gistfile1.sh

# Ghetto OCR
#
# Requires:
#  - brew install imagemagick
#  - brew install tesseract --all-languages
#
# Takes pdfs and spits out a txt file with anything it could OCR
function ocr {
   if (( $# < 1 ))
   then echo "usage: ocr filename.pdf"; return 1; fi

   for i in $*
   do
   file_name="$( basename "$i" .pdf)"
   echo "Converting ${file_name} to tif"
   convert -monochrome -density 600 $i "${file_name}.tif"
   echo "Starting OCR"
   tesseract -l nld "${file_name}.tif" "${file_name}" 2>/dev/null
   rm "${file_name}.tif"
   done
   echo "Done."
}