intersect.py

import datetime
import time

# Find out lines occurring in both "file_a" and "file_b" and print to "output-<ts>.txt"

def build_timestamp():
  t = time.time()
  return datetime.datetime.fromtimestamp(t).strftime('%Y%m%d-%H%M%S')

# params
file_a_path = 'file_a.txt'
file_b_path = 'file_b.txt'


output_file_path = 'output-' + build_timestamp() + '.txt'

file_a = open(file_a_path, 'r')
file_b = open(file_b_path, 'r')
output_file = open(output_file_path, 'w')

file_a_entries = file_a.read().splitlines()
file_a.close()

file_b_entries = file_b.read().splitlines()
file_b.close()

size_a = len(file_a_entries)
size_b = len(file_b_entries)
print str(size_a) + ' <- file a size'
print str(size_b) + ' <- file b size'

for a in file_a_entries:
  if a in file_b_entries:
    output_file.write(a + '\n')

print 'file with common lines: ' + output_file_path

output_file.close()