Last active
November 18, 2020 19:32
-
-
Save irgendwr/3ad324be7152276d464970bdc82561bf to your computer and use it in GitHub Desktop.
Converts multiple SVGs to a single PDF and applies OCR
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 bash | |
# Requires rsvg-convert, pdfunite and ocrmypdf | |
echo "This script will convert all *.svg files in the current directory to *.pdf files and merge them into a single PDF file called all.pdf and then apply OCR to create all_ocr.pdf. Existing files with the same names will be overwritten." | |
read -p "Do you want to proceed? [Y/n] " -n 1 -r | |
echo | |
if [[ $REPLY =~ ^([Yy]| ) ]] || [[ -z $REPLY ]]; then | |
# Convert all svg files to pdf files | |
for i in *.svg; do | |
rsvg-convert -f pdf -o ${i%.*}.pdf $i | |
done | |
# merge all pdf files into all.pdf | |
pdfunite *.pdf all.pdf | |
# apply ocr, export as all_ocr.pdf | |
ocrmypdf all.pdf all_ocr.pdf | |
fi |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment