Saltar al contenido
TakoAPI
Volver a skills

opencr-skill

por topdu

Image & Video Generation
557Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Extract text from images, documents and scanned PDFs using OpenOCR - supports text detection, recognition.

Descripción

Qué hace esta skill

OpenOCR is a Python library for extracting text from images, scanned documents, and PDFs. It provides five task modes: text detection, text recognition, end-to-end OCR, VLM-based recognition for formulas and tables, and document parsing with layout analysis. Supports Chinese, English, and other languages.

Handles text, formulas, tables, and layout-aware document parsing in a single library, eliminating the need for separate specialized OCR tools.

Cuándo usarla

  • Converting scanned PDF invoices to searchable text
  • Extracting LaTeX formulas from academic paper screenshots
  • Parsing tables from document images into structured format
  • Batch processing folders of scanned receipts
  • Converting document images to Markdown with layout preserved

Flujo de trabajo de ejemplo

ENTRADA

User asks: Parse this scanned research paper PDF and save it as Markdown

AGENTE
  1. 1

    Initialize OpenOCR with task='doc' and use_layout_detection=True

  2. 2

    Run document parsing on the PDF file

  3. 3

    Iterate over per-page results

  4. 4

    Save each page result to Markdown using doc.save_to_markdown()

SALIDA

Markdown files saved to output directory, one per page, with text, formulas, and tables preserved in structure

Instalación

clawhub install topdu/opencr-skill

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces