常用模块之正则表达式模块

Posted 2021-03-02 caoyu080202201

一、单个匹配

import re
print(re.findall(‘w‘, ‘aAbc123_*()-=‘))  # 规则为 “数字或字母或下划线” 结果为 [‘a‘, ‘A‘, ‘b‘, ‘c‘, ‘1‘, ‘2‘, ‘3‘, ‘_‘]
print(re.findall(‘W‘, ‘aAbc123_*()-= ‘))  # 规则为 “非数字且非字母且非下划线” 结果为 [‘*‘, ‘(‘, ‘)‘, ‘-‘, ‘=‘, ‘ ‘]
print(re.findall(‘s‘, ‘aA
bc	
12f3_*()-= ‘))  # 规则为 “空格类型” 结果为 [‘
‘, ‘	‘, ‘
‘, ‘x0c‘, ‘ ‘, ‘ ‘]
print(re.findall(‘S‘, ‘aA
bc	
12f3_*()-= ‘))  # 规则为 “非空格类型”  结果为 [‘a‘, ‘A‘, ‘b‘, ‘c‘, ‘1‘, ‘2‘, ‘3‘, ‘_‘, ‘*‘, ‘(‘, ‘)‘, ‘-‘, ‘=‘]
print(re.findall(‘d‘, ‘aA
bc	
12f3_*()-= ‘))  # 规则为 “数字” 结果为 [‘1‘, ‘2‘, ‘3‘]
print(re.findall(‘D‘, ‘aA
bc	
12f3_*()-= ‘))  # 规则为 “非数字” 结果为 [‘a‘, ‘A‘, ‘
‘, ‘b‘, ‘c‘, ‘	‘, ‘
‘, ‘x0c‘, ‘_‘, ‘*‘, ‘(‘, ‘)‘, ‘-‘, ‘=‘, ‘ ‘]
print(re.findall(‘Aalex‘,‘alexis alex sb‘))  # 规则为 首字符为 ‘alex‘ 结果为 [‘alex‘]
print(re.findall(‘sb‘,‘ alexis alexsb sb‘))  # 规则为 尾字符为 ‘sb‘ 结果为 [‘sb‘]，不可用于多行字符串
print(re.findall(‘^alex‘,‘alexis alex sb‘))  # 规则为 首字符为 ‘alex‘ 结果为 [‘alex‘]
print(re.findall(‘sb$‘,‘alexis alex sb‘))  # 规则为 尾字符为 ‘sb‘ 结果为 [‘sb‘]
print(re.findall(‘sb$‘,"""
alex
sb
"""))  # 规则为 尾字符为 ‘sb‘ 结果为 [‘sb‘]，可用于多行字符串

二、重复匹配

import re
print(re.findall(‘a.b‘, ‘a1b a2b a b abbbb a
b a	b a*b‘))
# 规则为 . 可以是任意除了 
 的字符，结果为 [‘a1b‘, ‘a2b‘, ‘a b‘, ‘abb‘, ‘a	b‘, ‘a*b‘]
print(re.findall(‘a.b‘, ‘a1b a2b a b abbbb a
b a	b a*b‘, re.DOTALL))
# 规则为 可以用 re.DOTALL 声明 . 也可以代表
 结果为 [‘a1b‘, ‘a2b‘, ‘a b‘, ‘abb‘, ‘a
b‘, ‘a	b‘, ‘a*b‘]
print(re.findall(‘ab*‘, ‘a ab abb abbbbbbbb bbbbbbbb‘))
# 规则为 * 前面的字符为 0到无穷多个，结果为 [‘a‘, ‘ab‘, ‘abb‘, ‘abbbbbbbb‘]
print(re.findall(‘ab+‘, ‘a ab abb abbbbbbbb bbbbbbbb‘)) 
# 规则为 + 前面的字符为 1到无穷多个，结果为 [‘ab‘, ‘abb‘, ‘abbbbbbbb‘]
print(re.findall(‘ab?‘, ‘a ab abb abbbbbbbb bbbbbbbb‘))
# 规则为 ？前面的字符为 0个或者1个，结果为 [‘a‘, ‘ab‘, ‘ab‘, ‘ab‘]
print(re.findall(‘ab{2,5}‘, ‘a ab abb abbb abbbb abbbbbbbb bbbbbbbb‘))
# 规则为 {2,5}前面的字符为2到5个，结果为 [‘abb‘, ‘abbb‘, ‘abbbb‘, ‘abbbbb‘]
print(re.findall(‘a[0-9a-zA-Z]b‘, ‘a1111111b axb a3b a1b a0b a4b a9b aXb a b a
b‘, re.DOTALL))
# 规则为 a与b之前的字符在[]范围内，结果为 [‘axb‘, ‘a3b‘, ‘a1b‘, ‘a0b‘, ‘a4b‘, ‘a9b‘, ‘aXb‘]
print(re.findall(‘a[^0-9a-zA-Z]b‘, ‘a1111111b axb a3b a1b a0b a4b a9b aXb a b a
b‘, re.DOTALL))
# 规则为 a与b之前的字符在[]范围外，结果为 [‘a b‘, ‘a
b‘]