Regular Expressions

Regular expressions is a concept used to search for patterns in string text.

This is a univerisal concept for any programming language or text editing program.

We're going to learn the concepts while we learn the syntax for python.

The goal of regular expressions is to be able to search for a specific type of text inside of a string. If we have a form on our webpage where we ask for email addresses, can we check whether the inputted string actually follows the form of an email? some letters or numbers or special characters, then an @ sign then some more letters numbers or special characters then a . then a few more letters

    .       - Any Character Except New Line
    \d      - Digit (0-9)
    \D      - Not a Digit (0-9)
    \w      - Word Character (a-z, A-Z, 0-9, _)
    \W      - Not a Word Character
    \s      - Whitespace (space, tab, newline)
    \S      - Not Whitespace (space, tab, newline)

    \b      - Word Boundary
    \B      - Not a Word Boundary
    ^       - Beginning of a String
    $       - End of a String

    []      - Matches Characters in brackets
    [^ ]    - Matches Characters NOT in brackets
    |       - Either Or
    ( )     - Group

    Quantifiers:

    *       - 0 or More
    +       - 1 or More
    ?       - 0 or One
    {3}     - Exact Number
    {3,4}   - Range of Numbers (Minimum, Maximum)

import re

text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
123abc

Hello HelloHello

MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )

utexas.edu

321-555-4321
123.555.1234

daniel-mitchell@utexas.edu

Mr. Johnson
Mr Smith
Ms Davis
Mrs. Robinson
Mr. T
'''

Searching literals

pattern = re.compile(r'abc')

matches = pattern.finditer(text_to_search)

for mat in matches:
    print(mat)

<re.Match object; span=(1, 4), match='abc'>
<re.Match object; span=(69, 72), match='abc'>

print(text_to_search[69:72])

abc

pattern = re.compile(r'cba')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

Searching special characters

pattern = re.compile(r'.')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(1, 2), match='a'>
<re.Match object; span=(2, 3), match='b'>
<re.Match object; span=(3, 4), match='c'>
<re.Match object; span=(4, 5), match='d'>
<re.Match object; span=(5, 6), match='e'>
<re.Match object; span=(6, 7), match='f'>
<re.Match object; span=(7, 8), match='g'>
<re.Match object; span=(8, 9), match='h'>
<re.Match object; span=(9, 10), match='i'>
<re.Match object; span=(10, 11), match='j'>
<re.Match object; span=(11, 12), match='k'>
<re.Match object; span=(12, 13), match='l'>
<re.Match object; span=(13, 14), match='m'>
<re.Match object; span=(14, 15), match='n'>
<re.Match object; span=(15, 16), match='o'>
<re.Match object; span=(16, 17), match='p'>
<re.Match object; span=(17, 18), match='q'>
<re.Match object; span=(18, 19), match='u'>
<re.Match object; span=(19, 20), match='r'>
<re.Match object; span=(20, 21), match='t'>
<re.Match object; span=(21, 22), match='u'>
<re.Match object; span=(22, 23), match='v'>
<re.Match object; span=(23, 24), match='w'>
<re.Match object; span=(24, 25), match='x'>
<re.Match object; span=(25, 26), match='y'>
<re.Match object; span=(26, 27), match='z'>
<re.Match object; span=(28, 29), match='A'>
<re.Match object; span=(29, 30), match='B'>
<re.Match object; span=(30, 31), match='C'>
<re.Match object; span=(31, 32), match='D'>
<re.Match object; span=(32, 33), match='E'>
<re.Match object; span=(33, 34), match='F'>
<re.Match object; span=(34, 35), match='G'>
<re.Match object; span=(35, 36), match='H'>
<re.Match object; span=(36, 37), match='I'>
<re.Match object; span=(37, 38), match='J'>
<re.Match object; span=(38, 39), match='K'>
<re.Match object; span=(39, 40), match='L'>
<re.Match object; span=(40, 41), match='M'>
<re.Match object; span=(41, 42), match='N'>
<re.Match object; span=(42, 43), match='O'>
<re.Match object; span=(43, 44), match='P'>
<re.Match object; span=(44, 45), match='Q'>
<re.Match object; span=(45, 46), match='R'>
<re.Match object; span=(46, 47), match='S'>
<re.Match object; span=(47, 48), match='T'>
<re.Match object; span=(48, 49), match='U'>
<re.Match object; span=(49, 50), match='V'>
<re.Match object; span=(50, 51), match='W'>
<re.Match object; span=(51, 52), match='X'>
<re.Match object; span=(52, 53), match='Y'>
<re.Match object; span=(53, 54), match='Z'>
<re.Match object; span=(55, 56), match='1'>
<re.Match object; span=(56, 57), match='2'>
<re.Match object; span=(57, 58), match='3'>
<re.Match object; span=(58, 59), match='4'>
<re.Match object; span=(59, 60), match='5'>
<re.Match object; span=(60, 61), match='6'>
<re.Match object; span=(61, 62), match='7'>
<re.Match object; span=(62, 63), match='8'>
<re.Match object; span=(63, 64), match='9'>
<re.Match object; span=(64, 65), match='0'>
<re.Match object; span=(66, 67), match='1'>
<re.Match object; span=(67, 68), match='2'>
<re.Match object; span=(68, 69), match='3'>
<re.Match object; span=(69, 70), match='a'>
<re.Match object; span=(70, 71), match='b'>
<re.Match object; span=(71, 72), match='c'>
<re.Match object; span=(74, 75), match='H'>
<re.Match object; span=(75, 76), match='e'>
<re.Match object; span=(76, 77), match='l'>
<re.Match object; span=(77, 78), match='l'>
<re.Match object; span=(78, 79), match='o'>
<re.Match object; span=(79, 80), match=' '>
<re.Match object; span=(80, 81), match='H'>
<re.Match object; span=(81, 82), match='e'>
<re.Match object; span=(82, 83), match='l'>
<re.Match object; span=(83, 84), match='l'>
<re.Match object; span=(84, 85), match='o'>
<re.Match object; span=(85, 86), match='H'>
<re.Match object; span=(86, 87), match='e'>
<re.Match object; span=(87, 88), match='l'>
<re.Match object; span=(88, 89), match='l'>
<re.Match object; span=(89, 90), match='o'>
<re.Match object; span=(92, 93), match='M'>
<re.Match object; span=(93, 94), match='e'>
<re.Match object; span=(94, 95), match='t'>
<re.Match object; span=(95, 96), match='a'>
<re.Match object; span=(96, 97), match='C'>
<re.Match object; span=(97, 98), match='h'>
<re.Match object; span=(98, 99), match='a'>
<re.Match object; span=(99, 100), match='r'>
<re.Match object; span=(100, 101), match='a'>
<re.Match object; span=(101, 102), match='c'>
<re.Match object; span=(102, 103), match='t'>
<re.Match object; span=(103, 104), match='e'>
<re.Match object; span=(104, 105), match='r'>
<re.Match object; span=(105, 106), match='s'>
<re.Match object; span=(106, 107), match=' '>
<re.Match object; span=(107, 108), match='('>
<re.Match object; span=(108, 109), match='N'>
<re.Match object; span=(109, 110), match='e'>
<re.Match object; span=(110, 111), match='e'>
<re.Match object; span=(111, 112), match='d'>
<re.Match object; span=(112, 113), match=' '>
<re.Match object; span=(113, 114), match='t'>
<re.Match object; span=(114, 115), match='o'>
<re.Match object; span=(115, 116), match=' '>
<re.Match object; span=(116, 117), match='b'>
<re.Match object; span=(117, 118), match='e'>
<re.Match object; span=(118, 119), match=' '>
<re.Match object; span=(119, 120), match='e'>
<re.Match object; span=(120, 121), match='s'>
<re.Match object; span=(121, 122), match='c'>
<re.Match object; span=(122, 123), match='a'>
<re.Match object; span=(123, 124), match='p'>
<re.Match object; span=(124, 125), match='e'>
<re.Match object; span=(125, 126), match='d'>
<re.Match object; span=(126, 127), match=')'>
<re.Match object; span=(127, 128), match=':'>
<re.Match object; span=(129, 130), match='.'>
<re.Match object; span=(130, 131), match=' '>
<re.Match object; span=(131, 132), match='^'>
<re.Match object; span=(132, 133), match=' '>
<re.Match object; span=(133, 134), match='$'>
<re.Match object; span=(134, 135), match=' '>
<re.Match object; span=(135, 136), match='*'>
<re.Match object; span=(136, 137), match=' '>
<re.Match object; span=(137, 138), match='+'>
<re.Match object; span=(138, 139), match=' '>
<re.Match object; span=(139, 140), match='?'>
<re.Match object; span=(140, 141), match=' '>
<re.Match object; span=(141, 142), match='{'>
<re.Match object; span=(142, 143), match=' '>
<re.Match object; span=(143, 144), match='}'>
<re.Match object; span=(144, 145), match=' '>
<re.Match object; span=(145, 146), match='['>
<re.Match object; span=(146, 147), match=' '>
<re.Match object; span=(147, 148), match=']'>
<re.Match object; span=(148, 149), match=' '>
<re.Match object; span=(149, 150), match='\\'>
<re.Match object; span=(150, 151), match=' '>
<re.Match object; span=(151, 152), match='|'>
<re.Match object; span=(152, 153), match=' '>
<re.Match object; span=(153, 154), match='('>
<re.Match object; span=(154, 155), match=' '>
<re.Match object; span=(155, 156), match=')'>
<re.Match object; span=(158, 159), match='u'>
<re.Match object; span=(159, 160), match='t'>
<re.Match object; span=(160, 161), match='e'>
<re.Match object; span=(161, 162), match='x'>
<re.Match object; span=(162, 163), match='a'>
<re.Match object; span=(163, 164), match='s'>
<re.Match object; span=(164, 165), match='.'>
<re.Match object; span=(165, 166), match='e'>
<re.Match object; span=(166, 167), match='d'>
<re.Match object; span=(167, 168), match='u'>
<re.Match object; span=(170, 171), match='3'>
<re.Match object; span=(171, 172), match='2'>
<re.Match object; span=(172, 173), match='1'>
<re.Match object; span=(173, 174), match='-'>
<re.Match object; span=(174, 175), match='5'>
<re.Match object; span=(175, 176), match='5'>
<re.Match object; span=(176, 177), match='5'>
<re.Match object; span=(177, 178), match='-'>
<re.Match object; span=(178, 179), match='4'>
<re.Match object; span=(179, 180), match='3'>
<re.Match object; span=(180, 181), match='2'>
<re.Match object; span=(181, 182), match='1'>
<re.Match object; span=(183, 184), match='1'>
<re.Match object; span=(184, 185), match='2'>
<re.Match object; span=(185, 186), match='3'>
<re.Match object; span=(186, 187), match='.'>
<re.Match object; span=(187, 188), match='5'>
<re.Match object; span=(188, 189), match='5'>
<re.Match object; span=(189, 190), match='5'>
<re.Match object; span=(190, 191), match='.'>
<re.Match object; span=(191, 192), match='1'>
<re.Match object; span=(192, 193), match='2'>
<re.Match object; span=(193, 194), match='3'>
<re.Match object; span=(194, 195), match='4'>
<re.Match object; span=(197, 198), match='d'>
<re.Match object; span=(198, 199), match='a'>
<re.Match object; span=(199, 200), match='n'>
<re.Match object; span=(200, 201), match='i'>
<re.Match object; span=(201, 202), match='e'>
<re.Match object; span=(202, 203), match='l'>
<re.Match object; span=(203, 204), match='-'>
<re.Match object; span=(204, 205), match='m'>
<re.Match object; span=(205, 206), match='i'>
<re.Match object; span=(206, 207), match='t'>
<re.Match object; span=(207, 208), match='c'>
<re.Match object; span=(208, 209), match='h'>
<re.Match object; span=(209, 210), match='e'>
<re.Match object; span=(210, 211), match='l'>
<re.Match object; span=(211, 212), match='l'>
<re.Match object; span=(212, 213), match='@'>
<re.Match object; span=(213, 214), match='u'>
<re.Match object; span=(214, 215), match='t'>
<re.Match object; span=(215, 216), match='e'>
<re.Match object; span=(216, 217), match='x'>
<re.Match object; span=(217, 218), match='a'>
<re.Match object; span=(218, 219), match='s'>
<re.Match object; span=(219, 220), match='.'>
<re.Match object; span=(220, 221), match='e'>
<re.Match object; span=(221, 222), match='d'>
<re.Match object; span=(222, 223), match='u'>
<re.Match object; span=(225, 226), match='M'>
<re.Match object; span=(226, 227), match='r'>
<re.Match object; span=(227, 228), match='.'>
<re.Match object; span=(228, 229), match=' '>
<re.Match object; span=(229, 230), match='J'>
<re.Match object; span=(230, 231), match='o'>
<re.Match object; span=(231, 232), match='h'>
<re.Match object; span=(232, 233), match='n'>
<re.Match object; span=(233, 234), match='s'>
<re.Match object; span=(234, 235), match='o'>
<re.Match object; span=(235, 236), match='n'>
<re.Match object; span=(237, 238), match='M'>
<re.Match object; span=(238, 239), match='r'>
<re.Match object; span=(239, 240), match=' '>
<re.Match object; span=(240, 241), match='S'>
<re.Match object; span=(241, 242), match='m'>
<re.Match object; span=(242, 243), match='i'>
<re.Match object; span=(243, 244), match='t'>
<re.Match object; span=(244, 245), match='h'>
<re.Match object; span=(246, 247), match='M'>
<re.Match object; span=(247, 248), match='s'>
<re.Match object; span=(248, 249), match=' '>
<re.Match object; span=(249, 250), match='D'>
<re.Match object; span=(250, 251), match='a'>
<re.Match object; span=(251, 252), match='v'>
<re.Match object; span=(252, 253), match='i'>
<re.Match object; span=(253, 254), match='s'>
<re.Match object; span=(255, 256), match='M'>
<re.Match object; span=(256, 257), match='r'>
<re.Match object; span=(257, 258), match='s'>
<re.Match object; span=(258, 259), match='.'>
<re.Match object; span=(259, 260), match=' '>
<re.Match object; span=(260, 261), match='R'>
<re.Match object; span=(261, 262), match='o'>
<re.Match object; span=(262, 263), match='b'>
<re.Match object; span=(263, 264), match='i'>
<re.Match object; span=(264, 265), match='n'>
<re.Match object; span=(265, 266), match='s'>
<re.Match object; span=(266, 267), match='o'>
<re.Match object; span=(267, 268), match='n'>
<re.Match object; span=(269, 270), match='M'>
<re.Match object; span=(270, 271), match='r'>
<re.Match object; span=(271, 272), match='.'>
<re.Match object; span=(272, 273), match=' '>
<re.Match object; span=(273, 274), match='T'>

