《学习日记之Python》——正则表达式

正则表达式 (Regular Expression) 又称 RegEx, 是用来匹配字符的一种工具. 在一大串字符中寻找你需要的内容.
注意：先输入import re后，才能用正则表达式

以下例子关于正则表达式的学习
1.# regular expression
pattern1 = “cat”
pattern2 = “bird”
string = “dog runs to cat”
print(re.search(pattern1, string)) # <_sre.SRE_Match object; span=(12, 15), match=‘cat’>
print(re.search(pattern2, string)) # None

2.# multiple patterns (“run” or “ran”)
ptn = r"r[au]n" # start with “r” means raw string
print(re.search(ptn, “dog runs to cat”)) # <_sre.SRE_Match object; span=(4, 7), match=‘run’>

3.# continue
print(re.search(r"r[A-Z]n", “dog runs to cat”)) # None
print(re.search(r"r[a-z]n", “dog runs to cat”)) # <_sre.SRE_Match object; span=(4, 7), match=‘run’>
print(re.search(r"r[0-9]n", “dog r2ns to cat”)) # <_sre.SRE_Match object; span=(4, 7), match=‘r2n’>
print(re.search(r"r[0-9a-z]n", “dog runs to cat”)) # <_sre.SRE_Match object; span=(4, 7), match=‘run’>

4.# \d : decimal digit
print(re.search(r"r\dn", “run r4n”)) # <_sre.SRE_Match object; span=(4, 7), match=‘r4n’>

5.# \D : any non-decimal digit
print(re.search(r"r\Dn", “run r4n”)) # <_sre.SRE_Match object; span=(0, 3), match=‘run’>

6.# \s : any white space [\t\n\r\f\v]
print(re.search(r"r\sn", “r\nn r4n”)) # <_sre.SRE_Match object; span=(0, 3), match=‘r\nn’>

7.# \S : opposite to \s, any non-white space
print(re.search(r"r\Sn", “r\nn r4n”)) # <_sre.SRE_Match object; span=(4, 7), match=‘r4n’>

8.# \w : [a-zA-Z0-9_]
print(re.search(r"r\wn", “r\nn r4n”)) # <_sre.SRE_Match object; span=(4, 7), match=‘r4n’>

9.# \W : opposite to \w
print(re.search(r"r\Wn", “r\nn r4n”)) # <_sre.SRE_Match object; span=(0, 3), match=‘r\nn’>

10.# \b : empty string (only at the start or end of the word)
print(re.search(r"\bruns\b", “dog runs to cat”)) # <_sre.SRE_Match object; span=(4, 8), match=‘runs’>

11.# \B : empty string (but not at the start or end of a word)
print(re.search(r"\B runs \B", “dog runs to cat”)) # <_sre.SRE_Match object; span=(8, 14), match=’ runs '>

12.# \ : match
print(re.search(r"runs\", “runs\ to me”)) # <_sre.SRE_Match object; span=(0, 5), match=‘runs\’>

13.# . : match anything (except \n)
print(re.search(r"r.n", “r[ns to me”)) # <_sre.SRE_Match object; span=(0, 3), match=‘r[n’>

14.# ^ : match line beginning
print(re.search(r"^dog", “dog runs to cat”)) # <_sre.SRE_Match object; span=(0, 3), match=‘dog’>

15.# $ : match line ending
print(re.search(r"cat$", “dog runs to cat”)) # <_sre.SRE_Match object; span=(12, 15), match=‘cat’>

16.# ? : may or may not occur
print(re.search(r"Mon(day)?", “Monday”)) # <_sre.SRE_Match object; span=(0, 6), match=‘Monday’>
print(re.search(r"Mon(day)?", “Mon”)) # <_sre.SRE_Match object; span=(0, 3), match=‘Mon’>

17.# multi-line
string = “”"
dog runs to cat.
I run to dog.
“”"
print(re.search(r"^I", string)) # None
print(re.search(r"^I", string, flags=re.M)) # <_sre.SRE_Match object; span=(18, 19), match=‘I’>

18.# * : occur 0 or more times
print(re.search(r"ab*", “a”)) # <_sre.SRE_Match object; span=(0, 1), match=‘a’>
print(re.search(r"ab*", “abbbbb”)) # <_sre.SRE_Match object; span=(0, 6), match=‘abbbbb’>

19.# + : occur 1 or more times
print(re.search(r"ab+", “a”)) # None
print(re.search(r"ab+", “abbbbb”)) # <_sre.SRE_Match object; span=(0, 6), match=‘abbbbb’>

20.# {n, m} : occur n to m times
print(re.search(r"ab{2,10}", “a”)) # None
print(re.search(r"ab{2,10}", “abbbbb”)) # <_sre.SRE_Match object; span=(0, 6), match=‘abbbbb’>

21.# group
match = re.search(r"(\d+), Date: (.+)", “ID: 021523, Date: Feb/12/2017”)
print(match.group()) # 021523, Date: Feb/12/2017
print(match.group(1)) # 021523
print(match.group(2)) # Date: Feb/12/2017

match = re.search(r"(?P\d+), Date: (?P.+)", “ID: 021523, Date: Feb/12/2017”)
print(match.group(‘id’)) # 021523
print(match.group(‘date’)) # Date: Feb/12/2017

22.# findall
print(re.findall(r"r[ua]n", “run ran ren”)) # [‘run’, ‘ran’]

23.# | : or
print(re.findall(r"(run|ran)", “run ran ren”)) # [‘run’, ‘ran’]

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

25.# re.split()
print(re.split(r"[,;.]", “a;b,c.d;e”)) # [‘a’, ‘b’, ‘c’, ‘d’, ‘e’]

26.# compile
compiled_re = re.compile(r"r[ua]n")
print(compiled_re.search(“dog ran to cat”)) # <_sre.SRE_Match object; span=(4, 7), match=‘ran’>

本文参考来自"莫烦PYTHON"的

https://github.com/MorvanZhou/tutorials/blob/master/basic/36_RegEx.py