Regular Expressions in Python — re Module Guide

What are Regular Expressions?

A regular expression (regex) is a pattern used to match, search, and manipulate text. Python's re module provides full regex support.

re Module Functions

Function	Description
`re.match(pattern, string)`	Match at the beginning 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 with repl
`re.split(pattern, string)`	Split string by pattern
`re.compile(pattern)`	Compile pattern for reuse

Basic Functions

import re

text = "The price is $25.99 and $10.50"

# search - find first match anywhere
match = re.search(r"\d+\.\d+", text)
if match:
    print(match.group())   # 25.99
    print(match.start())   # 14 (start index)
    print(match.end())     # 19 (end index)

# findall - find all matches
prices = re.findall(r"\$\d+\.\d+", text)
print(prices)   # ['$25.99', '$10.50']

# sub - replace matches
clean = re.sub(r"\$\d+\.\d+", "[PRICE]", text)
print(clean)    # The price is [PRICE] and [PRICE]

# split - split by pattern
sentence = "one,two;three four"
parts = re.split(r"[,; ]+", sentence)
print(parts)    # ['one', 'two', 'three', 'four']

Regex Pattern Syntax

Pattern	Matches	Example
`.`	Any character (except newline)	`a.c` -> "abc", "a1c"
`^`	Start of string	`^Hello`
`$`	End of string	`world$`
`*`	0 or more	`ab*` -> "a", "ab", "abb"
`+`	1 or more	`ab+` -> "ab", "abb"
`?`	0 or 1 (optional)	`colou?r` -> "color", "colour"
`{n}`	Exactly n times	`\d{4}` -> "2024"
`{n,m}`	Between n and m times	`\d{2,4}`
`[abc]`	Any of a, b, c	`[aeiou]`
`[^abc]`	Not a, b, or c	`[^0-9]`
`\d`	Digit [0-9]	`\d+` -> "123"
`\D`	Non-digit
`\w`	Word char [a-zA-Z0-9_]	`\w+`
`\W`	Non-word char
`\s`	Whitespace	`\s+`
`\S`	Non-whitespace
`\b`	Word boundary	`\bword\b`
`(abc)`	Capture group	`(\d+)-(\d+)`
`a\|b`	a or b	`cat\|dog`

Groups and Capturing

Groups

import re

# Capture groups with ()
date_str = "Today is 2024-06-15"
match = re.search(r"(\d{4})-(\d{2})-(\d{2})", date_str)
if match:
    print(match.group(0))  # 2024-06-15 (full match)
    print(match.group(1))  # 2024 (year)
    print(match.group(2))  # 06   (month)
    print(match.group(3))  # 15   (day)

# Named groups
match = re.search(r"(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})", date_str)
if match:
    print(match.group("year"))   # 2024
    print(match.group("month"))  # 06
    print(match.groupdict())     # {'year': '2024', 'month': '06', 'day': '15'}

# findall with groups returns list of tuples
text = "John: 25, Alice: 30, Bob: 22"
results = re.findall(r"(\w+): (\d+)", text)
print(results)  # [('John', '25'), ('Alice', '30'), ('Bob', '22')]

Practical Examples

Real-World Patterns

import re

# Email validation
def is_valid_email(email: str) -> bool:
    pattern = r"^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$"
    return bool(re.match(pattern, email))

print(is_valid_email("user@example.com"))   # True
print(is_valid_email("invalid-email"))      # False

# Phone number extraction
text = "Call us at 555-123-4567 or (800) 555-0199"
phones = re.findall(r"[\d\-\(\) ]{10,}", text)
print(phones)

# URL extraction
html = '<a href="https://example.com">Link</a> and <a href="http://test.org">Test</a>'
urls = re.findall(r'https?://[^\s"]+', html)
print(urls)   # ['https://example.com', 'http://test.org']

# Password strength check
def check_password(pwd: str) -> dict:
    return {
        "length": len(pwd) >= 8,
        "uppercase": bool(re.search(r"[A-Z]", pwd)),
        "lowercase": bool(re.search(r"[a-z]", pwd)),
        "digit": bool(re.search(r"\d", pwd)),
        "special": bool(re.search(r"[!@#$%^&*]", pwd)),
    }

result = check_password("MyPass123!")
print(result)

# Compile for reuse (faster when used many times)
email_re = re.compile(r"^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$")
emails = ["a@b.com", "bad", "x@y.org"]
valid = [e for e in emails if email_re.match(e)]
print(valid)  # ['a@b.com', 'x@y.org']