两天研习Python基础（九） 文本处理

>>> greeting = '===== Have a great day ====='
>>> greeting.translate(str.maketrans('=', '-'))
'----- Have a great day -----'

>>> greeting = '===== Have a great day!! ====='
>>> greeting.translate(str.maketrans('=', '-', '!'))
'----- Have a great day -----'

>>> import string
>>> quote = 'SIMPLICITY IS THE ULTIMATE SOPHISTICATION'
>>> tr_table = str.maketrans(string.ascii_uppercase, string.ascii_lowercase)
>>> quote.translate(tr_table)
'simplicity is the ultimate sophistication'

>>> sentence = "Thi1s is34 a senten6ce"
>>> sentence.translate(str.maketrans('', '', string.digits))
'This is a sentence'
>>> greeting.translate(str.maketrans('', '', string.punctuation))
' Have a great day '

>>> greeting = '      Have a nice day :)     '
>>> greeting.strip()
'Have a nice day :)'
>>> greeting.rstrip()
'      Have a nice day :)'
>>> greeting.lstrip()
'Have a nice day :)     '

>>> greeting.strip(') :')
'Have a nice day'

>>> greeting = '===== Have a great day!! ====='
>>> greeting.strip('=')
' Have a great day!! '

>>> ' Hello World '.center(40, '*')
'************* Hello World **************'

>>> sentence = 'thIs iS a saMple StrIng'

>>> sentence.capitalize()
'This is a sample string'

>>> sentence.title()
'This Is A Sample String'

>>> sentence.lower()
'this is a sample string'

>>> sentence.upper()
'THIS IS A SAMPLE STRING'

>>> sentence.swapcase()
'THiS Is A SAmPLE sTRiNG'

>>> 'good'.islower()
True

>>> 'good'.isupper()
False

>>> '1'.isnumeric()
True
>>> 'abc1'.isnumeric()
False
>>> '1.2'.isnumeric()
False

>>> sentence = 'This is a sample string'
>>> 'is' in sentence
True
>>> 'this' in sentence
False
>>> 'This' in sentence
True
>>> 'this' in sentence.lower()
True
>>> 'is a' in sentence
True
>>> 'test' not in sentence
True

>>> sentence = 'This is a sample string'
>>> sentence.count('is')
2
>>> sentence.count('w')
0

>>> word = 'phototonic'
>>> word.count('oto')
1

>>> sentence
'This is a sample string'

>>> sentence.startswith('This')
True
>>> sentence.startswith('The')
False

>>> sentence.endswith('ing')
True
>>> sentence.endswith('ly')
False

>>> sentence = 'This is a sample string'

>>> sentence.split()
['This', 'is', 'a', 'sample', 'string']

>>> "oranges:5".split(':')
['oranges', '5']
>>> "oranges :: 5".split(' :: ')
['oranges', '5']

>>> "a e i o u".split(' ', maxsplit=1)
['a', 'e i o u']
>>> "a e i o u".split(' ', maxsplit=2)
['a', 'e', 'i o u']

>>> line = '{1.0 2.0 3.0}'
>>> nums = [float(s) for s in line.strip('{}').split()]
>>> nums
[1.0, 2.0, 3.0]

>>> str_list
['This', 'is', 'a', 'sample', 'string']
>>> ' '.join(str_list)
'This is a sample string'
>>> '-'.join(str_list)
'This-is-a-sample-string'

>>> c = ' :: '
>>> c.join(str_list)
'This :: is :: a :: sample :: string'

>>> phrase = '2 be or not 2 be'
>>> phrase.replace('2', 'to')
'to be or not to be'

>>> phrase
'2 be or not 2 be'

>>> phrase.replace('2', 'to', 1)
'to be or not 2 be'

>>> phrase = phrase.replace('2', 'to')
>>> phrase
'to be or not to be'

re.search(pattern, string, flags=0)
re.findall(pattern, string, flags=0)
re.split(pattern, string, maxsplit=0, flags=0)

>>> import re
>>> string = "This is a sample string"

>>> bool(re.search('is', string))
True

>>> bool(re.search('this', string))
False

>>> bool(re.search('this', string, re.I))
True

>>> bool(re.search('T', string))
True

>>> bool(re.search('is a', string))
True

>>> re.findall('i', string)
['i', 'i', 'i']

>>> string
'This is a sample string'

>>> re.findall('is', string)
['is', 'is']

>>> re.findall('\bis', string)
[]

>>> re.findall(r'\bis', string)
['is']

>>> re.findall(r'\w+', string)
['This', 'is', 'a', 'sample', 'string']

>>> re.split(r'\s+', string)
['This', 'is', 'a', 'sample', 'string']

>>> re.split(r'\d+', 'Sample123string54with908numbers')
['Sample', 'string', 'with', 'numbers']

>>> re.split(r'(\d+)', 'Sample123string54with908numbers')
['Sample', '123', 'string', '54', 'with', '908', 'numbers']

>>> quote = "So many books, so little time"

>>> re.search(r'([a-z]{2,}).*\1', quote, re.I)
<_sre.SRE_Match object; span=(0, 17), match='So many books, so'>

>>> re.search(r'([a-z])\1', quote, re.I)
<_sre.SRE_Match object; span=(9, 11), match='oo'>

>>> re.findall(r'([a-z])\1', quote, re.I)
['o', 't']

re.sub(pattern, repl, string, count=0, flags=0)

>>> sentence = 'This is a sample string'
>>> re.sub('sample', 'test', sentence)
'This is a test string'

>>> sentence
'This is a sample string'
>>> sentence = re.sub('sample', 'test', sentence)
>>> sentence
'This is a test string'

>>> re.sub('/', '-', '25/06/2016')
'25-06-2016'
>>> re.sub('/', '-', '25/06/2016', count=1)
'25-06/2016'

>>> greeting = '***** Have a great day *****'
>>> re.sub('\*', '=', greeting)
'===== Have a great day ====='

>>> words = 'night and day'
>>> re.sub(r'(\w+)( \w+ )(\w+)', r'\3\2\1', words)
'day and night'

>>> line = 'Can you spot the the mistakes? I i seem to not'
>>> re.sub(r'\b(\w+) \1\b', r'\1', line, flags=re.I)
'Can you spot the mistakes? I seem to not'

>>> import math
>>> numbers = '1 2 3 4 5'

>>> def fact_num(n):
...     return str(math.factorial(int(n.group(1))))
...
>>> re.sub(r'(\d+)', fact_num, numbers)
'1 2 6 24 120'

>>> re.sub(r'(\d+)', lambda m: str(math.factorial(int(m.group(1)))), numbers)
'1 2 6 24 120'

>>> swap_words = re.compile(r'(\w+)( \w+ )(\w+)')
>>> swap_words
re.compile('(\\w+)( \\w+ )(\\w+)')

>>> words = 'night and day'

>>> swap_words.search(words).group()
'night and day'
>>> swap_words.search(words).group(1)
'night'
>>> swap_words.search(words).group(2)
' and '
>>> swap_words.search(words).group(3)
'day'
>>> swap_words.search(words).group(4)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
IndexError: no such group

>>> bool(swap_words.search(words))
True
>>> swap_words.findall(words)
[('night', ' and ', 'day')]

>>> swap_words.sub(r'\3\2\1', words)
'day and night'
>>> swap_words.sub(r'\3\2\1', 'yin and yang')
'yang and yin'