Regex

Question 1

import re

str = “The rain in Spain will rain.”
x = re.findall(“rain”, str)
print(x)

Answer 1

[‘rain’, ‘rain’]

Question 2

import re

str = “The rain in Spain will rain.”
x = re.findall(“rain|Spain”, str)
print(x)

Answer 2

[‘rain’, ‘Spain’, ‘rain’]

Question 3

import re

str = “The rain in Spain will rain.”
x = re.findall(“^rain|Spain”, str)
print(x)

Answer 3

[‘Spain’]

Question 4

import re

print(re.findall(“al{2}”, “fall”))
print(re.findall(“al{3}”, “fall”))
print(re.findall(“tal{2}”, “fall”))

Answer 4

[‘all’]
[]
[]

Question 5

import re

str = “alll aboard the pain train”
x = re.search(“aboard”, str)
print(x.span())

Answer 5

(5, 11)

Question 6

import re

str = “alll aboard the pain train”
x = re.search(“aboard”, str)
print(x.string)

Answer 6

#the .string gives you everything
alll aboard the pain train

Question 7

import re

print(re.findall(“[arn]”, “rainy”))
print(re.findall(“[^arn]”, “rainy”))
print(re.findall(“^[arn]”, “rainy”))

Answer 7

[‘r’, ‘a’, ‘n’]
[‘i’, ‘y’]
[‘r’]

Question 8

import re

str = “rainy”
x = re.findall(“[arn]”, str)
print(x)

Answer 8

[‘r’, ‘a’, ‘n’]

Question 9

import re

str = “8 times before 11:45 AM”
x = re.findall(“[0-5][0-9]”, str)
print(x)

Answer 9

#Returns anything with digits between 00 and 59
['11', '45']

Question 10

import re

str = “The rain in Spain”
x = re.findall(“\W”, str)
print(x)

Answer 10

#\W returns all non word characters, like white space
[' ', ' ', ' ']

Question 11

import re

str = “The rain in Spain”
x = re.findall(“\ASpain”, str)
print(x)

Answer 11

#\A checks if the string starts with something
[]

Question 12

import re

print(re.findall(“a…s$”, “abs”))
print(re.findall(“a…s$”, “alias”))
print(re.findall(“a…s$”, “abyss”))
print(re.findall(“a…s$”, “abacus”))

Answer 12

#Three periods means three characters that aren't newline
[]
['alias']
['abyss']
[]

Question 13

import re

str = “a aabc daaaat”
x = re.findall(“a{2,3}”, str)
print(x)

Answer 13

#At least 2, at most 3
['aa', 'aaa']

Question 14

import re

print(re.findall("ma*n", "mn"))
print(re.findall("ma*n", "man"))
print(re.findall("ma*n", "maaan"))
print(re.findall("ma*n", "main"))
print(re.findall("ma*n", "woman"))

Answer 14

#* means zero or more occurrences of the a
['mn']
['man']
['maaan']
[]
['man']

Question 15

import re

print(re.findall("ma+n", "mn"))
print(re.findall("ma+n", "man"))
print(re.findall("ma+n", "maaan"))
print(re.findall("ma+n", "main"))
print(re.findall("ma+n", "woman"))

Answer 15

#+ means 1 or more occurrences of the a
[]
['man']
['maaan']
[]
['man']

Question 16

import re

print(re.findall("ma?n", "mn"))
print(re.findall("ma?n", "man"))
print(re.findall("ma?n", "maaan"))
print(re.findall("ma?n", "main"))
print(re.findall("ma?n", "woman"))

Answer 16

#? means zero or 1 occurrence of the a
['mn']
['man']
[]
[]
['man']

Question 17

import re

print(re.findall(r”\bfoo”,”football”))
print(re.findall(r”\bfoo”,”a football”))
print(re.findall(r”\bfoo”,”afootball”))

Answer 17

checks for foo at the beginning of words

[‘foo’]
[‘foo’]
[]

Question 18

import re

print(re.findall(r”foo\b”,”the foo”))
print(re.findall(r”foo\b”,”the afoo test”))
print(re.findall(r”foo\b”,”the afootest”))

Answer 18

checks for foo at the end of words

[‘foo’]
[‘foo’]
[]

Question 19

import re

print(re.findall(r”\Bfoo”,”football”))
print(re.findall(r”\Bfoo”,”a football”))
print(re.findall(r”\Bfoo”,”afootball”))

Answer 19

makes sure foo is present, but NOT at the beginning of a word

[]
[]
[‘foo’]

Question 20

import re

print(re.findall(r”foo\B”,”the foo”))
print(re.findall(r”foo\B”,”the afoo test”))
print(re.findall(r”foo\B”,”the afootest”))

Answer 20

makes sure foo is present, but NOT at the end of a word

[]
[]
[‘foo’]

Question 21

import re

print(re.findall(“\d”,”12a!bc3”))
print(re.findall(“\d”,”Pyth@n”))

Answer 21

\d makes a match for all digits

[‘1’, ‘2’, ‘3’]
[]

Question 22

import re

print(re.findall(“\D”,”1a!b34’5”))
print(re.findall(“\D”,”1345”))

Answer 22

\D makes a match for all non-digits

[‘a’, ‘!’, ‘b’, “’”]
[]

Question 23

import re

print(re.findall(“\s”,”Python”))
print(re.findall(“\s”,”Python yo”))

Answer 23

Returns whitespace

[]
[’ ‘]

Question 24

import re

print(re.findall(“\S”,”a b”))
print(re.findall(“\s”,” “))

Answer 24

\S returns everything that isn’t whitespace

#\s returns whitespace
[‘a’, ‘b’]
[’ ‘]

Question 25

import re

print(re.findall(“\w”,”12&’: ;c”))
print(re.findall(“\w”,”’%> !”))

Answer 25

Returns all alphanumeric characters

[‘1’, ‘2’, ‘c’]
[]

Question 26

import re

print(re.findall(“\W”,”1a2%c”))
print(re.findall(“\W”,”’%> !”))

Answer 26

Returns all non-alphanumeric characters

[’%’]
[”’”, ‘%’, ‘>’, ‘ ‘, ‘!’]

Question 27

import re

print(re.findall(“Python\Z”,”I like Python”))
print(re.findall(“Python\Z”,”I like python”))
print(re.findall(“Python\Z”,”Python is fun”))

Answer 27

Returns ‘Python’ if the string ends with it

[‘Python’]
[]
[]