import sys
import re
import operator

regex = re.compile(r'^(\[.*\])\ (.*)\ (\d+\.\d+\.\d+\.\d+)\ \"(.*)\"\ (\d+) \"(.*)\"\ \"(.*)\"\ \"(.*)\"\ (.*)\ -\ (.*)$')


if len(sys.argv) < 2:
	print("Usage: script <logfile>")
	sys.exit(1)

def gettop10(arr, top):
	myDict = {}
	for line in arr:
		if line['referer'] not in myDict:
			myDict[line['referer']] = 1
		else:
			myDict[line['referer']] += 1
	for i in (sorted(myDict.items(), key=operator.itemgetter(1), reverse=True)[:top]):
		print(i)

def calcavgtime(arr):
	time = 0.0
	count = 0
	for line in arr:
		if int(line['response']) == 200:
			count += 1
			time += float(line['resp_time'])

	print("Avg time: %f\nNum 200: %d" % (time/count, count))

logLines = []
data = open(sys.argv[1], 'r').readlines()
for line in data:
	res = re.match(regex, line.strip())
	logLines.append({"date" : res.group(1), "url" : res.group(2), "ip" : res.group(3), "request" : res.group(4), "response" : res.group(5), "referer" : res.group(6), "UA" : res.group(7), "idk" : res.group(8), "resp_time" : res.group(9), "idk_num" : res.group(10)})



gettop10(logLines, 10)
calcavgtime(logLines)