OCR PDF file (aka make it searchable) using tesseract (super hacky, use at your own risk!)

ocr.sh

#!/bin/sh

mkdir -p __searchable__

y="`pwd`/$1"
echo Will create a searchable PDF for $y

x=`basename "$y"`
name=${x%.*}

mkdir "$name"
cd "$name"

# splitting to individual pages
gs -dSAFER -dBATCH -dNOPAUSE -sDEVICE=jpeg -r300 -dTextAlphaBits=4 -o out_%04d.jpg -f "$y"

# process each page
for f in $( ls *.jpg ); do
  # extract text
  tesseract $f ${f%.*} -l deu --psm 3 pdf
  rm $f
done

# combine all pages back to a single file
gs -dCompatibilityLevel=1.4 -dNOPAUSE -dQUIET -dBATCH -dNOPAUSE -q -sDEVICE=pdfwrite -sOutputFile="../__searchable__/${name}.pdf" *.pdf

cd ..
rm -rf "${name}"