Python之re模块的使用

re模块的作用

    正则表达式是用一种形式化语法描述的文本匹配模式。模式会被解释为一组指令,然后执行这些指今并提供一个字符串作为输入,
将生成一个匹配子集或者生成原字符串的一个修改版本。

1、查找文本中的模式,re.search()

import re

pattern = 'this'
text = 'Does this text match the pattern?'

match = re.search(pattern, text)

s = match.start()
e = match.end()

print('Found "{}"\nin "{}"\nfrom {} to {} ("{}")'.format(
    match.re.pattern, match.string, s, e, text[s:e]))
re_simple_match.py

运行效果

Found "this"
in "Does this text match the pattern?"
from 5 to 9 ("this")

2、编译表达式匹配模式,re.search()

import re

# Precompile the patterns
regexes = [
    re.compile(p)
    for p in ['this', 'that']
]
text = 'Does this text match the pattern?'

print('Text: {!r}\n'.format(text))

for regex in regexes:
    print('Seeking "{}" ->'.format(regex.pattern),
          end=' ')

    if regex.search(text):
        print('match!')
    else:
        print('no match')
re_simple_compiled.py

运行效果

Text: 'Does this text match the pattern?'

Seeking "this" -> match!
Seeking "that" -> no match

3、多重匹配模式,re.findall()

import re

text = 'abbaaabbbbaaaaa'

pattern = 'ab'
for match in re.findall(pattern, text):
    print('Found {!r}'.format(match))
re_findall.py

 运行效果

['ab', 'ab']
Found 'ab'
Found 'ab'

 4、多重匹配模式,返回迭代器,re.finditer()

import re

text = 'abbaaabbbbaaaaa'

pattern = 'ab'
for match in re.finditer(pattern, text):
    s = match.start()
    e = match.end()
    print('Found {!r} at {:d}:{:d}'.format(
        text[s:e], s, e))
re_finditer.py

运行效果

Found 'ab' at 0:2
Found 'ab' at 5:7

 5、定制一个匹配的函数,将匹配不到的用点号替换

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


if __name__ == '__main__':
    test_patterns('abbaaabbbbaaaaa',
                  [('ab', "'a' followed by 'b'"),
                   ])
re_test_patterns.py

运行效果

'ab' ('a' followed by 'b')

  'abbaaabbbbaaaaa'
  'ab'
  .....'ab'

6、重复匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'abbaabbba',
    [('ab*', 'a followed by zero or more b'),
     ('ab+', 'a followed by one or more b'),
     ('ab?', 'a followed by zero or one b'),
     ('ab{3}', 'a followed by three b'),
     ('ab{2,3}', 'a followed by two to three b')],
)
re_repetition.py

运行效果 

'ab*' (a followed by zero or more b)

  'abbaabbba'
  'abb'
  ...'a'
  ....'abbb'
  ........'a'

'ab+' (a followed by one or more b)

  'abbaabbba'
  'abb'
  ....'abbb'

'ab?' (a followed by zero or one b)

  'abbaabbba'
  'ab'
  ...'a'
  ....'ab'
  ........'a'

'ab{3}' (a followed by three b)

  'abbaabbba'
  ....'abbb'

'ab{2,3}' (a followed by two to three b)

  'abbaabbba'
  'abb'
  ....'abbb'

#总结
* : 0次或多次
+ : 1次或多次
?  :  0次或1次
{n} : 最大N次
{n:m}:最大M次和最小N次 

7、关闭贪婪匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'abbaabbba',
    [('ab*?', 'a followed by zero or more b'),
     ('ab+?', 'a followed by one or more b'),
     ('ab??', 'a followed by zero or one b'),
     ('ab{3}?', 'a followed by three b'),
     ('ab{2,3}?', 'a followed by two to three b')],
)
re_repetition_non_greedy.py

运行效果

'ab*?' (a followed by zero or more b)

  'abbaabbba'
  'a'
  ...'a'
  ....'a'
  ........'a'

'ab+?' (a followed by one or more b)

  'abbaabbba'
  'ab'
  ....'ab'

'ab??' (a followed by zero or one b)

  'abbaabbba'
  'a'
  ...'a'
  ....'a'
  ........'a'

'ab{3}?' (a followed by three b)

  'abbaabbba'
  ....'abbb'

'ab{2,3}?' (a followed by two to three b)

  'abbaabbba'
  'abb'
  ....'abb'

8、字符集合的匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'abbaabbba',
    [('[ab]', 'either a or b'),
     ('a[ab]+', 'a followed by 1 or more a or b'),
     ('a[ab]+?', 'a followed by 1 or more a or b, not greedy')],
)
re_charset.py

 运行效果

'[ab]' (either a or b)

  'abbaabbba'
  'a'
  .'b'
  ..'b'
  ...'a'
  ....'a'
  .....'b'
  ......'b'
  .......'b'
  ........'a'

'a[ab]+' (a followed by 1 or more a or b)

  'abbaabbba'
  'abbaabbba'

'a[ab]+?' (a followed by 1 or more a or b, not greedy)

  'abbaabbba'
  'ab'
  ...'aa'

9、排除字符集的匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'This is some text -- with punctuation.',
    [('[^-. ]+', 'sequences without -, ., or space')],
)
re_charset_exclude.py

运行效果

'[^-. ]+' (sequences without -, ., or space)

  'This is some text -- with punctuation.'
  'This'
  .....'is'
  ........'some'
  .............'text'
  .....................'with'
  ..........................'punctuation'

10、字符区间定义一个字符集范围匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'This is some text -- with punctuation.',
    [('[a-z]+', 'sequences of lowercase letters'),
     ('[A-Z]+', 'sequences of uppercase letters'),
     ('[a-zA-Z]+', 'sequences of letters of either case'),
     ('[A-Z][a-z]+', 'one uppercase followed by lowercase')],
)
re_charset_ranges.py

 运行效果

'[a-z]+' (sequences of lowercase letters)

  'This is some text -- with punctuation.'
  .'his'
  .....'is'
  ........'some'
  .............'text'
  .....................'with'
  ..........................'punctuation'

'[A-Z]+' (sequences of uppercase letters)

  'This is some text -- with punctuation.'
  'T'

'[a-zA-Z]+' (sequences of letters of either case)

  'This is some text -- with punctuation.'
  'This'
  .....'is'
  ........'some'
  .............'text'
  .....................'with'
  ..........................'punctuation'

'[A-Z][a-z]+' (one uppercase followed by lowercase)

  'This is some text -- with punctuation.'
  'This'

11、指定占位符匹配

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'abbaabbba',
    [('a.', 'a followed by any one character'),
     ('b.', 'b followed by any one character'),
     ('a.*b', 'a followed by anything, ending in b'),
     ('a.*?b', 'a followed by anything, ending in b')],
)
re_charset_dot.py

 运行效果

'a.' (a followed by any one character)

  'abbaabbba'
  'ab'
  ...'aa'

'b.' (b followed by any one character)

  'abbaabbba'
  .'bb'
  .....'bb'
  .......'ba'

'a.*b' (a followed by anything, ending in b)

  'abbaabbba'
  'abbaabbb'

'a.*?b' (a followed by anything, ending in b)

  'abbaabbba'
  'ab'
  ...'aab'

 12、转义码

CodeMeaning
\d 数字
\D 非数字
\s 空白字符(制表符、空格、换行等)
\S 非空白字符
\w 字母数字
\W 非字母数字
import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'A prime #1 example!',
    [(r'\d+', 'sequence of digits'),
     (r'\D+', 'sequence of non-digits'),
     (r'\s+', 'sequence of whitespace'),
     (r'\S+', 'sequence of non-whitespace'),
     (r'\w+', 'alphanumeric characters'),
     (r'\W+', 'non-alphanumeric')],
)
re_escape_codes.py

运行效果

'\d+' (sequence of digits)

  'A prime #1 example!'
  .........'1'

'\D+' (sequence of non-digits)

  'A prime #1 example!'
  'A prime #'
  ..........' example!'

'\s+' (sequence of whitespace)

  'A prime #1 example!'
  .' '
  .......' '
  ..........' '

'\S+' (sequence of non-whitespace)

  'A prime #1 example!'
  'A'
  ..'prime'
  ........'#1'
  ...........'example!'

'\w+' (alphanumeric characters)

  'A prime #1 example!'
  'A'
  ..'prime'
  .........'1'
  ...........'example'

'\W+' (non-alphanumeric)

  'A prime #1 example!'
  .' '
  .......' #'
  ..........' '
  ..................'!'

13、转义匹配特殊符号

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    r'\d+ \D+ \s+',
    [(r'\\.\+', 'escape code')],
)
re_escape_escapes.py

运行效果

'\\.\+' (escape code)

  '\d+ \D+ \s+'
  '\d+'
  .....'\D+'
  ..........'\s+'

14、定位匹配字符串

代码含义
^ 行开头
$ 行末尾
\A 字符串开头
\Z 字符串末尾
\b 单词开头或结尾处的空字符串
\B 空字符串,不在单词的开头或结尾

 

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'This is some text -- with punctuation.',
    [(r'^\w+', 'word at start of string'),
     (r'\A\w+', 'word at start of string'),
     (r'\w+\S*$', 'word near end of string'),
     (r'\w+\S*\Z', 'word near end of string'),
     (r'\w*t\w*', 'word containing t'),
     (r'\bt\w+', 't at start of word'),
     (r'\w+t\b', 't at end of word'),
     (r'\Bt\B', 't, not start or end of word')],
)
re_anchoring.py

 运行效果

'^\w+' (word at start of string)

  'This is some text -- with punctuation.'
  'This'

'\A\w+' (word at start of string)

  'This is some text -- with punctuation.'
  'This'

'\w+\S*$' (word near end of string)

  'This is some text -- with punctuation.'
  ..........................'punctuation.'

'\w+\S*\Z' (word near end of string)

  'This is some text -- with punctuation.'
  ..........................'punctuation.'

'\w*t\w*' (word containing t)

  'This is some text -- with punctuation.'
  .............'text'
  .....................'with'
  ..........................'punctuation'

'\bt\w+' (t at start of word)

  'This is some text -- with punctuation.'
  .............'text'

'\w+t\b' (t at end of word)

  'This is some text -- with punctuation.'
  .............'text'

'\Bt\B' (t, not start or end of word)

  'This is some text -- with punctuation.'
  .......................'t'
  ..............................'t'
  .................................'t'

15、限定搜索

re.match() : 从开头去匹配

re.search() : 从开头到结尾匹配

import re

text = 'This is some text -- with punctuation.'
pattern = 'is'

print('Text   :', text)
print('Pattern:', pattern)

m = re.match(pattern, text)
print('Match  :', m)
s = re.search(pattern, text)
print('Search :', s)
re_match.py

运行效果

Text   : This is some text -- with punctuation.
Pattern: is
Match  : None
Search : <re.Match object; span=(2, 4), match='is'>

16、re.fullmatch() : 要求整个输入字符串与模式匹配

import re

text = 'This is some text -- with punctuation.'
pattern = 'is'

print('Text       :', text)
print('Pattern    :', pattern)

m = re.search(pattern, text)
print('Search     :', m)
s = re.fullmatch(pattern, text)
print('Full match :', s)
re_fullmatch.py

 运行效果

Text       : This is some text -- with punctuation.
Pattern    : is
Search     : <re.Match object; span=(2, 4), match='is'>
Full match : None

17、编译正则表达式,指定位置搜索匹配模式

import re

text = 'This is some text -- with punctuation.'
pattern = re.compile(r'\b\w*is\w*\b')
# \b : 匹配一个单词边界
# \w : 匹配字母数字及下划线

print('Text:', text)
print()

pos = 0
while True:
    match = pattern.search(text, pos)
    if not match:
        break
    s = match.start()
    e = match.end()
    print('  {:>2d} : {:>2d} = "{}"'.format(
        s, e - 1, text[s:e]))
    # 在文本中前进,以便下一次搜索
    pos = e
re_search_substring.py

运行效果

Text: This is some text -- with punctuation.

   0 :  3 = "This"
   5 :  6 = "is"

18、用小括号模式来定义组

import re


def test_patterns(text, patterns):
    """给源文本和模式列表,查找文本中每个模式的匹配,并将它们打印到stdout"""
    # 查找文本中的每个模式并打印结果
    for pattern, desc in patterns:
        print("'{}' ({})\n".format(pattern, desc))
        print("  '{}'".format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            substr = text[s:e]
            n_backslashes = text[:s].count('\\')
            prefix = '.' * (s + n_backslashes)
            print("  {}'{}'".format(prefix, substr))
        print()
    return


test_patterns(
    'abbaaabbbbaaaaa',
    [('a(ab)', 'a followed by literal ab'),
     ('a(a*b*)', 'a followed by 0-n a and 0-n b'),
     ('a(ab)*', 'a followed by 0-n ab'),
     ('a(ab)+', 'a followed by 1-n ab')],
)
re_groups.py

运行效果

'a(ab)' (a followed by literal ab)

  'abbaaabbbbaaaaa'
  ....'aab'

'a(a*b*)' (a followed by 0-n a and 0-n b)

  'abbaaabbbbaaaaa'
  'abb'
  ...'aaabbbb'
  ..........'aaaaa'

'a(ab)*' (a followed by 0-n ab)

  'abbaaabbbbaaaaa'
  'a'
  ...'a'
  ....'aab'
  ..........'a'
  ...........'a'
  ............'a'
  .............'a'
  ..............'a'

'a(ab)+' (a followed by 1-n ab)

  'abbaaabbbbaaaaa'
  ....'aab'

19、使用groups(),获取分组的元素

import re

text = 'This is some text -- with punctuation.'

print(text)
print()

patterns = [
    (r'^(\w+)', 'word at start of string'),
    (r'(\w+)\S*$', 'word at end, with optional punctuation'),
    (r'(\bt\w+)\W+(\w+)', 'word starting with t, another word'),
    (r'(\w+t)\b', 'word ending with t'),
]

for pattern, desc in patterns:
    regex = re.compile(pattern)
    match = regex.search(text)
    print("'{}' ({})\n".format(pattern, desc))
    print('  ', match.groups())
    print()
re_groups_match.py

运行效果

This is some text -- with punctuation.

