正則表達(dá)式                                                              描述                                    匹配結(jié)果
\d+(\.\d*)?                                                       任意整數(shù)和浮點(diǎn)數(shù)                            0.004 2 75.

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

^http:\/\/([\w-]+(\.[\w-]+)+(\/[\w-.\/\?%&=\u4e00-\u9fa5]*)?)?$      驗(yàn)證網(wǎng)址                           http://www.baidu.com/?id=1

^[\u4e00-\u9fa5]{0,}$                                                驗(yàn)證漢字                                 漢字漢字

\w+([-+.']\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*                       驗(yàn)證電子郵件                             example@163.com

^[1-9]([0-9]{16}|[0-9]{13})[xX0-9]$                                 驗(yàn)證身份證                            14525419951215445X

^13[0-9]{1}[0-9]{8}|^15[9]{1}[0-9]{8}                               驗(yàn)證手機(jī)號                             138459572***

^(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])          驗(yàn)證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|)$                                驗(yàn)證域名                                baidu.com

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

<(.*)>(.*)<\/(.*)>|<(.*)\/>                                        HTML標(biāo)簽匹配(需修改)                          xxxx

re.I  使匹配對大小寫不敏感
re.L  做本地化識別匹配
re.M  多行匹配,影響^和$
re.S  使.匹配包括換行在內(nèi)的所有字符
re.U  根據(jù)Unicode字符集解析字符.這個(gè)標(biāo)志影響\w \W \b \B
re.X  該標(biāo)志通過給予你更靈活的格式以便你將正則表達(dá)式寫的更易于理解.

# 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('貪婪匹配:')
result = re.match(r'^The.*(\d+).*', content) #使用match匹配, 第一個(gè)參數(shù)為正則表達(dá)式, 第二個(gè)為要匹配的字符串
print(result.group()) #輸出匹配內(nèi)容
print('result = %s'%result.group(1)) #輸出第一個(gè)被()包裹的內(nèi)容

print('-'*20)

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

# 貪婪匹配:
# The 123456 is my one phone number.
# result = 6
# --------------------
# 非貪婪匹配:
# 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())

#輸出
#fooa
#('fooa', 's')

import re
regex = '<(.*)>(.*)<\/(.*)>|<(.*)\/>'
m = re.search(regex,"aa<a>aaaa</a>")
#一樣只有search能匹配到標(biāo)簽
if m is not None:
    print(m)
    print(m.group())

# 結(jié)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)

#結(jié)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)
#輸出
#['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)

#結(jié)果
# hello yudengwu

import re
st = "我喜歡你，喜歡你"
st = st.replace("喜歡","愛",1)
print(st)

# 我愛你，喜歡你