dircomp.py

import os, sys, json
from difflib import SequenceMatcher
from operator import itemgetter, attrgetter

path1 = sys.argv[1]
path2 = sys.argv[2]

ordered_differences_list=[]

if not (path1 and path2 ) :
	print 'Usage dircomp.py path1 path2'
	exit()
count=0
for root, dirs, files in os.walk(path1):
	for name in files:
		print str(count)+' '+os.path.join(root, name)
		if not os.path.isfile(path2+name):
			continue
		
		with open(os.path.join(root, name), 'r') as f1:
			c1=f1.read()
			with open(os.path.join(path2, name), 'r') as f2:
				c2=f2.read()
				s=SequenceMatcher(None, c1, c2)
				if s.ratio()<1:
					ordered_differences_list.append( [name, s.ratio() ] )
				count +=1

ordered_differences_list.sort( key=itemgetter(1) )
print ordered_differences_list
#with open('lastdircomp.txt', 'w') as outf:
#	json.dump(ordered_differences_list, outf)