'^(\w+)' (word at start of string)

   ('This',)

'(\w+)\S*$' (word at end, with optional punctuation)

   ('punctuation',)

'(\bt\w+)\W+(\w+)' (word starting with t, another word)

   ('text', 'with')

'(\w+t)\b' (word ending with t)

   ('text',)

20、使用单个组匹配,通过组id获取对应的值,0:表示获取匹配所有的元素,1:表示正式表达式第一个括号,以此类推

import re

text = 'This is some text -- with punctuation.'

print('Input text            :', text)

# word starting with 't' then another word
regex = re.compile(r'(\bt\w+)\W+(\w+)')
print('Pattern               :', regex.pattern)

match = regex.search(text)
print('Entire match          :', match.group(0))
print('Word starting with "t":', match.group(1))
print('Word after "t" word   :', match.group(2))
re_groups_individual.py

运行效果

Input text            : This is some text -- with punctuation.
Pattern               : (\bt\w+)\W+(\w+)
Entire match          : text -- with
Word starting with "t": text
Word after "t" word   : with

21、命令组名,通过组名获取取,这个是python扩展的功能,可以返回字典类型或元组类型

import re

text = 'This is some text -- with punctuation.'

print(text)
print()

patterns = [
    r'^(?P<first_word>\w+)',
    r'(?P<last_word>\w+)\S*$',
    r'(?P<t_word>\bt\w+)\W+(?P<other_word>\w+)',
    r'(?P<ends_with_t>\w+t)\b',
]

for pattern in patterns:
    regex = re.compile(pattern)
    match = regex.search(text)
    print("'{}'".format(pattern))
    print('  ', match.groups())
    print('  ', match.groupdict())
    print()
re_groups_named.py

运行效果

This is some text -- with punctuation.

'^(?P<first_word>\w+)'
   ('This',)
   {'first_word': 'This'}

'(?P<last_word>\w+)\S*$'
   ('punctuation',)
   {'last_word': 'punctuation'}

'(?P<t_word>\bt\w+)\W+(?P<other_word>\w+)'
   ('text', 'with')
   {'t_word': 'text', 'other_word': 'with'}

'(?P<ends_with_t>\w+t)\b'
   ('text',)
   {'ends_with_t': 'text'}

 22、更新test_patterns(),会显示一个模式匹配的编号组和命名组

import re


def test_patterns(text, patterns):
    for pattern, desc in patterns:
        print('{!r} ({})\n'.format(pattern, desc))
        print('  {!r}'.format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            prefix = ' ' * (s)
            print(
                '  {}{!r}{} '.format(prefix,
                                     text[s:e],
                                     ' ' * (len(text) - e)),
                end=' ',
            )
            print(match.groups())
            if match.groupdict():
                print('{}{}'.format(
                    ' ' * (len(text) - s),
                    match.groupdict()),
                )
        print()
    return

test_patterns(
    'abbaabbba',
    [(r'a((a*)(b*))', 'a followed by 0-n a and 0-n b')],
)
re_groups_nested.py

运行效果

'a((a*)(b*))' (a followed by 0-n a and 0-n b)

  'abbaabbba'
  'abb'        ('bb', '', 'bb')
     'aabbb'   ('abbb', 'a', 'bbb')
          'a'  ('', '', '')

23、组分匹配或的关系

import re


def test_patterns(text, patterns):
    for pattern, desc in patterns:
        print('{!r} ({})\n'.format(pattern, desc))
        print('  {!r}'.format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            prefix = ' ' * (s)
            print(
                '  {}{!r}{} '.format(prefix,
                                     text[s:e],
                                     ' ' * (len(text) - e)),
                end=' ',
            )
            print(match.groups())
            if match.groupdict():
                print('{}{}'.format(
                    ' ' * (len(text) - s),
                    match.groupdict()),
                )
        print()
    return


test_patterns(
    'abbaabbba',
    [(r'a((a+)|(b+))', 'a then seq. of a or seq. of b'),
     (r'a((a|b)+)', 'a then seq. of [ab]')],
)
re_groups_alternative.py

运行效果

'a((a+)|(b+))' (a then seq. of a or seq. of b)

  'abbaabbba'
  'abb'        ('bb', None, 'bb')
     'aa'      ('a', 'a', None)

'a((a|b)+)' (a then seq. of [ab])

  'abbaabbba'
  'abbaabbba'  ('bbaabbba', 'a')

24、非捕获分组,即取出正常分组的第一组元素,语法: (?:正则表达式)

import re


def test_patterns(text, patterns):
    for pattern, desc in patterns:
        print('{!r} ({})\n'.format(pattern, desc))
        print('  {!r}'.format(text))
        for match in re.finditer(pattern, text):
            s = match.start()
            e = match.end()
            prefix = ' ' * (s)
            print(
                '  {}{!r}{} '.format(prefix,
                                     text[s:e],
                                     ' ' * (len(text) - e)),
                end=' ',
            )
            print(match.groups())
            if match.groupdict():
                print('{}{}'.format(
                    ' ' * (len(text) - s),
                    match.groupdict()),
                )
        print()
    return


test_patterns(
    'abbaabbba',
    [(r'a((a+)|(b+))', 'capturing form'),
     (r'a((?:a+)|(?:b+))', 'noncapturing')],
)
re_groups_noncapturing.py

 运行效果

'a((a+)|(b+))' (capturing form)

  'abbaabbba'
  'abb'        ('bb', None, 'bb')
     'aa'      ('a', 'a', None)

'a((?:a+)|(?:b+))' (noncapturing)

  'abbaabbba'
  'abb'        ('bb',)
     'aa'      ('a',)

25、搜索选项,忽略大小写的匹配

import re

text = 'This is some text -- with punctuation.'
pattern = r'\bT\w+'
with_case = re.compile(pattern)
without_case = re.compile(pattern, re.IGNORECASE)

print('Text:\n  {!r}'.format(text))
print('Pattern:\n  {}'.format(pattern))
print('Case-sensitive:')
for match in with_case.findall(text):
    print('  {!r}'.format(match))
print('Case-insensitive:')
for match in without_case.findall(text):
    print('  {!r}'.format(match))
re_flags_ignorecase.py

运行效果

Text:
  'This is some text -- with punctuation.'
Pattern:
  \bT\w+
Case-sensitive:
  'This'
Case-insensitive:
  'This'
  'text'

26、搜索选项,多行匹配,即文本有回车符,当多行来进行匹配

import re

text = 'This is some text -- with punctuation.\nA second line.'
pattern = r'(^\w+)|(\w+\S*$)'
single_line = re.compile(pattern)
multiline = re.compile(pattern, re.MULTILINE)

print('Text:\n  {!r}'.format(text))
print('Pattern:\n  {}'.format(pattern))
print('Single Line :')
for match in single_line.findall(text):
    print('  {!r}'.format(match))
print('Multline    :')
for match in multiline.findall(text):
    print('  {!r}'.format(match))
re_flags_multiline.py

运行效果

Text:
  'This is some text -- with punctuation.\nA second line.'
Pattern:
  (^\w+)|(\w+\S*$)
Single Line :
  ('This', '')
  ('', 'line.')
Multline    :
  ('This', '')
  ('', 'punctuation.')
  ('A', '')
  ('', 'line.')

27、搜索选项,多行匹配,利用点的符号,当多行来进行匹配

import re

text = 'This is some text -- with punctuation.\nA second line.'
pattern = r'.+'
no_newlines = re.compile(pattern)
dotall = re.compile(pattern, re.DOTALL)

print('Text:\n  {!r}'.format(text))
print('Pattern:\n  {}'.format(pattern))
print('No newlines :')
for match in no_newlines.findall(text):
    print('  {!r}'.format(match))
print('Dotall      :')
for match in dotall.findall(text):
    print('  {!r}'.format(match))
re_flags_dotall.py

运行效果

Text:
  'This is some text -- with punctuation.\nA second line.'
Pattern:
  .+
No newlines :
  'This is some text -- with punctuation.'
  'A second line.'
Dotall      :
  'This is some text -- with punctuation.\nA second line.'

28、指示匹配的编码,默认是使用unicode,可以指定匹配ASCII码

import re

text = u'Français złoty Österreich'
pattern = r'\w+'
ascii_pattern = re.compile(pattern, re.ASCII)
unicode_pattern = re.compile(pattern)

print('Text    :', text)
print('Pattern :', pattern)
print('ASCII   :', list(ascii_pattern.findall(text)))
print('Unicode :', list(unicode_pattern.findall(text)))
re_flags_ascii.py

运行效果

Text    : Français złoty Österreich
Pattern : \w+
ASCII   : ['Fran', 'ais', 'z', 'oty', 'sterreich']
Unicode : ['Français', 'złoty', 'Österreich']

29、邮箱格式的复杂匹配

import re

address = re.compile('[\w\d.+-]+@([\w\d.]+\.)+(com|org|edu)')

candidates = [
    u'first.last@example.com',
    u'first.last+category@gmail.com',
    u'valid-address@mail.example.com',
    u'not-valid@example.foo',
]

for candidate in candidates:
    match = address.search(candidate)
    print('{:<30}  {}'.format(
        candidate, 'Matches' if match else 'No match')
    )
re_email_compact.py

运行效果

first.last@example.com          Matches
first.last+category@gmail.com   Matches
valid-address@mail.example.com  Matches
not-valid@example.foo           No match

