Python - re Module
** re Module - How to Write and Match Regular Expressions (Regex)
==========================================
print('\tTab')
print(r'\tTab')
---------------------------------
Tab
\tTab
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'abc')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(1, 4), match='abc'
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'abc')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
print(text_to_search[1:4])
---------------------------------
re.Match object; span=(1, 4), match='abc'
abc
---------------------------------
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'cba')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'.')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
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='H'
re.Match object; span=(67, 68), match='a'
re.Match object; span=(68, 69), match=' '
re.Match object; span=(69, 70), match='H'
re.Match object; span=(70, 71), match='a'
re.Match object; span=(71, 72), match='H'
re.Match object; span=(72, 73), match='a'
re.Match object; span=(74, 75), match='M'
re.Match object; span=(75, 76), match='e'
re.Match object; span=(76, 77), match='t'
re.Match object; span=(77, 78), match='a'
re.Match object; span=(78, 79), match='C'
re.Match object; span=(79, 80), match='h'
re.Match object; span=(80, 81), match='a'
re.Match object; span=(81, 82), match='r'
re.Match object; span=(82, 83), match='a'
re.Match object; span=(83, 84), match='c'
re.Match object; span=(84, 85), match='t'
re.Match object; span=(85, 86), match='e'
re.Match object; span=(86, 87), match='r'
re.Match object; span=(87, 88), match='s'
re.Match object; span=(88, 89), match=' '
re.Match object; span=(89, 90), match='('
re.Match object; span=(90, 91), match='N'
re.Match object; span=(91, 92), match='e'
re.Match object; span=(92, 93), match='e'
re.Match object; span=(93, 94), match='d'
re.Match object; span=(94, 95), match=' '
re.Match object; span=(95, 96), match='t'
re.Match object; span=(96, 97), match='o'
re.Match object; span=(97, 98), match=' '
re.Match object; span=(98, 99), match='b'
re.Match object; span=(99, 100), match='e'
re.Match object; span=(100, 101), match=' '
re.Match object; span=(101, 102), match='e'
re.Match object; span=(102, 103), match='s'
re.Match object; span=(103, 104), match='c'
re.Match object; span=(104, 105), match='a'
re.Match object; span=(105, 106), match='p'
re.Match object; span=(106, 107), match='e'
re.Match object; span=(107, 108), match='d'
re.Match object; span=(108, 109), match=')'
re.Match object; span=(109, 110), match=':'
re.Match object; span=(111, 112), match='.'
re.Match object; span=(112, 113), match=' '
re.Match object; span=(113, 114), match='^'
re.Match object; span=(114, 115), match=' '
re.Match object; span=(115, 116), match='$'
re.Match object; span=(116, 117), match=' '
re.Match object; span=(117, 118), match='*'
re.Match object; span=(118, 119), match=' '
re.Match object; span=(119, 120), match='+'
re.Match object; span=(120, 121), match=' '
re.Match object; span=(121, 122), match='?'
re.Match object; span=(122, 123), match=' '
re.Match object; span=(123, 124), match='{'
re.Match object; span=(124, 125), match=' '
re.Match object; span=(125, 126), match='}'
re.Match object; span=(126, 127), match=' '
re.Match object; span=(127, 128), match='['
re.Match object; span=(128, 129), 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=(139, 140), match='l'
re.Match object; span=(140, 141), match='i'
re.Match object; span=(141, 142), match='n'
re.Match object; span=(142, 143), match='u'
re.Match object; span=(143, 144), match='x'
re.Match object; span=(144, 145), match='e'
re.Match object; span=(145, 146), match='r'
re.Match object; span=(146, 147), match='h'
re.Match object; span=(147, 148), match='a'
re.Match object; span=(148, 149), match='n'
re.Match object; span=(149, 150), match='.'
re.Match object; span=(150, 151), match='c'
re.Match object; span=(151, 152), match='o'
re.Match object; span=(152, 153), match='m'
re.Match object; span=(154, 155), match='3'
re.Match object; span=(155, 156), match='2'
re.Match object; span=(156, 157), match='1'
re.Match object; span=(157, 158), match='-'
re.Match object; span=(158, 159), match='5'
re.Match object; span=(159, 160), match='5'
re.Match object; span=(160, 161), match='5'
re.Match object; span=(161, 162), match='-'
re.Match object; span=(162, 163), match='4'
re.Match object; span=(163, 164), match='3'
re.Match object; span=(164, 165), match='2'
re.Match object; span=(165, 166), match='1'
re.Match object; span=(167, 168), match='1'
re.Match object; span=(168, 169), match='2'
re.Match object; span=(169, 170), match='3'
re.Match object; span=(170, 171), match='.'
re.Match object; span=(171, 172), match='5'
re.Match object; span=(172, 173), match='5'
re.Match object; span=(173, 174), match='5'
re.Match object; span=(174, 175), match='.'
