python—正则表达式浅析

python 正则表达式

学习自莫烦python

导入模块

import re

简单python匹配

# matching string
pattern1 = "cat"
pattern2 = "bird"
string = "dog rans to cat"
print(pattern1 in string)
print(pattern2 in string)

True
False

使用正则寻找匹配

#regular experssion
pattern1 = "cat"
pattern2 = "dob"
string = "dog runs to cat"
print(re.search(pattern1, string))
print(re.search(pattern2, string))

<re.Match object; span=(12, 15), match='cat'>
None

匹配多种可能 使用[]

# numtiple patterns ("run" or "ran")
ptn = r"r[au]n" # r 表示转义， []之中存放多种字符，匹配时只要存在一个便匹配到了
string = "dog rans to cat"
print(re.search(ptn, string))

<re.Match object; span=(4, 7), match='ran'>

匹配更多种可能

# continue
print(re.search(r"r[A-Z]n", string))
print(re.search(r"r[a-z]n", string))
print(re.search(r"r[0-9]n", string))
print(re.search(r"r[0-9a-z]n", string))

None
<re.Match object; span=(4, 7), match='ran'>
None
<re.Match object; span=(4, 7), match='ran'>

特殊类型匹配

数字

# \d : decimal digit 所有数字
print(re.search(r"r\dn", "run r4n"))
# \D : any non_decimal digit 不是数字的所有字符
print(re.search(r"r\Dn", "run r4n"))

<re.Match object; span=(4, 7), match='r4n'>
<re.Match object; span=(0, 3), match='run'>

空白

# \s : any white space [\t\n\r\f\v] 所有空白符，制表符，空格，回车等
print(re.search(r"r\sn", 'run r n'))
# \S : opposite to \s, any non_white space 所用可显示字符
print(re.search(r"r\Sn", "run r n"))

<re.Match object; span=(4, 7), match='r n'>
<re.Match object; span=(0, 3), match='run'>

所有字母数字和下划线"_"

# \w : [a-zA-Z0-9_]
print(re.search(r"r\wn", "r\nn r4n"))
# \W : opposite to \w 与\w 相反
print(re.search(r"r\Wn", "r\nn r_n"))

<re.Match object; span=(4, 7), match='r4n'>
<re.Match object; span=(0, 3), match='r\nn'>

空白字符

# \b :empty string (only at the start or end of the word) 在紧贴单词前后的空白
print(re.search(r"\bruns\b", "dog runs to the cat"))
# \B : empty string (but not at the start or end of a word) 紧贴单词前后没有空白
print(re.search(r"\Bruns\B", "dogrunsto  the cat"))

<re.Match object; span=(4, 8), match='runs'>
<re.Match object; span=(3, 7), match='runs'>

特殊字符 任意字符

# \\ : match \  匹配反斜杠
print(re.search(r"runs\\", "runs\ to me"))
# . : metch anything (except \n) 除了换行符之外的所有字符
print(re.search(r"r.n", "r[n to me"))

<re.Match object; span=(0, 5), match='runs\\'>
<re.Match object; span=(0, 3), match='r[n'>

句尾句首

# ^ : match line begining #匹配句首
print(re.search(r"^dog", "dog runs to cat"))
print(re.search(r"^dog", "cat runs to dog"))
# $ : match line ending 匹配句尾
print(re.search(r"cat$", "dog runs to cat"))
print(re.search(r"cat$", "cat runs to dog"))

<re.Match object; span=(0, 3), match='dog'>
None
<re.Match object; span=(12, 15), match='cat'>
None

是否

# ? : may or may not occur # 括号里的有就匹配，没有也匹配只要括号外的有
print(re.search(r"Mon(day)?", "Monday"))
print(re.search(r"Mon(day)?", "Mon"))

<re.Match object; span=(0, 6), match='Monday'>
<re.Match object; span=(0, 3), match='Mon'>

多行匹配

# multi-line
string = '''
dog runs to cat.
I run to dof.
'''
print(re.search(r"^I", string)) #多行直接匹配句首没法匹配
print(re.search(r"^I", string, flags=re.M)) #flags=r.M 表示让其把每行当成单独的来匹配

None
<re.Match object; span=(18, 19), match='I'>

0或多次

# * ：occur 0 or more times
print(re.search(r"ab*", "a"))
print(re.search(r"ab*", "abbbb"))

<re.Match object; span=(0, 1), match='a'>
<re.Match object; span=(0, 5), match='abbbb'>

一或多次

# + ：occur 1 or more times
print(re.search(r"ab+", "a"))
print(re.search(r"ab+", "abbb"))

None
<re.Match object; span=(0, 4), match='abbb'>

可选次数

# {n, m} : occur n to m times 出现了n到m之间的次数
print(re.search(r"ab{2,10}", "a"))
print(re.search(r"ab{2,10}", "abbbb")) # 注意{}之中不要添加空格了，只有数字

None
<re.Match object; span=(0, 5), match='abbbb'>

group 组

# group
match = re.search(r"(\d+), Data: (.+)", "ID: 021523, Data: Feb/12/2017") #()里的东西相当于是一个组
print(match)
print(match.group()) #返回所用东西 7
print(match.group(1))
print(match.group(2))

<re.Match object; span=(4, 29), match='021523, Data: Feb/12/2017'>
021523, Data: Feb/12/2017
021523
Feb/12/2017

#自定义每一组的名字
match = re.search(r"(?P<id>\d+), Data: (?P<date>.+)", "ID: 021523, Data: Feb/12/2017")
print(match)
print(match.group('id'))
print(match.group('date'))

<re.Match object; span=(4, 29), match='021523, Data: Feb/12/2017'>
021523
Feb/12/2017

寻找所有匹配 findall

# findall
print(re.findall(r"r[ua]n", "run ran ren"))

['run', 'ran']

# | ： or
print(re.findall(r"run|ran", "run ran ren"))  #仅匹配|两侧的，如果有括号进匹配括号内的|的两侧的东西

['run', 'ran']

替换(查找并替换)

# re.sub() replace
print(re.sub(r"r[au]ns", "catches", "dog runs to cat"))

dog catches to cat

分裂 split

# re.split()
print(re.split(r"[,;\.]", "a;b,c.d;e")) #以【】中的为分隔符

['a', 'b', 'c', 'd', 'e']

compile

# compile
compiled_re = re.compile(r"r[ua]n") #相当于先将条件格式化
print(compiled_re.search("dog ran to cat"))

<re.Match object; span=(4, 7), match='ran'>