re.sub, flagi i skompilowane wzorce

Wprowadzenie

Podstawy re.sub

import re
result = re.sub(r'\d+', 'X', 'abc 123 def 456')
print(result)

re.sub z grupami

import re
# Swap first and last name
result = re.sub(r'(\w+),\s*(\w+)', r'\2 \1', 'Smith, John')
print(result)

re.sub z funkcją

import re
def double_num(m): return str(int(m.group())*2)
result = re.sub(r'\d+', double_num, '1 cats and 2 dogs')
print(result)

re.IGNORECASE (re.I)

import re
print(re.findall(r'hello', 'Hello HELLO hello', re.I))

re.MULTILINE (re.M)

import re
text = 'first\nsecond\nthird'
print(re.findall(r'^\w+', text, re.M))

re.DOTALL (re.S)

import re
text = 'line1\nline2'
print(re.search(r'line1.line2', text, re.S).group())

re.VERBOSE (re.X)

import re
pattern = re.compile(r'''
    (?P<year>\d{4})   # year
    -
    (?P<month>\d{2}) # month
    -
    (?P<day>\d{2})   # day
''', re.X)
print(pattern.search('2024-01-15').groupdict())

Łączenie flag

import re
print(re.findall(r'^\w+', 'Hello\nWorld', re.I | re.M))

re.compile — wydajność

import re
email_re = re.compile(r'[\w.+-]+@[\w-]+\.[\w.]+')
emails = ['user@example.com', 'invalid', 'test@test.org']
print([e for e in emails if email_re.fullmatch(e)])

re.escape()

import re
user_input = 'price.is $10+'
pattern = re.compile(re.escape(user_input))
text = 'The price.is $10+ today'
print(bool(pattern.search(text)))

Szybki test

Podsumowanie

Działaj dalej