This is a copy of this post for safe-keeping:
In a terminal, type:
sudo apt-get install pdftkThen, to add a password to a PDF file, type:
pdftk <input-file> output <output-file> user_pw <password>Example:
pdftk input.pdf output output.pdf user_pw 1234
sudo apt-get install tesseract-ocr/usr/share/tesseract-ocr/tessdata). E.g. for Hungarian:cd /usr/share/tesseract-ocr/tessdata
sudo wget https://github.com/tesseract-ocr/tessdata/raw/master/hun.traineddataTESSDATA_PREFIX to the directory containing the tessdata directory if you get the error that the language data cannot be found.tesseract input.png outbase -l hun pdfpdftk original.pdf output fixed.pdfpdftk fixed.pdf output uncompressed.pdf uncompresssed "s/Wow! eBook <WoweBook.Com>/ /g" uncompressed.pdf > unwatermarked.pdfpdftk unwatermarked.pdf output compressed.pdf compressls or another language’s equivalent)pdfinfo or an equivalent)pdftotextpdftohtml -xmlpdf2svgtidy -utf8 -c -o example_tidy.html example.html#!/bin/bash
# NAUTILUS SCRIPT
# automatically splits pdf file to single pages while renaming the output files using the first three of lines of the pdf
# read files
IFS=$'\n' read -d '' -r -a filelist < <(printf '%s\n' "$NAUTILUS_SCRIPT_SELECTED_FILE_PATHS"); unset $IFS
pagecount=1
datestamp=1
# burst and rename pages to separate files
for file in "${filelist[@]}"; do
pagecount=`pdfinfo $file | grep "Pages" | awk '{ print $2 }'`
for (( pageindex=1; pageindex<=$pagecount; pageindex+=1 )); do
newname=`pdftotext -f $pageindex -l $pageindex $file - | head -n 3 | tr '\n' ' ' | cut -f1 -d"("`
let "datestamp =`date +%s%N`" # to avoid overwriting with same new name
pdftk $file cat $pageindex output "$newname"$datestamp.pdf
done
done#!/bin/bash
# NAUTILUS SCRIPT
# automatically renames pdf file based on content maching a list of names
# read files
IFS=$'\n' read -d '' -r -a filelist < <(printf '%s\n' "$NAUTILUS_SCRIPT_SELECTED_FILE_PATHS"); unset $IFS
names=( "Aaa Aaa" "Bbb Bbb" "Ccc Ccc") # names to match in the files
# process files
for file in "${filelist[@]}"; do
# find name from names in the file
foundname=''
for name in "${names[@]}"; do
testname=`pdftotext "$file" - | grep $name`
if [[ $testname != "" ]]; then
foundname=$name
break
fi
done
# rename file based on found name
title=`pdftotext -f 1 -l 1 "$file" - | head -n 1`
let "datestamp =`date +%s%N`"
mv "$file" "${file%/*}/$foundname $title $datestamp.pdf"
done#!/bin/bash
# NAUTILUS SCRIPT
# automatically splits pdf file to multiple pages based on search criteria while renaming the output files using the search criteria and some of the pdf text.
# read files
IFS=$'\n' read -d '' -r -a filelist < <(printf '%s\n' "$NAUTILUS_SCRIPT_SELECTED_FILE_PATHS"); unset $IFS
# process files
for file in "${filelist[@]}"; do
pagecount=`pdfinfo $file | grep "Pages" | awk '{ print $2 }'`
# MY SEARCH CRITERIA is a 10 digit long ID number that begins with number 8:
storedid=`pdftotext -f 1 -l 1 $file - | egrep '8?[0-9]{9}'`
pattern=''
pagetitle=''
datestamp=''
for (( pageindex=1; pageindex<=$pagecount; pageindex+=1 )); do
header=`pdftotext -f $pageindex -l $pageindex $file - | head -n 1`
pageid=`pdftotext -f $pageindex -l $pageindex $file - | egrep '8?[0-9]{9}'`
let "datestamp =`date +%s%N`" # to avoid overwriting with same new name
# match ID found on the page to the stored ID
if [[ $pageid == $storedid ]]; then
pattern+="$pageindex " # adds number as text to variable separated by spaces
pagetitle+="$header+"
if [[ $pageindex == $pagecount ]]; then #process last output of the file
pdftk $file cat $pattern output "$storedid $pagetitle $datestamp.pdf"
storedid=0
pattern=''
pagetitle=''
fi
else
#process previous set of pages to output
pdftk $file cat $pattern output "$storedid $pagetitle $datestamp.pdf"
storedid=$pageid
pattern="$pageindex "
pagetitle="$header+"
fi
done
done#!/bin/bash
# NAUTILUS SCRIPT
# automatically splits pdf file to multiple pages based on given block size, and renames the files using the original filename plus datestamp
# read files
IFS=$'\n' read -d '' -r -a filelist < <(printf '%s\n' "$NAUTILUS_SCRIPT_SELECTED_FILE_PATHS"); unset $IFS
# process files
for file in "${filelist[@]}"; do
# variables
blocksize=3 # ADD BLOCK SIZE MANUALLY HERE
blocks=()
filename=${file%.pdf} # remove extension from filename
# calculate page range blocks
pagecount=`pdfinfo $file | grep "Pages" | awk '{ print $2 }'`
let setcount=$pagecount/$blocksize
for (( setindex=1; setindex<=$setcount; setindex+=1 )); do
if [[ $setindex -lt $setcount ]]; then
let lastpage=$setindex*$blocksize
let firstpage=$lastpage-$blocksize+1
elif [[ $setindex -eq $setcount ]]; then # handle last page
let lastpage=$pagecount
let firstpage=$setindex*$blocksize-$blocksize+1
fi
blocks+=("$firstpage-$lastpage")
done
# process ranges to output
for block in "${blocks[@]}"; do
let "datestamp =`date +%s%N`" # to avoid overwriting with same new name
pdftk $file cat $block output "$filename $datestamp.pdf"
done
donepdftk input.pdf cat 2 output page2.pdf
pdfinfo page2.pdfPage size: 595 x 842 pts (A4) pdfimages page2.pdf img
identify -verbose img-000.pbmGeometry: 2496x3440+0+0 Resolution: 72x72 Page geometry: 2496x3440+0+0 Modified the image through Gimp. Open, Edit, Save -> Export -> click Ok whenever needed. convert img-000.pbm -resample 300x300 -resize 2496x3440 img2.ps
identify -verbose img2.ps Geometry: 599x826+0+0 Resolution: 72x72 Page geometry: 599x826+0+0 ps2pdf12 -sPAPERSIZE=a4 -dFIXEDRESOLUTION img2.ps page2_v2.pdf
pdfinfo page2test4pdf.pdf Page size: 595 x 842 pts (A4) pdftk A=input.pdf B=page2_V2.pdf cat A1 B A3-end output output.pdf
mogrify -format ps -density 300x300 *.pbm#!/bin/bash
lista=(`find -iname '*.ps' | sort`)
for i in "${lista[@]}"
do
ps2pdf -r300 -g1880x2688 $i $i.pdf
donepdfjoin *.pdf --outfile output.pdf#!/bin/sh1.) open your favorite text editor
for i in `find -iname '*.jpg'`
do
convert $i -background white -flatten -colorspace Gray -negate -edge 1 -negate -normalize -sharpen 1 -threshold 50% -despeckle -blur 0x.5 -normalize +dither -posterize 8 gif:- >> $i.gif
done
mogrify -format pdf *.JPG
pdfjoin *.pdf --outfile newname.pdf