Python文本和字符串常用操作

## 字符串分割

 line = "This is my love!"
 fields = line.split(' ')
 print(fields)
 # ['This', 'is', 'my', 'love!']
 
 # 多条件分割
 import re
 
 line = "asd dfwerf, sdfs; jtyy. werwe, sdfsd"
 fields = re.split(r"(,|\.|;|\s)\s*", line)
 print(fields)
 # ['asd', ' ', 'dfwerf', ',', 'sdfs', ';', 'jtyy', '.', 'werwe', ',', 'sdfsd']
 
 # 如果不需要分隔符可以使用(?:...)不捕获分组
 fields = re.split(r"(?:,|\.|;|\s)\s*", line)
 print(fields)
 # ['asd', 'dfwerf', 'sdfs', 'jtyy', 'werwe', 'sdfsd']

## 开头或结尾匹配startswith(), endswith()

 url = 'https://www.baidu.com'
 print(url.startswith('https'))
 # True
 
 words = ['sd', 'asad', 'fgwer', 'jtdwse', 'qwieu', 'pqwej', 'ejwqi', 'iaweq']
 w = [word for word in words if word.startswith(('a', 'e', 'i'))]
 # startswith()，endswith()方法接收一个元组表示多项匹配，元组的括号不可以省略
 print(w)
 # ['asad', 'ejwqi', 'iaweq']
 
 # 判断某个目录下是否有某些类型的文件
 if any(name.endswith(('.c', '.h')) for name in listdir(dirname)):
     pass

## Shell通配符(*?[0-9])匹配

 from fnmatch import fnmatch, fnmatchcase
 
 print(fnmatch('hello.py', '*.py'))
 # True
 print(fnmatch('hello.py', '?ello.py'))
 # True
 print(fnmatch('hello-1.py', 'hello-[0-9].py'))
 # True
 print(fnmatch('hello.txt', '*.TXT'))
 # fnmatch()在不同操作系统中结果不同
 # 若在类UNIX系统中为False(即大小写敏感)，在Windows系统中为True(即大小写不敏感)
 
 print(fnmatchcase('hello.txt', '*.TXT'))
 # False
 # fnmatchcase()在任何操作系统中都大小写敏感

## 字符串匹配和搜索

 import re
 
 date = '7/24/2018'
 # 匹配
 print(bool(re.match(r'\d+/\d+/\d+', date)))
 # True
 
 # 同一模式多次使用可以预先编译
 date_pat = re.compile(r'\d+/\d+/\d+')
 print(bool(date_pat.match(date)))
 # True
 
 # 查找并捕获
 date_pat = re.compile(r'(\d+)/(\d+)/(\d+)')
 line = "Today is 7/24/2018, tomorrow is 7/25/2018"
 print(date_pat.findall(line))
 # [('7', '24', '2018'), ('7', '25', '2018')]
 
 m = date_pat.match(date)
 print(m)
 print(m.group())
 # 7/24/2018
 print(m.group(1))
 #
 print(m.group(2))
 #
 print(m.group(3))
 #
 print(m.group(0))
 # 7/24/2018

## 字符串的修改和替换

 line = "Yes, it's me!"
 print(line.replace("Yes", "Yeah"))
 # Yeah, it's me!
 
 import re
 
 text = "Today is 7/24/2018, tomorrow is 7/25/2018"
 date_pat = re.compile(r'(\d+)/(\d+)/(\d+)')
 print(date_pat.sub(r'\3-\1-\2', text))   # 其中r'\3-\1-\2'指的是通过正则捕获的数据的索引，和上面group()方法的对应关系相同
 # Today is 2018-7-24, tomorrow is 2018-7-25
 
 # sub()方法还可以接受一个函数作为参数以应对更加复杂的替换
 from calendar import month_abbr
 
 def change_date(m):  # 参数为match对象，即match()或者find()方法的返回值
     mon_name = month_abbr[int(m.group(1))]
     return "{} {} {}".format(m.group(2), mon_name, m.group(3))
 
 print(date_pat.sub(change_date, text))
 # Today is 24 Jul 2018, tomorrow is 25 Jul 2018
 
 # 查看subn()替换的数量
 print(date_pat.subn(change_date, text)) # 返回一个元组，第二个值为替换的次数
 # ('Today is 24 Jul 2018, tomorrow is 25 Jul 2018', 2)

## 搜索忽略大小写

 import re
 
 text = "UPPER PYTHON, lower python, Mixed Python"
 print(re.findall('python', text, flags=re.IGNORECASE))
 # ['PYTHON', 'python', 'Python']
 print(re.sub('python', 'java', text, flags=re.IGNORECASE))  # 替换并不会按照原有规则，而是所有匹配项都同一替换
 # UPPER java, lower java, Mixed java
 
 # 可以使用辅助函数弥补
 def matchcase(word):
     def replace(m): # 参数为一个match对象
         text = m.group()
         if text.isupper():
             return word.upper()
         if text.islower():
             return word.lower()
         if text[0].isupper(): # 首字母大写
             return word.title()
         return word
     return replace
 
 print(re.sub('python', matchcase('java'), text, flags=re.IGNORECASE))
 # UPPER JAVA, lower java, Mixed Java

