PDF Counting in Python

count.py

#!/usr/bin/env python3

import os
import sys
import textract

def main():
	if len(sys.argv) < 2:
		print('command usage: python count.py FileName <optional count to exclude>')
		exit(1)
	else:
		default_exclusion_count = 0
		pdf_file = sys.argv[1]
		count_to_exclude = sys.argv[2] if len(sys.argv) == 3 else default_exclusion_count

		try:
			if os.path.exists(pdf_file):
				pass
		except OSError as err:
			print(str(err))
			exit(1)

		try:
			count = len(textract.process(pdf_file).split(b' ')) - count_to_exclude
		except Exception as err:
			print('')
			print('-------------------------------------------------------------------------------')
			print("Extraction module for Textract not found. Install this from below and try again")
			print('-------------------------------------------------------------------------------')
			print('')
			raise

		print("Word count in %s: %d" %(pdf_file, count))

if __name__ == '__main__':
	main()

Run this to install the right dependencies

pip install textract

# If this doesnt work, or fails at some point do this instead
pip install --no-deps textract