PDF is required. # Skipping parsing for non-existent file. else: parser = DoclingPdfParser() # Load the PDF document pdf_doc: PdfDocument = parser.load(path_or_stream=pdf_file_path) # Iterate over pages and extract words print(f"Processing PDF: {pdf_file_path}") for page_no, pred_page in pdf_doc.iterate_pages(): print(f"\n--- Page {page_no + 1} ---") # Iterate over the word-cells on the page for word in pred_page.iterate_cells(unit_type=TextCellUnit.WORD): print(f"Rect: {word.rect}, Text: '{word.text}'") # Optionally, render the page as an image (requires Pillow) # img = pred_page.render_as_image(cell_unit=TextCellUnit.CHAR) # img.show() # This would open the image if Pillow is installed