Last active
May 11, 2024 14:26
-
-
Save didmar/4e0234f313c13f68ac3bc760fef5e3e0 to your computer and use it in GitHub Desktop.
Shell script to extract text from last screenshot taken
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/sh | |
# This script opens the last screenshot taken and runs OCR on it to extract text. | |
# It used tesseract (see https://tesseract-ocr.github.io/) | |
# Configured with Ubuntu's Screenshots folder. Change to your own. | |
SCREENSHOTS_DIR=$HOME/Pictures/Screenshots | |
# Create the folder to put the output into, if needed | |
mkdir -p $SCREENSHOTS_DIR/ocr_output | |
# Get the last screenshot taken | |
LAST_FILE="$SCREENSHOTS_DIR/$(ls --color=never -t $SCREENSHOTS_DIR | grep ".png" | head -n 1)" | |
# Run OCR on the screenshot | |
OUTPUT_FILE_WITHOUT_EXT="$SCREENSHOTS_DIR/ocr_output" | |
OUTPUT_FILE="${OUTPUT_FILE_WITHOUT_EXT}.txt" | |
tesseract "$LAST_FILE" "$OUTPUT_FILE_WITHOUT_EXT" | |
# Open the OCR output | |
echo "" | |
echo "===============================================" | |
echo "Extracted text from screenshot:" | |
echo "===============================================" | |
echo "" | |
cat "$OUTPUT_FILE" | |
# xdg-open "$OUTPUT_FILE" | |
# Optionally, copy text to clipboard (requires xclip to be installed) | |
# xclip -selection clipboard "$OUTPUT_FILE" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment