A shell script that runs OCRmyPDF with options suitable for document archival in PDFs while supporting text search and file optimization. Meant to be used in any platform that supports Homebrew, but can be adapted to any other Linux/Unix platform so long as the OCRmyPDF and tesseract dependencies are installed.

ocrmypdf.sh

#!/bin/bash

# This script performs OCR on a PDF file using OCRmyPDF, 
# optimizes images and document layout.
#
# Uses OCRmyPDF - https://github.com/ocrmypdf/OCRmyPDF
# 
# Dependencies:
# - `brew install tesseract-lang``  # Option 2: for all 
#   language packs (to support spanish and others)
# - OCRmyPDF: Install via Homebrew with the command 
#   `brew install ocrmypdf`.
# - Ensure Homebrew is installed on your Mac (https://brew.sh).

# Check if the correct number of arguments is provided
if [ $# -ne 1 ]; then
  echo "Usage: $0 <input-pdf-file-path>"
  exit 1
fi

# Input PDF file path
input_pdf="$1"

# Perform OCR with specified options
#  -l eng+spa \          # Support for both English and Spanish languages
#  --output-type pdfa \  # Enforce PDF/A for long-term archiving
#  --oversample 300 \    # Oversample to 300 DPI to improve OCR results
#  --force-ocr \         # Force OCR on pages that already contain text
#  -O 1 \                # Use safe, lossless optimizations
#  --deskew              # For pages that are not straight
#  --rotate-pages        # Rotates pages that need it

ocrmypdf \
  -l eng+spa \
  --output-type pdfa \
  --oversample 300 \
  --force-ocr \
  -O 1 \
  --deskew \
  --rotate-pages \
  "$input_pdf" "$input_pdf"

# Check if the OCR was successful
if [ $? -eq 0 ]; then
  echo "OCR completed successfully."
else
  echo "OCR encountered an error."
  exit 1
fi