Python 正则表达式

>>> import re
>>> exp = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"

1. 匹配任意字符0次到多次
>>> re.search('.*', exp).group()
'email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877'

2. 匹配任意字符1次到多次
>>> re.search('.+', exp).group()
'email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877'

3. 匹配任意字符0次到1次
>>> re.search('.?', exp).group()
'e'

4. 匹配 "\d" m次到n次
>>> re.search('\d{3,5}', exp).group()
'13607'

5. 匹配 "[a-z]" m次到n次
>>> re.search('[a-z]{2,10}', exp).group()
'email'

>>> import re
>>> exp = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"

1. 匹配任意字符0次到多次
>>> re.search('.*?', exp).group()
''

2. 匹配任意字符1次到多次
>>> re.search('.+?', exp).group()
'e'

3. 匹配任意字符0次到1次
>>> re.search('.??', exp).group()
''

4. 匹配 "\d" m次到n次
>>> re.search('\d{3,5}?', exp).group()
'136'

5. 匹配 "[a-z]" m次到n次
>>> re.search('[a-z]{2,10}?', exp).group()
'em'

re.match(pattern, string, flags=0)

>>> import re
>>> exp = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"

>>> re.match(r'(.*):(.*)?', exp).group()
'email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877'
>>> re.match(r'(.*):(.*)?', exp).group(1)
'email:opcoder@sina.com,博客:www.opcoder.cn,phone'
>>> re.match(r'(.*):(.*)?', exp).group(2)
'13607078877'

re.search(pattern, string, flags=0)

>>> import re
>>> exp = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"

>>> re.search(r'[a-z]+', exp).group()
'email'

>>> import re
>>> exp = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"

>>> re.match(r'\d+', exp)
>>> re.search(r'\d+', exp).group()
'13607078877'

re.compile(pattern[, flags])

# 用于匹配至少一个数字
>>> import re

>>> s = "email:opcoder@sina.com,博客:www.opcoder.cn,phone:13607078877"
>>> p = re.compile(r'\d+')

>>> p.match(s)

>>> p.search(s)
<_sre.SRE_Match object; span=(47, 58), match='13607078877'>

re.findall(string[, pos[, endpos]])

>>> import re

>>> p = re.compile(r'\d+')

>>> p.findall(r"baidu.com 123, google.com 456")
['123', '456']
>>> p.findall(r"baidu.com 123, google.com 456", 5, 15)
['123']

re.finditer(pattern, string, flags=0)

>>> [i.group() for i in re.finditer(r"\d+", "12a32bc43jf3")]
['12', '32', '43', '3']

re.split(pattern, string[, maxsplit=0, flags=0])

>>> import re

# 按照数字切分
>>> s = '''first 111 line
second 222 line
third 333 line'''
>>> re.split('\d+', s)
['first ', ' line\nsecond ', ' line\nthird ', ' line']

# "\.+" 匹配不到 返回包含自身的列表
>>> re.split('\.+', s, 1)
['first 111 line\nsecond 222 line\nthird 333 line']

# maxsplit 参数
>>> re.split('\d+', s, 1)
['first ', ' line\nsecond 222 line\nthird 333 line']

re.sub(pattern, repl, string, count=0)

>>> import re

>>> s = "the sum of 7 and 9 is [7+9]."

# 基本用法 将目标替换为固定字符串
>>> re.sub('\[7\+9\]', '16', s)
'the sum of 7 and 9 is 16.'

# 高级用法 使用前面匹配的到的内容 "\1 \2" 代表 pattern 中捕获到的第一个、第二个分组的内容
>>> re.sub('\[(7)\+(9)\]', r'\2\1', s)
'the sum of 7 and 9 is 97.'

>>> re.purge
<function purge at 0x1040fcea0>

>>> import re
>>> s = "Hello, opcoder.cn : 2018/08/23"

>>> p = re.compile(r'(?:(?P<name>\w+\.\w+))|(?P<no>\s+\.\w+).*?(\d+), re.X')

>>> print(p.flags)
32
>>> print(p.groupindex)
{'name': 1, 'no': 2}
>>> print(p.groups)
3
>>> print(p.pattern)
(?:(?P<name>\w+\.\w+))|(?P<no>\s+\.\w+).*?(\d+), re.X

>>> import re
>>> s = "Hello, opcoder.cn : 2018/08/23"

>>> r = re.search(r', (?P<name>\w+\.\w+).*?(\d+)', s)

>>> r
<_sre.SRE_Match object; span=(5, 24), match=', opcoder.cn : 2018'>

# 本次搜索的结束位置索引
>>> print(r.endpos)
30

# 本次搜索匹配到的最后一个分组的别名，没有则返回None
>>> print(r.lastgroup)
None

# 本次搜索匹配到的最后一个分组的索引
>>> print(r.lastindex)
2

# 本次搜索开始位置索引
>>> print(r.pos)
0

# 本次搜索使用的 SRE_Pattern 对象
>>> print(r.re)
re.compile(', (?P<name>\\w+\\.\\w+).*?(\\d+)')

# 返回元组，包含本次搜索匹配到的所有分组的起止位置 第一个元组为正则表达式匹配范围
>>> print(r.regs)
((5, 24), (7, 17), (20, 24))

# 本次搜索操作的字符串
>>> print(r.string)
Hello, opcoder.cn : 2018/08/23

>>> import re

>>> s = 'http://www.opcoder.cn/search/?q=python'
>>> print(re.search(r'.*q=(.*)', s).group(1))
python

>>> import re

>>> s = "allenli, www.opcoder.cn : date'2018-07-30'"
>>> res = re.search('(?P<name>\w+\.\w+)(.*?)(\d+)', s)

# 使用别名访问
>>> res.group('name')
'www.opcoder'

# 使用分组访问
>>> res.group()
"www.opcoder.cn : date'2018"
>>> res.group(1)
'www.opcoder'
>>> res.group(2)
".cn : date'"
>>> res.group(3)
'2018'

>>> import re
>>> s = 'age:18,name:Scott'

# 忽略分组
>>> p1 = re.compile('age:(?:\d+),name:(\w+)')
>>> print(re.findall(p1, s))
['Scott']

# 不忽略分组
>>> p2 = re.compile('age:(\d+),name:(\w+)')
>>> print(re.findall(p2, s))
[('18', 'Scott')]

import re

>>> s = 'abcdebbcde'
>>> p = re.compile(r'([ab])\1')

>>> print(re.findall(p, s))
['b']

>>> r = re.search(p, s)
>>> r
<_sre.SRE_Match object; span=(5, 7), match='bb'>
>>> r.group()
'bb'

>>> import re

>>> s = 'abab cdcd efek mmnn'
>>> p = re.compile(r'(\w\w)\1')
>>> print(re.findall(p, s))
['ab', 'cd']

>>> import re

>>> s = 'abab cdcd xxyy'
>>> p = re.compile(r'(\w)\1(\w)\2')
>>> print(re.findall(p, s))
[('x', 'y')]

import re

s = 'abab toot'
p = re.compile(r'(\w)(\w)\2\1')
print re.findall(p,s)

>>> import re

>>> exp1 = "a regular expression"
>>> print(re.compile(r're(?=gular).').findall(exp1))
['reg']

>>> exp2 = "I'm singing while you're dancing."
>>> p = re.compile(r'\b\w+(?=ing\b)')
>>> print(re.compile(r'\b\w+(?=ing\b)').findall(exp2))
['sing', 'danc']
>>> print([x + 'ing' for x in re.findall(p, exp2)])
['singing', 'dancing']

说明： "(?=ing\b)" 表示匹配 "ing\b" 位置之前的文本内容，且此位置满足正则 "ing\b" 并且它不会出现在匹配结果中。

>>> import re

>>> exp = "regex recent regular expression"
>>> print(re.compile(r're(?!g)\w+').findall(exp))
['recent', 'ression']

>>> import re

>>> exp = "regex represents regular expression"
>>> print(re.compile(r'(?<=\w)re\w+').findall(exp))
['resents', 'ression']

>>> import re

>>> exp = "regex represents regular expression"
>>> print(re.compile(r'(?<!\w)re\w+').findall(exp))
['regex', 'represents', 'regular']

>>> ip = "inet addr:172.26.83.189"
>>> print(re.compile(r'(?<=\.)?\d+(?=\.)?').findall(ip))
['172', '26', '83', '189']

>>> strs = ['_aaa','1aaa','aaaa','a_12','a1','a_123','1234','____']
>>> p = re.compile(r'^(?!_)(?!\d)(?!\d+$)(?![a-zA-Z]+$)\w{4}$')
>>> for s in strs:
...     print(re.findall(p, s))
... 
[]
[]
[]
['a_12']
[]
[]
[]
[]

import re

phone_pat = re.compile('^(13[0-9]|14[5|7]|15[0|1|2|3|5|6|7|8|9]|166|17[3|6|7]|18[0|1|2|3|5|6|7|8|9])\d{8}$')

while True:
    phone = input('请输入您的手机号:')
    res = re.search(phone_pat, phone)
    if res:
        print('正常手机号')
    else:
        print('不是手机号')

import re

email_pat = re.compile(r'^[a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+){0,4}@[a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+){0,4}$')

while True:
    email = input('请输入您的邮箱:')
    res = re.search(email_pat, email)
    if res:
        print('正常邮箱')
    else:
        print('不是邮箱')

^[\s\S]{8,16}$

import re

p_passwd = re.compile(r'^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)[\s\S]{8,16}$')
while True:
    i_passwd = input('请输入您的密码:')
    res = re.search(p_passwd, i_passwd)
    if res:
        print('True...')
    else:
        print('False...')

说明： "[\s\S]" 中的 "\s " 表示空白符，"\S" 表示非空白符，所以 "[\s\S]" 表示任意字符

import re

p_passwd = re.compile(r'^(?=.*[A-Za-z])(?=.*\d)[A-Za-z\d]{8,}$')
while True:
    i_passwd = input('请输入您的密码:')
    res = re.search(p_passwd, i_passwd)
    if res:
        print('True...')
    else:
        print('False...')

import re

p_passwd = re.compile(r'^(?=.*[A-Za-z])(?=.*\d)(?=.*[#$%&\'\"()*+,\-./:;<=>?@[\\\]^_`{|}~])[A-Za-z\d#$%&\'\"()*+,\-./:;<=>?@[\\\]^_`{|}~]{8,}$')

while True:
    i_passwd = input('请输入您的密码:')
    res = re.search(p_passwd, i_passwd)
    if res:
        print('True...')
    else:
        print('False...')

import re

p_passwd = re.compile(r'^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)[a-zA-Z\d]{8,}$')
while True:
    i_passwd = input('请输入您的密码:')
    res = re.search(p_passwd, i_passwd)
    if res:
        print('True...')
    else:
        print('False...')

import re

p_passwd = re.compile(r'^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[#$%&\'\"()*+,\-./:;<=>?@[\\\]^_`{|}~])[A-Za-z\d#$%&\'\"()*+,\-./:;<=>?@[\\\]^_`{|}~]{8,}')

while True:
    i_passwd = input('请输入您的密码:')
    res = re.search(p_passwd, i_passwd)
    if res:
        print('True...')
    else:
        print('False...')