30、格式化正则表达式邮箱格式的匹配

import re

address = re.compile(
    '''
    [\w\d.+-]+       # username
    @
    ([\w\d.]+\.)+    # domain name prefix
    (com|org|edu)    # TODO: support more top-level domains
    ''',
    re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'first.last+category@gmail.com',
    u'valid-address@mail.example.com',
    u'not-valid@example.foo',
]

for candidate in candidates:
    match = address.search(candidate)
    print('{:<30}  {}'.format(
        candidate, 'Matches' if match else 'No match'),
    )
re_email_verbose.py

运行效果

first.last@example.com          Matches
first.last+category@gmail.com   Matches
valid-address@mail.example.com  Matches
not-valid@example.foo           No match

31、定义组的别名和正则表达式的注释

import re

address = re.compile(
    '''

    # A name is made up of letters, and may include "."
    # for title abbreviations and middle initials.
    ((?P<name>
       ([\w.,]+\s+)*[\w.,]+)
       \s*
       # Email addresses are wrapped in angle
       # brackets < >, but only if a name is
       # found, so keep the start bracket in this
       # group.
       <
    )? # the entire name is optional

    # The address itself: username@domain.tld
    (?P<email>
      [\w\d.+-]+       # username
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >? # optional closing angle bracket
    ''',
    re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'first.last+category@gmail.com',
    u'valid-address@mail.example.com',
    u'not-valid@example.foo',
    u'First Last <first.last@example.com>',
    u'No Brackets first.last@example.com',
    u'First Last',
    u'First Middle Last <first.last@example.com>',
    u'First M. Last <first.last@example.com>',
    u'<first.last@example.com>',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Name :', match.groupdict()['name'])
        print('  Email:', match.groupdict()['email'])
    else:
        print('  No match')
re_email_with_name.py

运行效果

Candidate: first.last@example.com
  Name : None
  Email: first.last@example.com
Candidate: first.last+category@gmail.com
  Name : None
  Email: first.last+category@gmail.com
Candidate: valid-address@mail.example.com
  Name : None
  Email: valid-address@mail.example.com
Candidate: not-valid@example.foo
  No match
Candidate: First Last <first.last@example.com>
  Name : First Last
  Email: first.last@example.com
Candidate: No Brackets first.last@example.com
  Name : None
  Email: first.last@example.com
Candidate: First Last
  No match
Candidate: First Middle Last <first.last@example.com>
  Name : First Middle Last
  Email: first.last@example.com
Candidate: First M. Last <first.last@example.com>
  Name : First M. Last
  Email: first.last@example.com
Candidate: <first.last@example.com>
  Name : None
  Email: first.last@example.com

32、在编译模式,不会传入标志,解决方法:例如:忽略大小写匹配的模式

import re

text = 'This is some text -- with punctuation.'
pattern = r'(?i)\bT\w+'
regex = re.compile(pattern)

print('Text      :', text)
print('Pattern   :', pattern)
print('Matches   :', regex.findall(text))
re_flags_embedded.py

运行效果

Text      : This is some text -- with punctuation.
Pattern   : (?i)\bT\w+
Matches   : ['This', 'text']

33、前向断言匹配,(?= pattern)

import re

address = re.compile(
    '''
    # A name is made up of letters, and may include "."
    # for title abbreviations and middle initials.
    ((?P<name>
       ([\w.,]+\s+)*[\w.,]+
     )
     \s+
    ) # name is no longer optional

    # LOOKAHEAD
    # Email addresses are wrapped in angle brackets, but only
    # if both are present or neither is.
    (?= (<.*>$)       # remainder wrapped in angle brackets
        |
        ([^<].*[^>]$) # remainder *not* wrapped in angle brackets
      )

    <? # optional opening angle bracket

    # The address itself: username@domain.tld
    (?P<email>
      [\w\d.+-]+       # username
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >? # optional closing angle bracket
    ''',
    re.VERBOSE)

candidates = [
    u'First Last <first.last@example.com>',
    u'No Brackets first.last@example.com',
    u'Open Bracket <first.last@example.com',
    u'Close Bracket first.last@example.com>',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Name :', match.groupdict()['name'])
        print('  Email:', match.groupdict()['email'])
    else:
        print('  No match')
re_look_ahead.py

运行效果

Candidate: First Last <first.last@example.com>
  Name : First Last
  Email: first.last@example.com
Candidate: No Brackets first.last@example.com
  Name : No Brackets
  Email: first.last@example.com
Candidate: Open Bracket <first.last@example.com
  No match
Candidate: Close Bracket first.last@example.com>
  No match

34、前向断言取反匹配,(?= pattern)

import re

address = re.compile(
    '''
    ^

    # An address: username@domain.tld

    # Ignore noreply addresses
    (?!noreply@.*$)

    [\w\d.+-]+       # username
    @
    ([\w\d.]+\.)+    # domain name prefix
    (com|org|edu)    # limit the allowed top-level domains

