-
-
Save grahamc/7550de3b490598439558e6840fb59204 to your computer and use it in GitHub Desktop.
scan all the fronts, then the backs. stitch them together and ocrmypdf them.
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
#!/usr/bin/env nix-shell | |
#!nix-shell -I nixpkgs=/home/grahamc/projects/github.com/NixOS/nixpkgs | |
#!nix-shell -i bash -p sane-frontends netpbm imagemagick poppler_utils ocrmypdf | |
set -x | |
make_pdfs() ( | |
scanadf \ | |
-d pixma:04A91774_21C8AC \ | |
--source "Automatic Document Feeder" \ | |
--mode color \ | |
--resolution 300 \ | |
-l auto \ | |
-t auto | |
rm ./*.ps ./*.png ./*.pdf | |
for f in $(find -type f -name 'image-*' | sort -n); do | |
if ! pnmtopng "$f" > "$f.png" ; then | |
rm "$f.png" | |
continue | |
fi | |
convert "$f.png" "$f.pdf" | |
rm "$f.png" | |
done | |
) | |
( | |
cd fronts | |
make_pdfs | |
) | |
( | |
cd backs | |
make_pdfs | |
) | |
( | |
mkdir unite | |
cd unite | |
i=0 | |
while true; do | |
i=$(( i + 1 )) | |
front=$(find ../fronts -type f -name '*.pdf' | sort -n | head -n1) | |
if [ "x$front" != "x" ]; then | |
mv "$front" "./page-$i.pdf" | |
fi | |
i=$(( i + 1 )) | |
back=$(find ../backs -type f -name '*.pdf' | sort -nr | head -n1) | |
if [ "x$back" != "x" ]; then | |
mv "$back" "./page-$i.pdf" | |
else | |
break | |
fi | |
done | |
) | |
pdfunite $(find ./unite -type f -name '*.pdf' | sort -n) ./united.pdf | |
ocrmypdf \ | |
--clean \ | |
--rotate-pages \ | |
--deskew \ | |
--remove-background \ | |
--sidecar ./scan.txt \ | |
./united.pdf \ | |
./output.pdf | |
exit 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment