Python标准库re的使用举例(正则化匹配)

正则表达式                                                              描述                                    匹配结果
\d+(\.\d*)?                                                       任意整数和浮点数                            0.004 2 75.

\b[^\Wa-z0-9_][^\WA-Z0-9_]*\b                                      首字母只能大写                               Boo Foo

^http:\/\/([\w-]+(\.[\w-]+)+(\/[\w-.\/\?%&=\u4e00-\u9fa5]*)?)?$      验证网址                           http://www.baidu.com/?id=1

^[\u4e00-\u9fa5]{0,}$                                                验证汉字                                 汉字汉字

\w+([-+.']\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*                       验证电子邮件                             example@163.com

^[1-9]([0-9]{16}|[0-9]{13})[xX0-9]$                                 验证身份证                            14525419951215445X

^13[0-9]{1}[0-9]{8}|^15[9]{1}[0-9]{8}                               验证手机号                             138459572***

^(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])          验证IP                             192.168.1.1
\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)
\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)
\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])$	

^[a-zA-Z0-9]+([a-zA-Z0-9\-\.]+)?\.s|)$                                验证域名                                baidu.com

^([a-zA-Z]\:|\\)\\([^\\]+\\)*[^\/:*?"<>|]+\.txt(l)?$               验证文件路径	                             C:\user\wo

<(.*)>(.*)<\/(.*)>|<(.*)\/>                                        HTML标签匹配(需修改)                          xxxx

re.I  使匹配对大小写不敏感
re.L  做本地化识别匹配
re.M  多行匹配,影响^和$
re.S  使.匹配包括换行在内的所有字符
re.U  根据Unicode字符集解析字符.这个标志影响\w \W \b \B
re.X  该标志通过给予你更灵活的格式以便你将正则表达式写的更易于理解.

# 例子 result = re.match('^The.*?(\d+).*?phone.', content, re.S)

import re

if re.search(r'\\d', 'I have one nee\dle') is not None:
    print('match it',re.search(r'\\d', 'I have one nee\dle').group(0))
else:
    print('not match')

# match it \d

import re

content = 'The 123456 is my one phone number.'
print('贪婪匹配:')
result = re.match(r'^The.*(\d+).*', content) #使用match匹配, 第一个参数为正则表达式, 第二个为要匹配的字符串
print(result.group()) #输出匹配内容
print('result = %s'%result.group(1)) #输出第一个被()包裹的内容

print('-'*20)

print('非贪婪匹配:')
result = re.match(r'^The.*?(\d+).*', content) 
print(result.group())
print('result = %s'%result.group(1))

# 贪婪匹配:
# The 123456 is my one phone number.
# result = 6
# --------------------
# 非贪婪匹配:
# The 123456 is my one phone number.
# result = 123456

import re

content = '(百度)www.baidu.com'
result = re.match('(百度)www.baidu.com', content)
result2 = re.match('\(百度\)www\.baidu\.com', content)
if result:
    print(result.group())
else:
    print('result = None')
if result2:
    print(result2.group())
else:
    print('result2 = None')

# result = None
# (百度)www.baidu.com

import re

content1 = '2016-1-1 12:01'
content2 = '2017-1-1 12:02'
content3 = '2018-1-1 12:03'

pattern = re.compile('\d{2}:\d{2}')
result1 = re.sub(pattern, '', content1)
result2 = re.sub(pattern, '', content2)
result3 = re.sub(pattern, '', content3)
print(result1, result2, result3)

#2016-1-1  2017-1-1  2018-1-1 

import re
regex = '(foo\w)(\w)'
m = re.match(r'(foo\w)(\w)','fooasdfooasd')
if m is not None:
    print(m.group(1))
    print(m.groups())

#输出
#fooa
#('fooa', 's')

import re
regex = '<(.*)>(.*)<\/(.*)>|<(.*)\/>'
m = re.search(regex,"aa<a>aaaa</a>")
#一样只有search能匹配到标签
if m is not None:
    print(m)
    print(m.group())

# 结果
# <re.Match object; span=(2, 13), match='<a>aaaa</a>'>
# <a>aaaa</a>

import re
text = "I am so happy! "
array1 = re.findall("[a-zA-Z]", text)
array2 = re.findall("[a-zA-Z]+", text)
print(array1)
print(array2)

#结果
# ['I', 'a', 'm', 's', 'o', 'h', 'a', 'p', 'p', 'y']
# ['I', 'am', 'so', 'happy']

import re
regex = 'apple'
m = [ g.group() for g in re.finditer(regex,'apple1 apple2 apple3')]
print(m)
#输出
#['apple', 'apple', 'apple']

import re
list = [
'aaa,bbb,ccc',
'ddd,eee,fff',
]
for i in list:
    print(re.split(',',i))

# ['aaa', 'bbb', 'ccc']
# ['ddd', 'eee', 'fff']

import re
st = "hello 2019"
st = re.sub("([0-9]+)","yudengwu",st)
print(st)

#结果
# hello yudengwu

import re
st = "我喜欢你，喜欢你"
st = st.replace("喜欢","爱",1)
print(st)

# 我爱你，喜欢你