Python 字符串处理（笔记）

Python字符串处理

去空格或特殊字符 .strip()

input_str = ' 今天天气不错，挺风和日丽的 '
input_str1 =  ' 今天天气不错，挺风和日丽的 ! '

print(input_str)
print(input_str1)

 今天天气不错，挺风和日丽的 !
今天天气不错，挺风和日丽的

input_str.strip()

'今天天气不错，挺风和日丽的'

.strip()去空格，相关方法：仅去左边或右边空格，注：不能去句子中间空格

input_str.lstrip()

'今天天气不错，挺风和日丽的 '

input_str.rstrip()

' 今天天气不错，挺风和日丽的'

input_str1.strip()

'今天天气不错，挺风和日丽的 !'

亦可去掉其他字符

input_str2 =  'AAA今天天气不错，挺风和日丽的AAA'

input_str2.strip('A')

'今天天气不错，挺风和日丽的'

input_str2.lstrip('A')

'今天天气不错，挺风和日丽的AAA'

input_str2.rstrip('A')

'AAA今天天气不错，挺风和日丽的'

替换操作：.replace

input_str3 =  '今天天气不错，今天挺风和日丽的'

input_str3.replace('今天','昨天')

' 昨天天气不错，昨天挺风和日丽的 '

去掉句子中所有的某字符，亦可使用.replace（）操作

input_str3.replace('今天','')

' 天气不错，挺风和日丽的 '

查找操作 .find()

input_str3.find('今天')

0

.find()返回第一次出现的该字符串的位置索引

判断操作

input_str4 = 'the weather is fine, today.'
input_str5 = '今天天气真好a'
input_str6 = '13号星期五'
input_str7 = '123'
input_str8 = 'the weather is fine'
input_str9 = 'theweatherisfine'

input_str3.isalpha()

False

input_str4.isalpha()

False

input_str8.isalpha()

False

input_str9.isalpha()

True

.isalpha()判断某字符串是否全为字母，哪怕出现标点、空格返回值都为假

input_str3.isdigit()

False

input_str6.isdigit()

False

input_str7.isdigit()

True

.isdigit()判断字符串是否全为数字

分割合并操作

input_str10 = '今天 天气 不错 ， 今天 挺 风和日丽 的'

input_str10 = input_str10.split(' ')

input_str10

['今天', '天气', '不错', '，', '今天', '挺', '风和日丽', '的']

将原字符串按“ ”分割为列表，若保存该列表需有额外的复制操作

str1 = "".join(input_str10)

str1

'今天天气不错，今天挺风和日丽的'

以“”字符为连接符将列表内元素合并，并将结果保存在str中

帮助文档

str=""

help(str)

Help on class str in module builtins:

