Regular Expressions

Regular Expressions

Python’s re module provides full regex support.

import re

Core Functions

Function	Description
re.match(pattern, string)	Match at the start of string
re.search(pattern, string)	Search anywhere in string
re.findall(pattern, string)	Return all matches as a list
re.finditer(pattern, string)	Return iterator of match objects
re.sub(pattern, repl, string)	Replace matches
re.split(pattern, string)	Split string on matches
re.compile(pattern)	Compile pattern for reuse

Basic Patterns

text = "Hello, my email is user@example.com and phone is 555-1234."

# Search for email
match = re.search(r'[\w.+-]+@[\w-]+\.\w+', text)
if match:
    print(match.group())   # user@example.com

# Find all numbers
nums = re.findall(r'\d+', text)
print(nums)   # ['555', '1234']

Pattern Syntax

Pattern	Meaning
.	Any character except newline
\d	Digit [0-9]
\D	Non-digit
\w	Word char [a-zA-Z0-9_]
\W	Non-word char
\s	Whitespace
\S	Non-whitespace
^	Start of string
$	End of string
*	0 or more
+	1 or more
?	0 or 1 (optional)
{n}	Exactly n times
{n,m}	Between n and m times
[abc]	Character class
[^abc]	Negated class
(abc)	Capturing group
(?:abc)	Non-capturing group
a|b	a or b

Groups

text = "2024-01-15"
match = re.search(r'(\d{4})-(\d{2})-(\d{2})', text)
if match:
    print(match.group(0))  # 2024-01-15 (full match)
    print(match.group(1))  # 2024
    print(match.group(2))  # 01
    print(match.group(3))  # 15

Named Groups

match = re.search(r'(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})', "2024-01-15")
if match:
    print(match.group('year'))   # 2024
    print(match.groupdict())     # {'year': '2024', 'month': '01', 'day': '15'}

Substitution

text = "Hello World"
result = re.sub(r'\s+', '_', text)
print(result)   # Hello_World

# Using a function as replacement
def upper_match(m):
    return m.group().upper()

result = re.sub(r'\b\w+\b', upper_match, "hello world")
print(result)   # HELLO WORLD

Flags

# Case-insensitive
re.findall(r'hello', "Hello HELLO hello", re.IGNORECASE)
# ['Hello', 'HELLO', 'hello']

# Multiline — ^ and $ match start/end of each line
re.findall(r'^\d+', "123\n456\n789", re.MULTILINE)
# ['123', '456', '789']

# DOTALL — . matches newline too
re.search(r'start.*end', "start\nend", re.DOTALL)

Compiled Patterns

# Compile once, use many times
email_pattern = re.compile(r'[\w.+-]+@[\w-]+\.\w+')

emails = ["user@example.com", "bad-email", "admin@site.org"]
valid = [e for e in emails if email_pattern.match(e)]

Common Patterns

# Email
r'[\w.+-]+@[\w-]+\.\w+'

# URL
r'https?://[\w/:%#\$&\?\(\)~\.=\+\-]+'

# Phone (US)
r'\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}'

# IP address
r'\b(?:\d{1,3}\.){3}\d{1,3}\b'

# Hex color
r'#[0-9a-fA-F]{6}\b'

# Slug
r'^[a-z0-9]+(?:-[a-z0-9]+)*$'