table-extractor

Extract structured tabular data from PDF documents using camelot.

3|Updated Apr 2, 2026

Search Tags:#pdf #data #pandas #extraction #table #camelot

Ready to run

npx skills add https://github.com/legout/pi-config --skill table-extractor-legout

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: table-extractor
Source: https://github.com/legout/pi-config/tree/main/installed-skills/table-extractor
Command: npx skills add https://github.com/legout/pi-config --skill table-extractor-legout

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires camelot-py, pandas, ghostscript.

What problem does it solve?

This skill solves the difficulty of extracting tabular data from PDF documents, which often results in messy, unformatted text or broken layouts when using standard copy-paste methods.

Core Features & Use Cases

Precision Extraction: Uses the camelot library to identify and parse tables with high accuracy, handling both bordered (lattice) and borderless (stream) layouts.
Data Structuring: Automatically converts extracted tables into pandas DataFrames, ready for export to Excel, CSV, or JSON.
Use Case: Ideal for financial analysts or researchers who need to pull financial statements, scientific data, or invoice line items from multi-page PDF reports into clean, machine-readable formats.

Quick Start

Use the table-extractor skill to identify and extract all tables from the provided document named report.pdf.

Frequently Asked Questions about table-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract complex tables from PDF documents into structured data?▼

To extract complex tables from PDF documents into structured data, this skill uses the camelot library to identify table layouts and convert them directly into pandas DataFrames. It handles both bordered and borderless structures accurately.

Can I extract merged cells and multi-page tables from a PDF?▼

Yes, you can extract merged cells and multi-page tables from a PDF. The extraction process specifically supports complex table layouts including merged cells, multi-page tables, and borderless data structures using advanced detection algorithms.

Do I need ghostscript installed to parse PDF tables with camelot?▼

Yes, you need ghostscript installed to parse PDF tables with camelot. Both camelot-py and ghostscript are required dependencies to perform accurate table detection and successfully convert the extracted data into pandas DataFrames.

What is the best way to convert borderless PDF tables into pandas DataFrames?▼

The best way to convert borderless PDF tables into pandas DataFrames is using stream mode detection. This approach identifies and parses borderless data structures with high accuracy, automatically formatting the output into clean, machine-readable DataFrames.

Why does my PDF table extraction result in messy unformatted text?▼

Your PDF table extraction results in messy unformatted text when using standard copy-paste methods because they cannot interpret complex layouts. Using a dedicated library like camelot solves this by accurately detecting lattice and stream layouts.

How do I export extracted PDF tables to Excel or CSV?▼

To export extracted PDF tables to Excel or CSV, the skill first converts the identified tabular data into pandas DataFrames. Once the data is structured in a DataFrame, it is ready for immediate export to Excel, CSV, or JSON formats.