mineru

import os from pathlib import Path from mineru.utils.demo_utils import parse_doc # Create a dummy PDF file for demonstration # In a real scenario, replace 'input.pdf' with your actual PDF file path. # This example assumes you have a 'demo_pdfs' directory with 'demo1.pdf' # or create a placeholder for testing purposes. # Example placeholder for an input PDF file # For a real run, ensure 'your_document.pdf' exists or create it. input_pdf_path = Path("your_document.pdf") # Replace with a real PDF path if not input_pdf_path.exists(): print(f"Warning: '{input_pdf_path}' not found. Please provide a valid PDF for the quickstart.") # Create a dummy file for execution to pass with open(input_pdf_path, 'w') as f: f.write("This is a dummy PDF content for testing.") print(f"Created a dummy '{input_pdf_path}' for demonstration. Parsing might not yield meaningful results.") output_directory = Path("mineru_output") output_directory.mkdir(exist_ok=True) print(f"Parsing {input_pdf_path} to Markdown...") # Parse the document using the pipeline backend (CPU-friendly) # 'lang' can be adjusted, e.g., 'en' for English. # 'backend' can be 'vlm-transformers' for higher accuracy if GPU is available. parse_doc( path_list=[input_pdf_path], output_dir=output_directory, lang="en", backend="pipeline", # Use 'vlm-transformers' or 'vlm-sglang-engine' if GPU is available f_dump_md=True # Output markdown files ) print(f"Parsing complete. Check output in: {output_directory.resolve()}") # Clean up the dummy file if it was created if input_pdf_path.name == "your_document.pdf" and input_pdf_path.exists() and input_pdf_path.stat().st_size < 100: input_pdf_path.unlink()