Strip PDF Metadata (more improved version)

clean_pdf.sh

#!/usr/bin/env bash

set -euo pipefail

# Color Codes so that warnings/errors stick out
GREEN="\033[32m"
RED="\033[31m"
CLEAR="\033[0m"

USAGE="usage: $0 [<TARGET DIR>=.]"

_help(){
  cat << HELP
$USAGE
# --------------------------------------------------------------------
# Recursively find pdfs from the directory given as the first argument,
# otherwise search the current directory.
# Use exiftool and qpdf (both must be installed and locatable on \$PATH)
# to strip all top-level metadata from PDFs.
#
# Note - This only removes file-level metadata, not any metadata
# in embedded images, etc.
#
# Code is provided as-is, I take no responsibility for its use,
# and I make no guarantee that this code works
# or makes your PDFs "safe," whatever that means to you.
#
# You may need to enable execution of this script before using,
# eg. chmod +x $0
#
# example:
# clean current directory:
# $ $0
#
# clean specific directory:
# $ $0 some/other/directory
# --------------------------------------------------------------------
HELP
}

_clean_info() {
  local tmp target
  if [ $# = 1 ]; then
    target="$1"
  else
    return 1
  fi
  # output file as original filename with suffix _clean.pdf
  tmp="${target%.*}_clean.pdf"

  # remove the temporary file if it already exists
  if [ -f "$tmp" ]; then
    rm "$tmp"
  fi

  exiftool -q -all:all= "$target" -o "$tmp"
  qpdf --linearize --replace-input "$tmp" || :
  echo -e "=> ${GREEN}Processed${CLEAR}: ${GREEN}${tmp}${CLEAR}"
}

main() {
  local tempfile f cnt
  if ! command -v exiftool qpdf &> /dev/null; then
    echo 'err: Please install: exiftool, qpdf' >&2
    return 1
  fi
  # loop through all PDFs in first argument ($1),
  # or use '.' (this directory) if not given
  if [ $# -gt 1 ]; then
    echo "$USAGE" >&2
    return 1
  elif [[ "$1" =~ ^-h(elp)?$ ]]; then
    _help
    return 0
  fi

  DIR="${1:-.}"

  if ! [ -d "$DIR" ]; then
    echo "err: Target dir '${DIR}' is not found." >&2
  fi

  echo "Cleaning PDFs in directory $DIR"

  # use find to locate files, pip to while read to get the
  # whole line instead of space delimited
  # Note -- this will find pdfs recursively!!
  tempfile="$(mktemp)"
  find "$DIR" -type f -name "*.pdf" > "$tempfile"
  file_num="$(wc -l < "$tempfile")"
  cnt=1
  while read -r f; do
    echo -e "[${cnt}/${file_num}]: ${RED}${f}${CLEAR}"
    _clean_info "$f"
    ((cnt++))
  done < "$tempfile"
}
main "${@-}"
exit $?