re【正規表現】^{3.1 / 3.3 / 3.4 / 3.6～3.8}

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+)')

matched = pattern.search(s1)
print(matched)
# 出力：<re.Match object; span=(0, 9), match='The quick'>
print(matched.lastindex, matched[0], matched[1], matched[2], sep='/')
# 出力：2/The quick/The/quick

matched = pattern.search(s2)
print(matched)
# 出力：<re.Match object; span=(0, 9), match='THE QUICK'>
print(matched.lastindex, matched[0], matched[1], matched[2], sep='/')
# 出力：2/THE QUICK/THE/QUICK

import re

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

matched = re.search(r'\w*x\w*', s)
print(matched)
# 出力：<re.Match object; span=(16, 19), match='fox'>
print(matched[0])
# 出力：fox

matched = re.search(r'\w*y\w*', s)
print(matched)
# 出力：<re.Match object; span=(35, 39), match='lazy'>
print(matched[0])
# 出力：lazy

matched = re.search(r'\w*z\w*', s)
print(matched)
# 出力：<re.Match object; span=(35, 39), match='lazy'>
print(matched[0])
# 出力：lazy

matched = re.search(r'\w*@\w*', s)
print(matched)
# 出力：None

pattern = re.compile(r'\w+')

matched = pattern.search(s)
print(matched)
# 出力：<re.Match object; span=(0, 3), match='The'>
print(matched[0])
# 出力：The

matched = pattern.search(s, matched.end())
print(matched)
# 出力：<re.Match object; span=(4, 9), match='quick'>
print(matched[0])
# 出力：quick

matched = pattern.search(s, matched.end())
print(matched)
# 出力：<re.Match object; span=(10, 15), match='brown'>
print(matched[0])
# 出力：brown

import re

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

matched = re.match(p1, s)
print(matched)
# 出力：<re.Match object; span=(0, 3), match='The'>
print(matched[0])
# 出力：The

matched = re.match(p2, s)
print(matched)
# 出力：None

pattern = re.compile(p1)
matched = pattern.match(s)
print(matched)
# 出力：<re.Match object; span=(0, 3), match='The'>
print(matched[0])
# 出力：The

pattern = re.compile(p2)
matched = pattern.match(s)
print(matched)
# 出力：None

import re

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

matched = re.fullmatch(p1, s)
print(matched)
# 出力：<re.Match object; span=(0, 7), match='abc_xyz'>
print(matched[0])
# 出力：abc_xyz

matched = re.fullmatch(p2, s)
print(matched)
# 出力：None

pattern = re.compile(p1)
matched = pattern.fullmatch(s)
print(matched)
# 出力：<re.Match object; span=(0, 7), match='abc_xyz'>
print(matched[0])
# 出力：abc_xyz

pattern = re.compile(p2)
matched = pattern.fullmatch(s)
print(matched)
# 出力：None

import re

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

print(re.split(' ', s))
# 出力：['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog.']

print(re.split(' ', s, 3))
# 出力：['The', 'quick', 'brown', 'fox jumps over the lazy dog.']

pattern = re.compile(' ')

print(pattern.split(s))
# 出力：['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog.']

print(pattern.split(s, 3))
# 出力：['The', 'quick', 'brown', 'fox jumps over the lazy dog.']

import re

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

print(re.findall(r'\w+', s))
# 出力：['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']

print(re.findall(r'(\w+)', s))
# 出力：['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']

print(re.findall(r'(\w+) (\w+)', s))
# 出力：[('The', 'quick'), ('brown', 'fox'), ('jumps', 'over'), ('the', 'lazy')]

pattern = re.compile(r'\w+')

print(pattern.findall(s))
# 出力：['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']

print(pattern.findall(s, 4, 19))
# 出力：['quick', 'brown', 'fox']

import re

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

for matched in re.finditer(r'\w+', s):
    print(matched[0], matched)
# 出力：The <re.Match object; span=(0, 3), match='The'>
# 出力：quick <re.Match object; span=(4, 9), match='quick'>
# 出力：brown <re.Match object; span=(10, 15), match='brown'>
# 出力：fox <re.Match object; span=(16, 19), match='fox'>
# 出力：jumps <re.Match object; span=(20, 25), match='jumps'>
# 出力：over <re.Match object; span=(26, 30), match='over'>
# 出力：the <re.Match object; span=(31, 34), match='the'>
# 出力：lazy <re.Match object; span=(35, 39), match='lazy'>
# 出力：dog <re.Match object; span=(40, 43), match='dog'>

pattern = re.compile(r'\w+')
for matched in pattern.finditer(s):
    print(matched[0], matched)
# 出力：The <re.Match object; span=(0, 3), match='The'>
# 出力：quick <re.Match object; span=(4, 9), match='quick'>
# 出力：brown <re.Match object; span=(10, 15), match='brown'>
# 出力：fox <re.Match object; span=(16, 19), match='fox'>
# 出力：jumps <re.Match object; span=(20, 25), match='jumps'>
# 出力：over <re.Match object; span=(26, 30), match='over'>
# 出力：the <re.Match object; span=(31, 34), match='the'>
# 出力：lazy <re.Match object; span=(35, 39), match='lazy'>
# 出力：dog <re.Match object; span=(40, 43), match='dog'>

for matched in pattern.finditer(s, 4, 19):
    print(matched[0], matched)
# 出力：quick <re.Match object; span=(4, 9), match='quick'>
# 出力：brown <re.Match object; span=(10, 15), match='brown'>
# 出力：fox <re.Match object; span=(16, 19), match='fox'>

import re

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

print(re.sub(p, repl, s))
# 出力：The / quick / brown / fox / jumps / over / the / lazy / dog.
print(re.subn(p, repl, s, 3))
# 出力：('The / quick / brown / fox jumps over the lazy dog.', 3)

