Last active
December 28, 2020 17:22
-
-
Save bartoszek/398cfa45a42221927db914080e9ed79e to your computer and use it in GitHub Desktop.
unscramble pdf on gcloud/wsl
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
| #!/bin/bash | |
| #depends | |
| [[ $# != 1 ]] && { echo "useage: $(basename $0) pdf_file" >&2; exit 10; } | |
| hash pdftoppm pdfunite tesseract || sudo apt install -y poppler-utils tesseract-ocr{,-pol} | |
| #tmp | |
| tmp=$(mktemp -d) | |
| trap "rm -rf $tmp" EXIT | |
| #pdf->png | |
| echo "Resterizing ..." >&2 | |
| pdftoppm -png "$1" "$tmp/${1%.pdf}" 2>&1 | |
| echo "OCRing ..." >&2 | |
| #png->pdf | |
| imgs=("$tmp/${1%.pdf}"*.png) | |
| for img in "${imgs[@]}"; do | |
| echo -en "Page: $((++i))/${#imgs[@]}\r" >&2 | |
| tesseract -l pol --psm 1 --oem 1 "$img" "${img%.png}" pdf 1>/dev/null 2>&1 | |
| done | |
| #concat pdfs | |
| echo "Concating ..." >&2 | |
| pdfunite "$tmp/${1%.pdf}"*.pdf "${1%.pdf}".copy.pdf 2>&1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment