Created
September 3, 2012 05:42
-
-
Save finoradin/3607025 to your computer and use it in GitHub Desktop.
Analyzing a CSV of browsing data, where row[0]=timestamp and row[1]=url. Counts first five unique hostnames per day, counts results.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment