Skip to main content

Get Text

Uses OCR (Optical Character Recognition) to extract text from a specified region of the screen or from a reference image.

Common Properties

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.

Inputs

This node does not have direct inputs. It uses a reference image or screen region for text extraction.

Options

  • Confidence - Confidence level for image recognition when using reference images (default: 0.95).

Outputs

  • Text - The extracted text from the specified region or image.

How It Works

The Get Text node extracts text from images using OCR technology. When executed, the node:

  1. Downloads and prepares the reference image if needed
  2. Takes a screenshot of the current screen
  3. Uses OCR (pytesseract) to extract text from either:
    • The entire reference image
    • A specific region defined by anchor and target regions
  4. Returns the extracted text

Requirements

  • Valid reference image (optional, for targeted text extraction)
  • Confidence value between 0 and 1 (when using reference images)
  • Tesseract OCR engine installed and configured

Error Handling

The node will return specific errors in the following cases:

  • Could not read image - "Could not read image"
  • Missing confidence - "Confidence can not be empty"
  • Invalid confidence format - "Confidence is not valid"
  • Confidence out of range - "Confidence must be between 0 and 1"
  • Image not found - "Could not find image. Decreasing confidence may help"

Usage Notes

  • This node is useful for extracting text from UI elements, documents, or images
  • Can work with the entire screen or specific regions
  • When using regions, it first locates an anchor image and then extracts text from a target region
  • Works best with clear, high-contrast text
  • The confidence level affects the accuracy of anchor image recognition
  • Higher confidence values require more precise image matching
  • Lower confidence values may result in false positives but can handle variations better
  • Returns all text found in the specified area as a single string
  • May require preprocessing of images for better OCR results