A high-precision utility for extracting structured tables from PDF documents using advanced Lattice and Stream detection methods.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install table-extractor
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install table-extractor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Table Extractor?
The Table Extractor skill brings the power of the camelot-py library to your AI agent, allowing for the reliable conversion of PDF tables into structured data. Whether dealing with complex financial reports or research papers, this Openclaw Skills integration provides the technical depth needed to handle merged cells, borderless layouts, and multi-page data structures with high precision.
By utilizing specialized detection flavors, developers can ensure that even the most difficult document layouts are accurately parsed into pandas DataFrames. This skill bridges the gap between static PDF files and dynamic data analysis workflows, making it an essential tool for automated data entry and document processing.
Table Extractor Use Cases
- Extracting financial statements and balance sheets from corporate annual reports.
- Converting scientific data tables from research papers into structured formats for meta-analysis.
- Automating the capture of line-item data from invoices and receipts.
- Batch processing directories of PDFs to aggregate tabular data into a single database.
- Comparing different versions of a document to identify changes in tabular data.
How Table Extractor Works
- The skill receives a PDF document and identifies specific pages or extraction methods requested by the user.
- It analyzes the document structure using the Lattice method for bordered tables or the Stream method for borderless text-based tables.
- The camelot-py engine parses the PDF coordinates to identify cell boundaries and text alignment.
- Extracted data is converted into a pandas DataFrame for internal processing or immediate use.
- The skill applies optional post-processing like multi-page merging or header deduplication before exporting to formats like CSV, Excel, or JSON.
Table Extractor Setup
To use this skill, ensure you have camelot-py and its system dependencies installed:
pip install camelot-py[cv]
For system-level dependencies:
# macOS
brew install ghostscript tcl-tk
# Ubuntu
apt-get install ghostscript python3-tk
Table Extractor Data Schema & Taxonomy
The skill organizes extracted data into structured objects with the following metadata:
| Attribute | Description |
|---|---|
df |
The core pandas DataFrame containing the extracted table content. |
page |
The specific page number where the table was located. |
accuracy |
A percentage score indicating the confidence level of the extraction. |
whitespace |
The percentage of empty space found within the detected table area. |
parsing_report |
Technical logs detail how the table was identified and parsed. |
Table Extractor Advanced Features
- Advanced coordinate targeting using
table_areasto extract data from specific regions of a page. - Visual debugging support to plot detected table contours and text positioning for verification.
- Multi-page table concatenation to unify split tables across continuous document sections.
- Custom column specification to manually define separators for complex borderless documents.
- Flexible export options providing direct conversion to CSV, Excel, JSON, and HTML via Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Smart OCR
A high-performance OCR skill powered by PaddleOCR for extracting structured text and layout data from images and scanned documents in over 100 languages.
Resume Tailor
An intelligent assistant designed to customize resumes for specific job descriptions by optimizing for ATS and quantifying professional achievements.
PPTX Presentation Automation
A programmatic interface for creating and modifying Microsoft PowerPoint presentations using Python automation.
PDF Merge & Split
A versatile tool for programmatically merging, splitting, and reordering PDF files using AI-driven logic.
Template Engine
A powerful automation tool for programmatically filling document templates with structured data using Jinja2 syntax.
XLSX Spreadsheet Manipulation
A powerful skill for programmatically managing Microsoft Excel files using Python and the openpyxl library.
Featured*
