re【正規表現】^{3.1, 3.3, 3.4, 3.6, 3.7, 3.8}

re.compile(pattern, flags=0)

戻り値Pattern【正規表現オブジェクト】
pattern正規表現パターン
flags検索フラグ
例外re.error

import re

s1 = "The quick brown fox jumps over the lazy dog."
s2 = "THE QUICK BROWN FOX JUMPS OVER THE LAZY DOG."

pattern = re.compile(r"(\w+) (\w+)")
print(pattern.search(s1))
print(pattern.search(s2))

【出力例】
<re.Match object; span=(0, 9), match='The quick'>
<re.Match object; span=(0, 9), match='THE QUICK'>

re.search(pattern, string, flags=0)
re.match(pattern, string, flags=0)
re.fullmatch(pattern, string, flags=0) 3.4

Pattern.search(string[, pos[, endpos]])
Pattern.match(string[, pos[, endpos]])
Pattern.fullmatch(string[, pos[, endpos]]) 3.4

戻り値Match【マッチオブジェクト】 (一致無し：None)
pattern正規表現パターン
string検索元文字列
flags検索フラグ
pos検索開始位置インデックス (省略：0)
endpos検索終了位置インデックス
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."
print(re.search(r"\w*x\w*", s))
print(re.search(r"\w*y\w*", s))
print(re.search(r"\w*z\w*", s))
print(re.search(r"\w*@\w*", s))

pattern = re.compile(r"\w+")
match = pattern.search(s)
print(match)
match = pattern.search(s, match.end())
print(match)
match = pattern.search(s, match.end())
print(match)

【出力例】
<re.Match object; span=(16, 19), match='fox'>
<re.Match object; span=(35, 39), match='lazy'>
<re.Match object; span=(35, 39), match='lazy'>
None
<re.Match object; span=(0, 3), match='The'>
<re.Match object; span=(4, 9), match='quick'>
<re.Match object; span=(10, 15), match='brown'>

import re

s = "The quick brown fox jumps over the lazy dog."
p1 = r"\w*h\w*"
p2 = r"\w*x\w*"

print(re.match(p1, s))
print(re.match(p2, s))

pattern = re.compile(p1)
print(pattern.match(s))
pattern = re.compile(p2)
print(pattern.match(s))

【出力例】
<re.Match object; span=(0, 3), match='The'>
None
<re.Match object; span=(0, 3), match='The'>
None

import re

s = "abc_xyz"
p1 = r"a\w*z"
p2 = r"z\w*a"

print(re.fullmatch(p1, s))
print(re.fullmatch(p2, s))

pattern = re.compile(p1)
print(pattern.fullmatch(s))
pattern = re.compile(p2)
print(pattern.fullmatch(s))

【出力例】
<re.Match object; span=(0, 7), match='abc_xyz'>
None
<re.Match object; span=(0, 7), match='abc_xyz'>
None

re.split(pattern, string, maxsplit=0, flags=0)
Pattern.split(string, maxsplit=0)

戻り値分割リスト
pattern正規表現パターン
string分割元文字列
maxsplit最大分割数 (0：制限なし)
flags検索フラグ 3.1
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."

print(re.split(" ", s))
print(re.split(" ", s, 3))

pattern = re.compile(" ")
print(pattern.split(s))
print(pattern.split(s, 3))

【出力例】
['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog.']
['The', 'quick', 'brown', 'fox jumps over the lazy dog.']
['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog.']
['The', 'quick', 'brown', 'fox jumps over the lazy dog.']

re.findall(pattern, string, flags=0)
Pattern.findall(string[, pos[, endpos]])

戻り値検索結果リスト
キャプチャ２個未満：文字列のリスト
キャプチャ２個以上：キャプチャのタプルのリスト
pattern正規表現パターン
string検索元文字列
flags検索フラグ
pos検索開始位置インデックス (省略：0)
endpos検索終了位置インデックス
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."

print(re.findall(r"\w+", s))
print(re.findall(r"(\w+)", s))
print(re.findall(r"(\w+) (\w+)", s))

pattern = re.compile(r"\w+")
print(pattern.findall(s))
print(pattern.findall(s, 4, 19))

【出力例】
['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']
['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']
[('The', 'quick'), ('brown', 'fox'), ('jumps', 'over'), ('the', 'lazy')]
['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']
['quick', 'brown', 'fox']

re.finditer(pattern, string, flags=0)
Pattern.finditer(string[, pos[, endpos]])

