pdftotextOnDir.sh

#!/bin/bash

# pdftotextOnDir
# Runs pdftotext on all files in a directory 
# Author - Brendan Heussler ([email protected])
# argument 1 - Input Directory
# argument 2 - Output Directory

input_directory=$1	# Input Directory
output_directory=$2	# Output Directory

# Check to see if the input directory exists
if [ -d "$input_directory" ]; then
	echo "Input Directory Exists"
else
	echo "Input Directory Does Not Exist"
	echo "Terminating $0"
	exit 1
fi

# Check to see if the output directory exists
if [ -d "$output_directory" ]; then
	echo "Output Directory Exists"
else
	echo "Output Directory Does Not Exist"
	echo "Creating Output Directory"
	mkdir $output_directory
fi

# Run pdftotext on all files in the input directory
for file in $input_directory* 
do
	echo "Running pdftotext on $file"
	file_basename=$(basename $file .pdf)
	output_filename=${file_basename}.txt 
	pdftotext "$file" "$output_directory$output_filename"
done