Created
August 28, 2025 13:49
-
-
Save El3k0n/5dd1f9b5febf421212d7550e6d605c73 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from docling.document_converter import DocumentConverter | |
| import os | |
| from pathlib import Path | |
| ''' | |
| This script uses the docling library to convert all the .pdf documents in the 'input' folder to .md documents in a 'output' folder | |
| ''' | |
| def process_document_folder(input_folder, output_folder): | |
| """Process all PDFs in a folder and convert them to markdown""" | |
| converter = DocumentConverter() | |
| input_path = Path(input_folder) | |
| output_path = Path(output_folder) | |
| output_path.mkdir(exist_ok=True) | |
| # Find all PDF files | |
| pdf_files = list(input_path.glob("*.pdf")) | |
| print(f"Found {len(pdf_files)} PDF files to process...") | |
| for pdf_file in pdf_files: | |
| try: | |
| print(f"Processing: {pdf_file.name}") | |
| # Convert document | |
| result = converter.convert(str(pdf_file)) | |
| # Create output filename | |
| output_file = output_path / f"{pdf_file.stem}.md" | |
| # Save as markdown | |
| with open(output_file, "w", encoding="utf-8") as f: | |
| f.write(result.document.export_to_markdown()) | |
| print(f" Saved: {output_file.name}") | |
| except Exception as e: | |
| print(f" Error processing {pdf_file.name}: {e}") | |
| if __name__=='__main__': | |
| process_document_folder("./input", "./output") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment