New-Python-模块之re正则

1、findall---从头找到尾，把找成功的结果放到列表中

import re

print(re.findall('alex','12a3 alex say hello alex sb 123 _ 4%5*6'))

#alex, 匹配成功一个，从空格开始继续匹配，a成功，3不成功，再从3开始进行匹配；

2、w---字母数字下划线

print(re.findall('w','alex say alex sb 123 _ 4%5*'))

['a', 'l', 'e', 'x', 's', 'a', 'y', 'a', 'l', 'e', 'x', 's', 'b', '1', '2', '3', '_', '4', '5']

3、W---非字母数字下划线

print(re.findall('W','alex say alex sb 123 _ 4%5*'))

[' ', ' ', ' ', ' ', ' ', ' ', '%', '*']

4、s  S---（非）空白字符

print(re.findall('s','al	e
x hello alex sb 123 _ 4%5*'))
print(re.findall('S','al	e
x hello alex sb 123 _ 4%5*'))

['	', '
', ' ', ' ', ' ', ' ', ' ', ' ']
['a', 'l', 'e', 'x', 'h', 'e', 'l', 'l', 'o', 'a', 'l', 'e', 'x', 's', 'b', '1', '2', '3', '_', '4', '%', '5', '*']

#	  
  等

5、d---数字

print(re.findall('d','al	e
x hello alex sb 123 _ 4%5*'))
print(re.findall('dd','al	e
x hel12345lo alex sb 123 _ 4%5*'))

#后者匹配连续两位数
#D---匹配非数字

6、A---只从开头找

print(re.findall('Al','alex say hello'))

[]

7、---只从结尾找

print(re.findall('llo','alex say hello'))

['llo']

以上两个类似于：

print(re.findall('^l','alex say hello'))
print(re.findall('llo$','alex say hello'))

8、    

print(re.findall('
','al	e
x hello alex sb 123 _ 4%5*'))
print(re.findall('	','al	e
x hello alex sb 123 _ 4%5*'))

['
']
['	']

9、重复匹配：.   []   ?   *   +   {}

print(re.findall('a.c','a1c a%c abc accc acccc'))

['a1c', 'a%c', 'abc', 'acc', 'acc']

#注：只能匹配一行行的

print(re.findall('a.c','a1c a%c a
c accc acccc'))

['a1c', 'a%c', 'acc', 'acc']

print(re.findall('a.c','a1c a%c a
c accc acccc',re.S))
print(re.findall('a.c','a1c a%c a
c accc acccc',re.DOTALL))

这样就可以匹配换行符，其他类似。

print(re.findall('ab?','a ab abb abbb abbbbbb'))

['a', 'ab', 'ab', 'ab', 'ab']

print(re.findall('ab*','a ab abb abbb abbbbbb abbc123bbbb'))

['a', 'ab', 'abb', 'abbb', 'abbbbbb', 'abb']

print(re.findall('ab+','a ab abb abbb abbbbbb abbc123bbbb'))

['ab', 'abb', 'abbb', 'abbbbbb', 'abb']

print(re.findall('ab{1,3}','a ab abb abbb abbbbbb abbc123bbbb'))
print(re.findall('ab{3}','a ab abb abbb abbbbbb abbc123bbbb'))
print(re.findall('ab{3,}','a ab abb abbb abbbbbb abbc123bbbb'))


['ab', 'abb', 'abbb', 'abbb', 'abb']    #1到3个
['abbb', 'abbb']    #3个
['abbb', 'abbbbbb']    #至少3个


print(re.findall('ab{0,1}','a ab abb abbb abbbbbb abbc123bbbb'))
print(re.findall('ab{0,}','a ab abb abbb abbbbbb abbc123bbbb'))
print(re.findall('ab{1,}','a ab abb abbb abbbbbb abbc123bbbb'))
取代：
?
*
+

10、.*匹配所有字符

贪婪匹配，找到最长，最全的满足的字符

print(re.findall('a.*b','a123b456b'))

['a123b456b']

11、非贪婪匹配：.*?     固定格式，不具有?的特殊含义

print(re.findall('a.*?b','a123b456b'))

['a123b']

12、分组：()

#分组前：
print(re.findall('<imag href=".*" />',
                 '<h1>hello</h1><a href="http://www.baidu.com"></a><imag href="http://www.baidu.com/a.jpg" />'))

#分组后：只留下组内的东西
print(re.findall('<imag href="(.*)" />',
                 '<h1>hello</h1><a href="http://www.baidu.com"></a><imag href="http://www.baidu.com/a.jpg" />'))

['<imag href="http://www.baidu.com/a.jpg" />']
['http://www.baidu.com/a.jpg']

?:同分组前
print(re.findall('<imag href="(?:.*)" />',
                 '<h1>hello</h1><a href="http://www.baidu.com"></a><imag href="http://www.baidu.com/a.jpg" />'))

结果：
['<imag href="http://www.baidu.com/a.jpg" />']
['http://www.baidu.com/a.jpg']
['<imag href="http://www.baidu.com/a.jpg" />']

13、或者：|

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

['ies', 'y']
['companies', 'company']

#注意后面那个，取所有

14、匹配ac

print(re.findall('a\c','ac a12 a2c')) 

# 'a\c'字符串先被pycharm识别，然后交给re模块，做正则匹配这件事。

raw str 原生字符串，不需要python解释器转义！所以，

print(re.findall(r'a\c','ac a12 a2c')) #'a\c'

['a\c']

 补充---[]

print(re.findall('a[0-9]c','a1c a%c a
c accc acccc',re.S))
print(re.findall('a[a-z]c','a1c a%c a
c accc acccc',re.S))
print(re.findall('a[A-Z]c','a1c a%c a
c accc acccc aAc aAAc',re.S))
print(re.findall('a[0-9a-zA-Z]c','a1c a%c a
c accc acccc aAc aAAc',re.S))
print(re.findall('a[% ]c','a c a1c a%c a+c a-c a/c a*c',re.S))  #%或空格取出来
print(re.findall('a[^% ]c','a c a1c a%c a+c a-c a/c a*c',re.S))  #上面取反
print(re.findall('a[+-*/]c','a c a1c a%c a+c a-c a/c a*c',re.S))
print(re.findall('a[-+*/]c','a c a1c a%c a+c a-c a/c a*c',re.S))  #-号放在左边或者右边
print(re.findall('a[+*/-]c','a c a1c a%c a+c a-c a/c a*c',re.S))
print(re.findall('a.*?c','a c a1c a%c a+c a-c a/c a*c',re.S))