Python中re模块的使用

Python的re模块

#预备知识点
#正则表达式regex
#特殊符号和字符 ---> 元字符

正则表达式基础知识

通配符	含义	正则示例	匹配结果
reg1 | reg2	匹配正则表达式reg1或reg2	foo | bar	foo
.	匹配任何字符(\n除外)	a.a	abc
^	匹配字符串起始部分	^a	ab....
$	匹配字符串终止部分	.txt$	a.txt
*	匹配0次或者多次前面出现的正则表达式	a*	aaaaa
+	匹配1次或者多次前面出现的正则表达式	[a-z]+	aasx
?	匹配0次或者1次前面出现的正则表达式	first?	first
{N}	匹配N次前面出现的正则表达式	*.c{2}	first.c abc.c
{M,N}	匹配M~N次前面出现的正则表达式	*.c{0,1}	one.c
[...]	匹配来自字符集的任意单个字符	[abc]	b
[...x-y...]	匹配x~y范围中的任意单个字符	[0-9]	9
[^...]	不匹配次字符集中任意单个字符	[^0-9]	a
(*|+|?|{})?	匹配上面频繁出现符号的非贪婪版	(*|+|?|{})?	({})
(...)	匹配封闭的正则表达式，然后另存为子组	([0-1][0-9])?	12
\d	匹配任何十进制数字	\d.txt	1.txt
\w	匹配任何字母数字字符	\w{2}txt	1.txt
\s	匹配任何空格字符	a\sb	a b
\b	匹配任何单词边界	The\bdog	The dog
\N	匹配已保存的子组	([0-9])\1	1
\.	匹配"."这个字符	a\.txt	a.txt

常用正则表达式

正则表达式	描述	匹配结果
\d+(\.\d*)?	任意整数和浮点数	0.004 2 75.
\b[^\Wa-z0-9_][^\WA-Z0-9_]*\b	首字母只能大写	Boo Foo
^http:\/\/([\w-]+(\.[\w-]+)+(\/[\w-.\/\?%&=\u4e00-\u9fa5]*)?)?$	验证网址	http://www.baidu.com/?id=1
^[\u4e00-\u9fa5]{0,}$	验证汉字	汉字汉字
\w+([-+.']\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*	验证电子邮件	[e-mail]
^[1-9]([0-9]{16}|[0-9]{13})[xX0-9]$	验证身份证	14525419951215445X
^13[0-9]{1}[0-9]{8}|^15[9]{1}[0-9]{8}	验证手机号	138459572***
^(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])$	验证IP	192.168.1.1
^[a-zA-Z0-9]+([a-zA-Z0-9\-\.]+)?\.s|)$	验证域名	baidu.com
^([a-zA-Z]\:|\\)\\([^\\]+\\)*[^\/:*?"<>|]+\.txt(l)?$	验证文件路径	C:\user\wo
<(.*)>(.*)<\/(.*)>|<(.*)\/>	HTML标签匹配	xxxx

 

#re模块
#常用的方法
compile(pattern, flags = 0) 　　　　　　 匹配任何可选的标记来编译正则表达式的模式，然后返回一个正则表达式对象
match(pattern, string, flags = 0)　　　　 使用带有可选标记的正则表达式的模式来匹配字符串。如果匹配成功，返回匹配对象，否则返回None
search(pattern, string ,flags = 0) 　　　　使用可选标记搜索字符串中第一次出现的正则表达式模式。如果匹配成功，则返回匹配对象，否则返回None
findall(pattern, string[,flags] ) 　　　　     查找字符串中所有(非重复)出现的正则表达式模式，并返回一个匹配列表
finditer(pattern, string[,flags] ) 　　　　   与findall()相同，但返回的是一个迭代器。对于每一次匹配，迭代器都能返回一个匹配对象
split(pattern, string, max = 0) 　　　　    根据正则表达式的模式分隔符，split函数将字符串分割为列表，返回匹配列表，分割最多操作max次
group(num = 0) 　　　　　　　　  　　  返回整个匹配对象，或者编号为num的特定子组

 

import re
m = re.search('foo','asdasdfooasd')
#这里如果使用match将匹配不到任何字符串，因为match从第一个a开始匹配
if m is not None:
print(m.group())

regex = <(.*)>(.*)<\/(.*)>|<(.*)\/>
m = re.search(regex,"aa<a>aaaa</a>")
#一样只有search能匹配到标签
if m is not None:
print(m.group())

regex = '(foo\w)(\w)'
m = re.match(r'(foo\w)(\w)','fooasdfooasd')
if m is not None:
print(m.group(1))
print(m.groups())
#输出
#fooa
#('fooa', 's')

regex = 'apple'
m = re.findall(regex,'apple1 apple2 apple3')
print(m)
#输出
#['apple', 'apple', 'apple']

regex = 'apple'
m = [ g.group() for g in re.finditer(regex,'apple1 apple2 apple3')]
print(m)
#输出
#['apple', 'apple', 'apple']

list = [
'aaa, bbb ccc',
'ddd, eee fff',
]
for i in list:
print(re.split(', |(?= (?:[a-z]{3})) ',i))
#输出
#['aaa', 'bbb', 'ccc']
#['ddd', 'eee', 'fff']

 

re模块小实例：

__author__ = 'cq'

import  re
from random import randrange,choice,randint
from string import ascii_lowercase as lc
from time import ctime


#生成数据文件
def generate_data():
    with open('./data.txt','w') as f:
for i in range(randint(20,30)):
            tlds = ('com', 'edu', 'net', 'org', 'gov')
            dtint = randint(100000000,1200000000) #生成时间戳
            dtstr = ctime(dtint)  #将时间戳转化为特定时间格式
            llen = randrange(4, 8) #用户名长度
            login = ''.join(choice(lc) for i in range(llen))  #生成用户名
            dlen = randrange(llen,13)                         #域名长度
            dom = ''.join(choice(lc) for i in range(dlen))    #生成域名

            data_line = "%s::%s@%s.%s::%d-%d-%d\n" % (dtstr, login, dom, choice(tlds), dtint, llen, dlen)
            f.write(data_line) #写入文件
print(data_line)   #打印每行记录



#匹配指定日期的行
def match_date():
    regex = '(Mon|Tue|Wed|Thu|Fri|Sat|Sun)(.*)'
    with open('./data.txt','r') as f:
        m = re.findall(regex,f.read())
for i in m:
print(i)




#匹配在某时间段内的记录
def match_time_slot():
    regex = ' ([0-9]{1,2}) .*([0-9]{4})::(.*)'
# regex = ' ([0-9]{0,2}).*(::)(.*) '
    with open('./data.txt','r') as f:
        m = re.findall(regex,f.read())
for i in m:
if 2000 <= int(i[1]) and int(i[1]) <= 2020 and 20 <= int(i[0]) and int(i[0]) <= 31:
print(i)


#匹配某名单中人员的记录
def match_name():
    regex = '::([a-z]{2,13})@([a-z]{2,13})\.(com|edu|net|org|gov)'
    with open('./data.txt','r') as f:
        m = re.findall(regex,f.read())
for i in m:
print(i)



def main():
    generate_data()
print("\n---------------match_date--------------------\n")
    match_date()
print("\n---------------match_time_slot--------------------\n")
    match_time_slot()
print("\n---------------match_name--------------------\n")
    match_name()


if '__main__' == __name__:
    main()

 

