Creating PDF from images with OCR

convert.sh

#!/bin/bash
# Creating PDF from images with OCR
# 
# brew install tesseract tesseract-lang pdftk-java

# 
mkdir -p pdf_output


for file in $(ls RU_*.jpg | awk -F'[_\.]' '{ printf "%s\t%s\n", $2, $0 }' | sort -k1,1n | cut -f2-); do
    echo "Processing $file..."

    filename=$(basename "$file" .jpg)

    # Creating OCR
    tesseract "$file" "pdf_output/$filename" -l rus+eng+deu pdf
done


echo "Merging PDF files..."
pdftk pdf_output/*.pdf cat output combined.pdf

echo "Finished: book created combined.pdf"