正则表达式 RE模块

　　

正则表达式：re模块

1.正则表达式的作用是：实现对字符串的模糊查询。

2.正则表达式使用的元字符（特殊符号和字符）：

 

http://blog.csdn.net/yufenghyc/article/details/51078107

 

 

 

# =================================匹配模式=================================
#一对一的匹配
# 'hello'.replace(old,new)
# 'hello'.find('pattern')

#正则匹配
import re
#\w与\W
print(re.findall('\w','hello egon 123')) #['h', 'e', 'l', 'l', 'o', 'e', 'g', 'o', 'n', '1', '2', '3']
print(re.findall('\W','hello egon 123')) #[' ', ' ']

#\s与\S
print(re.findall('\s','hello  egon  123')) #[' ', ' ', ' ', ' ']
print(re.findall('\S','hello  egon  123')) #['h', 'e', 'l', 'l', 'o', 'e', 'g', 'o', 'n', '1', '2', '3']

#\n \t都是空,都可以被\s匹配
print(re.findall('\s','hello \n egon \t 123')) #[' ', '\n', ' ', ' ', '\t', ' ']

#\n与\t
print(re.findall(r'\n','hello egon \n123')) #['\n']
print(re.findall(r'\t','hello egon\t123')) #['\n']

#\d与\D
print(re.findall('\d','hello egon 123')) #['1', '2', '3']
print(re.findall('\D','hello egon 123')) #['h', 'e', 'l', 'l', 'o', ' ', 'e', 'g', 'o', 'n', ' ']

#\A与\Z
print(re.findall('\Ahe','hello egon 123')) #['he'],\A==>^
print(re.findall('123\Z','hello egon 123')) #['he'],\Z==>$

#^与$
print(re.findall('^h','hello egon 123')) #['h']
print(re.findall('3$','hello egon 123')) #['3']

# 重复匹配：| . | * | ? | .* | .*? | + | {n,m} |
#.
print(re.findall('a.b','a1b')) #['a1b']
print(re.findall('a.b','a1b a*b a b aaab')) #['a1b', 'a*b', 'a b', 'aab']
print(re.findall('a.b','a\nb')) #[]
print(re.findall('a.b','a\nb',re.S)) #['a\nb']
print(re.findall('a.b','a\nb',re.DOTALL)) #['a\nb']同上一条意思一样

#*
print(re.findall('ab*','bbbbbbb')) #[]
print(re.findall('ab*','a')) #['a']
print(re.findall('ab*','abbbb')) #['abbbb']

#?
print(re.findall('ab?','a')) #['a']
print(re.findall('ab?','abbb')) #['ab']
#匹配所有包含小数在内的数字
print(re.findall('\d+\.?\d*',"asdfasdf123as1.13dfa12adsf1asdf3")) #['123', '1.13', '12', '1', '3']

#.*默认为贪婪匹配
print(re.findall('a.*b','a1b22222222b')) #['a1b22222222b']

#.*?为非贪婪匹配：推荐使用
print(re.findall('a.*?b','a1b22222222b')) #['a1b']

#+
print(re.findall('ab+','a')) #[]
print(re.findall('ab+','abbb')) #['abbb']

#{n,m}
print(re.findall('ab{2}','abbb')) #['abb']
print(re.findall('ab{2,4}','abbb')) #['abb']
print(re.findall('ab{1,}','abbb')) #'ab{1,}' ===> 'ab+'
print(re.findall('ab{0,}','abbb')) #'ab{0,}' ===> 'ab*'

#[]
print(re.findall('a[1*-]b','a1b a*b a-b')) #[]内的都为普通字符了，且如果-没有被转意的话，应该放到[]的开头或结尾
print(re.findall('a[^1*-]b','a1b a*b a-b a=b')) #[]内的^代表的意思是取反，所以结果为['a=b']
print(re.findall('a[0-9]b','a1b a*b a-b a=b')) #[]内的^代表的意思是取反，所以结果为['a=b']
print(re.findall('a[a-z]b','a1b a*b a-b a=b aeb')) #[]内的^代表的意思是取反，所以结果为['a=b']
print(re.findall('a[a-zA-Z]b','a1b a*b a-b a=b aeb aEb')) #[]内的^代表的意思是取反，所以结果为['a=b']

#\# print(re.findall('a\\c','a\c')) #对于正则来说a\\c确实可以匹配到a\c,但是在python解释器读取a\\c时，会发生转义，然后交给re去执行，所以抛出异常
print(re.findall(r'a\\c','a\c')) #r代表告诉解释器使用rawstring，即原生字符串，把我们正则内的所有符号都当普通字符处理，不要转义
print(re.findall('a\\\\c','a\c')) #同上面的意思一样，和上面的结果一样都是['a\\c']

#():分组
print(re.findall('ab+','ababab123')) #['ab', 'ab', 'ab']
print(re.findall('(ab)+123','ababab123')) #['ab']，匹配到末尾的ab123中的ab
print(re.findall('(?:ab)+123','ababab123')) #findall的结果不是匹配的全部内容，而是组内的内容,?:可以让结果为匹配的全部内容

#|
print(re.findall('compan(?:y|ies)','Too many companies have gone bankrupt, and the next one is my company'))

import re
print(re.findall('.','abc'))
print(re.findall('.*','abc'))
print(re.findall('.+','abc'))
print(re.findall('.?','abc'))
print(re.findall('.{2}','abcd'))
print(re.findall('.{1,3}','abcd'))
print(re.findall('^abc','abcdcadasd'))
print(re.findall('^abc.+','abcdcadasd'))
print(re.findall('asd$','abcdcadasd'))
print(re.findall('.+asd$','abcdcadasd'))
print(re.findall(r'\byuan','yuanasas yuan saddsadsyuan'))
print(re.findall(r'yuan\b','yuanasas sasayuan saddsadsyuan'))
print(re.findall(r'\Byuan','yuanasas sasayuansad yuan dasdasyuan'))
print(re.findall('\Byuan','yu1anssyuan adsdyuandasdyuanyuan yuan1yuan'))
print(re.findall('\Byuan','yuanssyuan adsdyuandasdyuan'))
print(re.findall('y[abcd]an','yaanybanycanydn'))
print(re.findall('ab|cd','abcd'))  #不能用[]，因为[]只使用与单个的字符的or，多个字符要用|
print(re.findall('[0-9]+','12123dsad2233dasd2'))
print(re.findall('[A-z]+','dadas11daADDASDd2dsadasddasdasds11'))
print(re.findall('[^A-z]+','asdasd12123123dd313121d2122121'))#[]里面的^取非
print(re.findall('[^aeiou]+','asdascas12221oisaouidoasodji'))#非元音字符
res = re.search('\d+(\.?\d*)','1.123 121.21 0.122')
res1 =re.compile('\d{4}\-\d{8}')
print(res1.findall('02112-1212123dsada0791-888888881212dsadas'))
res2 = re.compile('\w+@\w+\.\w+')
print(res2.findall('[e-mail]'))
print(res2.findall('[e-mail]'))
print(re.findall('.+(\d+-\d+-\d+)','Tue Jan 13 04:26:57 1970:: [e-mail]::1024017-4-6'))  #贪婪匹配
print(re.findall('.+?(\d+-\d+-\d+)','Tue Jan 13 04:26:57 1970:: [e-mail]::1024017-4-6')) #非贪婪匹配


>>>>>>>>>
['a', 'b', 'c']
['abc', '']
['abc']
['a', 'b', 'c', '']
['ab', 'cd']
['abc', 'd']
['abc']
['abcdcadasd']
['asd']
['abcdcadasd']
['yuan', 'yuan']
['yuan', 'yuan']
['yuan', 'yuan']
['yuan', 'yuan', 'yuan', 'yuan', 'yuan']
['yuan', 'yuan', 'yuan']
['yaan', 'yban', 'ycan']
['ab', 'cd']
['12123', '2233', '2']
['dadas', 'daADDASDd', 'dsadasddasdasds']
['12123123', '313121', '2122121']
['sd', 'sc', 's12221', 's', 'd', 's', 'dj']
['0791-88888888']
['[e-mail]']
['[e-mail]']
['7-4-6']
['1024017-4-6']

3.re模块的方法：

# ===========================re模块提供的方法介绍===========================
import re
#1
print(re.findall('e','alex make love') )   #['e', 'e', 'e'],返回所有满足匹配条件的结果,放在列表里
#2
print(re.search('e','alex make love').group()) #e,只到找到第一个匹配然后返回一个包含匹配信息的对象,该对象可以通过调用group()方法得到匹配的字符串,如果字符串没有匹配，则返回None。

#3
print(re.match('e','alex make love'))    #None,同search,不过在字符串开始处进行匹配,完全可以用search+^代替match

#4
print(re.split('[ab]','abcd'))     #['', '', 'cd']，先按'a'分割得到''和'bcd',再对''和'bcd'分别按'b'分割

#5
print('===>',re.sub('a','A','alex make love')) #===> Alex mAke love，不指定n，默认替换所有
print('===>',re.sub('a','A','alex make love',1)) #===> Alex make love
print('===>',re.sub('a','A','alex make love',2)) #===> Alex mAke love
print('===>',re.sub('^(\w+)(.*?\s)(\w+)(.*?\s)(\w+)(.*?)$',r'\5\2\3\4\1','alex make love')) #===> love make alex

print('===>',re.subn('a','A','alex make love')) #===> ('Alex mAke love', 2),结果带有总共替换的个数


#6
obj=re.compile('\d{2}')

print(obj.search('abc123eeee').group()) #12
print(obj.findall('abc123eeee')) #['12'],重用了obj

import re
print(re.findall("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>","<h1>hello</h1>")) #['h1']
print(re.search("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>","<h1>hello</h1>").group()) #<h1>hello</h1>
print(re.search("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>","<h1>hello</h1>").groupdict()) #<h1>hello</h1>

print(re.search(r"<(\w+)>\w+</(\w+)>","<h1>hello</h1>").group())
print(re.search(r"<(\w+)>\w+</\1>","<h1>hello</h1>").group())

import re

print(re.findall(r'-?\d+\.?\d*',"1-12*(60+(-40.35/5)-(-4*3))")) #找出所有数字['1', '-12', '60', '-40.35', '5', '-4', '3']


#使用|，先匹配的先生效，|左边是匹配小数，而findall最终结果是查看分组，所有即使匹配成功小数也不会存入结果
#而不是小数时，就去匹配(-?\d+)，匹配到的自然就是，非小数的数，在此处即整数
print(re.findall(r"-?\d+\.\d*|(-?\d+)","1-2*(60+(-40.35/5)-(-4*3))")) #找出所有整数['1', '-2', '60', '', '5', '-4', '3']

#为何同样的表达式search与findall却有不同结果:
print(re.search('\(([\+\-\*\/]*\d+\.?\d*)+\)',"1-12*(60+(-40.35/5)-(-4*3))").group()) #(-40.35/5)
print(re.findall('\(([\+\-\*\/]*\d+\.?\d*)+\)',"1-12*(60+(-40.35/5)-(-4*3))")) #['/5', '*3']

#看这个例子:(\d)+相当于(\d)(\d)(\d)(\d)...,是一系列分组
print(re.search('(\d)+','123').group()) #group的作用是将所有组拼接到一起显示出来
print(re.findall('(\d)+','123')) #findall结果是组内的结果,且是最后一个组的结果

search与findall

 

#_*_coding:utf-8_*_
__author__ = 'Linhaifeng'
#在线调试工具:tool.oschina.net/regex/#
import re

s='''
http://www.baidu.com
[e-mail]
你好
010-3141
'''

#最常规匹配
# content='Hello 123 456 World_This is a Regex Demo'
# res=re.match('Hello\s\d\d\d\s\d{3}\s\w{10}.*Demo',content)
# print(res)
# print(res.group())
# print(res.span())

#泛匹配
# content='Hello 123 456 World_This is a Regex Demo'
# res=re.match('^Hello.*Demo',content)
# print(res.group())


#匹配目标,获得指定数据

# content='Hello 123 456 World_This is a Regex Demo'
# res=re.match('^Hello\s(\d+)\s(\d+)\s.*Demo',content)
# print(res.group()) #取所有匹配的内容
# print(res.group(1)) #取匹配的第一个括号内的内容
# print(res.group(2)) #去陪陪的第二个括号内的内容



#贪婪匹配:.*代表匹配尽可能多的字符
# import re
# content='Hello 123 456 World_This is a Regex Demo'
#
# res=re.match('^He.*(\d+).*Demo$',content)
# print(res.group(1)) #只打印6,因为.*会尽可能多的匹配,然后后面跟至少一个数字


#非贪婪匹配:?匹配尽可能少的字符
# import re
# content='Hello 123 456 World_This is a Regex Demo'
#
# res=re.match('^He.*?(\d+).*Demo$',content)
# print(res.group(1)) #只打印6,因为.*会尽可能多的匹配,然后后面跟至少一个数字


#匹配模式:.不能匹配换行符
content='''Hello 123456 World_This
is a Regex Demo
'''
# res=re.match('He.*?(\d+).*?Demo$',content)
# print(res) #输出None

# res=re.match('He.*?(\d+).*?Demo$',content,re.S) #re.S让.可以匹配换行符
# print(res)
# print(res.group(1))


#转义:\

# content='price is $5.00'
# res=re.match('price is $5.00',content)
# print(res)
#
# res=re.match('price is \$5\.00',content)
# print(res)


#总结:尽量精简,详细的如下
    # 尽量使用泛匹配模式.*
    # 尽量使用非贪婪模式:.*?
    # 使用括号得到匹配目标:用group(n)去取得结果
    # 有换行符就用re.S:修改模式















#re.search:会扫描整个字符串,不会从头开始,找到第一个匹配的结果就会返回

# import re
# content='Extra strings Hello 123 456 World_This is a Regex Demo Extra strings'
#
# res=re.match('Hello.*?(\d+).*?Demo',content)
# print(res) #输出结果为None

#
# import re
# content='Extra strings Hello 123 456 World_This is a Regex Demo Extra strings'
#
# res=re.search('Hello.*?(\d+).*?Demo',content) #
# print(res.group(1)) #输出结果为



#re.search:只要一个结果,匹配演练,
import re
content='''
<tbody>
<tr id="4766303201494371851675" class="even "><td><div class="hd"><span class="num">1</span><div class="rk "><span class="u-icn u-icn-75"></span></div></div></td><td class="rank"><div class="f-cb"><div class="tt"><a href="/song?id=476630320"><img class="rpic" src="http://p1.music.126.net/Wl7T1LBRhZFg0O26nnR2iQ==/19217264230385030.jpg?param=50y50&amp;quality=100"></a><span data-res-id="476630320" "
# res=re.search('<a\shref=.*?<b\stitle="(.*?)".*?b>',content)
# print(res.group(1))


#re.findall:找到符合条件的所有结果
# res=re.findall('<a\shref=.*?<b\stitle="(.*?)".*?b>',content)
# for i in res:
#     print(i)



#re.sub:字符串替换
import re
content='Extra strings Hello 123 456 World_This is a Regex Demo Extra strings'

# content=re.sub('\d+','',content)
# print(content)


#用\1取得第一个括号的内容
#用法:将123与456换位置
# import re
# content='Extra strings Hello 123 456 World_This is a Regex Demo Extra strings'
#
# # content=re.sub('(Extra.*?)(\d+)(\s)(\d+)(.*?strings)',r'\1\4\3\2\5',content)
# content=re.sub('(\d+)(\s)(\d+)',r'\3\2\1',content)
# print(content)




# import re
# content='Extra strings Hello 123 456 World_This is a Regex Demo Extra strings'
#
# res=re.search('Extra.*?(\d+).*strings',content)
# print(res.group(1))


# import requests,re
# respone=requests.get('https://book.douban.com/').text

# print(respone)
# print('======'*1000)
# print('======'*1000)
# print('======'*1000)
# print('======'*1000)
# res=re.findall('<li.*?cover.*?href="(.*?)".*?title="(.*?)">.*?more-meta.*?author">(.*?)</span.*?year">(.*?)</span.*?publisher">(.*?)</span.*?</li>',respone,re.S)
# # res=re.findall('<li.*?cover.*?href="(.*?)".*?more-meta.*?author">(.*?)</span.*?year">(.*?)</span.*?publisher">(.*?)</span>.*?</li>',respone,re.S)
#
#
# for i in res:
#     print('%s    %s    %s   %s' %(i[0].strip(),i[1].strip(),i[2].strip(),i[3].strip()))

#计算器作业参考：http://www.cnblogs.com/wupeiqi/articles/4949995.html
expression='1-2*((60+2*(-3-40.0/5)*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2))'

content=re.search('\(([\-\+\*\/]*\d+\.?\d*)+\)',expression).group() #(-3-40.0/5)

import re ,sys
'1-2*((60+2*(-3-40.0/5*-4)*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2))'
def Multiply_divide(variate_list):
    multiply_variate= variate_list[0]
    pattern = re.compile('\d+\.*\d*[\*\/]{1}[\+\-]?\d+\.*\d*')
    flag = pattern.search(multiply_variate)
    if not flag:
        return
    multiply_variate1 = pattern.search(multiply_variate).group()
    # print(multiply_variate1)
    if multiply_variate1.__contains__('*'):
        n1,n2 = multiply_variate1.split('*')
        value = float(n1) * float(n2)
    else:
        n1,n2 = multiply_variate1.split('/')
        value = float(n1) / float(n2)
    before,after = pattern.split(multiply_variate,1)
    new_variate = "%s%s%s" % (before,value,after)
    variate_list[0] = new_variate
    Multiply_divide(variate_list)
def add_substract(variate_list):
    add_variate = variate_list[0]
    while True:
        if add_variate.__contains__('--') or add_variate.__contains__('+-') or add_variate.__contains__('++') or add_variate.__contains__('-+'):
            add_variate =add_variate.replace('--','+')
            add_variate =add_variate.replace('+-','-')
            add_variate =add_variate.replace('++','+')
            add_variate =add_variate.replace('-+','-')
        else:break
    pattern = re.compile('[\+\-]?\d+\.?\d*[\+|-]{1}\d+\.?\d*')
    flag = pattern.search(add_variate)
    if not flag:
        return
    add_variate1 = pattern.search(add_variate).group()
    if add_variate1.startswith('-'):
        variate_list[1] = 2
        add_variate1 = add_variate1.replace('-','&')
        add_variate1 = add_variate1.replace('+','-')
        add_variate1 = add_variate1.replace('&','+')
        add_variate1 = add_variate1[1:len(add_variate1)-1]
    if add_variate1.__contains__('-'):
        n1,n2 = add_variate1.split('-')
        value = float(n1) - float(n2)
    if add_variate1.__contains__('+'):
        n1,n2 = add_variate1.split('+')
        value = float(n1) + float(n2)
    if variate_list[1] == 2:
        value = value * -1
        variate_list[1] = 1
    else:value = value
    before,after = pattern.split(add_variate,1)
    new_str = '%s%s%s' % (before,value,after)
    variate_list[0] = new_str
    add_substract(variate_list)
def computer(arg):
    variate_list = [arg,0]
    # print(variate_list)
    Multiply_divide(variate_list)
    add_substract(variate_list)
    # print(variate_list)
    return variate_list[0]
def operations(arg):
    expression = arg
    computerc_pattern = re.compile('\(([\+\-\*\/]*\d+\.*\d*){2,}\)')
    if not computerc_pattern.search(expression):
        final = computer(expression)
        return final
    variate = computerc_pattern.search(expression).group()
    print('\033[32;1m提取计算的表达式为%s：\033[0m' % variate)
    ret = computer(variate)
    ret = ret[1:len(ret)-1]
    print('\033[32;1m表达式的结果为：%.2f\033[0m' % float(ret))
    before,nothing,after = computerc_pattern.split(expression,1)
    new_str = '%s%s%s' % (before,ret,after)
    print('\033[32;1mAfter:计算后的表达式\033[0m'.center(100,'*'))
    print('\033[31;1m>>>>>>>>>:%s\033[0m' % new_str)
    expression = new_str
    return operations(expression)
def menu():
    while True:
        user_input = input('\033[31;1m请输入你的表达式：\033[0m')
        user_input = re.sub('\s*','',user_input)
        if user_input.lower() == 'q':
            sys.exit()
        if len(user_input) == 0 :
            continue
        if re.search('[^0-9\.\+\-\*\/\(\)]',user_input):
            print('输的表达式错误，请重新输入！')
            continue
        else:
            print('\033[32;1m开始计算表达式%s的值:\033[0m' % user_input)
            result = operations(user_input)
            print('\033[32;1m最后计算结果为：%.2f(精确小数后两位)\033[0m' % float(result))

 

from random import randint , choice
from string import ascii_lowercase
from sys import maxunicode
from time import ctime
# import logging

# def Logger():
#     Logger = logging.getLogger()
#     file_print = logging.FileHandler('random_file')
#     stream_print = logging.StreamHandler()
#     Logger.addHandler(file_print)
#     Logger.addHandler(stream_print)
#     return Logger
doms = ('com','edu','net','org','gov')
for i in range(randint(0,10)):
    dtint = randint(0,maxunicode-1)
    dtstr = ctime(dtint)
    shorter = randint(4,7)
    em = ' '
    for j in range(shorter):
        em += choice(ascii_lowercase)

    longer = randint(shorter,12)
    dn = ''
    for j in range(longer):
        dn += choice(ascii_lowercase)
    # res = Logger()
    # res.warning('%s::%s@%s.%s::%d-%d-%d' % (dtstr,em,dn,choice(doms),dtint,shorter,longer))
    print('%s::%s@%s.%s::%d-%d-%d' % (dtstr,em,dn,choice(doms),dtint,shorter,longer))

>>>>>>>>>
Sun Jan  4 05:07:10 1970:: [e-mail]::248830-5-11
Wed Jan  7 12:40:35 1970:: [e-mail]::535235-7-8
Mon Jan  5 22:25:58 1970:: [e-mail]::397558-7-9
Wed Jan  7 19:27:31 1970:: [e-mail]::559651-7-7
Sun Jan 11 11:59:51 1970:: [e-mail]::878391-6-12
Fri Jan  2 00:32:17 1970:: [e-mail]::59537-7-7
Sat Jan  3 09:55:38 1970:: [e-mail]::179738-6-7
Sat Jan 10 14:52:24 1970:: [e-mail]::802344-5-11