re.Match object; span=(175, 176), match='1'
re.Match object; span=(176, 177), match='2'
re.Match object; span=(177, 178), match='3'
re.Match object; span=(178, 179), match='4'
re.Match object; span=(180, 181), match='1'
re.Match object; span=(181, 182), match='2'
re.Match object; span=(182, 183), match='3'
re.Match object; span=(183, 184), match='*'
re.Match object; span=(184, 185), match='5'
re.Match object; span=(185, 186), match='5'
re.Match object; span=(186, 187), match='5'
re.Match object; span=(187, 188), match='*'
re.Match object; span=(188, 189), match='1'
re.Match object; span=(189, 190), match='2'
re.Match object; span=(190, 191), match='3'
re.Match object; span=(191, 192), match='4'
re.Match object; span=(193, 194), match='8'
re.Match object; span=(194, 195), match='0'
re.Match object; span=(195, 196), match='0'
re.Match object; span=(196, 197), match='-'
re.Match object; span=(197, 198), match='5'
re.Match object; span=(198, 199), match='5'
re.Match object; span=(199, 200), match='5'
re.Match object; span=(200, 201), match='-'
re.Match object; span=(201, 202), match='1'
re.Match object; span=(202, 203), match='2'
re.Match object; span=(203, 204), match='3'
re.Match object; span=(204, 205), match='4'
re.Match object; span=(206, 207), match='9'
re.Match object; span=(207, 208), match='0'
re.Match object; span=(208, 209), match='0'
re.Match object; span=(209, 210), match='-'
re.Match object; span=(210, 211), match='5'
re.Match object; span=(211, 212), match='5'
re.Match object; span=(212, 213), match='5'
re.Match object; span=(213, 214), match='-'
re.Match object; span=(214, 215), match='1'
re.Match object; span=(215, 216), match='2'
re.Match object; span=(216, 217), match='3'
re.Match object; span=(217, 218), match='4'
re.Match object; span=(219, 220), match='M'
re.Match object; span=(220, 221), match='r'
re.Match object; span=(221, 222), match='.'
re.Match object; span=(222, 223), match=' '
re.Match object; span=(223, 224), match='S'
re.Match object; span=(224, 225), match='c'
re.Match object; span=(225, 226), match='h'
re.Match object; span=(226, 227), match='a'
re.Match object; span=(227, 228), match='f'
re.Match object; span=(228, 229), match='e'
re.Match object; span=(229, 230), match='r'
re.Match object; span=(231, 232), match='M'
re.Match object; span=(232, 233), match='r'
re.Match object; span=(233, 234), match=' '
re.Match object; span=(234, 235), match='S'
re.Match object; span=(235, 236), match='m'
re.Match object; span=(236, 237), match='i'
re.Match object; span=(237, 238), match='t'
re.Match object; span=(238, 239), match='h'
re.Match object; span=(240, 241), match='M'
re.Match object; span=(241, 242), match='s'
re.Match object; span=(242, 243), match=' '
re.Match object; span=(243, 244), match='D'
re.Match object; span=(244, 245), match='a'
re.Match object; span=(245, 246), match='v'
re.Match object; span=(246, 247), match='i'
re.Match object; span=(247, 248), match='s'
re.Match object; span=(249, 250), match='M'
re.Match object; span=(250, 251), match='r'
re.Match object; span=(251, 252), match='s'
re.Match object; span=(252, 253), match='.'
re.Match object; span=(253, 254), match=' '
re.Match object; span=(254, 255), match='R'
re.Match object; span=(255, 256), match='o'
re.Match object; span=(256, 257), match='b'
re.Match object; span=(257, 258), match='i'
re.Match object; span=(258, 259), match='n'
re.Match object; span=(259, 260), match='s'
re.Match object; span=(260, 261), match='o'
re.Match object; span=(261, 262), match='n'
re.Match object; span=(263, 264), match='M'
re.Match object; span=(264, 265), match='r'
re.Match object; span=(265, 266), match='.'
re.Match object; span=(266, 267), match=' '
re.Match object; span=(267, 268), match='T'
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'\.')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(111, 112), match='.'
re.Match object; span=(149, 150), match='.'
re.Match object; span=(170, 171), match='.'
re.Match object; span=(174, 175), match='.'
re.Match object; span=(221, 222), match='.'
re.Match object; span=(252, 253), match='.'
re.Match object; span=(265, 266), match='.'
