re module provides regular expression matching operations.
Module Import
import re
Basic Matching
search() - Find First Match
import re
text = "The quick brown fox"
# Find pattern
match = re.search(r'quick', text)
if match:
print(match.group()) # 'quick'
print(match.start()) # 4
print(match.end()) # 9
match() - Match at Beginning
import re
text = "Hello, World!"
# Matches only at start
match = re.match(r'Hello', text)
if match:
print("Found at start")
findall() - Find All Matches
import re
text = "Contact: john@example.com or jane@test.com"
# Find all email addresses
emails = re.findall(r'\w+@\w+\.\w+', text)
print(emails) # ['john@example.com', 'jane@test.com']
finditer() - Iterator of Matches
import re
text = "The price is $10.50 and $25.00"
for match in re.finditer(r'\$([0-9.]+)', text):
print(f"Found ${match.group(1)} at position {match.start()}")
Pattern Syntax
Common Patterns
import re
# Digit: \d or [0-9]
re.findall(r'\d+', 'abc123def456') # ['123', '456']
# Word characters: \w or [a-zA-Z0-9_]
re.findall(r'\w+', 'hello_world 123') # ['hello_world', '123']
# Whitespace: \s
re.split(r'\s+', 'split by spaces') # ['split', 'by', 'spaces']
# Any character: .
re.findall(r'h.t', 'hat hit hot') # ['hat', 'hit', 'hot']
# Start/End: ^ and $
re.match(r'^Hello', 'Hello, World!') # Matches
re.search(r'World!$', 'Hello, World!') # Matches
Quantifiers
import re
# Zero or more: *
re.findall(r'ab*', 'a ab abb abbb') # ['a', 'ab', 'abb', 'abbb']
# One or more: +
re.findall(r'ab+', 'a ab abb abbb') # ['ab', 'abb', 'abbb']
# Zero or one: ?
re.findall(r'ab?', 'a ab abb') # ['a', 'ab', 'ab']
# Exactly n: {n}
re.findall(r'\d{3}', '123 45 6789') # ['123', '678']
# Range: {m,n}
re.findall(r'\d{2,4}', '1 12 123 1234 12345') # ['12', '123', '1234', '1234']
Substitution
sub() - Replace Pattern
import re
text = "Contact: 123-456-7890"
# Replace pattern
result = re.sub(r'\d', 'X', text)
print(result) # 'Contact: XXX-XXX-XXXX'
# With count
result = re.sub(r'\d', 'X', text, count=3)
print(result) # 'Contact: XXX-456-7890'
sub() with Function
import re
def replace_func(match):
return match.group(0).upper()
text = "hello world"
result = re.sub(r'\w+', replace_func, text)
print(result) # 'HELLO WORLD'
Groups and Capturing
import re
text = "John Doe, age: 30"
# Capture groups with ()
match = re.search(r'(\w+) (\w+), age: (\d+)', text)
if match:
print(match.group(0)) # 'John Doe, age: 30' (full match)
print(match.group(1)) # 'John' (first group)
print(match.group(2)) # 'Doe' (second group)
print(match.group(3)) # '30' (third group)
print(match.groups()) # ('John', 'Doe', '30')
# Named groups
match = re.search(r'(?P<first>\w+) (?P<last>\w+)', text)
if match:
print(match.group('first')) # 'John'
print(match.group('last')) # 'Doe'
print(match.groupdict()) # {'first': 'John', 'last': 'Doe'}
Compiled Patterns
import re
# Compile for reuse
pattern = re.compile(r'\d+')
result1 = pattern.findall('123 abc 456')
result2 = pattern.search('abc 789 def')
# With flags
pattern = re.compile(r'hello', re.IGNORECASE)
match = pattern.search('HELLO World') # Matches
Flags
import re
# Case insensitive
re.search(r'hello', 'HELLO', re.IGNORECASE)
# Multiline
text = """line 1
line 2
line 3"""
re.findall(r'^line', text, re.MULTILINE) # ['line', 'line', 'line']
# Dot matches newline
re.search(r'a.*b', 'a\nb', re.DOTALL)
# Verbose (allows comments)
pattern = re.compile(r"""
\d{3} # Area code
- # Separator
\d{4} # Number
""", re.VERBOSE)
Practical Examples
Email Validation
import re
def is_valid_email(email):
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
return re.match(pattern, email) is not None
print(is_valid_email('user@example.com')) # True
print(is_valid_email('invalid.email')) # False
Extract URLs
import re
text = "Visit https://example.com or http://test.org"
url_pattern = r'https?://[\w.-]+(?:\.[\w.-]+)+'
urls = re.findall(url_pattern, text)
print(urls) # ['https://example.com', 'http://test.org']
Phone Number Formatting
import re
def format_phone(phone):
# Remove non-digits
digits = re.sub(r'\D', '', phone)
# Format as (XXX) XXX-XXXX
return re.sub(r'(\d{3})(\d{3})(\d{4})', r'(\1) \2-\3', digits)
print(format_phone('1234567890')) # '(123) 456-7890'
print(format_phone('123.456.7890')) # '(123) 456-7890'
Compile patterns you use repeatedly for better performance.
Be careful with greedy quantifiers. Use
? for non-greedy matching: .*? instead of .*string
String operations
Built-in Types
String type