Last active
August 29, 2015 14:13
-
-
Save pm0u/dc60aaed6dfbca328968 to your computer and use it in GitHub Desktop.
pdf processing script, for personal use. with some adaptation it could suit other people as well.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# pdf scanning script | |
# 1/13/2015 | |
bold='\033[01m' #bold | |
red='\033[01;31m' #error color | |
NC='\033[0m' # No Color | |
if [ $# == 0 ]; then | |
#tell em whats up | |
echo -e "pdeffer ${bold}[ -q ] [ -i | -I${NC} input_location${bold} ] [ -o | -O${NC} output_location${bold} ] [ -f${NC} filename ${bold} ] [ -t ${NC}datestring ${bold}| -T ] [ -N ] [ -u | -U ]${NC}" | |
echo -e "${bold} -d${NC}\tdefault" | |
echo -e "${bold} -q${NC}\treally quiet. no terminal output at all." | |
echo -e "${bold} -i${NC}\tspecify #, defaults to /run/media/${USER}/AV_SCAN/200DOC" | |
echo -e "${bold} -I${NC}\tspecify an explicit input path" | |
echo -e "${bold} -o${NC}\tspecify Dropbox directory, defaults to ~/Dropbox/UNSORTED" | |
echo -e "${bold} -O${NC}\tspecify an explicit output path" | |
echo -e "${bold} -f${NC}\tspecify string to append to files (after datestamp)" | |
echo -e "${bold} -t${NC}\tspecify date string format (see ${bold}man date${NC}) be cautious of special characters. defaults to ${bold}%Y-%m-%d_%H.%M.%S${NC}" | |
echo -e "${bold} -T${NC}\tno date stamping" | |
echo -e "${bold} -N${NC}\tno processing (pdfsandwich). move and apply name if applicable" | |
echo -e "${bold} -u${NC}\tunite all pdfs in input directory before processing. defaults to no datestamp. uses ${bold}pdfunite${NC}" | |
echo -e "${bold} -U\t-u ${NC}with a date stamp." | |
else | |
#make it happen | |
while getopts "i:I:o:O:f:t:TvdqNuU" OPTNAME | |
do | |
case "$OPTNAME" in | |
"i") | |
INPUT="/run/media/$USER/AV_SCAN-$OPTARG/DCIM/200DOC" | |
;; | |
"I") | |
INPUT="$OPTARG" | |
;; | |
"o") | |
OUTPUT="$HOME/Dropbox/$OPTARG/" | |
;; | |
"O") | |
OUTPUT="$OPTARG" | |
;; | |
"f") | |
#echo "filename is ${OPTARG}" | |
FILENAME="${OPTARG}.PDF" | |
;; | |
"t") | |
DATESTRING="$OPTARG" | |
;; | |
"T") | |
NODATE=1 | |
;; | |
"q") | |
QUIET=1 | |
;; | |
"N") | |
NOPROC=1 | |
;; | |
"u") | |
UNITE=1 | |
NODATE=1 | |
;; | |
"U") | |
UNITE=1 | |
;; | |
"d") | |
;; | |
esac | |
done | |
#set defaults | |
############ | |
if [ -z $INPUT ]; then INPUT="/run/media/$USER/AV_SCAN/DCIM/200DOC"; fi | |
if [ -z $OUTPUT ]; then OUTPUT="$HOME/Dropbox/UNSORTED/"; fi | |
if [ -z $DATESTRING ]; then DATESTRING="%Y-%m-%d_%H.%M.%S"; fi | |
############ | |
FILEES=$(find "$INPUT" -maxdepth 1 -name '*.PDF' -printf '%f\n' | sort) | |
if [ ! -z $UNITE ]; then | |
if [ -z $QUIET ]; then | |
UNITECOUNT=0 | |
for z in $FILEES; do let "UNITECOUNT += 1"; done | |
echo -e "${bold}>>>>>Uniting $UNITECOUNT pdfs...${NC}" | |
fi | |
PDFUNITEFILES=$(find "$INPUT" -maxdepth 1 -name '*.PDF' -print0 | sort | sed -e 's/\x0/ /g') | |
