#!/bin/bash - # ############## security pack ############################## PATH='/sbin:/bin:/usr/sbin:/usr/bin:/usr/X11R6/bin:/usr/local/sbin:/usr/local/bin:/usr/games:~/bin' ; hash -r ; # - Bash Cookbook, 1st ed.,, #14.5 ulimit -H -c 0 -- ; # - Bash Cookbook, 1st ed.,, #14.6 IFS=$' \t\n' ; # - Bash Cookbook, 1st ed.,, #14.7 UMASK='002' ; umask $UMASK ; # - Bash Cookbook, 1st ed.,, #14.8 \unalias -a # - Bash Cookbook, 1st ed.,, #14.4 # ############## security pack ############################## USAGE="$0 -h | file.pdf | file.ps [ startpage# [ endpage# ] ]" ; VERSION='$Id: pdfimagesview,v 1.1 2008/07/08 09:20:30 dallas Exp dallas $' ; set -e ; shopt -s nocasematch expand_aliases ; alias RM='/bin/rm -f 2> /dev/null ' ; alias RMDIR='/bin/rmdir 2> /dev/null ' ; alias MKDIR='/bin/mkdir 2> /dev/null ' ; alias PDFIMAGES='/usr/bin/pdfimages' ; alias EZGV='exec /usr/bin/zgv' ; # alias ZGV='/usr/bin/zgv' ; # pdfimages is from the poppler-utils package, # referenced in 'Linux Journal' May, 2008, p. 83, Tech Tip # 'Extract Images from PDF Files', Matthew Martin. # It extracts the images from a pdf file THEPDFFILE=${1} ; case ${THEPDFFILE} in [-/][h?]* ) echo 'Usage: '${USAGE} ; exit ; ;; [-/]v* ) echo ${VERSION} ; exit ; ;; *.ps ) THETTAG=${THEPDFFILE%.ps} ; ;; *.pdf ) THETAG=${THEPDFFILE%.pdf} ; ;; * ) exit ; esac if [ ! -f ${THEPDFFILE} ] ; then echo 'File needed' ; echo ${USAGE} ; exit ; fi if [[ ${THETAG} == */* ]] ; then THETAG=${THETAG##*/} ; fi ; THEDIR1='/tmp/pdfimages' ; THEDIR2="${THEDIR1}/${THETAG}" ; THEFILES="${THEDIR2}/${THETAG}" ; for ii in ${!THEDIR*} do if [ ! -d ${!ii} ] ; then RM ${!ii} ; MKDIR ${!ii} ; fi ; done ; RM ${THEDIR2}/* ; PDFIMAGES -f ${2:-1} -l ${3:-200} ${THEPDFFILE} ${THEFILES} ; EZGV --visual ${THEDIR2}/ ; exit
Friday, August 1, 2008
4) individual embedded images
The following script extracts each individual image embedded in a PDF document and displays them. As documented in the script, it is based on a tool I recently became aware of from a "Tech Tip" in Linux Journal. The tool, pdfimages, extracts the individual images from the PDF document, which are then viewed using zgv. I call this script 'pdfimagesview'.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment