ocr.sh

# OCR PDF file

ocrmypdf -l ces input.pdf output.pdf

# -l                    => language: -l eng+deu, -l ces
# --sidecar             => Generate text files that contain the same text recognized by OCR
# --title TITLE         => Set document title (place multiple words in quotes)
# --author AUTHOR       => Set document author
# --subject SUBJECT     => Set document subject description
# --keywords KEYWORDS   => Set document keywords
# -r                    => Automatically rotate pages based on detected text orientation
# -q                    => fewer messages
# --remove-background   => Attempt to remove background from gray or color pages
# --unpaper-args '--layout double --no-noisefilter' => when two pages are scanned together

## OCR all PDF files

find . -name '*.pdf' | while read pdf; do ocrmypdf "$pdf" "${pdf}_ocr.pdf"; done

pdf-reduce-size.sh

## Reduce size of PDF

gs -dNOPAUSE -dBATCH -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 -dPDFSETTINGS=/screen -sOutputFile=output.pdf input.pdf

# -dNOPAUSE                 => no pause after page
# -dBATCH                   => Exit after last file
# -sDEVICE=pdfwrite         => PDF writer
# -dCompatibilityLevel      => 1.5 (compatibility with Preview.app), 1.7 (compatibility with Acrobat)
# -dPDFSETTINGS             => (small) /screen /ebook /printer /prepress (large)
# -g<width>x<height>        => page size in pixels
# -r<res>                   => pixels/inch resolution
# -q                        => fewer messages
# -sPAPERSIZE               => a4, legal…
# -dColorConversionStrategy => /Gray
# -dProcessColorModel       => /DeviceGray

## Reduce all PDF files

find . -name '*.pdf' | while read pdf; do gs -sDEVICE=pdfwrite -dCompatibilityLevel=1.4 -dPDFSETTINGS=/ebook -dNOPAUSE -dQUIET -dBATCH -sOutputFile="${pdf}_new.pdf" "$pdf"; done