WSJ pdf watermark remover

removePdfWatermark-WSJ2.sh

#!/bin/bash
interactive=
filename=~/removePdfWatermark-WSJ2.sh


bfile=$(basename $1)


#cd /home/osboxes/ZysProj/pdf


# the directory of the script
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
#echo "the directory of the script"
#echo $DIR
#cd $DIR

# the temp directory used, within $DIR
# omit the -p parameter to create a temporal directory in the default location
WORK_DIR=`mktemp -d -p "$DIR"`

# check if tmp dir was created
if [[ ! "$WORK_DIR" || ! -d "$WORK_DIR" ]]; then
  echo "Could not create temp dir"
  exit 1
fi

#echo "tmp dir"
#echo $WORK_DIR

cp $1  $WORK_DIR


echo "input file name = $bfile"
#bfilename=$(basename $filename)


# Un-compress
pdftk $WORK_DIR/$bfile output $WORK_DIR/doc.unc.pdf uncompress

# remove watermark in uncompressed file
echo "remove watermark in uncompressed file..."
sed -E -e "s/For personal,|non-commercial use only.|Do not edit, alter or reproduce. For commercial reproduction or distribution, contact Dow Jones Reprints & Licensing at \\\\\(800\\\\\) 843-0008 or|www.djreprints.com//g" < $WORK_DIR/doc.unc.pdf > $WORK_DIR/tmp.pdf

#Compress pdf
echo "Compress pdf..."
pdftk $WORK_DIR/tmp.pdf output $WORK_DIR/$bfile compress



#copy file back
cp $WORK_DIR/$bfile /media/HostDownload/
echo "New file been created. processed/$bfilename"

#cleanup
#rm doc.unc.pdf tmp.pdf

# deletes the temp directory
function cleanup {      
  rm -rf "$WORK_DIR"
  echo "Deleted temp working directory $WORK_DIR"
}

trap cleanup EXIT