day10.md

第十天

索引

• Python标准库--re
• Python好的文章python 的静态类型检查工具 mypy
• Python代码片段
• Python读书--Python cookbook day3
• Python框架相关--Django路由系统
• Python项目相关--mkdoc
• Python之外--DarkSun的个人博客

python标准库 re

1. 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]))

2. re.compile

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')

3. re.findall -> 返回列表
4. re pattern

import re

def test_patterns(text, patterns):
    """Given source text and a list of patterns, look for
    matches for each pattern within the text and print
    them to stdout.
    """
    # Look for each pattern in the text and print the results
    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')],
)

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')],
)

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

5. unicode

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)))

6. Verbose Expression Syntax

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')
    )

7. re.sub ()

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))

8. re.split

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()

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()