10 Handy Python Regular Expression Scripts for Common Tasks

Hey friends! Today we explore the magic of Python regular expressions with ten concise scripts that solve common coding problems.

1. Validate email address

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

2. Extract URLs from HTML

html_content = '''
Example
'''
urls = re.findall(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', html_content)
print(urls)  # Output: ['http://www.example.com']

3. Replace numbers in text

text = "The price is $100."
new_text = re.sub(r'\$\d+', '$XXX', text)
print(new_text)  # Output: The price is $XXX.

4. Check password strength

password = 'Password123!'
def check_password_strength(password):
    if len(password) < 8:
        return False
    elif not re.search("[a-z]", password):
        return False
    elif not re.search("[A-Z]", password):
        return False
    elif not re.search("[0-9]", password):
        return False
    elif not re.search("[_@$]", password):
        return False
    else:
        return True
print(check_password_strength(password))  # Output: True

5. Split a string

text = "one,two,three,four"
words = re.split(',', text)
print(words)  # Output: ['one', 'two', 'three', 'four']

6. Match date format

date_string = "2023-03-15"
def match_date(date):
    pattern = r'\d{4}-\d{2}-\d{2}'
    if re.match(pattern, date):
        return True
    else:
        return False
print(match_date(date_string))  # Output: True

7. Remove HTML tags

html = "Hello, world!"
clean_text = re.sub('<[^<]+?>', '', html)
print(clean_text)  # Output: Hello, world!

8. Capitalize first letters of words

text = "hello World from python"
capitalized_words = re.findall(r'\b[A-Z][a-z]*', text)
print(capitalized_words)  # Output: ['World']

9. Find phone numbers

text = "Contact us at +1 (123) 456-7890 or 123-456-7890."
def find_phone_numbers(text):
    pattern = r'\+?1?\s?\(?\d{3}\)?[\s.-]?\d{3}[\s.-]?\d{4}'
    return re.findall(pattern, text)
print(find_phone_numbers(text))  # Output: ['+1 (123) 456-7890', '123-456-7890']

10. Replace specific characters

text = "Hello, World!"
new_text = re.sub('[,]', ' ', text)
print(new_text)  # Output: Hello  World!

These scripts are just the tip of the iceberg; regular expressions offer far more power. Keep practicing to master them, and don’t forget to like, share, and follow for more programming tips!