pattern = re.compile(r'\.')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(129, 130), match='.'>
<re.Match object; span=(164, 165), match='.'>
<re.Match object; span=(186, 187), match='.'>
<re.Match object; span=(190, 191), match='.'>
<re.Match object; span=(219, 220), match='.'>
<re.Match object; span=(227, 228), match='.'>
<re.Match object; span=(258, 259), match='.'>
<re.Match object; span=(271, 272), match='.'>

pattern = re.compile(r'\d')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(55, 56), match='1'>
<re.Match object; span=(56, 57), match='2'>
<re.Match object; span=(57, 58), match='3'>
<re.Match object; span=(58, 59), match='4'>
<re.Match object; span=(59, 60), match='5'>
<re.Match object; span=(60, 61), match='6'>
<re.Match object; span=(61, 62), match='7'>
<re.Match object; span=(62, 63), match='8'>
<re.Match object; span=(63, 64), match='9'>
<re.Match object; span=(64, 65), match='0'>
<re.Match object; span=(66, 67), match='1'>
<re.Match object; span=(67, 68), match='2'>
<re.Match object; span=(68, 69), match='3'>
<re.Match object; span=(170, 171), match='3'>
<re.Match object; span=(171, 172), match='2'>
<re.Match object; span=(172, 173), match='1'>
<re.Match object; span=(174, 175), match='5'>
<re.Match object; span=(175, 176), match='5'>
<re.Match object; span=(176, 177), match='5'>
<re.Match object; span=(178, 179), match='4'>
<re.Match object; span=(179, 180), match='3'>
<re.Match object; span=(180, 181), match='2'>
<re.Match object; span=(181, 182), match='1'>
<re.Match object; span=(183, 184), match='1'>
<re.Match object; span=(184, 185), match='2'>
<re.Match object; span=(185, 186), match='3'>
<re.Match object; span=(187, 188), match='5'>
<re.Match object; span=(188, 189), match='5'>
<re.Match object; span=(189, 190), match='5'>
<re.Match object; span=(191, 192), match='1'>
<re.Match object; span=(192, 193), match='2'>
<re.Match object; span=(193, 194), match='3'>
<re.Match object; span=(194, 195), match='4'>

pattern = re.compile(r'\D')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(0, 1), match='\n'>
<re.Match object; span=(1, 2), match='a'>
<re.Match object; span=(2, 3), match='b'>
<re.Match object; span=(3, 4), match='c'>
<re.Match object; span=(4, 5), match='d'>
<re.Match object; span=(5, 6), match='e'>
<re.Match object; span=(6, 7), match='f'>
<re.Match object; span=(7, 8), match='g'>
<re.Match object; span=(8, 9), match='h'>
<re.Match object; span=(9, 10), match='i'>
<re.Match object; span=(10, 11), match='j'>
<re.Match object; span=(11, 12), match='k'>
<re.Match object; span=(12, 13), match='l'>
<re.Match object; span=(13, 14), match='m'>
<re.Match object; span=(14, 15), match='n'>
<re.Match object; span=(15, 16), match='o'>
<re.Match object; span=(16, 17), match='p'>
<re.Match object; span=(17, 18), match='q'>
<re.Match object; span=(18, 19), match='u'>
<re.Match object; span=(19, 20), match='r'>
<re.Match object; span=(20, 21), match='t'>
<re.Match object; span=(21, 22), match='u'>
<re.Match object; span=(22, 23), match='v'>
<re.Match object; span=(23, 24), match='w'>
<re.Match object; span=(24, 25), match='x'>
<re.Match object; span=(25, 26), match='y'>
<re.Match object; span=(26, 27), match='z'>
<re.Match object; span=(27, 28), match='\n'>
<re.Match object; span=(28, 29), match='A'>
<re.Match object; span=(29, 30), match='B'>
<re.Match object; span=(30, 31), match='C'>
<re.Match object; span=(31, 32), match='D'>
<re.Match object; span=(32, 33), match='E'>
<re.Match object; span=(33, 34), match='F'>
<re.Match object; span=(34, 35), match='G'>
<re.Match object; span=(35, 36), match='H'>
<re.Match object; span=(36, 37), match='I'>
<re.Match object; span=(37, 38), match='J'>
<re.Match object; span=(38, 39), match='K'>
<re.Match object; span=(39, 40), match='L'>
<re.Match object; span=(40, 41), match='M'>
<re.Match object; span=(41, 42), match='N'>
<re.Match object; span=(42, 43), match='O'>
<re.Match object; span=(43, 44), match='P'>
<re.Match object; span=(44, 45), match='Q'>
<re.Match object; span=(45, 46), match='R'>
<re.Match object; span=(46, 47), match='S'>
<re.Match object; span=(47, 48), match='T'>
<re.Match object; span=(48, 49), match='U'>
<re.Match object; span=(49, 50), match='V'>
<re.Match object; span=(50, 51), match='W'>
<re.Match object; span=(51, 52), match='X'>
<re.Match object; span=(52, 53), match='Y'>
<re.Match object; span=(53, 54), match='Z'>
<re.Match object; span=(54, 55), match='\n'>
<re.Match object; span=(65, 66), match='\n'>
<re.Match object; span=(69, 70), match='a'>
<re.Match object; span=(70, 71), match='b'>
<re.Match object; span=(71, 72), match='c'>
<re.Match object; span=(72, 73), match='\n'>
<re.Match object; span=(73, 74), match='\n'>
<re.Match object; span=(74, 75), match='H'>
<re.Match object; span=(75, 76), match='e'>
<re.Match object; span=(76, 77), match='l'>
<re.Match object; span=(77, 78), match='l'>
<re.Match object; span=(78, 79), match='o'>
<re.Match object; span=(79, 80), match=' '>
<re.Match object; span=(80, 81), match='H'>
<re.Match object; span=(81, 82), match='e'>
<re.Match object; span=(82, 83), match='l'>
<re.Match object; span=(83, 84), match='l'>
<re.Match object; span=(84, 85), match='o'>
<re.Match object; span=(85, 86), match='H'>
<re.Match object; span=(86, 87), match='e'>
<re.Match object; span=(87, 88), match='l'>
<re.Match object; span=(88, 89), match='l'>
<re.Match object; span=(89, 90), match='o'>
<re.Match object; span=(90, 91), match='\n'>
<re.Match object; span=(91, 92), match='\n'>
<re.Match object; span=(92, 93), match='M'>
<re.Match object; span=(93, 94), match='e'>
<re.Match object; span=(94, 95), match='t'>
<re.Match object; span=(95, 96), match='a'>
<re.Match object; span=(96, 97), match='C'>
<re.Match object; span=(97, 98), match='h'>
<re.Match object; span=(98, 99), match='a'>
<re.Match object; span=(99, 100), match='r'>
<re.Match object; span=(100, 101), match='a'>
<re.Match object; span=(101, 102), match='c'>
<re.Match object; span=(102, 103), match='t'>
<re.Match object; span=(103, 104), match='e'>
<re.Match object; span=(104, 105), match='r'>
<re.Match object; span=(105, 106), match='s'>
<re.Match object; span=(106, 107), match=' '>
<re.Match object; span=(107, 108), match='('>
<re.Match object; span=(108, 109), match='N'>
<re.Match object; span=(109, 110), match='e'>
<re.Match object; span=(110, 111), match='e'>
<re.Match object; span=(111, 112), match='d'>
<re.Match object; span=(112, 113), match=' '>
<re.Match object; span=(113, 114), match='t'>
<re.Match object; span=(114, 115), match='o'>
<re.Match object; span=(115, 116), match=' '>
<re.Match object; span=(116, 117), match='b'>
<re.Match object; span=(117, 118), match='e'>
<re.Match object; span=(118, 119), match=' '>
<re.Match object; span=(119, 120), match='e'>
<re.Match object; span=(120, 121), match='s'>
<re.Match object; span=(121, 122), match='c'>
<re.Match object; span=(122, 123), match='a'>
<re.Match object; span=(123, 124), match='p'>
<re.Match object; span=(124, 125), match='e'>
<re.Match object; span=(125, 126), match='d'>
<re.Match object; span=(126, 127), match=')'>
<re.Match object; span=(127, 128), match=':'>
<re.Match object; span=(128, 129), match='\n'>
<re.Match object; span=(129, 130), match='.'>
<re.Match object; span=(130, 131), match=' '>
<re.Match object; span=(131, 132), match='^'>
<re.Match object; span=(132, 133), match=' '>
<re.Match object; span=(133, 134), match='$'>
<re.Match object; span=(134, 135), match=' '>
<re.Match object; span=(135, 136), match='*'>
<re.Match object; span=(136, 137), match=' '>
<re.Match object; span=(137, 138), match='+'>
<re.Match object; span=(138, 139), match=' '>
<re.Match object; span=(139, 140), match='?'>
<re.Match object; span=(140, 141), match=' '>
<re.Match object; span=(141, 142), match='{'>
<re.Match object; span=(142, 143), match=' '>
<re.Match object; span=(143, 144), match='}'>
<re.Match object; span=(144, 145), match=' '>
<re.Match object; span=(145, 146), match='['>
<re.Match object; span=(146, 147), match=' '>
<re.Match object; span=(147, 148), match=']'>
<re.Match object; span=(148, 149), match=' '>
<re.Match object; span=(149, 150), match='\\'>
<re.Match object; span=(150, 151), match=' '>
<re.Match object; span=(151, 152), match='|'>
<re.Match object; span=(152, 153), match=' '>
<re.Match object; span=(153, 154), match='('>
<re.Match object; span=(154, 155), match=' '>
<re.Match object; span=(155, 156), match=')'>
<re.Match object; span=(156, 157), match='\n'>
<re.Match object; span=(157, 158), match='\n'>
<re.Match object; span=(158, 159), match='u'>
<re.Match object; span=(159, 160), match='t'>
<re.Match object; span=(160, 161), match='e'>
<re.Match object; span=(161, 162), match='x'>
<re.Match object; span=(162, 163), match='a'>
<re.Match object; span=(163, 164), match='s'>
<re.Match object; span=(164, 165), match='.'>
<re.Match object; span=(165, 166), match='e'>
<re.Match object; span=(166, 167), match='d'>
<re.Match object; span=(167, 168), match='u'>
<re.Match object; span=(168, 169), match='\n'>
<re.Match object; span=(169, 170), match='\n'>
<re.Match object; span=(173, 174), match='-'>
<re.Match object; span=(177, 178), match='-'>
<re.Match object; span=(182, 183), match='\n'>
<re.Match object; span=(186, 187), match='.'>
<re.Match object; span=(190, 191), match='.'>
<re.Match object; span=(195, 196), match='\n'>
<re.Match object; span=(196, 197), match='\n'>
<re.Match object; span=(197, 198), match='d'>
<re.Match object; span=(198, 199), match='a'>
<re.Match object; span=(199, 200), match='n'>
<re.Match object; span=(200, 201), match='i'>
<re.Match object; span=(201, 202), match='e'>
<re.Match object; span=(202, 203), match='l'>
<re.Match object; span=(203, 204), match='-'>
<re.Match object; span=(204, 205), match='m'>
<re.Match object; span=(205, 206), match='i'>
<re.Match object; span=(206, 207), match='t'>
<re.Match object; span=(207, 208), match='c'>
<re.Match object; span=(208, 209), match='h'>
<re.Match object; span=(209, 210), match='e'>
<re.Match object; span=(210, 211), match='l'>
<re.Match object; span=(211, 212), match='l'>
<re.Match object; span=(212, 213), match='@'>
<re.Match object; span=(213, 214), match='u'>
<re.Match object; span=(214, 215), match='t'>
<re.Match object; span=(215, 216), match='e'>
<re.Match object; span=(216, 217), match='x'>
<re.Match object; span=(217, 218), match='a'>
<re.Match object; span=(218, 219), match='s'>
<re.Match object; span=(219, 220), match='.'>
<re.Match object; span=(220, 221), match='e'>
<re.Match object; span=(221, 222), match='d'>
<re.Match object; span=(222, 223), match='u'>
<re.Match object; span=(223, 224), match='\n'>
<re.Match object; span=(224, 225), match='\n'>
<re.Match object; span=(225, 226), match='M'>
<re.Match object; span=(226, 227), match='r'>
<re.Match object; span=(227, 228), match='.'>
<re.Match object; span=(228, 229), match=' '>
<re.Match object; span=(229, 230), match='J'>
<re.Match object; span=(230, 231), match='o'>
<re.Match object; span=(231, 232), match='h'>
<re.Match object; span=(232, 233), match='n'>
<re.Match object; span=(233, 234), match='s'>
<re.Match object; span=(234, 235), match='o'>
<re.Match object; span=(235, 236), match='n'>
<re.Match object; span=(236, 237), match='\n'>
<re.Match object; span=(237, 238), match='M'>
<re.Match object; span=(238, 239), match='r'>
<re.Match object; span=(239, 240), match=' '>
<re.Match object; span=(240, 241), match='S'>
<re.Match object; span=(241, 242), match='m'>
<re.Match object; span=(242, 243), match='i'>
<re.Match object; span=(243, 244), match='t'>
<re.Match object; span=(244, 245), match='h'>
<re.Match object; span=(245, 246), match='\n'>
<re.Match object; span=(246, 247), match='M'>
<re.Match object; span=(247, 248), match='s'>
<re.Match object; span=(248, 249), match=' '>
<re.Match object; span=(249, 250), match='D'>
<re.Match object; span=(250, 251), match='a'>
<re.Match object; span=(251, 252), match='v'>
<re.Match object; span=(252, 253), match='i'>
<re.Match object; span=(253, 254), match='s'>
<re.Match object; span=(254, 255), match='\n'>
<re.Match object; span=(255, 256), match='M'>
<re.Match object; span=(256, 257), match='r'>
<re.Match object; span=(257, 258), match='s'>
<re.Match object; span=(258, 259), match='.'>
<re.Match object; span=(259, 260), match=' '>
<re.Match object; span=(260, 261), match='R'>
<re.Match object; span=(261, 262), match='o'>
<re.Match object; span=(262, 263), match='b'>
<re.Match object; span=(263, 264), match='i'>
<re.Match object; span=(264, 265), match='n'>
<re.Match object; span=(265, 266), match='s'>
<re.Match object; span=(266, 267), match='o'>
<re.Match object; span=(267, 268), match='n'>
<re.Match object; span=(268, 269), match='\n'>
<re.Match object; span=(269, 270), match='M'>
<re.Match object; span=(270, 271), match='r'>
<re.Match object; span=(271, 272), match='.'>
<re.Match object; span=(272, 273), match=' '>
<re.Match object; span=(273, 274), match='T'>
<re.Match object; span=(274, 275), match='\n'>

