Python RegEx

❑ A RegEx, or Regular Expression, is a sequence of characters that forms a search pattern.

❑ RegEx can be used to check if a string contains the specified search pattern.

❑ RegEx Module

✓ Python has a built-in package called re, which can be used to work with Regular Expressions.

✓ Import the re module: import re

➢ import re #Check if the string starts with "The" and ends with "Spain":

txt = "The rain in Spain"

Output: x = re.search("^The.*Spain$", txt)

YES! We have a match! if x:

print("YES! We have a match!")
else:
print("No match")
 RegEx Functions

❑ The re module offers a set of functions that allows us to search a string for a match:

❑ Function Description

✓ findall Returns a list containing all matches

✓ search Returns a Match object if there is a match anywhere in the string
✓ split Returns a list where the string has been split at each match
✓ sub Replaces one or many matches with a string

import re
Output: #Return a list containing every occurrence of "ai":
['ai', 'ai'] txt = "The rain in Spain"
x = re.findall("ai", txt)
print(x)

Note: The list contains the matches in the order they are found. If no matches are found, an empty list is returned.
import re

#The search() function returns a Match object:

#Split at each white-space character:
txt = "The rain in Spain"
x = re.search("ai", txt)
import re
print(x) #<_sre.SRE_Match object; span=(5, 7), match='ai'>
txt = "The rain in Spain"
x = re.split("\s", txt)
#Search for the first white-space character in the string: print(x)

import re #Output: ['The', 'rain', 'in', 'Spain']

txt = "The rain in Spain"

x = re.search("\s", txt)

print("The first white-space character is located in position:", x.start())

#Output: The first white-space character is located in position: 3

#Split the string only at the first occurrence:

import re

txt = "The rain in Spain"

x = re.split("\s", txt, 1)
print(x) #Replace the first 2 occurrences:

#output: ['The', 'rain in Spain'] import re

txt = "The rain in Spain"

#Replace every white-space character with the number 9: x = re.sub("\s", "9", txt, 2)
print(x)
import re
#output: The9rain9in Spain
txt = "The rain in Spain"
x = re.sub("\s", "9", txt)
print(x)

#output: The9rain9in9Spain
❑ The Match object has properties and methods used to retrieve information about the search, and the result:

✓ .span() returns a tuple containing the start-, and end positions of the match.
✓ .string returns the string passed into the function
✓ .group() returns the part of the string where there was a match Print the string passed into the function:

Print the position (start- and end-position) of the first match import re
occurrence.
txt = "The rain in Spain"
The regular expression looks for any words that starts with x = re.search(r"\bS\w+", txt)
an upper case "S": print(x.string) #The rain in Spain

import re Print the part of the string where there was a match.

txt = "The rain in Spain" The regular expression looks for any words that
x = re.search(r"\bS\w+", txt) starts with an upper case "S":
print(x.span()) #(12, 17)
import re

txt = "The rain in Spain"

x = re.search(r"\bS\w+", txt)
print(x.group()) #Spain
❑ Metacharacters

✓ Metacharacters are characters with a special meaning:

import re

txt = "The rain in Spain"

#Find all lower case characters alphabetically between "a" and "m":

x = re.findall("[a-m]", txt)

print(x) #['h', 'e', 'a', 'i', 'i', 'a', 'i']

import re

txt = "That will be 59 dollars"

#Find all digit characters:

x = re.findall("\d", txt)

print(x) #['5', '9']

import re

txt = "hello world"

#Search for a sequence that starts with "he", followed by two (any) characters, and an "o":

x = re.findall("he..o", txt)

print(x) #['hello']
import re

txt = "hello world"

#Check if the string starts with 'hello':

x = re.findall("^hello", txt)
if x:
print("Yes, the string starts with 'hello'")
else:
print("No match")

Output: Yes, the string starts with 'hello'

txt = "hello world"

#Check if the string ends with 'world':

x = re.findall("world$", txt)
if x:
print("Yes, the string ends with 'world'")
else:
print("No match")

Output: Yes, the string ends with 'world'

import re

txt = "The rain in Spain falls mainly in the plain!"

#Check if the string contains "ai" followed by 0 or more "x" characters:

x = re.findall("aix*", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

Output: ['ai', 'ai', 'ai', 'ai’] Yes, there is at least one match!
import re

txt = "The rain in Spain falls mainly in the plain!"

#Check if the string contains "ai" followed by 1 or more "x" characters:

x = re.findall("aix+", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

Output: [] No match
import re

txt = "The rain in Spain falls mainly in the plain!"

#Check if the string contains "a" followed by exactly two "l" characters:

x = re.findall("al{2}", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

Output: ['all’] Yes, there is at least one match!

import re

txt = "The rain in Spain falls mainly in the plain!"

#Check if the string contains either "falls" or "stays":

x = re.findall("falls|stays", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

Output: ['falls’] Yes, there is at least one match!