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'linuxerhan\.com')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(139, 153), match='linuxerhan.com'
---------------------------------
==========================================
==========================================
import re
pattern = re.compile(r'\d\d\d.\d\d\d.\d\d\d\d')
with open('data.txt', 'r', encoding = 'utf-8') as f:
contents = f.read()
matches = pattern.finditer(contents)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(12, 24), match='615-555-7164'
re.Match object; span=(102, 114), match='800-555-5669'
re.Match object; span=(191, 203), match='560-555-5153'
re.Match object; span=(281, 293), match='900-555-9340'
re.Match object; span=(378, 390), match='714-555-7405'
re.Match object; span=(467, 479), match='800-555-6771'
re.Match object; span=(557, 569), match='783-555-4799'
re.Match object; span=(647, 659), match='516-555-4615'
re.Match object; span=(740, 752), match='127-555-1867'
re.Match object; span=(829, 841), match='608-555-4938'
re.Match object; span=(915, 927), match='568-555-6051'
re.Match object; span=(1003, 1015), match='292-555-1875'
re.Match object; span=(1091, 1103), match='900-555-3205'
re.Match object; span=(1180, 1192), match='614-555-1166'
re.Match object; span=(1269, 1281), match='530-555-2676'
re.Match object; span=(1355, 1367), match='470-555-2750'
re.Match object; span=(1439, 1451), match='800-555-6089'
re.Match object; span=(1526, 1538), match='880-555-8319'
re.Match object; span=(1614, 1626), match='777-555-8378'
re.Match object; span=(1697, 1709), match='998-555-7385'
re.Match object; span=(1790, 1802), match='800-555-7100'
re.Match object; span=(1874, 1886), match='903-555-8277'
re.Match object; span=(1962, 1974), match='196-555-5674'
re.Match object; span=(2051, 2063), match='900-555-5118'
re.Match object; span=(2135, 2147), match='905-555-1630'
re.Match object; span=(2216, 2228), match='203-555-3475'
re.Match object; span=(2300, 2312), match='884-555-8444'
re.Match object; span=(2387, 2399), match='904-555-8559'
re.Match object; span=(2475, 2487), match='889-555-7393'
re.Match object; span=(2562, 2574), match='195-555-2405'
re.Match object; span=(2647, 2659), match='321-555-9053'
re.Match object; span=(2734, 2746), match='133-555-1711'
re.Match object; span=(2826, 2838), match='900-555-5428'
re.Match object; span=(2915, 2927), match='760-555-7147'
re.Match object; span=(3012, 3024), match='391-555-6621'
re.Match object; span=(3103, 3115), match='932-555-7724'
re.Match object; span=(3192, 3204), match='609-555-7908'
re.Match object; span=(3284, 3296), match='800-555-8810'
re.Match object; span=(3372, 3384), match='149-555-7657'
re.Match object; span=(3452, 3464), match='130-555-9709'
re.Match object; span=(3535, 3547), match='143-555-9295'
re.Match object; span=(3624, 3636), match='903-555-9878'
re.Match object; span=(3714, 3726), match='574-555-3194'
re.Match object; span=(3802, 3814), match='496-555-7533'
re.Match object; span=(3887, 3899), match='210-555-3757'
re.Match object; span=(3971, 3983), match='900-555-9598'
re.Match object; span=(4056, 4068), match='866-555-9844'
re.Match object; span=(4140, 4152), match='669-555-7159'
re.Match object; span=(4225, 4237), match='152-555-7417'
re.Match object; span=(4317, 4329), match='893-555-9832'
re.Match object; span=(4407, 4419), match='217-555-7123'
re.Match object; span=(4498, 4510), match='786-555-6544'
re.Match object; span=(4588, 4600), match='780-555-2574'
re.Match object; span=(4676, 4688), match='926-555-8735'
re.Match object; span=(4762, 4774), match='895-555-3539'
re.Match object; span=(4859, 4871), match='874-555-3949'
re.Match object; span=(4945, 4957), match='800-555-2420'
re.Match object; span=(5034, 5046), match='936-555-6340'
re.Match object; span=(5123, 5135), match='372-555-9809'
re.Match object; span=(5210, 5222), match='890-555-5618'
re.Match object; span=(5292, 5304), match='670-555-3005'
re.Match object; span=(5382, 5394), match='509-555-5997'
re.Match object; span=(5475, 5487), match='721-555-5632'
re.Match object; span=(5566, 5578), match='900-555-3567'
re.Match object; span=(5656, 5668), match='147-555-6830'
re.Match object; span=(5745, 5757), match='582-555-3426'
re.Match object; span=(5830, 5842), match='400-555-1706'
re.Match object; span=(5921, 5933), match='525-555-1793'
re.Match object; span=(6011, 6023), match='317-555-6700'
re.Match object; span=(6099, 6111), match='974-555-8301'
re.Match object; span=(6189, 6201), match='800-555-3216'
re.Match object; span=(6273, 6285), match='746-555-4094'
re.Match object; span=(6360, 6372), match='922-555-1773'
re.Match object; span=(6445, 6457), match='711-555-4427'
re.Match object; span=(6530, 6542), match='355-555-1872'
re.Match object; span=(6619, 6631), match='852-555-6521'
re.Match object; span=(6711, 6723), match='691-555-5773'
re.Match object; span=(6803, 6815), match='332-555-5441'
re.Match object; span=(6889, 6901), match='900-555-7755'
re.Match object; span=(6971, 6983), match='379-555-3685'
re.Match object; span=(7061, 7073), match='127-555-9682'
re.Match object; span=(7152, 7164), match='789-555-7032'
re.Match object; span=(7243, 7255), match='783-555-5135'
re.Match object; span=(7336, 7348), match='315-555-6507'
re.Match object; span=(7427, 7439), match='481-555-5835'
re.Match object; span=(7515, 7527), match='365-555-8287'
re.Match object; span=(7607, 7619), match='911-555-7535'
re.Match object; span=(7693, 7705), match='681-555-2460'
re.Match object; span=(7779, 7791), match='274-555-9800'
re.Match object; span=(7864, 7876), match='800-555-1372'
re.Match object; span=(7953, 7965), match='300-555-7821'
re.Match object; span=(8043, 8055), match='133-555-3889'
re.Match object; span=(8129, 8141), match='705-555-6863'
re.Match object; span=(8218, 8230), match='215-555-9449'
re.Match object; span=(8309, 8321), match='988-555-6112'
re.Match object; span=(8395, 8407), match='623-555-3006'
re.Match object; span=(8479, 8491), match='192-555-4977'
re.Match object; span=(8564, 8576), match='178-555-4899'
re.Match object; span=(8648, 8660), match='952-555-3089'
re.Match object; span=(8741, 8753), match='900-555-6426'
---------------------------------
321-555-4321
123.555.1234
123*555*1234
800-555-1234
900-555-1234
==========================================
pattern = re.compile(r'\d\d\d[-.]\d\d\d[-.]\d\d\d\d')
---------------------------------
re.Match object; span=(154, 166), match='321-555-4321'
re.Match object; span=(167, 179), match='123.555.1234'
re.Match object; span=(193, 205), match='800-555-1234'
re.Match object; span=(206, 218), match='900-555-1234'
---------------------------------
pattern = re.compile(r'[89]00[-.]\d\d\d[-.]\d\d\d\d')
---------------------------------
re.Match object; span=(194, 206), match='800-555-1234'
re.Match object; span=(207, 219), match='900-555-1234'
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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
cat
mat
pat
bat
'''
sentence = 'Start a sentence and then bring it to an end'
pattern = re.compile(r'[^b]at')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(274, 277), match='cat'
re.Match object; span=(278, 281), match='mat'
re.Match object; span=(282, 285), match='pat'
---------------------------------
==========================================
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'[1-5]')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
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=(154, 155), match='3'
re.Match object; span=(155, 156), match='2'
re.Match object; span=(156, 157), match='1'
re.Match object; span=(159, 160), match='5'
re.Match object; span=(160, 161), match='5'
re.Match object; span=(161, 162), match='5'
re.Match object; span=(163, 164), match='4'
re.Match object; span=(164, 165), match='3'
re.Match object; span=(165, 166), match='2'
re.Match object; span=(166, 167), match='1'
re.Match object; span=(168, 169), match='1'
re.Match object; span=(169, 170), match='2'
re.Match object; span=(170, 171), match='3'
re.Match object; span=(172, 173), match='5'
re.Match object; span=(173, 174), match='5'
re.Match object; span=(174, 175), match='5'
re.Match object; span=(176, 177), match='1'
re.Match object; span=(177, 178), match='2'
re.Match object; span=(178, 179), match='3'
re.Match object; span=(179, 180), match='4'
re.Match object; span=(181, 182), match='1'
re.Match object; span=(182, 183), match='2'
re.Match object; span=(183, 184), match='3'
re.Match object; span=(185, 186), match='5'
re.Match object; span=(186, 187), match='5'
re.Match object; span=(187, 188), match='5'
re.Match object; span=(189, 190), match='1'
re.Match object; span=(190, 191), match='2'
re.Match object; span=(191, 192), match='3'
re.Match object; span=(192, 193), match='4'
re.Match object; span=(198, 199), match='5'
re.Match object; span=(199, 200), match='5'
re.Match object; span=(200, 201), match='5'
re.Match object; span=(202, 203), match='1'
re.Match object; span=(203, 204), match='2'
re.Match object; span=(204, 205), match='3'
re.Match object; span=(205, 206), match='4'
re.Match object; span=(211, 212), match='5'
re.Match object; span=(212, 213), match='5'
re.Match object; span=(213, 214), match='5'
re.Match object; span=(215, 216), match='1'
re.Match object; span=(216, 217), match='2'
re.Match object; span=(217, 218), match='3'
re.Match object; span=(218, 219), match='4'
---------------------------------
pattern = re.compile(r'[a-z]')
---------------------------------
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=(67, 68), match='a'
re.Match object; span=(70, 71), match='a'
re.Match object; span=(72, 73), match='a'
re.Match object; span=(75, 76), match='e'
re.Match object; span=(76, 77), match='t'
re.Match object; span=(77, 78), match='a'
re.Match object; span=(79, 80), match='h'
re.Match object; span=(80, 81), match='a'
re.Match object; span=(81, 82), match='r'
re.Match object; span=(82, 83), match='a'
re.Match object; span=(83, 84), match='c'
re.Match object; span=(84, 85), match='t'
re.Match object; span=(85, 86), match='e'
re.Match object; span=(86, 87), match='r'
re.Match object; span=(87, 88), match='s'
re.Match object; span=(91, 92), match='e'
re.Match object; span=(92, 93), match='e'
re.Match object; span=(93, 94), match='d'
re.Match object; span=(95, 96), match='t'
re.Match object; span=(96, 97), match='o'
re.Match object; span=(98, 99), match='b'
re.Match object; span=(99, 100), match='e'
re.Match object; span=(101, 102), match='e'
re.Match object; span=(102, 103), match='s'
re.Match object; span=(103, 104), match='c'
re.Match object; span=(104, 105), match='a'
re.Match object; span=(105, 106), match='p'
re.Match object; span=(106, 107), match='e'
re.Match object; span=(107, 108), match='d'
re.Match object; span=(139, 140), match='l'
re.Match object; span=(140, 141), match='i'
re.Match object; span=(141, 142), match='n'
re.Match object; span=(142, 143), match='u'
re.Match object; span=(143, 144), match='x'
re.Match object; span=(144, 145), match='e'
re.Match object; span=(145, 146), match='r'
re.Match object; span=(146, 147), match='h'
re.Match object; span=(147, 148), match='a'
re.Match object; span=(148, 149), match='n'
re.Match object; span=(150, 151), match='c'
re.Match object; span=(151, 152), match='o'
re.Match object; span=(152, 153), match='m'
re.Match object; span=(221, 222), match='r'
re.Match object; span=(225, 226), match='c'
re.Match object; span=(226, 227), match='h'
re.Match object; span=(227, 228), match='a'
re.Match object; span=(228, 229), match='f'
re.Match object; span=(229, 230), match='e'
re.Match object; span=(230, 231), match='r'
re.Match object; span=(233, 234), match='r'
re.Match object; span=(236, 237), match='m'
re.Match object; span=(237, 238), match='i'
re.Match object; span=(238, 239), match='t'
re.Match object; span=(239, 240), match='h'
re.Match object; span=(242, 243), match='s'
re.Match object; span=(245, 246), match='a'
re.Match object; span=(246, 247), match='v'
re.Match object; span=(247, 248), match='i'
re.Match object; span=(248, 249), match='s'
re.Match object; span=(251, 252), match='r'
re.Match object; span=(252, 253), match='s'
re.Match object; span=(256, 257), match='o'
re.Match object; span=(257, 258), match='b'
re.Match object; span=(258, 259), match='i'
re.Match object; span=(259, 260), match='n'
re.Match object; span=(260, 261), match='s'
re.Match object; span=(261, 262), match='o'
re.Match object; span=(262, 263), match='n'
re.Match object; span=(265, 266), match='r'
---------------------------------
pattern = re.compile(r'[a-zA-Z]')
---------------------------------
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=(66, 67), match='H'
re.Match object; span=(67, 68), match='a'
re.Match object; span=(69, 70), match='H'
re.Match object; span=(70, 71), match='a'
re.Match object; span=(71, 72), match='H'
re.Match object; span=(72, 73), match='a'
re.Match object; span=(74, 75), match='M'
re.Match object; span=(75, 76), match='e'
re.Match object; span=(76, 77), match='t'
re.Match object; span=(77, 78), match='a'
re.Match object; span=(78, 79), match='C'
re.Match object; span=(79, 80), match='h'
re.Match object; span=(80, 81), match='a'
re.Match object; span=(81, 82), match='r'
re.Match object; span=(82, 83), match='a'
re.Match object; span=(83, 84), match='c'
re.Match object; span=(84, 85), match='t'
re.Match object; span=(85, 86), match='e'
re.Match object; span=(86, 87), match='r'
re.Match object; span=(87, 88), match='s'
re.Match object; span=(90, 91), match='N'
re.Match object; span=(91, 92), match='e'
re.Match object; span=(92, 93), match='e'
re.Match object; span=(93, 94), match='d'
re.Match object; span=(95, 96), match='t'
re.Match object; span=(96, 97), match='o'
re.Match object; span=(98, 99), match='b'
re.Match object; span=(99, 100), match='e'
re.Match object; span=(101, 102), match='e'
re.Match object; span=(102, 103), match='s'
re.Match object; span=(103, 104), match='c'
re.Match object; span=(104, 105), match='a'
re.Match object; span=(105, 106), match='p'
re.Match object; span=(106, 107), match='e'
re.Match object; span=(107, 108), match='d'
re.Match object; span=(139, 140), match='l'
re.Match object; span=(140, 141), match='i'