    $
    ''',
    re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'noreply@example.com',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Match:', candidate[match.start():match.end()])
    else:
        print('  No match')
re_negative_look_ahead.py

 运行效果

Candidate: first.last@example.com
  Match: first.last@example.com
Candidate: noreply@example.com
  No match

35、后向断言匹配,否定向后【(?<!pattern)

import re

address = re.compile(
    '''
    ^

    # An address: username@domain.tld

    [\w\d.+-]+       # username

    # Ignore noreply addresses
    (?<!noreply)

    @
    ([\w\d.]+\.)+    # domain name prefix
    (com|org|edu)    # limit the allowed top-level domains

    $
    ''',
    re.VERBOSE)

candidates = [
    u'first.last@example.com',
    u'noreply@example.com',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Match:', candidate[match.start():match.end()])
    else:
        print('  No match')
re_negative_look_behind.py

 运行效果

Candidate: first.last@example.com
  Match: first.last@example.com
Candidate: noreply@example.com
  No match

36、后向断言匹配,肯定向后【(?<=pattern)】

import re

twitter = re.compile(
    '''
    # A twitter handle: @username
    (?<=@)
    ([\w\d_]+)       # username
    ''',
    re.VERBOSE)

text = '''This text includes two Twitter handles.
One for @ThePSF, and one for the author, @doughellmann.
'''

print(text)
for match in twitter.findall(text):
    print('Handle:', match)
re_look_behind.py

 运行效果

This text includes two Twitter handles.
One for @ThePSF, and one for the author, @doughellmann.

Handle: ThePSF
Handle: doughellmann

37、自引用表达式,采用\num进行分组,然后用group(num)获取值

import re

address = re.compile(
    r'''

    # The regular name
    (\w+)               # first name
    \s+
    (([\w.]+)\s+)?      # optional middle name or initial
    (\w+)               # last name

    \s+

    <

    # The address: first_name.last_name@domain.tld
    (?P<email>
      \1               # first name
      \.
      \4               # last name
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >
    ''',
    re.VERBOSE | re.IGNORECASE)

candidates = [
    u'First Last <first.last@example.com>',
    u'Different Name <first.last@example.com>',
    u'First Middle Last <first.last@example.com>',
    u'First M. Last <first.last@example.com>',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Match name :', match.group(1), match.group(4))
        print('  Match email:', match.group(5))
    else:
        print('  No match')
re_refer_to_group.py

运行效果

Candidate: First Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com
Candidate: Different Name <first.last@example.com>
  No match
Candidate: First Middle Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com
Candidate: First M. Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com

38、自引用表达式,采用(?P=name) ,groupdict()['name'])

import re

address = re.compile(
    '''

    # The regular name
    (?P<first_name>\w+)
    \s+
    (([\w.]+)\s+)?      # optional middle name or initial
    (?P<last_name>\w+)

    \s+

    <

    # The address: first_name.last_name@domain.tld
    (?P<email>
      (?P=first_name)
      \.
      (?P=last_name)
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
    )

    >
    ''',
    re.VERBOSE | re.IGNORECASE)

candidates = [
    u'First Last <first.last@example.com>',
    u'Different Name <first.last@example.com>',
    u'First Middle Last <first.last@example.com>',
    u'First M. Last <first.last@example.com>',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Match name :', match.groupdict()['first_name'],
              end=' ')
        print(match.groupdict()['last_name'])
        print('  Match email:', match.groupdict()['email'])
    else:
        print('  No match')
re_refer_to_named_group.py

运行效果

Candidate: First Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com
Candidate: Different Name <first.last@example.com>
  No match
Candidate: First Middle Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com
Candidate: First M. Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com

39、反向引用

语法:

(?P<brackets>(?=(<.*>$))) #匹配
      |
      (?=([^<].*[^>]$)) #非匹配
 )
import re

address = re.compile(
    '''
    ^

    # A name is made up of letters, and may include "."
    # for title abbreviations and middle initials.
    (?P<name>
       ([\w.]+\s+)*[\w.]+
     )?
    \s*

    # Email addresses are wrapped in angle brackets, but
    # only if a name is found.
    (?(name)
      # remainder wrapped in angle brackets because
      # there is a name
      (?P<brackets>(?=(<.*>$)))
      |
      # remainder does not include angle brackets without name
      (?=([^<].*[^>]$))
     )

    # Look for a bracket only if the look-ahead assertion
    # found both of them.
    (?(brackets)<|\s*)

    # The address itself: username@domain.tld
    (?P<email>
      [\w\d.+-]+       # username
      @
      ([\w\d.]+\.)+    # domain name prefix
      (com|org|edu)    # limit the allowed top-level domains
     )