❑ Special Sequences

✓ A special sequence is a \ followed by one of the characters in the list below, and has a special meaning:

import re

txt = "The rain in Spain"

#Check if the string starts with "The": Output:

x = re.findall("\AThe", txt) ['The']

print(x) Yes, there is a match!
if x:
print("Yes, there is a match!")
else:
print("No match")
import re import re

txt = "The rain in Spain" txt = "The rain in Spain"

#Check if "ain" is present at the beginning of a WORD: #Check if "ain" is present at the end of a WORD:

x = re.findall(r"\bain", txt) x = re.findall(r"ain\b", txt)

print(x) print(x)

if x: if x:
print("Yes, there is at least one match!") print("Yes, there is at least one match!")
else: else:
print("No match") print("No match")
import re import re

txt = "The rain in Spain" txt = "The rain in Spain"

#Check if "ain" is present, but NOT at the beginning of a #Check if "ain" is present, but NOT at the end of a
word: word:

x = re.findall(r"\Bain", txt) x = re.findall(r"ain\B", txt)

print(x) print(x)
if x: if x:
print("Yes, there is at least one match!") print("Yes, there is at least one match!")
else: else:
print("No match") print("No match")

#['ain', 'ain’] Yes, there is at least one match! # [] No match

import re

txt = "The rain in Spain"

#Check if the string contains any digits (numbers from 0-9):

x = re.findall("\d", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#[] No match
import re

txt = "The rain in Spain"

#Return a match at every no-digit character:

x = re.findall("\D", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#['T', 'h', 'e', ' ', 'r', 'a', 'i', 'n', ' ', 'i', 'n', ' ', 'S', 'p', 'a', 'i', 'n’] Yes, there is at least one match!
import re

txt = "The rain in Spain"

#Return a match at every white-space character:

x = re.findall("\s", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#[' ', ' ', ‘ ‘] Yes, there is at least one match!

import re

txt = "The rain in Spain"

#Return a match at every NON white-space character:

x = re.findall("\S", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#['T', 'h', 'e', 'r', 'a', 'i', 'n', 'i', 'n', 'S', 'p', 'a', 'i', 'n’] Yes, there is at least one match!
import re

txt = "The rain in Spain"

#Return a match at every word character (characters from a to Z, digits from 0-9, and the underscore _
character):

x = re.findall("\w", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#['T', 'h', 'e', 'r', 'a', 'i', 'n', 'i', 'n', 'S', 'p', 'a', 'i', 'n’] Yes, there is at least one match!
import re

txt = "The rain in Spain"

#Return a match at every NON word character (characters NOT between a and Z. Like "!", "?" white-space etc.):

x = re.findall("\W", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

# [‘ ', ‘ ', ‘ ‘ ‘] Yes, there is at least one match!

import re

txt = "The rain in Spain"

#Check if the string ends with "Spain":

x = re.findall("Spain\Z", txt)

print(x)

if x:
print("Yes, there is a match!")
else:
print("No match")

#['Spain’] Yes, there is a match!

❑ Sets

✓ A set is a set of characters inside a pair of square brackets [] with a special meaning:

import re

txt = "The rain in Spain"

#Check if the string has any a, r, or n characters:

Output:
x = re.findall("[arn]", txt)
['r', 'a', 'n', 'n', 'a', 'n']
print(x) Yes, there is at least one match!

if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "The rain in Spain"

#Check if the string has any characters between a and n:

x = re.findall("[a-n]", txt) Output:

print(x) ['h', 'e', 'a', 'i', 'n', 'i', 'n', 'a', 'i', 'n']
Yes, there is at least one match!
if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "The rain in Spain"

#Check if the string has other characters than a, r, or n:

x = re.findall("[^arn]", txt) Output:

print(x) ['T', 'h', 'e', ' ', 'i', ' ', 'i', ' ', 'S', 'p', 'i']
Yes, there is at least one match!
if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "The rain in Spain"

#Check if the string has any 0, 1, 2, or 3 digits:

x = re.findall("[0123]", txt) Output:

print(x) []
No match
if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "8 times before 11:45 AM"

#Check if the string has any digits: Output:

x = re.findall("[0-9]", txt) ['8', '1', '1', '4', '5']

Yes, there is at least one match!
print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "8 times before 11:45 AM"

#Check if the string has any two-digit numbers, from 00 to

59:
Output:
x = re.findall("[0-5][0-9]", txt)
['11', '45']
print(x) Yes, there is at least one match!

if x:
print("Yes, there is at least one match!")
else:
print("No match")
import re

txt = "8 times before 11:45 AM"

#Check if the string has any characters from a to z lower case, and A to Z upper case:

x = re.findall("[a-zA-Z]", txt)

print(x)

if x:
print("Yes, there is at least one match!")
else:
print("No match")

#['t', 'i', 'm', 'e', 's', 'b', 'e', 'f', 'o', 'r', 'e', 'A', 'M’] Yes, there is at least one match!
import re

txt = "8 times before 11:45 AM"

#Check if the string has any + characters:

Output:
x = re.findall("[+]", txt)
[]
print(x) No match

if x:
print("Yes, there is at least one match!")
else:
print("No match")