MapReduce example

map.py

#!/usr/bin/env python
import sys
import re

prog = re.compile("From.*\S{3}\s(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)\s\d{2}\s\d{2}:\d{2}:\d{2}\s\d{4}")
for line in sys.stdin:
	res =  prog.search(line.strip())
	if res:
		res = res.group().split(" ")
		print '%s %s %s %s\t%s' % (res[2],res[3],res[4],res[6],1)

reduce.py

#!/usr/bin/env python
import sys

results = {}

for line in sys.stdin:
	line = line.strip()
	date,count = line.split("\t",1)
	try:
		count = int(count)
	except:
		pass
	results[date] = results.get(date,0) + count

for date,count in results.iteritems():
	print '%s\t%s' % (date,count)