pattern = re.compile(r'\d\w')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(55, 57), match='12'>
<re.Match object; span=(57, 59), match='34'>
<re.Match object; span=(59, 61), match='56'>
<re.Match object; span=(61, 63), match='78'>
<re.Match object; span=(63, 65), match='90'>
<re.Match object; span=(66, 68), match='12'>
<re.Match object; span=(68, 70), match='3a'>
<re.Match object; span=(170, 172), match='32'>
<re.Match object; span=(174, 176), match='55'>
<re.Match object; span=(178, 180), match='43'>
<re.Match object; span=(180, 182), match='21'>
<re.Match object; span=(183, 185), match='12'>
<re.Match object; span=(187, 189), match='55'>
<re.Match object; span=(191, 193), match='12'>
<re.Match object; span=(193, 195), match='34'>

pattern = re.compile(r'\d\s')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(64, 66), match='0\n'>
<re.Match object; span=(181, 183), match='1\n'>
<re.Match object; span=(194, 196), match='4\n'>

Word boundary

# Hello HelloHello
pattern = re.compile(r'Hello')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(74, 79), match='Hello'>
<re.Match object; span=(80, 85), match='Hello'>
<re.Match object; span=(85, 90), match='Hello'>

pattern = re.compile(r'Hello\b')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(74, 79), match='Hello'>
<re.Match object; span=(85, 90), match='Hello'>

pattern = re.compile(r'\bHello\b')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(74, 79), match='Hello'>

pattern = re.compile(r'\BHello\b')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(85, 90), match='Hello'>

pattern = re.compile(r'\b\d')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(55, 56), match='1'>
<re.Match object; span=(66, 67), match='1'>
<re.Match object; span=(170, 171), match='3'>
<re.Match object; span=(174, 175), match='5'>
<re.Match object; span=(178, 179), match='4'>
<re.Match object; span=(183, 184), match='1'>
<re.Match object; span=(187, 188), match='5'>
<re.Match object; span=(191, 192), match='1'>

pattern = re.compile(r'^\s')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(0, 1), match='\n'>

Character sets

pattern = re.compile(r'[123]\w')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(55, 57), match='12'>
<re.Match object; span=(57, 59), match='34'>
<re.Match object; span=(66, 68), match='12'>
<re.Match object; span=(68, 70), match='3a'>
<re.Match object; span=(170, 172), match='32'>
<re.Match object; span=(179, 181), match='32'>
<re.Match object; span=(183, 185), match='12'>
<re.Match object; span=(191, 193), match='12'>
<re.Match object; span=(193, 195), match='34'>

pattern = re.compile(r'[a-z][a-z]')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(1, 3), match='ab'>
<re.Match object; span=(3, 5), match='cd'>
<re.Match object; span=(5, 7), match='ef'>
<re.Match object; span=(7, 9), match='gh'>
<re.Match object; span=(9, 11), match='ij'>
<re.Match object; span=(11, 13), match='kl'>
<re.Match object; span=(13, 15), match='mn'>
<re.Match object; span=(15, 17), match='op'>
<re.Match object; span=(17, 19), match='qu'>
<re.Match object; span=(19, 21), match='rt'>
<re.Match object; span=(21, 23), match='uv'>
<re.Match object; span=(23, 25), match='wx'>
<re.Match object; span=(25, 27), match='yz'>
<re.Match object; span=(69, 71), match='ab'>
<re.Match object; span=(75, 77), match='el'>
<re.Match object; span=(77, 79), match='lo'>
<re.Match object; span=(81, 83), match='el'>
<re.Match object; span=(83, 85), match='lo'>
<re.Match object; span=(86, 88), match='el'>
<re.Match object; span=(88, 90), match='lo'>
<re.Match object; span=(93, 95), match='et'>
<re.Match object; span=(97, 99), match='ha'>
<re.Match object; span=(99, 101), match='ra'>
<re.Match object; span=(101, 103), match='ct'>
<re.Match object; span=(103, 105), match='er'>
<re.Match object; span=(109, 111), match='ee'>
<re.Match object; span=(113, 115), match='to'>
<re.Match object; span=(116, 118), match='be'>
<re.Match object; span=(119, 121), match='es'>
<re.Match object; span=(121, 123), match='ca'>
<re.Match object; span=(123, 125), match='pe'>
<re.Match object; span=(158, 160), match='ut'>
<re.Match object; span=(160, 162), match='ex'>
<re.Match object; span=(162, 164), match='as'>
<re.Match object; span=(165, 167), match='ed'>
<re.Match object; span=(197, 199), match='da'>
<re.Match object; span=(199, 201), match='ni'>
<re.Match object; span=(201, 203), match='el'>
<re.Match object; span=(204, 206), match='mi'>
<re.Match object; span=(206, 208), match='tc'>
<re.Match object; span=(208, 210), match='he'>
<re.Match object; span=(210, 212), match='ll'>
<re.Match object; span=(213, 215), match='ut'>
<re.Match object; span=(215, 217), match='ex'>
<re.Match object; span=(217, 219), match='as'>
<re.Match object; span=(220, 222), match='ed'>
<re.Match object; span=(230, 232), match='oh'>
<re.Match object; span=(232, 234), match='ns'>
<re.Match object; span=(234, 236), match='on'>
<re.Match object; span=(241, 243), match='mi'>
<re.Match object; span=(243, 245), match='th'>
<re.Match object; span=(250, 252), match='av'>
<re.Match object; span=(252, 254), match='is'>
<re.Match object; span=(256, 258), match='rs'>
<re.Match object; span=(261, 263), match='ob'>
<re.Match object; span=(263, 265), match='in'>
<re.Match object; span=(265, 267), match='so'>

