re模块

re模块

一、导入方式

import re

二、作用

从字符串里找特定的字符串

三、基本语法

• ^匹配开头

s = 'yjyyjyijksodh'
print(re.findall('^yjy',s))
----------------------------------------------------------
yjy

• $匹配结尾

s = 'yjyyjyijksodh'
print(re.findall('dh$',s))
----------------------------------------------------------
dh

• []匹配中间的字符

s = 'acefghjkacefsdfsdf'
print(re.findall('[acef]', s))  # 只要单个字符
-------------------------------------------------------------
['a', 'c', 'e', 'f', 'a', 'c', 'e', 'f', 'f', 'f']

• ^[]^对[]里面的元素取反

s = 'acefghjkacefsdfsdf'
print(re.findall('[^acef]', s))
------------------------------------------------------
['g', 'h', 'j', 'k', 's', 'd', 's', 'd']

• .任意字符（除了\n）

s = 'acefghjkacefsdfsdf'
print(re.findall('a..', s))
------------------------------------------------------
['aba', 'ada']

• *前面的字符0-无穷个

s = 'abaacaaaaa'
print(re.findall('a*', s))
------------------------------------------------------
['a', '', 'aa', '', 'aaaaa', '']

• +前面的字符1-无穷个

s = 'abaacaaaaa'
print(re.findall('a+', s))
------------------------------------------------------
['a', 'aa', 'aaaaa']

• ?前面的字符0-1个

s = 'abaacaaaaa'
print(re.findall('a?', s))
------------------------------------------------------
['a', '', 'a', 'a', '', 'a', 'a', 'a', 'a', 'a', '']

• {m}前面的字符m个

s = 'abaacaaaaa'
print(re.findall('a{5}', s))
------------------------------------------------------
['aaaaa']

• {m,n}前面的字符m-n个

s = 'abaacaaaaa'
print(re.findall('a{2,5}', s))
------------------------------------------------------
['aa', 'aaaaa']

• \d数字

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\d', s)
------------------------------------------------------
['1', '2', '3']

• \D非数字

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\D', s)
------------------------------------------------------
['s', ' ', ' ', ' ', ' ', ' ', 's', '+', '\n', '=', '$', '\t', '_', 's', ' ', ' ']

• \w数字/字母/下划线

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\w', s))
------------------------------------------------------
['s', '1', 's', '2', '_', 's', '3']

• \W非数字/字母/下划线

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\W', s))
------------------------------------------------------
[' ', ' ', ' ', ' ', ' ', '+', '\n', '=', '$', '\t', ' ', ' ']

• \s空格/\t/\n

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\s', s))
------------------------------------------------------
[' ', ' ', ' ', ' ', ' ', '\n', '\t', ' ', ' ']

• \S非空格/\t/\n

s = 's  1   s+\n=$\t2_s  3'
print(re.findall('\S', s))
------------------------------------------------------
['s', '1', 's', '+', '=', '$', '2', '_', 's', '3']

• \取消意义

s = 'aba\d'
print(re.findall(r'a\\d', s))
------------------------------------------------------
['a\\d']

• .*贪婪模式(最大化),找到继续找,让结果最大化

s = 'abbbcabc'
print(re.findall('a.*c', s))
------------------------------------------------------
['abbbcabc']

• .*?非贪婪模式(最小化),找到就马上停止

s = 'abbbcabc'
print(re.findall('a.*?c', s))
------------------------------------------------------
['abbbc', 'abc']

• ()只要括号内的

s = 'abacad'
print(re.findall('a(.)', s))
------------------------------------------------------
['b', 'c', 'd']

• A|B A和B都要

s = 'abacad'
print(re.findall('a|b', s))
------------------------------------------------------
['a', 'b', 'a', 'a']

四、模块方法

re.mathch(): 从开头搜索,搜索到了就有,没搜索到就是none

s = 'abc123\ndef456'
res = re.match('\d+', s)  #从开头搜索数字,搜索到了就有,没搜索到就是none 
print(res)
----------------------------------------------
None

s = '123abc123\ndef456'
res = re.match('\d+', s)
print(res)   #返回的是一个对象
print(res.group())  #对象必须用group()返回
-----------------------------------------------------
<re.Match object; span=(0, 3), match='123'>

re.search(): 搜索第一个匹配结果,找到了就不找了

s = '123abc123\ndef456'
res = re.search('\d+', s)
print(res)
print(res.group())
------------------------------------------------------
123

re.split(): 按照匹配规则切割

s1 = 'abc324asdfk234lkjsf324lkj'
print(re.split('\d+', s1))
-----------------------------------------------
['abc', 'asdfk', 'lkjsf', 'lkj']

re.sub(): 按照匹配规则替换(重点)

s1 = 'abc324asdfk234lkjsf324lkj'
print(re.sub('\d+', '***', s1))
-----------------------------------------------
abc***asdfk***lkjsf***lkj

re.subn(): 按照匹配规则替换,并计数

s1 = 'abc324asdfk234lkjsf324lkj'
print(re.subn('\d+', '***', s1))
-----------------------------------------------
('abc***asdfk***lkjsf***lkj', 3)