if [ "$QUIET" = 1 ]; then | |
pdfunite ${PDFUNITEFILES} "$INPUT/UNITED.PDF" &> /dev/null | |
else | |
pdfunite ${PDFUNITEFILES} "$INPUT/UNITED.PDF" | |
fi | |
ORIGFILES=$FILEES | |
FILEES="UNITED.PDF" | |
fi | |
if [ -z $QUIET ]; then echo -e "${bold}>>>>>Copying pdfs to ~/pdfs..${NC}"; fi | |
for z in $FILEES | |
do | |
if [ -z $FILENAME ]; then FILENAME="$z"; fi | |
if [ -z $NODATE ]; then | |
TIMESTAMP="$(stat ${INPUT}/${z} --printf %y | sed 's/\([0-9]*-[0-9]*-[0-9]*\) \([0-9]*\):\([0-9]*\):\([0-9]*\).*/\1_\2.\3.\4/')_" | |
else | |
TIMESTAMP="" | |
fi | |
ORIGINALNAME="$z" | |
if [ "$QUIET" = 1 ]; then | |
cp --preserve=timestamps "${INPUT}/${ORIGINALNAME}" "$HOME/pdfs/${TIMESTAMP}${FILENAME}" &> /dev/null | |
else | |
cp -v --preserve=timestamps "${INPUT}/${ORIGINALNAME}" "$HOME/pdfs/${TIMESTAMP}${FILENAME}" | |
fi | |
done | |
if [ -z $NOPROC ]; then | |
if [ -z $QUIET ]; then echo -e "${bold}>>>>>pdfsandwiching them..${NC}"; fi | |
FILES=$(find "$HOME"/pdfs -maxdepth 1 -name '*.PDF' | sort) | |
PDFCOUNT=0 | |
PDFTOT=0 | |
for z in $FILES; do let "PDFTOT += 1"; done | |
for f in $FILES | |
do | |
let "PDFCOUNT += 1" | |
echo -e "${bold}>>>>>Processing $PDFCOUNT of $PDFTOT - $f${NC}" | |
if [ "$QUIET" = 1 ]; then | |
pdfsandwich -quiet -coo "-black-threshold 70% -enhance" $f &> /dev/null | |
PDFSTATUS="$?" | |
else | |
pdfsandwich -coo "-black-threshold 70% -enhance" $f | |
PDFSTATUS="$?" | |
fi | |
done | |
else | |
PDFSTATUS=0 | |
fi | |
if [ "$PDFSTATUS" = 0 ]; then | |
if [ -z $QUIET ]; then echo -e "${bold}>>>>>Moving processed PDFs to ${OUTPUT}...${NC}"; fi | |
if [ "$QUIET" = 1 ]; then | |
mv "$HOME"/pdfs/*.PDF "$OUTPUT" &> /dev/null | |
else | |
mv -v "$HOME"/pdfs/*.PDF "$OUTPUT" | |
fi | |
if [ -z $QUIET ]; then echo -e "${bold}>>>>>moving PDFs to completed directory on scanner...${NC}"; fi | |
if [ "$QUIET" = 1 ]; then | |
for z in $FILEES | |
do | |
mv ${INPUT}/${z} ${INPUT}/OCRdone &> /dev/null | |
done | |
if [ ! -z "$ORIGFILES" ]; then | |
for z in $ORIGFILES | |
do | |
mv ${INPUT}/${z} ${INPUT}/OCRdone &> /dev/null | |
done | |
fi | |
else | |
for z in $FILEES | |
do | |
mv -v ${INPUT}/${z} ${INPUT}/OCRdone | |
done | |
if [ ! -z "$ORIGFILES" ]; then | |
for z in $ORIGFILES | |
do | |
mv -v ${INPUT}/${z} ${INPUT}/OCRdone | |
done | |
fi | |
fi | |
if [ -z $QUIET ]; then echo -e "${bold}>>>>completed, please check for errors${NC}"; fi | |
exit 0 | |
else | |
echo -e "${red}>>>>>>pdfsandwich encountered an error, aborting...${NC}" | |
exit 2 | |
fi | |
fi |
eliminated verbose, made it fully verbose by default. specify -q for totally silent.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
updated to move original files as well as united files to completed dir after processing
also a file count / total count for progess