Python模块学习------ 正则表达式

import re
#f = open('data.txt','r')
#for eachline in f.readlines():
    #print re.split('\s\s+', eachline)

## !/usr/bin/env python

from random import randint, choice
from string import lowercase
from sys import maxint
from time import ctime

doms = ('com', 'edu', 'net', 'org', 'gov')

for i in range(randint(5, 10)):
    dtint = randint(0, maxint -1)
    dtstr = ctime(dtint)

    shorter = randint (4,7)
    em = ''
    for j in range(shorter):
        em += choice(lowercase)

    longer = randint (shorter, 12)
    dn = ''
    for j in range(longer):
        dn += choice(lowercase)

    print "%s::%s@%s.%s::%d-%d-%d" % (dtstr, em, dn, choice(doms), dtint, shorter, longer)

运行结果：

Sat Mar 13 01:58:52 2032::cdrnpl@spvxjivzlzux.net::1962727132-6-12
Wed May 17 00:02:49 2034::cvyyd@nrfry.net::2031408169-5-5
Mon Oct 04 00:23:55 2004::zvkxrhv@fwbdncrl.org::1096820635-7-8
Sat Feb 16 01:46:48 2013::lgkzuz@fvratahza.edu::1360950408-6-9
Fri Aug 13 02:20:00 1976::dvsptdy@szsfeub.edu::208722000-7-7
Sun Dec 01 04:54:59 1991::oqdoh@dcuqagr.gov::691534499-5-7
Thu Oct 11 01:32:08 1990::qaoevt@kvbjqd.edu::655579928-6-6
Tue Aug 04 04:33:58 2009::jnejg@jmzwb.gov::1249331638-5-5
Sun Jul 20 08:11:48 2003::nuohl@svtgnn.net::1058659908-5-6
Tue May 29 12:09:07 2001::pgfzf@segsnmusti.net::991109347-5-10

import re
data = 'Mon May 18 01:40:03 2020::mkxvej@pbhhwbxzgk.edu::1589737203-6-10'
patt1 = '^(Mon|Tue|Wed|Thu|Fri|Sat|Sun)'
s_patt = '-(\d)-'
s_search = re.search(s_patt, data)
print s_search.group()
m_patt_0 = '.+(\d+-\d+-\d+)'
m_match_0 = re.match(m_patt_0, data)
print m_match_0.group(1)
m_patt = '.+?(\d+-\d+-\d+)'
m_match = re.match(m_patt, data)
print m_match.group(1)

“非贪婪”操作符“？”， 可以用在“*”、“+”、“？”的后面。可以使正则表达式引擎匹配的字符越少越好。

运行结果：

-6-
3-6-10
1589737203-6-10