Analyzing a CSV of browsing data, where row[0]=timestamp and row[1]=url. Counts first five unique hostnames per day, counts results.

browser_history.py

import csv
from collections import defaultdict, Counter
from datetime import datetime
from urlparse import urlsplit

indiv = Counter()

domains = defaultdict(lambda: defaultdict(int))
with open("history.csv", "rb") as f:
	for timestr, url in csv.reader(f):
		dt = datetime.strptime(timestr, "%Y-%m-%d %H:%M:%S")
		if 6 <= dt.hour < 11: # between 6am and 11am
			today_domains = domains[dt.date()]
			domain = urlsplit(url).hostname
			if len(today_domains) < 5 and domain not in today_domains:
				today_domains[domain] += 1
				indiv += Counter([domain])
for domain in indiv:
	print '%s,%d' % (domain, indiv[domain])