re模块

 

# Author: Sure Feng

'''
re模块
'''

import re


# 最常用的匹配语法（匹配的套路）
# 1、re.match 匹配开头，没有则匹配不成功
print(re.match("s+","asddf123fssa")) # None
print(re.match(".","asddf123fssa")) # <re.Match object; span=(0, 1), match='a'>

# 2、re.search  从头到位匹配
print(re.search("s+","asddf123fssa")) # <re.Match object; span=(1, 2), match='s'>

# 3、re.findall 把所有匹配成功的字符放到列表中并返回
print(re.findall("s+","asddf123fssa")) # ['s', 'ss']

# 4、re.sub  把成功匹配到的字符替换，并返回一个新的字符串
# re.sub(pattern, repl, string, count=0, flags=0),count为替换次数，不写默认全替换
print(re.sub("s+","&","asddf123fssa",1)) # a&ddf123fssa，count=1匹配成功一次结束


# 常用正则表达式符号
# '.'默认匹配除\n之外的任意一个字符, 若指定flag DOTALL,则匹配任意字符，包括换行
print(re.search("v.","asddf123fsvsa")) # <re.Match object; span=(10, 12), match='vs'>

# '^'、'\A'匹配字符开头，re.match用不上
# 若指定flags MULTILINE,这种也可以匹配上，(r"^a","\nabc\neee",flags=re.MULTILINE)
print(re.search("^v.","asddf123fsvsa")) # None
print(re.search("\Av.","asddf123fsvsa")) # None

# '$'、'\Z'匹配字符结尾，或e.search("foo$","bfoo\nsdfsf",flags=re.MULTILINE).group()也可以
print(re.search(".a$","asddf123fsvsa")) # <re.Match object; span=(11, 13), match='sa'>
print(re.search(".a\Z","asddf123fsvsa")) # <re.Match object; span=(11, 13), match='sa'>

# '*'匹配*号前的字符0次或多次
print(re.findall("ab*","cabb3abcbbac")) # ['abb', 'ab', 'a'],pattern可以是：a/ab/abb/abbb....

# '+'匹配前一个字符1次或多次，re.findall("ab+","ab+cd+abb+bba") 结果['ab', 'abb']
print(re.findall("ab+","cabb3abcbbac")) # ['abb', 'ab'],pattern可以是：ab/abb/abbb

# '?'匹配前一个字符1次或0次
print(re.findall("ab?","cabb3abcbbac")) # ['ab', 'ab', 'a'],pattern可以是：a/ab

# '{m}'    匹配前一个字符m次
print(re.findall("ab{2}","abb abc abbcbbb")) # ['abb', 'abb'],pattern是：abb

# '{n,m}'匹配前一个字符n到m次
print(re.findall("ab{1,3}","abbb abc abbcbbb"))#['abbb','ab','abb'],pattern可以是:ab/abb/abbb

# '|'匹配|左或|右的字符
print(re.search("abc|ABC","ABCBabcCD").group()) # ABC, group()返回匹配成功的结果

# '(...)' 分组匹配
print(re.search("(abc){2}a(123|456)c", "abcabca456c").group()) # abcabca456c

# '(?P<name>...)' 分组匹配
print(re.search("(?P<province>[0-9]{4})(?P<city>[0-9]{2})(?P<birthday>[0-9]{4})","371481199306143242").groupdict())
# 结果：{'province': '3714', 'city': '81', 'birthday': '1993'}


# '\d'    匹配数字0-9
# '\D'    匹配非数字
# '\w'    匹配[A-Za-z0-9]
# '\W'    匹配非[A-Za-z0-9]
# '\s'    匹配空白字符、\t、\n、\r
print(re.search("\s+",'ab\tc1\n3').group()) # 结果 '\t'

# re.I(re.IGNORECASE): 忽略大小写（括号内是完整写法，下同）
print(re.search("[a-z]+","AFJa",flags=re.I)) # <re.Match object; span=(0, 4), match='AFJa'>

# M(MULTILINE): 多行模式，改变'^'和'$'的行为（参见上图）
print(re.search(r"^e.","\nabc\neee",flags=re.M)) # <re.Match object; span=(5, 7), match='ee'>

# S(DOTALL): 点任意匹配模式，改变'.'的行为
print(re.search("v.+","asddf123fsvsa\n", flags=re.S)) # <re.Match object; span=(10, 14), match='vsa\n'>

None
<re.Match object; span=(0, 1), match='a'>
<re.Match object; span=(1, 2), match='s'>
['s', 'ss']
a&ddf123fssa
<re.Match object; span=(10, 12), match='vs'>
None
None
<re.Match object; span=(11, 13), match='sa'>
<re.Match object; span=(11, 13), match='sa'>
['abb', 'ab', 'a']
['abb', 'ab']
['ab', 'ab', 'a']
['abb', 'abb']
['abbb', 'ab', 'abb']
ABC
abcabca456c
{'province': '3714', 'city': '81', 'birthday': '1993'}
    
<re.Match object; span=(0, 4), match='AFJa'>
<re.Match object; span=(5, 7), match='ee'>
<re.Match object; span=(10, 14), match='vsa\n'>