re.Match object; span=(141, 142), match='n'
re.Match object; span=(142, 143), match='u'
re.Match object; span=(143, 144), match='x'
re.Match object; span=(144, 145), match='e'
re.Match object; span=(145, 146), match='r'
re.Match object; span=(146, 147), match='h'
re.Match object; span=(147, 148), match='a'
re.Match object; span=(148, 149), match='n'
re.Match object; span=(150, 151), match='c'
re.Match object; span=(151, 152), match='o'
re.Match object; span=(152, 153), match='m'
re.Match object; span=(220, 221), match='M'
re.Match object; span=(221, 222), match='r'
re.Match object; span=(224, 225), match='S'
re.Match object; span=(225, 226), match='c'
re.Match object; span=(226, 227), match='h'
re.Match object; span=(227, 228), match='a'
re.Match object; span=(228, 229), match='f'
re.Match object; span=(229, 230), match='e'
re.Match object; span=(230, 231), match='r'
re.Match object; span=(232, 233), match='M'
re.Match object; span=(233, 234), match='r'
re.Match object; span=(235, 236), match='S'
re.Match object; span=(236, 237), match='m'
re.Match object; span=(237, 238), match='i'
re.Match object; span=(238, 239), match='t'
re.Match object; span=(239, 240), match='h'
re.Match object; span=(241, 242), match='M'
re.Match object; span=(242, 243), match='s'
re.Match object; span=(244, 245), match='D'
re.Match object; span=(245, 246), match='a'
re.Match object; span=(246, 247), match='v'
re.Match object; span=(247, 248), match='i'
re.Match object; span=(248, 249), match='s'
re.Match object; span=(250, 251), match='M'
re.Match object; span=(251, 252), match='r'
re.Match object; span=(252, 253), match='s'
re.Match object; span=(255, 256), match='R'
re.Match object; span=(256, 257), match='o'
re.Match object; span=(257, 258), match='b'
re.Match object; span=(258, 259), match='i'
re.Match object; span=(259, 260), match='n'
re.Match object; span=(260, 261), match='s'
re.Match object; span=(261, 262), match='o'
re.Match object; span=(262, 263), match='n'
re.Match object; span=(264, 265), match='M'
re.Match object; span=(265, 266), match='r'
re.Match object; span=(268, 269), match='T'
---------------------------------
pattern = re.compile(r'[^a-zA-Z]')
---------------------------------
re.Match object; span=(0, 1), match='\n'
re.Match object; span=(27, 28), match='\n'
re.Match object; span=(54, 55), match='\n'
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=(65, 66), match='\n'
re.Match object; span=(68, 69), match=' '
re.Match object; span=(73, 74), match='\n'
re.Match object; span=(88, 89), match=' '
re.Match object; span=(89, 90), match='('
re.Match object; span=(94, 95), match=' '
re.Match object; span=(97, 98), match=' '
re.Match object; span=(100, 101), match=' '
re.Match object; span=(108, 109), match=')'
re.Match object; span=(109, 110), match=':'
re.Match object; span=(110, 111), match='\n'
re.Match object; span=(111, 112), match='.'
re.Match object; span=(112, 113), match=' '
re.Match object; span=(113, 114), match='^'
re.Match object; span=(114, 115), match=' '
re.Match object; span=(115, 116), match='$'
re.Match object; span=(116, 117), match=' '
re.Match object; span=(117, 118), match='*'
re.Match object; span=(118, 119), match=' '
re.Match object; span=(119, 120), match='+'
re.Match object; span=(120, 121), match=' '
re.Match object; span=(121, 122), match='?'
re.Match object; span=(122, 123), match=' '
re.Match object; span=(123, 124), match='{'
re.Match object; span=(124, 125), match=' '
re.Match object; span=(125, 126), match='}'
re.Match object; span=(126, 127), match=' '
re.Match object; span=(127, 128), match='['
re.Match object; span=(128, 129), 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='\n'
re.Match object; span=(149, 150), match='.'
re.Match object; span=(153, 154), match='\n'
re.Match object; span=(154, 155), match='3'
re.Match object; span=(155, 156), match='2'
re.Match object; span=(156, 157), match='1'
re.Match object; span=(157, 158), match='-'
re.Match object; span=(158, 159), match='-'
re.Match object; span=(159, 160), match='5'
re.Match object; span=(160, 161), match='5'
re.Match object; span=(161, 162), match='5'
re.Match object; span=(162, 163), match='-'
re.Match object; span=(163, 164), match='4'
re.Match object; span=(164, 165), match='3'
re.Match object; span=(165, 166), match='2'
re.Match object; span=(166, 167), match='1'
re.Match object; span=(167, 168), match='\n'
re.Match object; span=(168, 169), match='1'
re.Match object; span=(169, 170), match='2'
re.Match object; span=(170, 171), match='3'
re.Match object; span=(171, 172), match='.'
re.Match object; span=(172, 173), match='5'
re.Match object; span=(173, 174), match='5'
re.Match object; span=(174, 175), match='5'
re.Match object; span=(175, 176), match='.'
