pdfocr - script to transform a PDF containing a scanned book into a searchable PDF

pdfocr

#!/bin/bash

# This is a script to transform a PDF containing a scanned book into a searchable PDF.
# Based on previous script and many good tips by Konrad Voelkel:
# http://blog.konradvoelkel.de/2010/01/linux-ocr-and-pdf-problem-solved/
# http://blog.konradvoelkel.de/2013/03/scan-to-pdfa/
# Depends on convert (ImageMagick), pdftk and hocr2pdf (ExactImage).
# $ sudo apt-get install imagemagick pdftk exactimage
# You also need at least one OCR software which can be either tesseract or cuneiform.
# $ sudo apt-get install tesseract-ocr
# $ sudo apt-get install cuneiform
# To install languages into tesseract do (e.g. for Portuguese):
# $ sudo apt-get install tesseract-ocr-por

echo "usage: ./pdfocr.sh document.pdf ocr-sfw split lang author title"
# where ocr-sfw is either tesseract or cuneiform
# split is either 0 (already single-paged) or 1 (2 book-pages per pdf-page)
# lang is a language as in "tesseract --list-langs" or "cuneiform -l".
# and author, title are used for the PDF metadata.
#
# usage example:
# ./pdfocr.sh SomeFile.pdf tesseract 1 por "Some Author" "Some Title"
pdftk "$1" burst dont_ask
for f in pg_*.pdf
do
	if [ "1" == "$3" ]; then
		convert -normalize -density 300 -depth 8 -crop 50%x100% +repage $f "$f.png"
	else
		convert -normalize -density 300 -depth 8 $f "$f.png"
	fi
done
rm pg_*.pdf

for f in pg_*.png
do
	if [ "tesseract" == "$2" ]; then
		tesseract -l $4 -psm 1 $f $f hocr
	elif [ "cuneiform" == "$2" ]; then
		cuneiform -l $4 -f hocr -o "$f.html" $f
	else
		echo "$2 is not a valid OCR software."
	fi
	hocr2pdf -i $f -r 300 -s -o "$f.pdf" < "$f.html"
done

pdftk pg_*.pdf cat output merged.pdf

pdftk merged.pdf update_info_utf8 doc_data.txt output merged+data.pdf
echo "InfoBegin" > in.info
echo "InfoKey: Author" >> in.info
echo "InfoValue: $5" >> in.info
echo "InfoBegin" >> in.info
echo "InfoKey: Title" >> in.info
echo "InfoValue: $6" >> in.info
echo "InfoBegin" >> in.info
echo "InfoKey: Creator" >> in.info
echo "InfoValue: PDF OCR scan script" >> in.info
in_filename="${1%.*}"
pdftk merged+data.pdf update_info_utf8 in.info output "$in_filename-ocr.pdf"

rm -r doc_data.txt in.info merged* pg_*