Bash script that extracts image files from PDFs in a directory

extract-img-from-pdf.sh

#!/bin/bash

# set the exit status to non-zero (failure) if any commands fail
set -e
# set the exit status to non-zero (failure) if any variable is referenced before being set
set -u
# set the shell to be more strict
set -o pipefail

function show_usage {
  echo "Usage: $0 [-h|--help] directory"
  echo "Extracts images from all PDF files in the specified directory."
  echo ""
  echo "Options:"
  echo "  -h, --help  Show this help message and exit."
}

# check if the directory argument was provided
if [ "$#" -ne 1 ]; then
  show_usage
  exit 1
fi

# check if the -h or --help option was provided
if [ "$1" = "-h" ] || [ "$1" = "--help" ]; then
  show_usage
  exit 0
fi

# set the directory to the argument provided
dir="$1"

# make sure the directory exists
if [ ! -d "$dir" ]; then
  echo "Error: $dir is not a directory."
  exit 1
fi

# make sure the directory contains PDF files
if [ $(find "$dir" -name '*.pdf' | wc -l) -eq 0 ]; then
  echo "Error: $dir does not contain any PDF files."
  exit 1
fi

# loop through all PDF files in the directory
i=0
total=$(find "$dir" -name '*.pdf' | wc -l)
for file in "$dir"/*.pdf; do
  i=$((i + 1))
  echo "Processing $file $i/$total..."
  pdfimages -j -all "$file" "${file%.pdf}"
done
echo "Done!"