pattern = re.compile(p)
print(pattern.sub(repl, s))
# 出力：The / quick / brown / fox / jumps / over / the / lazy / dog.
print(pattern.subn(repl, s, 3))
# 出力：('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))
# 出力：[brown quick The] [over jumps fox] [dog lazy the].
print(re.subn(p, repl, s, 2))
# 出力：('[brown quick The] [over jumps fox] the lazy dog.', 2)

pattern = re.compile(p)
print(pattern.sub(repl, s))
# 出力：[brown quick The] [over jumps fox] [dog lazy the].
print(pattern.subn(repl, s, 2))
# 出力：('[brown quick The] [over jumps fox] the lazy dog.', 2)

import re

def func_repl(matched):
    s = matched.group(0)
    return s + '(' + str(len(s)) + ')'

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

print(re.sub(p, func_repl, s))
# 出力：The(3) quick(5) brown(5) fox(3) jumps(5) over(4) the(3) lazy(4) dog(3).
print(re.subn(p, func_repl, s, 3))
# 出力：('The(3) quick(5) brown(5) fox jumps over the lazy dog.', 3)

pattern = re.compile(p)
print(pattern.sub(func_repl, s))
# 出力：The(3) quick(5) brown(5) fox(3) jumps(5) over(4) the(3) lazy(4) dog(3).
print(pattern.subn(func_repl, s, 3))
# 出力：('The(3) quick(5) brown(5) fox jumps over the lazy dog.', 3)

import re

def func_repl(matched):
    return '[' + matched.group('group2') + ' ' + matched.group(1) + ']'

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

print(re.sub(p, func_repl, s))
# 出力：[quick The] [fox brown] [over jumps] [lazy the] dog.
print(re.sub(pattern, func_repl, s))
# 出力：[quick The] [fox brown] [over jumps] [lazy the] dog.
print(pattern.sub(func_repl, s))
# 出力：[quick The] [fox brown] [over jumps] [lazy the] dog.

print(re.subn(p, func_repl, s, 2))
# 出力：('[quick The] [fox brown] jumps over the lazy dog.', 2)
print(re.subn(pattern, func_repl, s, 2))
# 出力：('[quick The] [fox brown] jumps over the lazy dog.', 2)
print(pattern.subn(func_repl, s, 2))
# 出力：('[quick The] [fox brown] jumps over the lazy dog.', 2)

import re

print(re.escape('abc()[].+*?XYZ'))
# 出力：abc\(\)\[\]\.\+\*\?XYZ

import re

s = 'The quick brown fox jumps over the lazy dog.'
matched = re.search(r'(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)', s)
print(matched)
# 出力：<re.Match object; span=(0, 19), match='The quick brown fox'>
print(matched[1], matched[2], matched[3], matched[4], sep='/')
# 出力：The/quick/brown/fox
print(matched.expand(r'\g<group4> \g<3> \g<group2> \1'))
# 出力：fox brown quick The

import re

s = 'The quick brown fox jumps over the lazy dog.'
matched = re.search(r'(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)', s)
print(matched[0])
# 出力：The quick brown fox
print(matched[1])
# 出力：The
print(matched[2])
# 出力：quick
print(matched[3])
# 出力：brown
print(matched[4])
# 出力：fox
print(matched['group2'])
# 出力：quick
print(matched['group4'])
# 出力：fox

import re

s = 'The quick brown fox jumps over the lazy dog.'
matched = re.search(r'(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)', s)
print(matched.group(0))
# 出力：The quick brown fox
print(matched.group(1))
# 出力：The
print(matched.group(2))
# 出力：quick
print(matched.group(3))
# 出力：brown
print(matched.group(4))
# 出力：fox
print(matched.group('group2'))
# 出力：quick
print(matched.group('group4'))
# 出力：fox
print(matched.group(3, 'group4'))
# 出力：('brown', 'fox')

import re

s = 'The quick brown fox jumps over the lazy dog.'
matched = re.search(r'(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)', s)
print(matched.groupdict())
# 出力：{'group2': 'quick', 'group4': 'fox'}

matched = re.search(r'(?P<group1>\w+) (?P<group2>\w+) (?P<group9>xyz\w+)?', s)
print(matched.groupdict())
# 出力：{'group1': 'The', 'group2': 'quick', 'group9': None}
print(matched.groupdict('EMPTY'))
# 出力：{'group1': 'The', 'group2': 'quick', 'group9': 'EMPTY'}

import re

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

matched = re.search(r'(?P<group1>\w+) (?P<group2>\w+) (?P<group9>xyz\w+)?', s)
print(matched.groups())
# 出力：('The', 'quick', None)
print(matched.groups('EMPTY'))
# 出力：('The', 'quick', 'EMPTY')

import re

s = 'The quick brown fox jumps over the lazy dog.'
matched = re.search(r'\w*c\w*', s)
print(matched)
# 出力：<re.Match object; span=(4, 9), match='quick'>
print(matched.start())
# 出力：4
print(matched.end())
# 出力：9
print(matched.span())
# 出力：(4, 9)

matched = re.search(r'(\w+) (?P<group2>\w+) (\w+) (?P<group4>\w+)', s)
print(matched)
# 出力：<re.Match object; span=(0, 19), match='The quick brown fox'>
print(matched.start())
# 出力：0
print(matched.end())
# 出力：19
print(matched.span())
# 出力：(0, 19)

print(matched.start(1))
# 出力：0
print(matched.end(1))
# 出力：3
print(matched.span(1))
# 出力：(0, 3)

print(matched.start('group4'))
# 出力：16
print(matched.end('group4'))
# 出力：19
print(matched.span('group4'))
# 出力：(16, 19)