convert.sh

#!/bin/bash
FILE=./input.doc
if test -f "$FILE"; then
  lowriter --convert-to pdf:writer_pdf_Export input.doc
fi

mkdir image
pdftoppm input.pdf image/page -png

mkdir text
page=1
for image_file in ./image/*.png; do
  additional_zeros=""
  if [ $page -lt 10 ]
  then
    additional_zeros="00"
  elif [ $page -lt 100 ]
  then
    additional_zeros="0"
  fi
  tesseract $image_file "./text/"$additional_zeros$page -l spa
  page=$((page+1))
done


for text_file in ./text/*.txt; do
  cat $text_file >> output.txt