戻り値イテレータ (Match【マッチオブジェクト】)
pattern正規表現パターン
string検索元文字列
flags検索フラグ
pos検索開始位置インデックス (省略：0)
endpos検索終了位置インデックス
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."

print("re.finditer()")
for item in re.finditer(r"\w+", s):
    print(item)

print("pattern.finditer()")
pattern = re.compile(r"\w+")
for item in pattern.finditer(s):
    print(item)

print("pattern.finditer(, 4, 19)")
for item in pattern.finditer(s, 4, 19):
    print(item)

【出力例】
re.finditer()
<re.Match object; span=(0, 3), match='The'>
<re.Match object; span=(4, 9), match='quick'>
<re.Match object; span=(10, 15), match='brown'>
<re.Match object; span=(16, 19), match='fox'>
<re.Match object; span=(20, 25), match='jumps'>
<re.Match object; span=(26, 30), match='over'>
<re.Match object; span=(31, 34), match='the'>
<re.Match object; span=(35, 39), match='lazy'>
<re.Match object; span=(40, 43), match='dog'>
pattern.finditer()
<re.Match object; span=(0, 3), match='The'>
<re.Match object; span=(4, 9), match='quick'>
<re.Match object; span=(10, 15), match='brown'>
<re.Match object; span=(16, 19), match='fox'>
<re.Match object; span=(20, 25), match='jumps'>
<re.Match object; span=(26, 30), match='over'>
<re.Match object; span=(31, 34), match='the'>
<re.Match object; span=(35, 39), match='lazy'>
<re.Match object; span=(40, 43), match='dog'>
pattern.finditer(, 4, 19)
<re.Match object; span=(4, 9), match='quick'>
<re.Match object; span=(10, 15), match='brown'>
<re.Match object; span=(16, 19), match='fox'>

re.sub(pattern, repl, string, count=0, flags=0 3.1)
re.subn(pattern, repl, string, count=0, flags=0 3.1)

Pattern.sub(repl, string, count=0)
Pattern.subn(repl, string, count=0)

戻り値処理結果
sub()置換後の文字列
subn()タプル (置換後の文字列, 置換個数)
pattern置換パターン (正規表現パターン・Pattern【正規表現オブジェクト】)
repl置換文字列 または 置換文字列を返却する置換関数 (引数：Match【マッチオブジェクト】)
(キャプチャの参照については、メモ 参照)
string置換元文字列
count最大置換数 (0：全置換)
flags検索フラグ
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."
p = r"\s"
repl = " / "

print(re.sub(p, repl, s))
print(re.subn(p, repl, s, 3))

pattern = re.compile(p)
print(pattern.sub(repl, s))
print(pattern.subn(repl, s, 3))

【出力例】
The / quick / brown / fox / jumps / over / the / lazy / dog.
('The / quick / brown / fox jumps over the lazy dog.', 3)
The / quick / brown / fox / jumps / over / the / lazy / dog.
('The / quick / brown / fox jumps over the lazy dog.', 3)

import re

s = "The quick brown fox jumps over the lazy dog."
p = r"(\w+) (?P<group2>\w+) (\w+)"
repl = r"[\3 \g<group2> \g<1>]"

print(re.sub(p, repl, s))
print(re.subn(p, repl, s, 2))

pattern = re.compile(p)
print(pattern.sub(repl, s))
print(pattern.subn(repl, s, 2))

【出力例】
[brown quick The] [over jumps fox] [dog lazy the].
('[brown quick The] [over jumps fox] the lazy dog.', 2)
[brown quick The] [over jumps fox] [dog lazy the].
('[brown quick The] [over jumps fox] the lazy dog.', 2)

import re

def repl(match):
    s = match.group(0)
    return s + "(" + str(len(s)) + ")"

s = "The quick brown fox jumps over the lazy dog."
p = r"\w+"

print(re.sub(p, repl, s))
print(re.subn(p, repl, s, 3))

pattern = re.compile(p)
print(pattern.sub(repl, s))
print(pattern.subn(repl, s, 3))