re.Match object; span=(176, 177), match='1'
re.Match object; span=(177, 178), match='2'
re.Match object; span=(178, 179), match='3'
re.Match object; span=(179, 180), match='4'
re.Match object; span=(180, 181), match='\n'
re.Match object; span=(181, 182), match='1'
re.Match object; span=(182, 183), match='2'
re.Match object; span=(183, 184), match='3'
re.Match object; span=(184, 185), match='*'
re.Match object; span=(185, 186), match='5'
re.Match object; span=(186, 187), match='5'
re.Match object; span=(187, 188), match='5'
re.Match object; span=(188, 189), match='*'
re.Match object; span=(189, 190), match='1'
re.Match object; span=(190, 191), match='2'
re.Match object; span=(191, 192), match='3'
re.Match object; span=(192, 193), match='4'
re.Match object; span=(193, 194), match='\n'
re.Match object; span=(194, 195), match='8'
re.Match object; span=(195, 196), match='0'
re.Match object; span=(196, 197), match='0'
re.Match object; span=(197, 198), match='-'
re.Match object; span=(198, 199), match='5'
re.Match object; span=(199, 200), match='5'
re.Match object; span=(200, 201), match='5'
re.Match object; span=(201, 202), match='-'
re.Match object; span=(202, 203), match='1'
re.Match object; span=(203, 204), match='2'
re.Match object; span=(204, 205), match='3'
re.Match object; span=(205, 206), match='4'
re.Match object; span=(206, 207), match='\n'
re.Match object; span=(207, 208), match='9'
re.Match object; span=(208, 209), match='0'
re.Match object; span=(209, 210), match='0'
re.Match object; span=(210, 211), match='-'
re.Match object; span=(211, 212), match='5'
re.Match object; span=(212, 213), match='5'
re.Match object; span=(213, 214), match='5'
re.Match object; span=(214, 215), match='-'
re.Match object; span=(215, 216), match='1'
re.Match object; span=(216, 217), match='2'
re.Match object; span=(217, 218), match='3'
re.Match object; span=(218, 219), match='4'
re.Match object; span=(219, 220), match='\n'
re.Match object; span=(222, 223), match='.'
re.Match object; span=(223, 224), match=' '
re.Match object; span=(231, 232), match='\n'
re.Match object; span=(234, 235), match=' '
re.Match object; span=(240, 241), match='\n'
re.Match object; span=(243, 244), match=' '
re.Match object; span=(249, 250), match='\n'
re.Match object; span=(253, 254), match='.'
re.Match object; span=(254, 255), match=' '
re.Match object; span=(263, 264), match='\n'
re.Match object; span=(266, 267), match='.'
re.Match object; span=(267, 268), match=' '
re.Match object; span=(269, 270), match='\n'
---------------------------------
pattern = re.compile(r'\d\d\d.\d\d\d.\d\d\d\d')
---------------------------------
re.Match object; span=(170, 182), match='123.555.1234'
re.Match object; span=(183, 195), match='123*555*1234'
re.Match object; span=(196, 208), match='800-555-1234'
re.Match object; span=(209, 221), match='900-555-1234'
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'\d{3}.\d{3}.\d{4}')
matches = pattern.finditer(text_to_search)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(156, 168), match='321-555-4321'
re.Match object; span=(169, 181), match='123.555.1234'
re.Match object; span=(182, 194), match='123*555*1234'
re.Match object; span=(195, 207), match='800-555-1234'
re.Match object; span=(208, 220), match='900-555-1234'
---------------------------------
pattern = re.compile(r'Mr\.')
---------------------------------
re.Match object; span=(222, 225), match='Mr.'
re.Match object; span=(266, 269), match='Mr.'
---------------------------------
pattern = re.compile(r'Mr\.?')
---------------------------------
re.Match object; span=(222, 225), match='Mr.'
re.Match object; span=(234, 236), match='Mr'
re.Match object; span=(252, 254), match='Mr'
re.Match object; span=(266, 269), match='Mr.'
---------------------------------
pattern = re.compile(r'Mr\.?\s[A-Z]')
---------------------------------
re.Match object; span=(222, 227), match='Mr. S'
re.Match object; span=(234, 238), match='Mr S'
re.Match object; span=(266, 271), match='Mr. T'
---------------------------------
pattern = re.compile(r'Mr\.?\s[A-Z]\w+')
---------------------------------
re.Match object; span=(222, 233), match='Mr. Schafer'
re.Match object; span=(234, 242), match='Mr Smith'
---------------------------------
pattern = re.compile(r'Mr\.?\s[A-Z]\w*')
---------------------------------
re.Match object; span=(222, 233), match='Mr. Schafer'
re.Match object; span=(234, 242), match='Mr Smith'
re.Match object; span=(266, 271), match='Mr. T'
---------------------------------
pattern = re.compile(r'M(r|s|rs)\.?\s[A-Z]\w*')
---------------------------------
re.Match object; span=(222, 233), match='Mr. Schafer'
re.Match object; span=(234, 242), match='Mr Smith'
re.Match object; span=(243, 251), match='Ms Davis'
re.Match object; span=(252, 265), match='Mrs. Robinson'
re.Match object; span=(266, 271), match='Mr. T'
---------------------------------
pattern = re.compile(r'(Mr|Ms|Mrs)\.?\s[A-Z]\w*')
---------------------------------
re.Match object; span=(222, 233), match='Mr. Schafer'
re.Match object; span=(234, 242), match='Mr Smith'
re.Match object; span=(243, 251), match='Ms Davis'
re.Match object; span=(252, 265), match='Mrs. Robinson'
re.Match object; span=(266, 271), match='Mr. T'
---------------------------------
==========================================
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)
---------------------------------
