Common Data Validation Functions in Python Using Regular Expressions

1. Phone number validation

import re

def validate_phone_number(phone):
    pattern = r'^1[3-9]\d{9}$'
    return bool(re.match(pattern, phone))
# Example
print(validate_phone_number('13800138000'))  # True

2. ID card validation

def validate_id_card(id_card):
    pattern = r'(^\d{15}$)|(^\d{17}([0-9]|X)$)'
    return bool(re.match(pattern, id_card))
# Example
print(validate_id_card('11010519491231002X'))  # True

3. Chinese/English name validation

def validate_name(name):
    pattern = r'^[\u4e00-\u9fa5a-zA-Z\s]+$'
    return bool(re.match(pattern, name))
# Example
print(validate_name('张三'))  # True
print(validate_name('Zhang San'))  # True

4. Email address validation

def validate_email(email):
    pattern = r'^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$'
    return bool(re.match(pattern, email))
# Example
print(validate_email('[email protected]'))  # True

5. URL validation

def validate_url(url):
    pattern = r'^(https?:\/\/)?([\da-z\.-]+)\.([a-z\.]{2,6})([\/\w \.-]*)*\/?$'
    return bool(re.match(pattern, url))
# Example
print(validate_url('http://www.example.com'))  # True

6. IP address validation

def validate_ip(ip):
    pattern = r'^((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)$'
    return bool(re.match(pattern, ip))
# Example
print(validate_ip('192.168.0.1'))  # True

7. Scheduled task using the schedule library

import schedule
import time

def job():
    print("I'm working...")

schedule.every(10).minutes.do(job)

while True:
    schedule.run_pending()
    time.sleep(1)

8. Credit card number validation

def validate_credit_card(card_number):
    pattern = r'^(?:4[0-9]{12}(?:[0-9]{3})?|[25][1-7][0-9]{14}|6(?:011|5[0-9][0-9])[0-9]{12}|3[47][0-9]{13}|3(?:0[0-5]|[68][0-9])[0-9]{11}|(?:2131|1800|35)\d{3}\d{11})$'
    return bool(re.match(pattern, card_number))
# Example
print(validate_credit_card('4111111111111111'))  # True

9. Date format (YYYY‑MM‑DD) validation

def validate_date(date_text):
    pattern = r'^\d{4}-\d{2}-\d{2}$'
    if re.match(pattern, date_text):
        try:
            datetime.datetime.strptime(date_text, '%Y-%m-%d')
            return True
        except ValueError:
            return False
    else:
        return False
# Example
print(validate_date('2025-05-05'))  # True

10. Password strength validation (at least one uppercase, one lowercase, one digit, one special character)

def validate_password(password):
    pattern = r'^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[@$!%*?&])[A-Za-z\d@$!%*?&]{8,}$'
    return bool(re.match(pattern, password))
# Example
print(validate_password('Password@123'))  # True

11. Filename validation (no special characters)

def validate_filename(filename):
    pattern = r'^[\w,\s-]+\.[A-Za-z]{2,}$'
    return bool(re.match(pattern, filename))
# Example
print(validate_filename('example.txt'))  # True

12. Integer validation

def validate_integer(integer_str):
    pattern = r'^-?\d+$'
    return bool(re.match(pattern, integer_str))
# Example
print(validate_integer('123'))  # True
print(validate_integer('-123'))  # True

13. Float validation

def validate_float(float_str):
    pattern = r'^-?\d+(\.\d+)?$'
    return bool(re.match(pattern, float_str))
# Example
print(validate_float('123.45'))  # True
print(validate_float('-123.45'))  # True

14. Chinese postal code validation

def validate_postal_code(postal_code):
    pattern = r'^\d{6}$'
    return bool(re.match(pattern, postal_code))
# Example
print(validate_postal_code('100000'))  # True

15. HTML tag removal

def remove_html_tags(text):
    clean = re.compile('<.*?>')
    return re.sub(clean, '', text)
# Example
html_content = "Hello, world!"
print(remove_html_tags(html_content))  # Hello, world!

16. Extract domain from URL

def extract_domain(url):
    pattern = r'https?://([A-Za-z_0-9.-]+).*'
    match = re.match(pattern, url)
    if match:
        return match.group(1)
    return None
# Example
print(extract_domain("http://www.example.com/path"))  # www.example.com

17. Check for repeated words in a string

def has_repeated_words(text):
    pattern = r'\b(\w+)\s+\1\b'
    return bool(re.search(pattern, text, flags=re.IGNORECASE))
# Example
print(has_repeated_words("This is is a test."))  # True

18. IPv6 address validation

def validate_ipv6(ipv6):
    pattern = r'^((?:[A-Fa-f0-9]{1,4}:){7}[A-Fa-f0-9]{1,4})$'
    return bool(re.match(pattern, ipv6))
# Example
print(validate_ipv6('2001:0db8:85a3:0000:0000:8a2e:0370:7334'))  # True

19. Clean phone number by removing non‑digit characters

def clean_phone_number(phone):
    cleaned = re.sub(r'\D', '', phone)  # \D matches any non‑digit character
    return cleaned
# Example
print(clean_phone_number('+1-800-123-4567'))  # 18001234567

20. Extract all email addresses from text

def extract_emails(text):
    emails = re.findall(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+', text)
    return emails
# Example
text = "Contact us at [email protected] or [email protected]"
print(extract_emails(text))  # ['[email protected]', '[email protected]']