输出结果

Sun Mar  5 00:55:55 1989::[e-mail]::605033755-4-8

Mon Oct 17 17:16:31 2005::[e-mail]::1129540591-4-10

Tue Oct  7 06:33:30 2003::[e-mail]::1065479610-4-12

Mon Oct 16 00:01:06 2006::[e-mail]::1160928066-5-8

Wed Mar 15 06:37:35 2000::[e-mail]::953073455-4-12

Wed Mar 26 12:27:25 1980::[e-mail]::322892845-6-7

Mon Jun  5 13:54:28 1989::[e-mail]::613029268-4-9

Sun Jul 25 05:27:23 2004::[e-mail]::1090704443-7-12

Mon Nov 14 16:15:36 2005::[e-mail]::1131956136-4-6

Sun Jan 14 23:20:42 2007::[e-mail]::1168788042-6-6

Sun Jul 27 02:00:13 1980::[e-mail]::333482413-7-11

Sun Feb 20 16:10:34 2005::[e-mail]::1108887034-6-8

Wed Jun 27 06:13:05 1979::[e-mail]::299283185-5-12

Wed Oct 12 19:52:54 1994::[e-mail]::781962774-5-7

Thu Aug 23 01:46:59 1973::[e-mail]::114889619-6-10

Sat Dec 21 11:36:20 1991::[e-mail]::693286580-4-4

Tue Jun 22 14:42:19 1993::[e-mail]::740731339-6-6

Sun Feb 23 04:50:57 2003::[e-mail]::1045947057-5-5

Fri Jun 10 13:38:02 1983::[e-mail]::424071482-5-10

Sat Jan 24 21:56:37 1998::[e-mail]::885650197-7-7

Sun Jun  3 07:48:45 2007::[e-mail]::1180828125-7-7

Mon Nov 19 00:34:41 2001::[e-mail]::1006101281-5-5

Sat Dec  1 21:01:23 1973::[e-mail]::123598883-4-4

Sun Dec 16 17:42:51 1979::[e-mail]::314185371-4-5

Mon Jul 21 23:46:13 1986::[e-mail]::522344773-5-9


---------------match_date--------------------

('Sun', ' Mar  5 00:55:55 1989::[e-mail]::605033755-4-8')
('Mon', ' Oct 17 17:16:31 2005::[e-mail]::1129540591-4-10')
('Tue', ' Oct  7 06:33:30 2003::[e-mail]::1065479610-4-12')
('Mon', ' Oct 16 00:01:06 2006::[e-mail]::1160928066-5-8')
('Wed', ' Mar 15 06:37:35 2000::[e-mail]::953073455-4-12')
('Wed', ' Mar 26 12:27:25 1980::[e-mail]::322892845-6-7')
('Mon', ' Jun  5 13:54:28 1989::[e-mail]::613029268-4-9')
('Sun', ' Jul 25 05:27:23 2004::[e-mail]::1090704443-7-12')
('Mon', ' Nov 14 16:15:36 2005::[e-mail]::1131956136-4-6')
('Sun', ' Jan 14 23:20:42 2007::[e-mail]::1168788042-6-6')
('Sun', ' Jul 27 02:00:13 1980::[e-mail]::333482413-7-11')
('Sun', ' Feb 20 16:10:34 2005::[e-mail]::1108887034-6-8')
('Wed', ' Jun 27 06:13:05 1979::[e-mail]::299283185-5-12')
('Wed', ' Oct 12 19:52:54 1994::[e-mail]::781962774-5-7')
('Thu', ' Aug 23 01:46:59 1973::[e-mail]::114889619-6-10')
('Sat', ' Dec 21 11:36:20 1991::[e-mail]::693286580-4-4')
('Tue', ' Jun 22 14:42:19 1993::[e-mail]::740731339-6-6')
('Sun', ' Feb 23 04:50:57 2003::[e-mail]::1045947057-5-5')
('Fri', ' Jun 10 13:38:02 1983::[e-mail]::424071482-5-10')
('Sat', ' Jan 24 21:56:37 1998::[e-mail]::885650197-7-7')
('Sun', ' Jun  3 07:48:45 2007::[e-mail]::1180828125-7-7')
('Mon', ' Nov 19 00:34:41 2001::[e-mail]::1006101281-5-5')
('Sat', ' Dec  1 21:01:23 1973::[e-mail]::123598883-4-4')
('Sun', ' Dec 16 17:42:51 1979::[e-mail]::314185371-4-5')
('Mon', ' Jul 21 23:46:13 1986::[e-mail]::522344773-5-9')

---------------match_time_slot--------------------

('25', '2004', '[e-mail]::1090704443-7-12')
('20', '2005', '[e-mail]::1108887034-6-8')
('23', '2003', '[e-mail]::1045947057-5-5')

---------------match_name--------------------

('qvnc', 'ygeowwaf', 'com')
('yene', 'rtewqvvyfe', 'edu')
('wlyi', 'coagmnososzy', 'edu')
('zsgok', 'jkpiplcm', 'edu')
('paok', 'anpekysphicu', 'com')
('bodqoe', 'iydohek', 'org')
('fgiy', 'oppcjnafx', 'gov')
('agmljfx', 'qvxgjqtkiwnl', 'org')
('tctz', 'bcikib', 'gov')
('qqlfkf', 'isslbh', 'com')
('cpiqwau', 'drbpfsfglip', 'edu')
('aguqfd', 'hnrcaged', 'com')
('kowyk', 'ruoackjavkpq', 'net')
('kqaol', 'mzewoas', 'edu')
('uofpdq', 'zdeidbobin', 'org')
('hodw', 'wfbw', 'org')
('azgagm', 'nfmguh', 'org')
('cysfu', 'fnzdo', 'com')
('qdhqw', 'fcdsvlmnhx', 'net')
('dfyicjw', 'fklbymd', 'org')
('wptuyjk', 'tsngnle', 'edu')
('ocjlb', 'nusyk', 'net')
('bvhx', 'lmir', 'net')
('rpgs', 'hppau', 'org')
('fnsro', 'nmbcwdmie', 'org')

Process finished with exit code 0