Takes two files and strips bad chars, spaces and diffs lists

diff_lists.py

'''
Takes two files and strips bad chars, spaces and diffs lists
Usage: python diff_lists.py new.txt old.txt

Example:
:: new.txt ::
len:  14
['1044530', '1179274', '1184663', '1191162', '1195569', '1210586', '1221294', '1224056', '1226094', '1236372', '1237824', '1239042', '1241141', '1241851']
:: old.txt ::
len:  15
['1044530', '1179274', '1184663', '1191162', '1195569', '1210586', '1221294', '1224056', '1226094', '1236372', '1237824', '1239042', '1241141', '1241851', '1241860']
unique items between two lists
['1241860']
'''

import re
import sys

bad_chars = "(){}<>'"

# def data_to_csv(d):
#     li = re.replace('\n|,', d)
#     return map(str.strip, li)

def data_to_list(data):
    for ch in bad_chars:
        data = data.replace(ch, "")
    li = re.split('\n|,', data)
    return map(str.strip, li)

def compare_lists(listA, listB):
    a = list(set(listA) - set(listB))
    b = list(set(listB) - set(listA))
    return a + b

def read_file(f):
    with open(f) as file:
        data = file.read()
    return data

def test_1():
    s = 'a,b,c,d,e,f'
    s1 = 'z,y,x,d,e,f,m,n,o'
    l = data_to_list(s)
    l1 = data_to_list(s1)
    print compare_lists(l, l1)

def diff_lists(f1, f2):
    s = read_file(f1)
    s1 = read_file(f2)
    l = data_to_list(s)
    l.sort()
    print "::", f1, "::"
    print 'len: ', len(l)
    print l
    l1 = data_to_list(s1)
    l1.sort()
    print "::", f2, "::"
    print 'len: ', len(l1)
    print l1
    print "Unique items between two lists"
    out = compare_lists(l, l1)
    print 'len: ', len(out)
    print out
    print "In vertical list format:"
    for p in out: print p

if __name__ == '__main__':
    if len(sys.argv) < 3:
        sys.stderr.write('Usage: python diff_lists.py file1 file2 ')
        sys.exit(1)
    diff_lists(sys.argv[1], sys.argv[2])