Python正课64 —— re模块

本文内容皆为作者原创，如需转载，请注明出处：https://www.cnblogs.com/xuexianqi/p/12615660.html

一：常用匹配模式表

二：详解

import re

# 匹配字母、数字、下划线
print(re.findall('w','aAbc123_*()-='))
# ['a', 'A', 'b', 'c', '1', '2', '3', '_']

# 匹配非字母、数字、下划线
print(re.findall('W','aAbc123_*()-= '))
# ['*', '(', ')', '-', '=', ' ']

# 匹配任意空白字符，等价于[ 	 
 
 f ]
print(re.findall('s','aA
bc	
12f3_*()-= '))
# ['
', '	', '
', 'x0c', ' ']

# 匹配任意非空字符
print(re.findall('S','aA
bc	
12f3_*()-= '))
# ['a', 'A', 'b', 'c', '1', '2', '3', '_', '*', '(', ')', '-', '=']

# 匹配任意数字，等价于[0-9]
print(re.findall('d','aA
bc	
12f3_*()-= '))
# ['1', '2', '3']

# 匹配任意非数字
print(re.findall('D','aA
bc	
12f3_*()-= '))
# ['a', 'A', '
', 'b', 'c', '	', '
', 'x0c', '_', '*', '(', ')', '-', '=', ' ']


# 匹配字符串开始
print(re.findall('Aalex',' alexis alex sb'))
#                          alex
# []


#匹配字符串结束，如果是存在换行，只匹配到换行前的结束字符串
print(re.findall('sb',' alexis alexsb sb'))
#                                       sb
# ['sb']

print(re.findall('sb',"""alex
alexis
alex
sb
"""))
# []


# 匹配字符串的开头
print(re.findall('^alex','alexis alex sb'))
# ['alex']

# 匹配字符串的末尾
print(re.findall('sb$','alexis alex sb'))
# ['sb']

print(re.findall('sb$',"""alex
alexis
alex
sb
"""))
# ['sb']

print(re.findall('^alex$','alexis alex sb'))    # []
print(re.findall('^alex$','al       ex'))       # []
print(re.findall('^alex$','alex'))              # ['alex']



# 重复匹配：| . | * | ? | .* | .*? | + | {n,m} |
# 1、.:匹配任意字符，除了换行符；当re.DOTALL标记被指定时，则可以匹配包括换行符的任意字符
print(re.findall('a.b','a1b a2b a b abbbb a
b a	b a*b'))
#                                                   a.b
# ['a1b','a2b','a b','abb','a	b','a*b']

print(re.findall('a.b','a1b a2b a b abbbb a
b a	b a*b',re.DOTALL))
# ['a1b', 'a2b', 'a b', 'abb', 'a
b', 'a	b', 'a*b']



# 2、*：匹配0个或多个的表达式，左侧字符重复0次或无穷次，性格贪婪
print(re.findall('ab*','a ab abb abbbbbbbb bbbbbbbb'))
#                                                ab*
#['a','ab','abb','abbbbbbbb']



# 3、+：匹配1个或多个的表达式，左侧字符重复1次或无穷次，性格贪婪
print(re.findall('ab+','a ab abb abbbbbbbb bbbbbbbb'))
#                         ab+
# ['ab', 'abb', 'abbbbbbbb']



# 4、？：左侧字符重复0次或1次，性格贪婪
print(re.findall('ab?','a ab abb abbbbbbbb bbbbbbbb'))
#                                                ab?
# ['a','ab','ab','ab']



# 5、{n,m}：匹配n到m次，左侧字符重复n次到m次，由前面的正则表达式定义的片段，贪婪方式
# {0,} => *
# {1,} => +
# {0,1} => ?
# {n}单独一个n代表只出现n次，多一次不行少一次也不行


print(re.findall('ab{2,5}','a ab abb abbb abbbb abbbbbbbb bbbbbbbb'))
#                                                           ab{2,5}
# ['abb','abbb','abbbb','abbbbb]

print(re.findall('d+.?d*',"asdfasdf123as1111111.123dfa12adsf1asdf3"))
#                                                                   d+.?d*                                      d+.?d+
# ['123', '1111111.123', '12', '1', '3']


# []匹配指定字符一个
print(re.findall('adb','a1111111b a3b a4b a9b aXb a b a
b',re.DOTALL))
# ['a3b', 'a4b', 'a9b']

print(re.findall('a[501234]b','a1111111b a3b a4b a9b aXb a b a
b',re.DOTALL))
# ['a3b', 'a4b']

print(re.findall('a[0-5]b','a1111111b a3b a1b a0b a4b a9b aXb a b a
b',re.DOTALL))
# ['a3b', 'a1b', 'a0b', 'a4b']

print(re.findall('a[0-9a-zA-Z]b','a1111111b axb a3b a1b a0b a4b a9b aXb a b a
b',re.DOTALL))
# ['axb', 'a3b', 'a1b', 'a0b', 'a4b', 'a9b', 'aXb']

print(re.findall('a[^0-9a-zA-Z]b','a1111111b axb a3b a1b a0b a4b a9b aXb a b a
b',re.DOTALL))
# ['a b', 'a
b']

print(re.findall('a-b','a-b aXb a b a
b',re.DOTALL))
# ['a-b']

print(re.findall('a[-0-9
]b','a-b a0b a1b a8b aXb a b a
b',re.DOTALL))
# ['a-b', 'a0b', 'a1b', 'a8b', 'a
b']