Communityv1.0.0

OCR with python

Extract Chinese and English text from images and scanned PDFs, including documents like invoices and contracts, using PaddleOCR in Python.

1.6kdownloads10active installsRoamer 徐
View on ClawHubBack to Skills

Skill Details

Slug
ocr-python
Latest Version
1.0.0
Author
Roamer 徐
Published
Feb 21, 2026
Updated
Apr 28, 2026
Total Versions
1

How to Install

  1. 1 on OpenClawdBots (takes under 60 seconds).
  2. 2Open your bot dashboard and go to the Skills tab.
  3. 3Switch to the ClawHub tab and search for “OCR with python”.
  4. 4Click Install and the skill is deployed to your bot automatically.

Changelog — v1.0.0

- Initial release of the OCR skill using PaddleOCR. - Supports text extraction from PDF and image files in both Chinese and English. - Output includes recognized text and confidence scores in JSON format. - Typical use cases covered: scanned PDFs, images, invoices, contracts, and multi-page documents. - Includes quick start guide and dependency installation instructions.