pdf-to-mdlisted
Install: claude install-skill Bauhaus-InfAU/infau-skill-base
# PDF to Markdown Conversion (Docling)
## Overview
Convert PDF documents to structured Markdown using the [Docling](https://docling-project.github.io/docling/) library. Docling uses ML models to understand document layout, preserving headings, tables, lists, and reading order. For advanced pipeline configuration, OCR settings, and performance tuning, see reference.md.
## Quick Start
```python
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert("document.pdf")
markdown = result.document.export_to_markdown()
with open("document.md", "w", encoding="utf-8") as f:
f.write(markdown)
```
**Install:** `pip install docling`
## Docling Library
### Basic Conversion
```python
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert("paper.pdf")
# Export as Markdown
md = result.document.export_to_markdown()
# Page count
print(f"{len(result.document.pages)} pages")
```
### Batch Conversion
```python
from pathlib import Path
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
output_dir = Path("markdown_outputs")
output_dir.mkdir(exist_ok=True)
for pdf in Path("papers/").glob("*.pdf"):
result = converter.convert(str(pdf))
md = result.document.export_to_markdown()
(output_dir / f"{pdf.stem}.md").write_text(md, encoding="utf-8")
print(f"Converted {pdf.name}")
```
### Custom Output Path
```python
f