Bash script for cleaning and combing multiple PDFs into one

pdfcleancombine.sh

#!/bin/bash

# Note files need to be in correct order to start with. ie. number chapters first

# Required tools:
# * http://www.pdflabs.com/tools/pdftk-server/
# * brew install mupdf

# Works as follows:

# Step 1. Clean all files in dir and write clean file names in order to textfile
# mutool clean <infile.pdf> <outfile.pdf>

# Step 2. Combine all files from textfile into one pdf
# pdftk <files listed in order> cat output output.pdf


CLEANDIR=clean;
echo "CLEANDIR is $CLEANDIR"
mkdir -p "$CLEANDIR";

CLEANFILES=DBCleanFiles.txt

if [ -f "$CLEANFILES" ]; then
	echo "Removing existing $CLEANFILES"
	rm -rf "$CLEANFILES"
fi

FILENUM=1
find *.pdf | sort -n | while read -r pdffile;
do
echo "Cleaning $pdffile as $FILENUM";
mutool clean "$pdffile" "$CLEANDIR"/"$FILENUM".pdf;
echo "$CLEANDIR"/"$FILENUM".pdf >> $CLEANFILES
((FILENUM++))
done

OUTFILE=${PWD##*/}

echo "Combining files"
pdftk $(cat $CLEANFILES) cat output "$CLEANDIR"/"$OUTFILE".pdf
echo "Finished. created $CLEANDIR/$OUTFILE.pdf"