Python正規表示式(Regular expression)

by 龍冥

Regular expression翻譯有幾種版本:正則表達式、正規表示式、正規表示法、規則運算式。
若是看到這幾種敘述,皆是指Regular expression。

重要的第一步:匯入re模組

只要使用正規表示式,必須要在開頭處打匯入re模組指令:

import requests

若是沒有匯入,會得到錯誤:

NameError: name 're' is not defined

參考莫凡正規表示式教學的範例碼,另外也可從「Python正規表示式:不一定要會,但會了超省力」這篇文章找到使用教學。

# %%
pattern1 = "cat"
pattern2 = "dog"
string = "dog run!"
print(pattern1 in string)
print(pattern2 in string)

# %%
import re
# regular expression
pattern1 = "cat"
pattern2 = "dog"
string = "dog run!"
print(re.search(pattern1 , string))
print(re.search(pattern2 , string))
# %%
# 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'>

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'>

# %%
# \d : decimal digit
print(re.search(r"r\dn", "run r4n"))                # <_sre.SRE_Match object; span=(4, 7), match='r4n'>
# \D : any non-decimal digit
print(re.search(r"r\Dn", "run r4n"))                # <_sre.SRE_Match object; span=(0, 3), match='run'>

# %%
# \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'>
# \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'>

# %%
# \w : [a-zA-Z0-9_]
print(re.search(r"r\wn", "r\nn r4n"))               # <_sre.SRE_Match object; span=(4, 7), match='r4n'>
# \W : opposite to \w
print(re.search(r"r\Wn", "r\nn r4n"))               # <_sre.SRE_Match object; span=(0, 3), match='r\nn'>

#%%空白文字
# \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'>
# \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 '>

# %%找尋反斜線(\)
# \\ : match \
print(re.search(r"runs\\", "runs\ to me"))          # <_sre.SRE_Match object; span=(0, 5), match='runs\\'>
# . : match anything (except \n)(可以找尋任何特殊字元)
print(re.search(r"r.n", "r[ns to me"))              # <_sre.SRE_Match object; span=(0, 3), match='r[n'>

# %%句首句尾
# ^ : match line beginning(只能在句首)
print(re.search(r"^dog", "dog runs to cat"))        # <_sre.SRE_Match object; span=(0, 3), match='dog'>
# $ : match line ending(只能在句尾)
print(re.search(r"cat$", "dog runs to cat"))        # <_sre.SRE_Match object; span=(12, 15), match='cat'>

# %%是否
# ? : may or may not occur(括號內的文字無論是否存在,皆會找到)
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'>

# %%
# multi-line判斷多行
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'>

# %%
# * : occur 0 or more times出現過0或多次
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'>

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

# %%
# {n, m} : occur n to m times(介於重複n到m次之間)
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'>

# %%
# group(搜尋結果分組)
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

# %%
# findall(找尋全部)
print(re.findall(r"r[ua]n", "run ran ren"))         # ['run', 'ran']

# %%
# | : or(或者條件的指令)
print(re.findall(r"(run|ran)", "run ran ren"))      # ['run', 'ran']

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


# %%
# re.split()(分隔指令)
print(re.split(r"[,;\.]", "a;b,c.d;e"))             # ['a', 'b', 'c', 'd', 'e']

# %%
# 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'>
image 26
image 27

Related Posts

Copyright © 2024 龍冥 | 本站採用 reCAPTCHA保護機制 隱私權&條款