A local, privacy-focused tool that converts image-based PDFs into searchable text using Tesseract OCR and Python.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdf-ocr-extraction
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 pdf-ocr-extraction 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 PDF OCR Extractor?
The PDF OCR Extractor is a specialized utility designed for the Openclaw Skills ecosystem to bridge the gap between static image scans and machine-readable text. Unlike many cloud-based alternatives, this skill operates entirely on your local machine, ensuring that sensitive documents are never transmitted to third-party servers.
By leveraging the Tesseract engine and Python's imaging libraries, it renders PDF pages into high-resolution images and applies advanced optical character recognition. This makes it an essential tool for developers and researchers who need to process historical archives, scanned receipts, or non-searchable document batches within their AI workflows.
PDF OCR Extractor Use Cases
- Digitizing scanned paper documents and legacy archives for further data analysis.
- Extracting text from multi-language PDFs, including support for scripts like Simplified Chinese.
- Automating document processing pipelines where cloud API costs or data privacy are primary concerns.
- Converting non-selectable text in image-based PDFs into searchable Markdown or plain text formats.
How PDF OCR Extractor Works
- The user provides a path to a scanned or image-based PDF file.
- The skill utilizes pypdfium2 to render each PDF page into a high-resolution bitmap image.
- Temporary image files are generated in the system /tmp/ directory for processing.
- Pytesseract interfaces with the local Tesseract OCR binary to analyze the images and extract text based on installed language packs.
- The skill aggregates the text from all pages, cleans up the temporary image files, and returns the full text output to the agent.
PDF OCR Extractor Setup
To utilize this within the Openclaw Skills framework, ensure your system has the necessary binaries and Python packages installed:
# Install Tesseract OCR (Debian/Ubuntu example)
sudo apt-get install tesseract-ocr tesseract-ocr-eng tesseract-ocr-chi-sim
# Install required Python dependencies
pip install pypdfium2 pytesseract Pillow
PDF OCR Extractor Data Schema & Taxonomy
The skill manages data through a temporary processing lifecycle to minimize storage footprint:
| Data Type | Description | Persistence |
|---|---|---|
| Input PDF | The source file provided by the user. | User-managed |
| Temp Images | Intermediate PNG files created per page in /tmp/. | Deleted after OCR |
| Extracted Text | Raw string output containing the OCR results. | Returned to Agent |
| Language Packs | Tesseract .traineddata files required for specific scripts. | System-installed |
PDF OCR Extractor Advanced Features
- Multi-language support allowing simultaneous OCR for mixed-script documents (e.g., English and Chinese).
- High-resolution rendering (scale=2) to improve character recognition accuracy on small or blurry text.
- Local-first architecture designed for execution in air-gapped or secure sandbox environments.
- Zero-API dependency, providing unlimited extraction without recurring subscription costs or rate limits.
SKILL.md
Loading
Related Openclaw Skills
Page Saver
A local, zero-dependency reference tool providing instant access to Page Saver documentation, patterns, and best practices directly in your terminal.
Kiwi Receipts
A dedicated New Zealand tax assistant that transforms receipt photos into IRD-ready GST reports and comprehensive annual tax summaries.
Save to Email
A powerful utility to send formatted HTML emails and notifications through the Resend API via a simple shell interface.
Amortize Reference Tool
A zero-dependency reference tool providing instant access to Amortize devtools documentation and implementation patterns.
Deep Research Pro v2.1
A professional-grade research agent that enforces data integrity through mandatory source carding and evidence-based reporting.
Disney Plus Information Organizer
A specialized tool for extracting and organizing public metadata, membership details, and creator guidelines from the Disney Plus platform.
Featured*