【出力例】
The(3) quick(5) brown(5) fox(3) jumps(5) over(4) the(3) lazy(4) dog(3).
('The(3) quick(5) brown(5) fox jumps over the lazy dog.', 3)
The(3) quick(5) brown(5) fox(3) jumps(5) over(4) the(3) lazy(4) dog(3).
('The(3) quick(5) brown(5) fox jumps over the lazy dog.', 3)

import re

def repl(match):
    return "[" + match.group("group2") + " " + match.group(1) + "]"

s = "The quick brown fox jumps over the lazy dog."
p = r"(\w+) (?P<group2>\w+)"
pattern = re.compile(p)

print("(A)", re.sub(p, repl, s))
print("(B)", re.sub(pattern, repl, s))
print("(C)", pattern.sub(repl, s))

print("(D)", re.subn(p, repl, s, 2))
print("(E)", re.subn(pattern, repl, s, 2))
print("(F)", pattern.subn(repl, s, 2))

【出力例】
(A) [quick The] [fox brown] [over jumps] [lazy the] dog.
(B) [quick The] [fox brown] [over jumps] [lazy the] dog.
(C) [quick The] [fox brown] [over jumps] [lazy the] dog.
(D) ('[quick The] [fox brown] jumps over the lazy dog.', 2)
(E) ('[quick The] [fox brown] jumps over the lazy dog.', 2)
(F) ('[quick The] [fox brown] jumps over the lazy dog.', 2)

re.escape(pattern)

戻り値エスケープ後の文字列
pattern文字列

import re

print(re.escape("()[].+*?"))

【出力例】
\(\)\[\]\.\+\*\?

re.purge()

戻り値なし

Match.expand(template)

戻り値展開後の文字列
templateテンプレート文字列 (キャプチャの参照については、メモ 参照)
例外re.error

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match)
print(match.expand(r"\g<group4> \g<3> \g<group2> \1"))

【出力例】
<re.Match object; span=(0, 19), match='The quick brown fox'>
fox brown quick The

Match.__getitem__(g) 3.6

戻り値キャプチャ値
gキャプチャ番号 または キャプチャ名
例外IndexError

Match.group([group1, ...])

戻り値
引数０個：マッチ文字列全体
引数１個：キャプチャ値
引数２個以上：キャプチャ値のタプル
groupNキャプチャ番号 または キャプチャ名
例外IndexError

Match.groupdict(default=None)

戻り値辞書 (キャプチャ名, キャプチャ値)
default一致しないキャプチャの対応値

Match.groups(default=None)

戻り値タプル (キャプチャ値)
default一致しないキャプチャの対応値

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match[0])
print(match[1])
print(match[2])
print(match[3])
print(match["group2"])
print(match["group4"])

【出力例】
The quick brown fox
The
quick
brown
quick
fox

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match.group(0))
print(match.group(1))
print(match.group(2))
print(match.group(3))
print(match.group("group2"))
print(match.group("group4"))
print(match.group(3, "group4"))

【出力例】
The quick brown fox
The
quick
brown
quick
fox
('brown', 'fox')

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match.groupdict())

match = re.search(r"(?P<group1>\w+) (?P<group2>\w+) (?P<group9>xyz\w+)?", s)
print(match.groupdict())
print(match.groupdict("EMPTY"))

【出力例】
{'group2': 'quick', 'group4': 'fox'}
{'group1': 'The', 'group2': 'quick', 'group9': None}
{'group1': 'The', 'group2': 'quick', 'group9': 'EMPTY'}

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match.groups())

match = re.search(r"(?P<group1>\w+) (?P<group2>\w+) (?P<group9>xyz\w+)?", s)
print(match.groups())
print(match.groups("EMPTY"))

【出力例】
('The', 'quick', 'brown', 'fox')
('The', 'quick', None)
('The', 'quick', 'EMPTY')

Match.start([group])
Match.end([group])

戻り値先頭または末尾のマッチ位置インデックス
groupキャプチャ番号 または キャプチャ名

Match.span([group])

戻り値タプル (先頭マッチ位置インデックス, 末尾マッチ位置インデックス)
groupキャプチャ番号 または キャプチャ名 (省略 / 0：マッチ部分全体)

import re

s = "The quick brown fox jumps over the lazy dog."
match = re.search(r"\w*c\w*", s)
print(match)
print(match.start())
print(match.end())
print(match.span())
print()

match = re.search(r"(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)", s)
print(match)
print(match.start())
print(match.end())
print(match.span())
print()
print(match.start(1))
print(match.end(1))
print(match.span(1))
print()
print(match.start("group4"))
print(match.end("group4"))
print(match.span("group4"))

【出力例】
<re.Match object; span=(4, 9), match='quick'>
4
9
(4, 9)

<re.Match object; span=(0, 19), match='The quick brown fox'>
0
19
(0, 19)

0
3
(0, 3)

16
19
(16, 19)