duplicatefiledeleter.py

#!/usr/bin/env python

import sys

filename = sys.argv[1]
token = sys.argv[2]

def set_contains(set, token):
	for item in set:
		if token in item:
			return True
	return False

def get_first_not_matching(set, token):
	for item in set:
		if token not in item:
			return item
	return ""
	
	
with open(filename) as lines:
	files = set()
	for line in lines:
		if line == "\n":
			file_to_delete = ""
			if set_contains(files, token):
				file_to_delete = get_first_not_matching(files, token)
			if len(file_to_delete) > 0:
				print file_to_delete.rstrip('\n').replace(" ", "\ ")
			files = set()
		else:
			files.add(line)

usage

USAGE:

1. fdupes -rq . > "fdupes-$(date +"%Y%m%d%H%M%S").txt"
2. token="./the/prefix"; ./duplicatefiledeleter.py fdupes-* "$token" | while read line; do rm -f "$line" > /dev/null; done; rm -f fdupes-*;