pattern = re.compile(r'[a-zA-Z0-9][a-zA-z-]')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(1, 3), match='ab'>
<re.Match object; span=(3, 5), match='cd'>
<re.Match object; span=(5, 7), match='ef'>
<re.Match object; span=(7, 9), match='gh'>
<re.Match object; span=(9, 11), match='ij'>
<re.Match object; span=(11, 13), match='kl'>
<re.Match object; span=(13, 15), match='mn'>
<re.Match object; span=(15, 17), match='op'>
<re.Match object; span=(17, 19), match='qu'>
<re.Match object; span=(19, 21), match='rt'>
<re.Match object; span=(21, 23), match='uv'>
<re.Match object; span=(23, 25), match='wx'>
<re.Match object; span=(25, 27), match='yz'>
<re.Match object; span=(28, 30), match='AB'>
<re.Match object; span=(30, 32), match='CD'>
<re.Match object; span=(32, 34), match='EF'>
<re.Match object; span=(34, 36), match='GH'>
<re.Match object; span=(36, 38), match='IJ'>
<re.Match object; span=(38, 40), match='KL'>
<re.Match object; span=(40, 42), match='MN'>
<re.Match object; span=(42, 44), match='OP'>
<re.Match object; span=(44, 46), match='QR'>
<re.Match object; span=(46, 48), match='ST'>
<re.Match object; span=(48, 50), match='UV'>
<re.Match object; span=(50, 52), match='WX'>
<re.Match object; span=(52, 54), match='YZ'>
<re.Match object; span=(68, 70), match='3a'>
<re.Match object; span=(70, 72), match='bc'>
<re.Match object; span=(74, 76), match='He'>
<re.Match object; span=(76, 78), match='ll'>
<re.Match object; span=(80, 82), match='He'>
<re.Match object; span=(82, 84), match='ll'>
<re.Match object; span=(84, 86), match='oH'>
<re.Match object; span=(86, 88), match='el'>
<re.Match object; span=(88, 90), match='lo'>
<re.Match object; span=(92, 94), match='Me'>
<re.Match object; span=(94, 96), match='ta'>
<re.Match object; span=(96, 98), match='Ch'>
<re.Match object; span=(98, 100), match='ar'>
<re.Match object; span=(100, 102), match='ac'>
<re.Match object; span=(102, 104), match='te'>
<re.Match object; span=(104, 106), match='rs'>
<re.Match object; span=(108, 110), match='Ne'>
<re.Match object; span=(110, 112), match='ed'>
<re.Match object; span=(113, 115), match='to'>
<re.Match object; span=(116, 118), match='be'>
<re.Match object; span=(119, 121), match='es'>
<re.Match object; span=(121, 123), match='ca'>
<re.Match object; span=(123, 125), match='pe'>
<re.Match object; span=(158, 160), match='ut'>
<re.Match object; span=(160, 162), match='ex'>
<re.Match object; span=(162, 164), match='as'>
<re.Match object; span=(165, 167), match='ed'>
<re.Match object; span=(172, 174), match='1-'>
<re.Match object; span=(176, 178), match='5-'>
<re.Match object; span=(197, 199), match='da'>
<re.Match object; span=(199, 201), match='ni'>
<re.Match object; span=(201, 203), match='el'>
<re.Match object; span=(204, 206), match='mi'>
<re.Match object; span=(206, 208), match='tc'>
<re.Match object; span=(208, 210), match='he'>
<re.Match object; span=(210, 212), match='ll'>
<re.Match object; span=(213, 215), match='ut'>
<re.Match object; span=(215, 217), match='ex'>
<re.Match object; span=(217, 219), match='as'>
<re.Match object; span=(220, 222), match='ed'>
<re.Match object; span=(225, 227), match='Mr'>
<re.Match object; span=(229, 231), match='Jo'>
<re.Match object; span=(231, 233), match='hn'>
<re.Match object; span=(233, 235), match='so'>
<re.Match object; span=(237, 239), match='Mr'>
<re.Match object; span=(240, 242), match='Sm'>
<re.Match object; span=(242, 244), match='it'>
<re.Match object; span=(246, 248), match='Ms'>
<re.Match object; span=(249, 251), match='Da'>
<re.Match object; span=(251, 253), match='vi'>
<re.Match object; span=(255, 257), match='Mr'>
<re.Match object; span=(260, 262), match='Ro'>
<re.Match object; span=(262, 264), match='bi'>
<re.Match object; span=(264, 266), match='ns'>
<re.Match object; span=(266, 268), match='on'>
<re.Match object; span=(269, 271), match='Mr'>

