Lucas Vivohost
f313e9edfa
refactor: optimize PDF image splitting script - simplify path and filename handling - safely quote file paths - improve temporary directory management - remove redundant shell pipelines - simplify image batching - add error handling and progress output - document usage and processing steps
102 lines
2.0 KiB
Bash
Executable File
102 lines
2.0 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
# Convert a PDF into processed JPG images and split them into
|
|
# multiple PDF files, with a maximum of 100 images per output PDF.
|
|
|
|
set -e
|
|
|
|
if [ "$#" -ne 1 ]; then
|
|
echo "Usage: $0 <pdf-file>"
|
|
exit 1
|
|
fi
|
|
|
|
pdf_file="$1"
|
|
|
|
if [ ! -f "$pdf_file" ]; then
|
|
echo "Error: '$pdf_file' does not exist."
|
|
exit 1
|
|
fi
|
|
|
|
echo "Using $pdf_file"
|
|
|
|
# Resolve the input directory and filename.
|
|
pdf_dir="$(cd "$(dirname "$pdf_file")" && pwd)"
|
|
pdf_name="$(basename "$pdf_file")"
|
|
base_name="${pdf_name%.*}"
|
|
|
|
buffer_dir="$pdf_dir/.BUFFERFOLDER"
|
|
|
|
# Recreate the temporary working directory.
|
|
rm -rf "$buffer_dir"
|
|
mkdir -p "$buffer_dir"
|
|
|
|
cp "$pdf_file" "$buffer_dir/$pdf_name"
|
|
|
|
cd "$buffer_dir"
|
|
|
|
echo "Extracting images..."
|
|
|
|
# Extract PDF images as PNG.
|
|
pdfimages -png "$pdf_name" "$base_name"
|
|
|
|
count=0
|
|
|
|
shopt -s nullglob
|
|
|
|
for img in *.png; do
|
|
jpg="${img%.png}.jpg"
|
|
|
|
echo "Processing $jpg"
|
|
|
|
# PNG -> JPG
|
|
convert "$img" "$jpg"
|
|
rm "$img"
|
|
|
|
# Normalize image dimensions.
|
|
convert "$jpg" -resize 2550x3300! "$jpg"
|
|
|
|
# Use different crop dimensions for images containing "000".
|
|
if [[ "$jpg" == *000* ]]; then
|
|
convert "$jpg" -crop 2206x3200+200+50 "$jpg"
|
|
else
|
|
convert "$jpg" -crop 2106x3200+200+50 "$jpg"
|
|
fi
|
|
|
|
# Remove white background.
|
|
convert "$jpg" -fuzz 20% -transparent White "$jpg"
|
|
|
|
# Center image on a white 2550x3300 canvas.
|
|
convert "$jpg" \
|
|
-resize 2550x3300 \
|
|
-gravity center \
|
|
-background White \
|
|
-extent 2550x3300 \
|
|
"$jpg"
|
|
|
|
# Group images into batches of 100.
|
|
split_var=$((count / 100))
|
|
split_dir="split_${split_var}"
|
|
|
|
mkdir -p "$split_dir"
|
|
mv "$jpg" "$split_dir/"
|
|
|
|
((count++)) || true
|
|
done
|
|
|
|
# Convert each group of images into a PDF.
|
|
for split_dir in split_*; do
|
|
[ -d "$split_dir" ] || continue
|
|
|
|
split_number="${split_dir#split_}"
|
|
|
|
echo "Converting Part $split_number"
|
|
|
|
convert "$split_dir"/*.jpg \
|
|
"$pdf_dir/${base_name}_split_${split_number}.pdf"
|
|
done
|
|
|
|
# Remove temporary files.
|
|
cd "$pdf_dir"
|
|
rm -rf "$buffer_dir"
|
|
|
|
echo "Done." |