常用正则表达式RE（慕课网_Meshare_huang）

import re

str1 = 'imooc python'
# str1.find('l1')          输出：      -1
# str1.find('imooc')                  0

# str1.startswith('imooc')            True

pa = re.compile(r'imooc')             #加个r 代表是个原字符串
# pa = re.compile('imooc\n')          \n会转译成一个换行符

# type: _sre.SRE_Pattern

pa.match(str1)
ma = pa.match(str1)
# ma.span()                           (0, 5)
# ma.group()                          'imooc'

# ma.string                             'imooc python'
# ma.re                                 re.compile(r'imooc', re.UNICODE)

pa1 = re.compile(r'_')
ma1 = pa1.match('_value')
# ma1.group                          <function SRE_Match.group>

# pa                                 re.compile(r'imooc', re.UNICODE)

ma = pa.match('imooc python')
# ma.group()                         'imooc'

# pa = pa.match('imoOc python', re.I)
# type(pa)                           NoneType

pa = re.compile(r'(imooc)', re.I)    #组    大写的i
ma = pa.match(str1)
# ma.group()                           'imooc'
# ma.groups()                          ('imooc',)

# ma = re.match(r'imooc', str1)
# ma                                    <_sre.SRE_Match object; span=(0, 5), match='imooc'>
# ma.group()                            'imooc'

　　

语法

# . 匹配任意字符 除了\n
# ma = re.match(r'a', 'a')
# ma.group()                            'a'

# ma = re.match(r'.', 'b')
# ma.group()                            'b'

# ma = re.match(r'.', '0')
# ma.group()                            '0'

# ma = re.match(r'{.}', '{a}')
# ma.group()                           '{a}'

# ma = re.match(r'{..}', '{a0}')
# ma.group()                           '{a0}'

# [...] 匹配字符集
# ma = re.match(r'{[abc]}', '{a}')
# ma.group()                             '{a}'

# ma = re.match(r'{[abc]}', '{d}')
# ma.group()                             AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'{[a-z]}', '{d}')
# ma.group()                             '{d}'

# ma = re.match(r'{[a-zA-Z]}', '{D}')
# ma.group()                             '{D}'

# ma = re.match(r'{[a-zA-Z0-9]}', '{9}')
# ma.group()                             '{9}'

# ma = re.match(r'{[\w]}', '{0}')
# ma.group()                             '{0}'

# ma = re.match(r'{[\w]}', '{ }')
# ma.group()    AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'{[\W]}', '{ }')
# ma.group()                            '{ }'

# ma = re.match(r'{[[\w]]}', '[0]')
# ma.group()                            AttributeError:

# ma = re.match(r'\[[\w]\]', '[0]') 要加转译字符
# ma.group()                            '[0]'

　　

import re

# ma = re.match(r'[A-Z][a-z]', 'Aa')
# ma.group()                            'Aa'

# ma = re.match(r'[A-Z][a-z]*', 'A')
# ma.group()                             'A'

# ma = re.match(r'[A-Z][a-z]*', 'AdsfafeadcxAe') 如果出现数字是匹配不上的
# ma.group()                             'Adsfafeadcx'

# _ = 10
# _                                             10

# ma = re.match(r'[0-9]?[0-9]', '90')
# ma.group()                              '90'

# ma = re.match(r'[0-9]?[0-9]', '9')
# ma.group()                               '9'

# ma = re.match(r'[0-9]?[0-9]', '09')
# ma.group()                              '09'

# ma = re.match(r'[a-zA-Z0-9]{6}', 'abc123')
# ma.group()                              'abc123'

# ma = re.match(r'[a-zA-Z0-9]', 'abc123')
# ma.group()                              'a'

# ma = re.match(r'[a-zA-Z0-9]{6}', 'abc123__')
# ma.group()                             'abc123'

# ma = re.match(r'[a-zA-Z0-9]{6}@163.com', 'abc123@163.com')
# ma.group()                             'abc123@163.com'

# ma = re.match(r'[a-zA-Z0-9]{6, 10}@163.com', 'imoocedu@163.com')
# ma.group()                             AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'[0-9][a-z]*?', '1bc')
# ma.group()                            '1'

# ma = re.match(r'[a-zA-Z0-9]+?', '1bc')
# ma.group()                            '1'

　　

# ma = re.match(r'\Aimooc[\w]', 'imoocpython') 边界匹配

# ma.group()                            'imoocp'

　　

# ma = re.match(r'abc|d', 'abc')
# ma.group()                            'abc'

# ma = re.match(r'[1-9]?\d$', '9')
# ma.group()                            '9'

# ma = re.match(r'[1-9]?\d|100$', '100')
# ma.group()                            '10'

# ma = re.match(r'[1-9]?\d|100$', '99')
# ma.group()                            '99'

# ma = re.match(r'[1-9]?\d|100$', '9')
# ma.group()                            '9'

# ma = re.match(r'[\w]{4, 6}@(163|126).com', 'imooc@163.com')
# ma.group()                            AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'[\w]{4, 6}@(163|126).com', 'imooc@126.com')
# ma.group()                            AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'<[\w]+>', '<book>')
# ma.group()                           '<book>'

# ma = re.match(r'<([\w]+>)', '<book>')
# ma.group()                          '<book>'

# ma = re.match(r'<([\w]+>)\1', '<book>')
# ma.group()                          AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'<([\w]+>)\1', '<book>book>')
# ma.group()                          '<book>book>'

# ma = re.match(r'<([\w]>)[\w]+</\1', '<book>python</book>')
# ma.group()                          AttributeError: 'NoneType' object has no attribute 'group'

# ma = re.match(r'<(?P<mark>[\w]>)[\w]+</(?P=mark)', '<book>python</book>')
# ma.group()                          AttributeError: 'NoneType' object has no attribute 'group'

　　

import re

str1 = 'imooc videonum = 100'

# str1.find('100')                     # 17

info = re.search(r'\d+', str1)
# info # <_sre.SRE_Match object; span=(17, 20), match='100'>

str1 = 'imooc videonum = 10000'
# info.group()                         # '100'

str2 = 'c++=100, java=90, python=80'
info = re.findall(r'\d+', str2)
# info                                        ['100', '90', '80']
# sum([int(x) for x in info])         270

str3 = 'imooc videonum = 10000'
info = re.sub(r'\d+', '1001', str3)
# info                                        'imooc videonum = 1001'

def add1(match):
val = match.group()
num = int(val) + 1
return str(num)

# re.sub(r'\d+', add1, str3)       'imooc videonum = 10001'

str4 = 'imooc:c c++ java python'
#不能仅仅使用空格分割
re.split(r':| ', str4)                      #['imooc', 'c', 'c++', 'java', 'python']

# str4 = 'imooc:c c++ java python,c#'
# re.split(r':| |,', str4)                ['imooc', 'c', 'c++', 'java', 'python', 'c#']