    # Look for a bracket only if the look-ahead assertion
    # found both of them.
    (?(brackets)>|\s*)

    $
    ''',
    re.VERBOSE)

candidates = [
    u'First Last <first.last@example.com>',
    u'No Brackets first.last@example.com',
    u'Open Bracket <first.last@example.com',
    u'Close Bracket first.last@example.com>',
    u'no.brackets@example.com',
]

for candidate in candidates:
    print('Candidate:', candidate)
    match = address.search(candidate)
    if match:
        print('  Match name :', match.groupdict()['name'])
        print('  Match email:', match.groupdict()['email'])
    else:
        print('  No match')
re_id.py

运行效果

Candidate: First Last <first.last@example.com>
  Match name : First Last
  Match email: first.last@example.com
Candidate: No Brackets first.last@example.com
  No match
Candidate: Open Bracket <first.last@example.com
  No match
Candidate: Close Bracket first.last@example.com>
  No match
Candidate: no.brackets@example.com
  Match name : None
  Match email: no.brackets@example.com

40、用模式修改字符串,sub('替换新的字符串',匹配结果):将匹配到的字符串,替换为新的字符串,再更新到原来的字符串

import re

bold = re.compile(r'\*{2}(.*?)\*{2}')

text = 'Make this **bold**.  This **too**.'

print('Text:', text)
print('Bold:', bold.sub(r'<b>\1</b>', text))
re_sub.py

运行效果

Text: Make this **bold**.  This **too**.
['bold', 'too']
Bold: Make this <b>bold</b>.  This <b>too</b>.

41、通过组的命名替换,\g<name>

import re

bold = re.compile(r'\*{2}(?P<bold_text>.*?)\*{2}')

text = 'Make this **bold**.  This **too**.'

print('Text:', text)
print('Bold:', bold.sub(r'<b>\g<bold_text></b>', text))
re_sub_named_groups.py

运行效果

Text: Make this **bold**.  This **too**.
Bold: Make this <b>bold</b>.  This <b>too</b>.

42、通过组的命名替换字符串,定义count设置替换的次数

import re

bold = re.compile(r'\*{2}(.*?)\*{2}')

text = 'Make this **bold**.  This **too**.'

print('Text:', text)
print('Bold:', bold.sub(r'<b>\1</b>', text, count=1))
re_sub_count.py

 运行效果

Text: Make this **bold**.  This **too**.
Bold: Make this <b>bold</b>.  This **too**.

 43、subn()的使用,sub()与subn()的区别,subn()会返回替换结果和替换的次数

import re

bold = re.compile(r'\*{2}(.*?)\*{2}')

text = 'Make this **bold**.  This **too**.'

print('Text:', text)
print('Bold:', bold.subn(r'<b>\1</b>', text))
re_subn.py

运行效果

Text: Make this **bold**.  This **too**.
Bold: ('Make this <b>bold</b>.  This <b>too</b>.', 2)

 44、利用两个\n分割字符串取值,传统的方法

import re

text = '''Paragraph one
on two lines.

Paragraph two.


Paragraph three.'''
for num, para in enumerate(re.findall(r'(.+?)\n{2,}',
                                      text,
                                      flags=re.DOTALL)):
    print(num, repr(para))
    print()
re_paragraphs_findall.py

运行效果

0 'Paragraph one\non two lines.'

1 'Paragraph two.'

45、利用正则表达对字符串进行分隔,此示例是以两个回车符为例进行切割

import re

text = '''Paragraph one
on two lines.

Paragraph two.


Paragraph three.'''

print('With findall:')
for num, para in enumerate(re.findall(r'(.+?)(\n{2,}|$)',
                                      text,
                                      flags=re.DOTALL)):
    print(num, repr(para))
    print()

print()
print('With split:')
for num, para in enumerate(re.split(r'\n{2,}', text)):
    print(num, repr(para))
    print()
re_split.py

运行效果

With findall:
0 ('Paragraph one\non two lines.', '\n\n')

1 ('Paragraph two.', '\n\n\n')

2 ('Paragraph three.', '')


With split:
0 'Paragraph one\non two lines.'

1 'Paragraph two.'

2 'Paragraph three.'

46、指定分组正则表达式切分字符串,并且返回匹配到的分割符

import re

text = '''Paragraph one
on two lines.

Paragraph two.


Paragraph three.'''

print('With split:')
for num, para in enumerate(re.split(r'(\n{2,})', text)):
    print(num, repr(para))
    print()
re_split_groups.py

 运行效果

With split:
0 'Paragraph one\non two lines.'

1 '\n\n'

2 'Paragraph two.'

3 '\n\n\n'

4 'Paragraph three.'

 

posted @ 2020-07-09 15:30  小粉优化大师  阅读(361)  评论(0编辑  收藏  举报