pattern = re.compile(r'[a-zA-Z][^a-zA-z]')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(26, 28), match='z\n'>
<re.Match object; span=(53, 55), match='Z\n'>
<re.Match object; span=(71, 73), match='c\n'>
<re.Match object; span=(78, 80), match='o '>
<re.Match object; span=(89, 91), match='o\n'>
<re.Match object; span=(105, 107), match='s '>
<re.Match object; span=(111, 113), match='d '>
<re.Match object; span=(114, 116), match='o '>
<re.Match object; span=(117, 119), match='e '>
<re.Match object; span=(125, 127), match='d)'>
<re.Match object; span=(163, 165), match='s.'>
<re.Match object; span=(167, 169), match='u\n'>
<re.Match object; span=(202, 204), match='l-'>
<re.Match object; span=(211, 213), match='l@'>
<re.Match object; span=(218, 220), match='s.'>
<re.Match object; span=(222, 224), match='u\n'>
<re.Match object; span=(226, 228), match='r.'>
<re.Match object; span=(235, 237), match='n\n'>
<re.Match object; span=(238, 240), match='r '>
<re.Match object; span=(244, 246), match='h\n'>
<re.Match object; span=(247, 249), match='s '>
<re.Match object; span=(253, 255), match='s\n'>
<re.Match object; span=(257, 259), match='s.'>
<re.Match object; span=(267, 269), match='n\n'>
<re.Match object; span=(270, 272), match='r.'>
<re.Match object; span=(273, 275), match='T\n'>

Character groups

pattern = re.compile(r'(abc|edu|texas)\b')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(69, 72), match='abc'>
<re.Match object; span=(159, 164), match='texas'>
<re.Match object; span=(165, 168), match='edu'>
<re.Match object; span=(214, 219), match='texas'>
<re.Match object; span=(220, 223), match='edu'>

pattern = re.compile(r'([A-Z]|llo)[a-zA-z]')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(28, 30), match='AB'>
<re.Match object; span=(30, 32), match='CD'>
<re.Match object; span=(32, 34), match='EF'>
<re.Match object; span=(34, 36), match='GH'>
<re.Match object; span=(36, 38), match='IJ'>
<re.Match object; span=(38, 40), match='KL'>
<re.Match object; span=(40, 42), match='MN'>
<re.Match object; span=(42, 44), match='OP'>
<re.Match object; span=(44, 46), match='QR'>
<re.Match object; span=(46, 48), match='ST'>
<re.Match object; span=(48, 50), match='UV'>
<re.Match object; span=(50, 52), match='WX'>
<re.Match object; span=(52, 54), match='YZ'>
<re.Match object; span=(74, 76), match='He'>
<re.Match object; span=(80, 82), match='He'>
<re.Match object; span=(82, 86), match='lloH'>
<re.Match object; span=(92, 94), match='Me'>
<re.Match object; span=(96, 98), match='Ch'>
<re.Match object; span=(108, 110), match='Ne'>
<re.Match object; span=(225, 227), match='Mr'>
<re.Match object; span=(229, 231), match='Jo'>
<re.Match object; span=(237, 239), match='Mr'>
<re.Match object; span=(240, 242), match='Sm'>
<re.Match object; span=(246, 248), match='Ms'>
<re.Match object; span=(249, 251), match='Da'>
<re.Match object; span=(255, 257), match='Mr'>
<re.Match object; span=(260, 262), match='Ro'>
<re.Match object; span=(269, 271), match='Mr'>

Quantifiers

pattern = re.compile(r'Mr\.?\s[A-Z]')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(225, 230), match='Mr. J'>
<re.Match object; span=(237, 241), match='Mr S'>
<re.Match object; span=(269, 274), match='Mr. T'>

pattern = re.compile(r'Mr\.?\s[A-Z][a-z]*')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(225, 236), match='Mr. Johnson'>
<re.Match object; span=(237, 245), match='Mr Smith'>
<re.Match object; span=(269, 274), match='Mr. T'>

pattern = re.compile(r'M(s|rs)\.?\s[A-Z][a-z]*')  #find either Ms or Mrs
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(246, 254), match='Ms Davis'>
<re.Match object; span=(255, 268), match='Mrs. Robinson'>

pattern = re.compile(r'\d{3}[.-]\d{3}[.-]\d{4}') # find a phone number
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(170, 182), match='321-555-4321'>
<re.Match object; span=(183, 195), match='123.555.1234'>

pattern = re.compile(r'[a-zA-Z0-9_]+\.[a-z]{3}') # find website
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(158, 168), match='utexas.edu'>
<re.Match object; span=(213, 223), match='utexas.edu'>

pattern = re.compile(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+') # Match email address
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat)

<re.Match object; span=(197, 223), match='daniel-mitchell@utexas.edu'>

Accessing information in the Match object

pattern = re.compile(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]{2,4}')
matches = pattern.finditer(text_to_search)
for mat in matches:
    print(mat.span(0))
    print(mat.group(0))
    print(text_to_search[mat.span(0)[0]:mat.span(0)[1]])
    
    

(197, 223)
daniel-mitchell@utexas.edu
daniel-mitchell@utexas.edu

urls = r'''
https://www.google.com
http://yahoo.com
https://www.whitehouse.gov
https://craigslist.org
'''

pattern = re.compile(r'https?://(www\.)?\w+\.\w+')
matches = pattern.finditer(urls)
for mat in matches:
    print(mat)

<re.Match object; span=(1, 23), match='https://www.google.com'>
<re.Match object; span=(24, 40), match='http://yahoo.com'>
<re.Match object; span=(41, 67), match='https://www.whitehouse.gov'>
<re.Match object; span=(68, 90), match='https://craigslist.org'>

pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
matches = pattern.finditer(urls)
for mat in matches:
    print(mat.group(2)+mat.group(3))

google.com
yahoo.com
whitehouse.gov
craigslist.org

pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
matches = pattern.finditer(urls)
for mat in matches:
    print(mat.group(0))
    print(urls[mat.span(2)[0]:mat.span(2)[1]]+urls[mat.span(3)[0]:mat.span(3)[1]])

https://www.google.com
google.com
http://yahoo.com
yahoo.com
https://www.whitehouse.gov
whitehouse.gov
https://craigslist.org
craigslist.org