Question

我正在使用具有以下结构的CSV：

"2012-09-01 20:03:15","http://example.com"

数据是我浏览历史记录的清理转储。我有兴趣计算每一天的前五个独特域名。以下是我到目前为止的情况：

from urlparse import urlparse
import csv
from collections import Counter

domains = Counter()

with open("history.csv") as f:
    for row in csv.reader(f):
        d = row[0]
        dt = d[11:19]
        dt = dt.replace(":","")
        dd = d[0:10]
        if (dt < "090000") and (dt > "060000"):
            url = row[1]
            p = urlparse(url)
            ph = p.hostname
            print dd + "," + dt + "," + ph
            domains += Counter([ph])
t = str(domains.most_common(20))

使用d，dt和dd，我将日期和时间分开。使用上面的示例行，dt = 20:03:15，dd = 2012-09-01。 “if（dt＆lt;”090000“）和（dt＆gt;”060000“）”只是说我只对计算在早上6点到9点之间访问过的网站感兴趣。我怎么说“只计算每天早上6点之前访问过的前五个网站”？任何给定日期都有数百行，行按时间顺序排列。

Answer 1

我有兴趣计算每一天的前五个唯一域名。

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

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 < 9: # between 6am and 9am
            today_domains = domains[dt.date()] #  per given day
            domain = urlsplit(url).hostname
            if len(today_domains) < 5 or domain in today_domains:
               today_domains[domain] += 1 # count the first 5 unique domains

print(domains)

Answer 2

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])

基于Python CSV行值的流控制

2 个答案: