字符串和文本
使用多个界定符分割字符串
>>> line = 'asdf fjdk; afed, fjek,asdf, foo'
>>> import re
>>> re.split(r'[;,\s]\s*', line)
['asdf', 'fjdk', 'afed', 'fjek', 'asdf', 'foo']
>>> import re
>>> line = 'asdf fjdk; afed, fjek,asdf, foo'
>>> fields = re.split(r'(;|,|\s)\s*', line) #分割字符串也会出现在列表中
>>> fields
['asdf', ' ', 'fjdk', ';', 'afed', ',', 'fjek', ',', 'asdf', ',', 'foo']
>>> re.split(r'(?:,|;|\s)\s*', line) #不想保留分割字符串且仍需要括号来分组正则，确保分组傻逼非捕获分组
['asdf', 'fjdk', 'afed', 'fjek', 'asdf', 'foo']
字符串开头或结尾匹配
>>> filename = 'spam.txt'
>>> filename.endswith('.txt')
True
>>> filename.startswith('file:')
False
>>> url = 'http://www.python.org'
>>> url.startswith('http:')
True
>>> import os
>>> filename = os.listdir('.')
>>> filename
['DLLs', 'Doc', 'include', 'Lib', 'libs', 'LICENSE.txt', 'NEWS.txt', 'python.exe', 'python3.dll', 'python38.dll', 'pythonw.exe', 'Scripts', 'tcl', 'Tools', 'vcruntime140.dll', 'vcruntime140_1.dll']
>>> [name for name in filename if name.endswith(('.dll', '.txt'))] #参数类型必须是元组
['LICENSE.txt', 'NEWS.txt', 'python3.dll', 'python38.dll', 'vcruntime140.dll', 'vcruntime140_1.dll']
>>> any(name.endswith('.txt') for name in filename)
True
>>>
用shell通配符匹配字符串
>> from fnmatch import fnmatch, fnmatchcase
>>> fnmatch('foo.txt', '*.txt')
True
>>> fnmatch('foo.txt', '?oo.txt')
True
>>> fnmatch('Dat45.csv', 'Dat[0-9]*')
True
fnmatch()使用底层操作系统的大小写敏感规则，导致不同的系统结果是不同的，可以使用fnmatchcase()来代替
>>> fnmatch('foo.txt', '*.TXT')
True
>>> fnmatchcase('foo.txt', '*.TXT')
False
>>>
字符串匹配和搜索
匹配字面字符串
>>> test = 'yeah, but, no, but, yeah, but, no, but, yeah'
>>> test == 'yeah'
False
>>> test.startswith('yeah')
True
>>> test.endswith('no')
False
>>> test.find('but')
6
>>>
复杂匹配，需要使用正则表达式和re模块
>>> text1 = '11/27/2012'
>>> text2 = 'Nov 27, 2012'
>>> import re
>>> if re.match(r'\d+/\d+/\d', text1):
print('yes')
else:
print('No')
yes
>>>
使用同一模式做多次匹配，先将模式字符串预编译为模式对象
>>> datepat = re.compile(r'\d+/\d+/\d')
>>> if datepat.match(text1):
print('yes')
else:
print('no')
yes
>>>
match()总是从字符串开始匹配，若想查找任意部分，使用findall()
>>> text = 'Today is 11/27/2012. PyCon starts 3/13/2013.'
>>> datepat.findall(text)
['11/27/2', '3/13/2']
>>>
定义正则表达式时，会利用括号捕获分组
>>> datepat = re.compile(r'(\d+)/(\d+)/(\d+)')
>>> m = datepat.match('11/27/2012')
>>> m
<re.Match object; span=(0, 10), match='11/27/2012'>
>>> m.group(1)
'11'
>>> m.group(2)
'27'
>>> m.group(3)
'2012'
>>> m.groups()
('11', '27', '2012')
>>> month, day, year = m.groups()
>>> datepat.findall(text)
[('11', '27', '2012'), ('3', '13', '2013')]
>>> datepat = re.compile(r'(\d+)/(\d+)/(\d+)$') #精确匹配时正则表达式以$结尾
>>> datepat.match('11/27/2/12abcd')
>>> datepat.match('11/27/2012')
<re.Match object; span=(0, 10), match='11/27/2012'>
>>>
findall()是以列表形式返回匹配，如果以迭代形式返回，可以使用finditer()
>>> for m in datepat.finditer(text):
print(m.groups())
('11', '27', '2012')
('3', '13', '2013')
>>>
字符串搜索和替换
简单的字面模式
>>> text = 'yeah, but. no. bnut, yeah, but, no, but, yeah'
>>> text.replace('yeah', 'yep')
'yep, but. no. bnut, yep, but, no, but, yep'
>>>
复杂模式，使用sub()
>>> text = 'Today is 11/27/2012. PyCon starts 3/13/2013.'
>>> import re
>>> re.sub(r'(\d+)/(\d+)/(\d+)', r'\3-\1-\2', text) #\3指向前面模式的捕获组号
'Today is 2012-11-27. PyCon starts 2013-3-13.'
>>>
多次替换，可以先编译模式
>>> datepat = re.compile(r'(\d+)/(\d+)/(\d+)')
>>> re.sub(r'(\d+)/(\d+)/(\d+)', r'\3-\1-\2', text)
'Today is 2012-11-27. PyCon starts 2013-3-13.'
>>>
更复杂的替换，可以传递一个回调函数
>>> from calendar import month_abbr
>>> def change_date(m):
mon_name = month_abbr[int(m.group(1))]
return '{} {} {}'.format(m.group(2), mon_name, m.group(3))
>>> datepat.sub(change_date, text)
'Today is 27 Nov 2012. PyCon starts 13 Mar 2013.'
>>>
想知道有多少替换发生，使用subn()
>>> newtext, n = datepat.subn(r'\3-\1-\2', text)
>>> newtext
'Today is 2012-11-27. PyCon starts 2013-3-13.'
>>> n
2
>>>
字符串忽略大小写的搜索替换
>>> text = 'UPPER PYTHON, lower python, Mixed Python'
>>> re.findall('python', text, flags=re.IGNORECASE)
['PYTHON', 'python', 'Python']
>>> re.sub('python', 'snake', text, flags=re.IGNORECASE)
'UPPER snake, lower snake, Mixed snake'
>>>
最短匹配模式
>>> str_pat = re.compile(r'\"(.*)\"')
>>> text1 = 'Computer says "no."'
>>> str_pat.findall(text1)
['no.']
>>> text2 = 'Computer says "no." Phone says "yes."'
>>> str_pat.findall(text2)
['no." Phone says "yes.'] #匹配的内容不是我们想要的
>>> str_pat = re.compile(r'\"(.*?)\"') #追加“？”
>>> str_pat.findall(text2)
['no.', 'yes.']
>>>
多行匹配模式
>>> comment = re.compile(r'/\*(.*?)\*/')
>>> text1 = '/* this is a comment */'
>>> text2 = '''/* this is a
multiline comment */
'''
>>> comment.findall(text1)
[' this is a comment ']
>>> comment.findall(text2)
[]
>>> comment = re.compile('/\*((?:.|\n)*?)\*/')
>>> comment.findall(text2)
[' this is a\nmultiline comment ']
>>> comment.findall(text1)
[' this is a comment ']
>>>
将Unicode文本标准化
>>> s1 = 'Spicy Jalape\u00f1o' #使用整体字符(U+00F1)
>>> s2 = 'spicy Jalapen\u0303o' #使用拉丁字母加~的组合(U+0303)
>>> s1
'Spicy Jalape?o'
>>> s2
'spicy Jalapen?o'
>>> s1 == s2 #字符串看起来一样，但是比较时返回False
False
>>> len(s1)
14
>>> len(s2)
15
>>>
>>> import unicodedata
>>> t1 = unicodedata.normalize('NFC', s1) #NFC,NFD,NFKC,NFKD
>>> t2 = unicodedata.normalize('NFC', s2)
>>> t1 == t2
True
>>> print(ascii(t1))
'Spicy Jalape\xf1o'
>>> print(ascii(t2))
'Spicy Jalape\xf1o'
>>>
>>> t1 = unicodedata.normalize('NFD', s1)
>>> ''.join(c for c in t1 if not unicodedata.combining(c)) #测试字符是否是音字符
'Spicy Jalapeno'
>>>
在正则表达式中使用Unicode
>>> import re
>>> num = re.compile('\d+') #re模块已经有了基本的支持
>>> num.match('123')
<re.Match object; span=(0, 3), match='123'>
>>> num.match('\u0661\u0662\u0663')
<re.Match object; span=(0, 3), match='???'>
>>>
删除字符串中不需要的字符
strip()用于删除开始或结尾的字符，lstrip()和rstrip()分别从左右执行删除
>>> s.strip()
'hello world'
>>> s.lstrip()
'hello world \n'
>>> s.rstrip()
' hello world'
>>> t = '---hello ==='
>>> t.lstrip('-')
'hello ==='
>>> t.rstrip('=')
'---hello '
>>> t.strip('-=')
'hello '
>>> t.strip(' -=')
'hello'
>>>
审阅清理文本字符串
>>> s = 'python\fis\tawesome\r\n'
>>> s
'python\x0cis\tawesome\r\n'
>>> remap = {
ord('\t'):'',
ord('\f'):'',
ord('\r'):None
}
>>> a = s.translate(remap)
>>> a
'pythonisawesome\n'
>>>
字符串对齐
>>> text = 'Hello World'
>>> text.ljust(20)
'Hello World '
>>> text.rjust(20)
' Hello World'
>>> text.center(20)
' Hello World '
>>> text.rjust(20, '=')
'=========Hello World'
>>> text.center(20, '*')
'****Hello World*****'
>>> format(text, '=>20s')
'=========Hello World'
>>> format(text, '>20')
' Hello World'
>>> format(text, '<20')
'Hello World '
>>> format(text, '*^20s')
'****Hello World*****'
>>> '{:>10s} {:>10s}'.format('Hello', 'World')
' Hello World'
>>> x = 1.2345
>>> format(x, '-10.2f')
' 1.23'
>>> format(x, '>10')
' 1.2345'
>>> format(x, '-10.2f')
' 1.23'
>>>
合并拼接字符串
>>> parts = ['Is', 'Chicago', 'Not', 'Chicago?']
>>> ''.join(parts)
'IsChicagoNotChicago?'
>>> ','.join(parts)
'Is,Chicago,Not,Chicago?'
>>> ' '.join(parts)
'Is Chicago Not Chicago?'
>>> a = 'Is Chicago'
>>> b = 'Not Chicago?'
>>> a + '' + b
'Is ChicagoNot Chicago?'
>>> a = 'Hello' 'World'
>>> a
'HelloWorld'
>>>
永远不要这样连接字符串：
>>> s = ''
>>> for p in parts:
s += p #每次+=都会创建一个新的字符串对象
可以利用生成器表达式
>>> data = ['ACME', 50, 91, 1]
>>> ','.join(str(d) for d in data)
'ACME,50,91,1'
>>>
不必要的字符串连接操作：
>>>print(a + ';' + 'b' + ':' + c) #可以，但是冗余
>>>print(a, b, c, sep=':')
字符串中插入变量
>>> s = '{name} has {n} messages.'
>>> s.format(name = 'Guido', n = 37)
'Guido has 37 messages.'
>>>
>>> name = 'Guido'
>>> n = 37
>>> s.format_map(vars()) #在变量域查找变量，且适用于对象实例
'Guido has 37 messages.'
>>>
format()和format_map()的一个缺陷时不能处理变量缺失
>>> s.format(name='Guido')
Traceback (most recent call last):
File "<pyshell#341>", line 1, in <module>
s.format(name='Guido')
KeyError: 'n'
>>>
避免这种错误的方法是定义一个字典对象：
>>> class safesub(dict):
def __missing__(self, key):
return '{' + key + '}'
>>> del n
>>> s.format_map(safesub(vars()))
'Guido has {n} messages.'
>>>
可以封装之后使用：
>>> import sys
>>> def sub(text):
return text.format_map(safesub(sys._getframe(1).f_locals))
>>> name = 'Guido'
>>> n = 37
>>> print(sub('Hello {name}'))
Hello Guido
>>> print(sub('You have {n} messages.'))
You have 37 messages.
>>> print(sub('Your favorite color is {color}'))
Your favorite color is {color}
以指定列宽格式化字符串
>>> s = "Look into my eyes, look into my eyes,the eyes, the eyes,\
the eyes, not around the eyes, don't look around the eyes,\
look into my eyes, you're under."
>>> import textwrap
>>> print(textwrap.fill(s, 70))
Look into my eyes, look into my eyes,the eyes, the eyes,the eyes, not
around the eyes, don't look around the eyes,look into my eyes, you're
under.
>>> print(textwrap.fill(s, 40, initial_indent=' '))
Look into my eyes, look into my
eyes,the eyes, the eyes,the eyes, not
around the eyes, don't look around the
eyes,look into my eyes, you're under.
>>> print(textwrap.fill(s, 40, subsequent_indent=' '))
Look into my eyes, look into my eyes,the
eyes, the eyes,the eyes, not around
the eyes, don't look around the
eyes,look into my eyes, you're
under.
>>>
在字符串中处理html和xml
>>> s = 'Elements are written as "<tag>text</tag>".'
>>> import html
>>> print(s)
Elements are written as "<tag>text</tag>".
>>> print(html.escape(s))
Elements are written as "<tag>text</tag>".
>>> print(html.escape(s, quote=False))
Elements are written as "<tag>text</tag>".
>>>
>>> s = 'Spicy Jalape?o'
>>> s.encode('ascii', errors='xmlcharrefreplace')
b'Spicy Jalapeño'
>>>
含有编码值的原始文本，需要如下方法替换字符串：
>>> s = 'Spicy "Jalapeño".'
>>> from html.parser import HTMLPar
>>> html.unescape(s)
'Spicy "Jalape?o".'
>>>
>>> t = 'The prompt is >>>'
>>> from xml.sax.saxutils import unescape
>>> unescape(t)
'The prompt is >>>'
>>>
字符串令牌解析
暂时没用到
实现一个递归下降分析器
暂时没用到
