Last active
November 10, 2016 02:30
-
-
Save vicro/16e8c80a40fc53e2b8d4fe6abf6c5df2 to your computer and use it in GitHub Desktop.
Python REGEX quick ref
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#import regex module | |
import re | |
#Simple match of a phone number 090-1234-5678 | |
print("####### Simple match of a phone number 090-1234-5678 #######") | |
match = re.match( r"\d{3}-\d{4}-\d{4}", "090-1234-5678" ) | |
print(match) | |
#No match | |
print("####### No match #######") | |
match = re.match( r"\d{3}-\d{4}-\d{4}", "090-XXXX-5678" ) | |
print(match) | |
#With groups | |
print("####### With groups #######") | |
match = re.match( r"(\d{3})-(\d{4})-(\d{4})", "090-1234-5678" ) | |
print(match) | |
print(match.group(0)) #group 0 is always the whole match string | |
print(match.group(1)) #group 1 | |
print(match.group(2)) #group 2 | |
print(match.group(3)) #group 3 | |
#Compile regex for easy reuse | |
print("####### Compile regex for easy reuse #######") | |
phone_regex = re.compile( r"(\d{3})-(\d{4})-(\d{4})" ) | |
print(phone_regex.match("123-1234-1234")) | |
print(phone_regex.match("123-1234-abcd")) | |
#Replace groups | |
print("####### Replace groups #######") | |
print( re.sub(phone_regex, r"first: \1 second:\2 third:\3", "090-1234-5678") ) | |
print( phone_regex.sub(r"first: \1 second:\2 third:\3", "090-1234-5678") ) | |
#Multiline regex (SINGLE LINE IS DEFAULT!!) | |
print("####### Multiline regex (SINGLE LINE IS DEFAULT!!) #######") | |
pattern = re.compile( r"title:(\w+)\ndesc:(\w+)", re.MULTILINE ) | |
match = pattern.match("title:Foo\ndesc:Bar") | |
print( match.group(1) ) | |
print( match.group(2) ) | |
#Named groups | |
print("####### Named groups #######") | |
match = re.match( r"(?P<variable>\w+)\s*=\s*(?P<value>\w+)", "x = 10" ) | |
print(match.group("variable")) | |
print(match.group("value")) | |
#Verbose mode (with comments and ignored whitespace in regex string) | |
print("####### Verbose mode #######") | |
pattern = re.compile( r"""^\s* #whitespace at the beginning of line | |
\w+ #a word | |
\s+ #followed by whitespace | |
\d{3} #then a 3 digit number | |
""", re.VERBOSE ) | |
print(pattern.match("hello 123")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment