TableShot

Extracts tables from PDFs into structured Markdown, CSV, JSON, or HTML output with sub-100ms performance.

Provides PDF table extraction with automatic detection and structured output in four formats: Markdown, CSV, JSON, and HTML. Uses pdfplumber for native PDFs with text layers, with optional Table Transformer and OCR backends for scanned documents and images. Offers two tools -- extract_tables for full extraction with page selection and format control, and list_tables for quick previews of table dimensions and headers. Lightweight ~33MB install with no model downloads or API keys required.