Rasterize PDF files

rasterize_pdf.sh

#!/bin/bash

# Terminate on first error
set -e

# Check if input file is provided
if [ -z "$1" ]; then
  echo "Usage: $0 <input_file.pdf>"
  exit 1
fi

# Get the input file name and its directory
input_file="$1"
input_dir=$(dirname -- "$input_file")
base_name=$(basename -- "$input_file")
name_no_ext="${base_name%.pdf}"

# Create a temporary directory in /tmp
tmp_dir=$(mktemp -d -p "$HOME")

# Burst the original PDF into individual pages
pdftk "$input_file" burst output "${tmp_dir}/${name_no_ext}_page_%04d.pdf"

# # Loop over each page and rasterize it
# for page in ${tmp_dir}/${name_no_ext}_page_*.pdf; do
#   convert -density 100 "$page" -quality 90 "${tmp_dir}/raster_$(basename -- "$page")"
# done

# Parallel
export tmp_dir
find "${tmp_dir}" -name "${name_no_ext}_page_*.pdf" | parallel --eta 'convert -density 300 {} -quality 90 ${tmp_dir}/raster_{/}'


# Combine the rasterized pages into one PDF
output_file="${input_dir}/${name_no_ext}.rasterized.pdf"
pdftk ${tmp_dir}/raster_${name_no_ext}_page_*.pdf cat output "$output_file"

# Clean up the individual pages and metadata
rm -r "$tmp_dir"