Get scanned images as a single PDF file from web user interface of Canon iR2870.

scan.sh

#!/bin/bash
# Get scanned images as a single PDF file from Canon iR2870 user mailboxes.
# Original author: ŐRY Máté <orymate at iit.bme.hu>
# Public domain. Originally published at https://gist.github.com/orymate

# Requirements: imagemagick, pdftk, jbgtopbm <http://www.cl.cam.ac.uk/~mgk25/jbigkit/>

#set -x

SERVER='10.0.0.xxx'
if [ $# -lt 2 -o $# -gt 4 ]
then
    echo Usage: $0 MAILBOX DOCUMENT [OUTPUT.pdf] [even]
fi

cookies=$(mktemp)

MAILBOX=$1
DOCUMENT=$(tr -dc 0-9 <<<"$2")
OUTPUT=${3:-OUTPUT.pdf}
EVEN=${4:-no}

# get sessid
wget --keep-session-cookies --save-cookies $cookies "http://$SERVER/" -O/dev/null

## list mailboxes
#d=$(date +%s)
#wget --keep-session-cookies --load-cookies $cookies "http://$SERVER/bpbl.cgi?BoxKind=UserBox&Dummy=$d" -O- #-O/dev/null
#read

# log in!
d=$(date +%s)
wget --load-cookies $cookies "http://$SERVER/blogin.cgi?BOX_No=$MAILBOX&Cookie=&Dummy=$d" -O/dev/null

## get mailbox
#d=$(date +%s)
#wget --load-cookies $cookies "http://$SERVER/bdocs.cgi?BOX_No=$MAILBOX&DocStart=1&DIDS=&Dummy=$d" -O-
#read


#d=$(date +%s)
#I=1
#URI="http://$SERVER/image.jbg?B=$MAILBOX&D=$DOCUMENT&P=$I&M=M&RX=600&RY=600&Dummy=$d"
#URI="http://$SERVER/image.jbg?B=$MAILBOX&D=$DOCUMENT&P=$I&M=MX&RX=600&RY=600&Dummy=$d"
#wget --load-cookies $cookies --save-headers $URI -O-
#read


t=$(mktemp -d)


I=1

while true
do
    d=$(date +%s)
    URI="http://$SERVER/image.jbg?B=$MAILBOX&D=$DOCUMENT&P=$I&M=MV&RX=600&RY=600&Dummy=$d"
    wget --load-cookies $cookies $URI -O$t/page_$(printf "%04d" $I).jbg
    if grep -qs "Document does not exist." $t/page_$(printf "%04d" $I).jbg
    then
        #echo $t
        rm  $t/page_$(printf "%04d" $I).jbg
        pdftk $t/*.pdf output "$OUTPUT" && rm -r $t
        echo $[$I-1] pages written to
        echo "$OUTPUT"
        rm $cookies
        exit 0
    fi

    jbgtopbm $t/page_$(printf "%04d" $I).jbg > $t/page_$(printf "%04d" $I).pbm
    convert -density 150 -resize 25% -rotate 270 $t/page_$(printf "%04d" $I).{pbm,pdf}
    rm  $t/page_$(printf "%04d" $I).{pbm,jbg}
    let I++
    if [ $EVEN = even ]
    then
        let I++
    fi
done