## 贪婪匹配和最短匹配

 import re
 
 text = 'You said "Yes", I said "No"'
 print(re.findall(r'\".*\"', text))  # 贪婪匹配，匹配结果尽可能长
 # ['"Yes", I said "No"']
 
 print(re.findall(r'\".*?\"', text)) # 最短匹配， 匹配结果尽可能短
 # ['"Yes"', '"No"']

## 多行匹配

 import re
 
 comment = re.compile(r'/\*(.*?)\*/')    # 此模式无法匹配多行, 因为 . 号无法匹配换行符
 text1 = "/* this is a comment */"
 text2 = """
     /* this is a
     multiline comment */
 """
 print(comment.findall(text1))
 # [' this is a comment ']
 
 print(comment.findall(text2))
 # []
 
 comment = re.compile(r'/\*((?:.|\n)*?)\*/') # 在模式中加上换行符，可以匹配多行
 print(comment.findall(text1))
 
 print(comment.findall(text2))
 # [' this is a\n    multiline comment ']
 
 comment = re.compile(r'/\*(.*?)\*/', flags=re.DOTALL) # flags=re.DOTALL使 . 号可以匹配所有字符
 print(comment.findall(text1))
 # [' this is a comment ']
 print(comment.findall(text2))
 # [' this is a\n    multiline comment ']

## 删除多余字符

 text = "---Hello   World+++"
 print(text.strip("-+")) # 参数默认为 ‘ ’ 空格， 只能清除两侧的多余内容，字符串中间的内容无法清除
 # Hello   World
 print(text.lstrip("-")) # 清除左侧多余字符
 # Hello   World+++
 print(text.rstrip("+")) # 清除右侧多余字符
 # ---Hello   World
 
 text = "Hello  World"
 print(text.replace('  ', ' ')) # 只能清除/替换固定个数的字符
 # Hello World
 
 import re
 
 text = "Hello     World"
 print(re.sub('\s+', ' ', text))  # 可以清除/替换不定个数的字符
 # Hello World

## 字符串对齐

 text = "Hello World"
 print(text.ljust(20, '-')) #v 第一个参数为总字符数， 第二个参数为填充字符，默认为空格
 # Hello World---------
 print(text.rjust(20))
 #          Hello World
 print(text.center(20, '-'))
 # ----Hello World-----
 
 print(format(text, '>20'))
 #          Hello World
 
 print(format(text, '-<20'))
 # Hello World---------
 
 print(format(text, '+^20'))
 # ++++Hello World+++++
 
 print(format(3.14159265, '-^10.4f'))  # 格式化数字
 # --3.1416--

## 字符串中插入变量

 text = 'Hello, {name}!'
 print(text.format(name="Stanley"))
 # Hello, Stanley!
 
 text = '{name} has {n} message(s).'
 name = "Stanley"
 n = 32
 print(text.format_map(vars())) # 从全局变量中查找相应数据
 # Stanley has 32 message(s).
 
 class UserInfo:
     def __init__(self, name, n):
         self.name = name
         self.n = n
 
 a = UserInfo('Stanley', 30)
 print(text.format_map(vars(a))) # 从实例属性中查找数据
 # Stanley has 30 message(s).

　　

　　　　- 定义一个类包装输入，避免变量找不到的问题

 class safesub(dict):
     def __missing__(self, key): # 重写__missing__()方法
         return "{" + key + "}"
 
 text = '{name} has {n} message(s).'
 name = "Stanley"
 print(text.format_map(safesub(vars())))
 # Stanley has {n} message(s).

## 文本换行

 import textwrap
 
 text = "Python is an interpreted high-level programming language for general-purpose programming. Created by Guido van Rossum and first released in 1991, Python has a design philosophy that emphasizes code readability, notably using significant whitespace. It provides constructs that enable clear programming on both small and large scales. In July 2018, the creator Guido Rossum stepped down as the leader in the language community after 30 years."
 print(textwrap.fill(text, 40))
 """
 Python is an interpreted high-level
 programming language for general-purpose
 programming. Created by Guido van Rossum
 and first released in 1991, Python has a
 design philosophy that emphasizes code
 readability, notably using significant
 whitespace. It provides constructs that
 enable clear programming on both small
 and large scales. In July 2018, the
 creator Guido Rossum stepped down as the
 leader in the language community after
 30 years.
 """
 print(textwrap.fill(text, 80, initial_indent="      "))  # 首行缩进
 """
       Python is an interpreted high-level programming language for general-
 purpose programming. Created by Guido van Rossum and first released in 1991,
 Python has a design philosophy that emphasizes code readability, notably using
 significant whitespace. It provides constructs that enable clear programming on
 both small and large scales. In July 2018, the creator Guido Rossum stepped down
 as the leader in the language community after 30 years.
 """
 print(textwrap.fill(text, 80, subsequent_indent="      "))  # 悬挂缩进
 """
 Python is an interpreted high-level programming language for general-purpose
       programming. Created by Guido van Rossum and first released in 1991,
       Python has a design philosophy that emphasizes code readability, notably
       using significant whitespace. It provides constructs that enable clear
       programming on both small and large scales. In July 2018, the creator
       Guido Rossum stepped down as the leader in the language community after 30
       years.
 """

参考资料：
　　Python Cookbook, 3rd edition, by David Beazley and Brian K. Jones (O’Reilly).