Tabula PDF Table Extraction Agent

Uses Tabula Java library via tabula-py bindings to detect and extract tables from PDF documents. Supports both lattice and stream extraction modes with configurable area coordinates and outputs to pandas DataFrames or CSV.

Installation

Requirements and caveats from upstream:

• the Ruby, Python, R, and Node.js bindings

Basic usage or getting-started notes:

• Commandline Usage Examples

• [-g] [-h] [-i] [-l] [-n] [-o <OUTFILE>] [-p <PAGES>] [-r] [-s

• <PASSWORD>] [-t] [-u] [-v]

• Source: https://github.com/tabulapdf/tabula-java

• Extracted from upstream docs: https://raw.githubusercontent.com/tabulapdf/tabula-java/HEAD/README.md

Source

• Agent Skill Exchange