Regular Expressions in Python || Python Tutorial || Learn Python Programming
import re
string = 'Bruce Lee'
pattern = '^(\w+)\s+(\w+)$' #match firstname lastname
match = re.search(pattern, string)
if match:
print(string) #Bruce Lee
print(match.span()) #(0,9)
print(match.group()) #Bruce Lee
pattern = '^(?P<fn>\w+)\s+(?P<ln>\w+)$' #match firstname lastname
match = re.search(pattern, string)
if match:
print(string) #Bruce Lee
print(match.span()) #(0,9)
print(match.group('fn')) #Bruce
print(match.group('ln')) #Lee
pattern = '^[a-zA-Z!]+$'
string='m!sha'
match = re.search(pattern, string)
if match:
print(string) #m!sha
re.search() # return the first match
re.findall(pattern, string, flags=0) # return all non-overlapping matched of pattern in string, as a list of strings or tuples
string='Bruce Lee'
pattern = '[a-z]+' #match firstname lastname
match = re.findall(pattern, string)
if match:
print(match) #['ruce','ee']
match = re.finditer(pattern, string) #iterator version
re.match(pattern, string, flags=0) #
match(pattern, string, flags=0)
Try to apply the pattern at the start of the string, returning
a Match object, or None if no match was found.
re.fullmatch(pattern, string, flags=0) #
fullmatch(pattern, string, flags=0)
Try to apply the pattern to all of the string, returning
a Match object, or None if no match was found.
values = ['https://www.socratica.com', 'http://www.socratica.org','not_a_www_https://']
regex = 'https?://w{3}.\w+.(org|com)'
for value in values:
if re.fullmatch(regex, value):print(value)
https://www.youtube.com/watch?v=K8L6KVGG-7o
https://github.com/CoreyMSchafer/code_snippets/tree/master/Python-Regular-Expressions
import re
emails = '''
CoreyMSchafer@gmail.com
corey.schafer@university.edu
corey-321-schafer@my-work.net
'''
pattern = re.compile(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+')
matches = pattern.finditer(emails)
for match in matches:
print(match)
#https://github.com/CoreyMSchafer/code_snippets/blob/master/Python-Regular-Expressions/simple.py
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
coreyms.com
321-555-4321
123.555.1234
123*555*1234
800-555-1234
900-555-1234
Mr. Schafer
Mr Smith
Ms Davis
Mrs. Robinson
Mr. T
'''
sentence = 'Start a sentence and then bring it to an end'
pattern = re.compile(r'start', re.I)
matches = pattern.search(sentence)
print(matches)
##
# https://github.com/CoreyMSchafer/code_snippets/blob/master/Python-Regular-Expressions/urls.py
import re
urls = '''
https://www.google.com
http://coreyms.com
https://youtube.com
https://www.nasa.gov
'''
pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
subbed_urls = pattern.sub(r'\2\3', urls) #back reference
print(subbed_urls)
# matches = pattern.finditer(urls)
# for match in matches:
# print(match.group(3))
Example of callable in re.sub()
s='abcdeABCDE'
def star_ord(m):
return f'*<{m.group(0)}>*'
re.sub('[ae]',star_ord,s)
#'*<a>*bcd*<e>*ABCDE'
reference:
https://docs.python.org/3/library/re.html
https://www.youtube.com/watch?v=nxjwB8up2gI
https://github.com/CoreyMSchafer/code_snippets/tree/master/Python-Regular-Expressions
https://www.python-engineer.com/posts/regular-expressions/
https://youtu.be/AEE9ecgLgdQ?si=2XZpygF-cFoAL0-i
