Last active
April 28, 2016 01:12
-
-
Save drbr/23949fc921ead6b2917d to your computer and use it in GitHub Desktop.
A shell script that uses pdftk to break a PDF file into smaller files, each with an equal number of pages
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/zsh | |
if (($# != 2)); then | |
echo | |
echo "This script breaks the given PDF file into a set of PDf files," | |
echo "each with block_size pages." | |
echo | |
echo "Usage:" | |
echo " extract_pages.sh filename block_size" | |
echo | |
exit 1 | |
fi | |
filename=$1 | |
block_size=$2 | |
page_count=$(pdftk $filename dump_data &>/dev/null | grep NumberOfPages | awk '{print $2}') | |
echo; echo "Detected $page_count pages in the PDF file"; echo | |
num_blocks=$(($page_count / $block_size)) | |
for i ({1..$num_blocks}); do | |
start_page=$((($i - 1) * $block_size + 1)) | |
end_page=$(($i * $block_size)) | |
echo "Running command:" | |
echo " pdftk $filename cat ${start_page}-${end_page} output ${i}.pdf" | |
pdftk $filename cat ${start_page}-${end_page} output ${i}.pdf | |
echo | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment