Lists duplicate BibTex entries in a .bib file

duplicatebibs.py

"""Find duplicate BitTex entries."""

import sys
import os
from collections import Counter
from pprint import pprint


def extract_id(line):
	x = line.index('{')
	y = line.index(',')
	return line[x+1: y].strip()


def main():
	filepath = sys.argv[1]
	assert os.path.exists(filepath)

	with open(filepath, 'r') as fp:
		lines = [extract_id(line) for line in fp.readlines() if line.startswith('@')]

	counts = Counter(lines)
	for k,v in counts.items():
		if v > 1:
			print('{:>35}: {}'.format(k, v))

if __name__ == '__main__':
	main()