re.Match object; span=(1, 24), match='CoreyMSchafer@gmail.com'
re.Match object; span=(25, 53), match='corey.schafer@university.edu'
re.Match object; span=(54, 83), match='corey-321-schafer@my-work.net'
---------------------------------
pattern = re.compile(r'[a-zA-Z]+@[a-zA-Z]+\.com')
---------------------------------
re.Match object; span=(1, 24), match='CoreyMSchafer@gmail.com'
---------------------------------
pattern = re.compile(r'[a-zA-Z.]+@[a-zA-Z]+\.(com|edu)')
---------------------------------
re.Match object; span=(1, 24), match='CoreyMSchafer@gmail.com'
re.Match object; span=(25, 53), match='corey.schafer@university.edu'
---------------------------------
pattern = re.compile(r'[a-zA-Z0-9.-]+@[a-zA-Z-]+\.(com|edu|net)')
---------------------------------
re.Match object; span=(1, 24), match='CoreyMSchafer@gmail.com'
re.Match object; span=(25, 53), match='corey.schafer@university.edu'
re.Match object; span=(54, 83), match='corey-321-schafer@my-work.net'
---------------------------------
pattern = re.compile(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+')
---------------------------------
re.Match object; span=(1, 24), match='CoreyMSchafer@gmail.com'
re.Match object; span=(25, 53), match='corey.schafer@university.edu'
re.Match object; span=(54, 83), match='corey-321-schafer@my-work.net'
---------------------------------
==========================================
import re
urls = '''
https://www.google.com
http://blogspot.com
https://youtube.com
https://www.nasa.gov
'''
pattern = re.compile(r'https?://(www\.)?')
matches = pattern.finditer(urls)
for match in matches:
print(match)
---------------------------------
re.Match object; span=(1, 13), match='https://www.'
re.Match object; span=(24, 31), match='http://'
re.Match object; span=(44, 52), match='https://'
re.Match object; span=(64, 76), match='https://www.'
---------------------------------
pattern = re.compile(r'https?://(www\.)?\w+\.\w+')
---------------------------------
re.Match object; span=(1, 23), match='https://www.google.com'
re.Match object; span=(24, 43), match='http://blogspot.com'
re.Match object; span=(44, 63), match='https://youtube.com'
re.Match object; span=(64, 84), match='https://www.nasa.gov'
---------------------------------
pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
---------------------------------
re.Match object; span=(1, 23), match='https://www.google.com'
re.Match object; span=(24, 43), match='http://blogspot.com'
re.Match object; span=(44, 63), match='https://youtube.com'
re.Match object; span=(64, 84), match='https://www.nasa.gov'
---------------------------------
==========================================
import re
urls = '''
https://www.google.com
http://blogspot.com
https://youtube.com
https://www.nasa.gov
'''
pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
matches = pattern.finditer(urls)
for match in matches:
print(match.group(0))
---------------------------------
https://www.google.com
http://blogspot.com
https://youtube.com
https://www.nasa.gov
---------------------------------
for match in matches:
print(match.group(1))
---------------------------------
www.
None
None
www.
---------------------------------
for match in matches:
print(match.group(2))
---------------------------------
blogspot
youtube
nasa
---------------------------------
for match in matches:
print(match.group(3))
---------------------------------
.com
.com
.com
.gov
---------------------------------
==========================================
import re
urls = '''
https://www.google.com
http://blogspot.com
https://youtube.com
https://www.nasa.gov
'''
pattern = re.compile(r'https?://(www\.)?(\w+)(\.\w+)')
subbed_urls = pattern.sub(r'\2\3', urls)
print(subbed_urls)
---------------------------------
google.com
blogspot.com
youtube.com
nasa.gov
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'(Mr|Ms|Mrs)\.?\s[A-Z]\w*')
matches = pattern.findall(text_to_search)
for match in matches:
print(match)
---------------------------------
Mr
Mr
Ms
Mrs
Mr
---------------------------------
pattern = re.compile(r'\d{3}.\d{3}.\d{4}')
---------------------------------
321-555-4321
123.555.1234
123*555*1234
800-555-1234
900-555-1234
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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')
matches = pattern.match(sentence)
print(matches)
---------------------------------
re.Match object; span=(0, 5), match='Start'
---------------------------------
pattern = re.compile(r'sentence')
---------------------------------
None
---------------------------------
==========================================
import re
text_to_search = '''
abcdefghijklmnopqurtuvwxyz
ABCDEFGHIJKLMNOPQRSTUVWXYZ
1234567890
Ha HaHa
MetaCharacters (Need to be escaped):
. ^ $ * + ? { } [ ] \ | ( )
linuxerhan.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'sentence')
matches = pattern.search(sentence)
print(matches)
---------------------------------
re.Match object; span=(8, 16), match='sentence'
---------------------------------
pattern = re.compile(r'dne')
---------------------------------
None
---------------------------------
pattern = re.compile(r'start', re.IGNORECASE)
---------------------------------
re.Match object; span=(0, 5), match='Start'
---------------------------------
pattern = re.compile(r'start', re.I)
---------------------------------
re.Match object; span=(0, 5), match='Start'
---------------------------------