## This is not an RE. You can use simple string methods to perform actions on a string

## however you're limited in the actions you can perrom

>>> s = '100 NORTH MAIN ROAD'

>>> s.replace('ROAD', 'RD.') ①

'100 NORTH MAIN RD.'

### Doing substitutions with REGEx

>>> s = '100 NORTH BROAD ROAD'

>>> import re ④

>>> re.sub('ROAD$', 'RD.', s) ⑤

'100 NORTH BROAD RD.'

### this example displays use of a raw string. it means "do not escape characters". This is required because

### in python strings, backslaches '\' must be escaped. You can avoid this in a raw string.

>>> s = '100 BROAD ROAD APT. 3'

>>> re.sub(r'\bROAD\b', 'RD.', s) ④

'100 BROAD RD. APT 3'

#### a straight forward match

>>> import re

>>> pattern = '^M?M?M?$' ①

>>> re.search(pattern, 'M') ②

>>> pattern = '^M?M?M?(CM|CD|D?C?C?C?)$' ①

>>> re.search(pattern, 'MMMCCC') ④

<_sre.SRE_Match object at 010748A8>

#### Verbose Regex: This is a feature Python allows. It ignores spaces and comments. It lets you do

#### something pretty like this. Notice you need to passed the 're.VERBOSE' argument to enable this feature.

>>> pattern = '''

^ # beginning of string

M{0,3} # thousands - 0 to 3 Ms

(CM|CD|D?C{0,3}) # hundreds - 900 (CM), 400 (CD), 0-300 (0 to 3 Cs),

# or 500-800 (D, followed by 0 to 3 Cs)

(XC|XL|L?X{0,3}) # tens - 90 (XC), 40 (XL), 0-30 (0 to 3 Xs),

# or 50-80 (L, followed by 0 to 3 Xs)

(IX|IV|V?I{0,3}) # ones - 9 (IX), 4 (IV), 0-3 (0 to 3 Is),

# or 5-8 (V, followed by 0 to 3 Is)

$ # end of string

'''

>>> re.search(pattern, 'M', re.VERBOSE) ①

<_sre.SRE_Match object at 0x008EEB48>

>>> re.search(pattern, 'MCMLXXXIX', re.VERBOSE) ②

<_sre.SRE_Match object at 0x008EEB48>

>>> phonePattern = re.compile(r'(\d{3})\D*(\d{3})\D*(\d{4})\D*(\d*)$') ①

>>> phonePattern.search('work 1-(800) 555.1212 #1234').groups() ②

('800', '555', '1212', '1234')

>>> phonePattern = re.compile(r'''

# don't match beginning of string, number can start anywhere

(\d{3}) # area code is 3 digits (e.g. '800')

\D* # optional separator is any number of non-digits

(\d{3}) # trunk is 3 digits (e.g. '555')

\D* # optional separator

(\d{4}) # rest of number is 4 digits (e.g. '1212')

\D* # optional separator

(\d*) # extension is optional and can be any number of digits

$ # end of string

''', re.VERBOSE)

>>> phonePattern.search('work 1-(800) 555.1212 #1234').groups() ①

('800', '555', '1212', '1234')

>>> phonePattern.search('800-555-1212') ②

('800', '555', '1212', '')

① Other than being spread out over multiple lines, this is exactly the same regular expression as the last step, so it’s no surprise that it parses the same inputs.

② Final sanity check. Yes, this still works. You’re done.

## Reference

http://www.diveintopython3.net/regular-expressions.html