class str(object)
 |  str(object='') -> str
 |  str(bytes_or_buffer[, encoding[, errors]]) -> str
 |  
 |  Create a new string object from the given object. If encoding or
 |  errors is specified, then the object must expose a data buffer
 |  that will be decoded using the given encoding and error handler.
 |  Otherwise, returns the result of object.__str__() (if defined)
 |  or repr(object).
 |  encoding defaults to sys.getdefaultencoding().
 |  errors defaults to 'strict'.
 |  
 |  Methods defined here:
 |  
 |  __add__(self, value, /)
 |      Return self+value.
 |  
 |  __contains__(self, key, /)
 |      Return key in self.
 |  
 |  __eq__(self, value, /)
 |      Return self==value.
 |  
 |  __format__(self, format_spec, /)
 |      Return a formatted version of the string as described by format_spec.
 |  
 |  __ge__(self, value, /)
 |      Return self>=value.
 |  
 |  __getattribute__(self, name, /)
 |      Return getattr(self, name).
 |  
 |  __getitem__(self, key, /)
 |      Return self[key].
 |  
 |  __getnewargs__(...)
 |  
 |  __gt__(self, value, /)
 |      Return self>value.
 |  
 |  __hash__(self, /)
 |      Return hash(self).
 |  
 |  __iter__(self, /)
 |      Implement iter(self).
 |  
 |  __le__(self, value, /)
 |      Return self<=value.
 |  
 |  __len__(self, /)
 |      Return len(self).
 |  
 |  __lt__(self, value, /)
 |      Return self int
 |      
 |      Return the number of non-overlapping occurrences of substring sub in
 |      string S[start:end].  Optional arguments start and end are
 |      interpreted as in slice notation.
 |  
 |  encode(self, /, encoding='utf-8', errors='strict')
 |      Encode the string using the codec registered for encoding.
 |      
 |      encoding
 |        The encoding in which to encode the string.
 |      errors
 |        The error handling scheme to use for encoding errors.
 |        The default is 'strict' meaning that encoding errors raise a
 |        UnicodeEncodeError.  Other possible values are 'ignore', 'replace' and
 |        'xmlcharrefreplace' as well as any other name registered with
 |        codecs.register_error that can handle UnicodeEncodeErrors.
 |  
 |  endswith(...)
 |      S.endswith(suffix[, start[, end]]) -> bool
 |      
 |      Return True if S ends with the specified suffix, False otherwise.
 |      With optional start, test S beginning at that position.
 |      With optional end, stop comparing S at that position.
 |      suffix can also be a tuple of strings to try.
 |  
 |  expandtabs(self, /, tabsize=8)
 |      Return a copy where all tab characters are expanded using spaces.
 |      
 |      If tabsize is not given, a tab size of 8 characters is assumed.
 |  
 |  find(...)
 |      S.find(sub[, start[, end]]) -> int
 |      
 |      Return the lowest index in S where substring sub is found,
 |      such that sub is contained within S[start:end].  Optional
 |      arguments start and end are interpreted as in slice notation.
 |      
 |      Return -1 on failure.
 |  
 |  format(...)
 |      S.format(*args, **kwargs) -> str
 |      
 |      Return a formatted version of S, using substitutions from args and kwargs.
 |      The substitutions are identified by braces ('{' and '}').
 |  
 |  format_map(...)
 |      S.format_map(mapping) -> str
 |      
 |      Return a formatted version of S, using substitutions from mapping.
 |      The substitutions are identified by braces ('{' and '}').
 |  
 |  index(...)
 |      S.index(sub[, start[, end]]) -> int
 |      
 |      Return the lowest index in S where substring sub is found, 
 |      such that sub is contained within S[start:end].  Optional
 |      arguments start and end are interpreted as in slice notation.
 |      
 |      Raises ValueError when the substring is not found.
 |  
 |  isalnum(self, /)
 |      Return True if the string is an alpha-numeric string, False otherwise.
 |      
 |      A string is alpha-numeric if all characters in the string are alpha-numeric and
 |      there is at least one character in the string.
 |  
 |  isalpha(self, /)
 |      Return True if the string is an alphabetic string, False otherwise.
 |      
 |      A string is alphabetic if all characters in the string are alphabetic and there
 |      is at least one character in the string.
 |  
 |  isascii(self, /)
 |      Return True if all characters in the string are ASCII, False otherwise.
 |      
 |      ASCII characters have code points in the range U+0000-U+007F.
 |      Empty string is ASCII too.
 |  
 |  isdecimal(self, /)
 |      Return True if the string is a decimal string, False otherwise.
 |      
 |      A string is a decimal string if all characters in the string are decimal and
 |      there is at least one character in the string.
 |  
 |  isdigit(self, /)
 |      Return True if the string is a digit string, False otherwise.
 |      
 |      A string is a digit string if all characters in the string are digits and there
 |      is at least one character in the string.
 |  
 |  isidentifier(self, /)
 |      Return True if the string is a valid Python identifier, False otherwise.
 |      
 |      Use keyword.iskeyword() to test for reserved identifiers such as "def" and
 |      "class".
 |  
 |  islower(self, /)
 |      Return True if the string is a lowercase string, False otherwise.
 |      
 |      A string is lowercase if all cased characters in the string are lowercase and
 |      there is at least one cased character in the string.
 |  
 |  isnumeric(self, /)
 |      Return True if the string is a numeric string, False otherwise.
 |      
 |      A string is numeric if all characters in the string are numeric and there is at
 |      least one character in the string.
 |  
 |  isprintable(self, /)
 |      Return True if the string is printable, False otherwise.
 |      
 |      A string is printable if all of its characters are considered printable in
 |      repr() or if it is empty.
 |  
 |  isspace(self, /)
 |      Return True if the string is a whitespace string, False otherwise.
 |      
 |      A string is whitespace if all characters in the string are whitespace and there
 |      is at least one character in the string.
 |  
 |  istitle(self, /)
 |      Return True if the string is a title-cased string, False otherwise.
 |      
 |      In a title-cased string, upper- and title-case characters may only
 |      follow uncased characters and lowercase characters only cased ones.
 |  
 |  isupper(self, /)
 |      Return True if the string is an uppercase string, False otherwise.
 |      
 |      A string is uppercase if all cased characters in the string are uppercase and
 |      there is at least one cased character in the string.
 |  
 |  join(self, iterable, /)
 |      Concatenate any number of strings.
 |      
 |      The string whose method is called is inserted in between each given string.
 |      The result is returned as a new string.
 |      
 |      Example: '.'.join(['ab', 'pq', 'rs']) -> 'ab.pq.rs'
 |  
 |  ljust(self, width, fillchar=' ', /)
 |      Return a left-justified string of length width.
 |      
 |      Padding is done using the specified fill character (default is a space).
 |  
 |  lower(self, /)
 |      Return a copy of the string converted to lowercase.
 |  
 |  lstrip(self, chars=None, /)
 |      Return a copy of the string with leading whitespace removed.
 |      
 |      If chars is given and not None, remove characters in chars instead.
 |  
 |  partition(self, sep, /)
 |      Partition the string into three parts using the given separator.
 |      
 |      This will search for the separator in the string.  If the separator is found,
 |      returns a 3-tuple containing the part before the separator, the separator
 |      itself, and the part after it.
 |      
 |      If the separator is not found, returns a 3-tuple containing the original string
 |      and two empty strings.
 |  
 |  replace(self, old, new, count=-1, /)
 |      Return a copy with all occurrences of substring old replaced by new.
 |      
 |        count
 |          Maximum number of occurrences to replace.
 |          -1 (the default value) means replace all occurrences.
 |      
 |      If the optional argument count is given, only the first count occurrences are
 |      replaced.
 |  
 |  rfind(...)
 |      S.rfind(sub[, start[, end]]) -> int
 |      
 |      Return the highest index in S where substring sub is found,
 |      such that sub is contained within S[start:end].  Optional
 |      arguments start and end are interpreted as in slice notation.
 |      
 |      Return -1 on failure.
 |  
 |  rindex(...)
 |      S.rindex(sub[, start[, end]]) -> int
 |      
 |      Return the highest index in S where substring sub is found,
 |      such that sub is contained within S[start:end].  Optional
 |      arguments start and end are interpreted as in slice notation.
 |      
 |      Raises ValueError when the substring is not found.
 |  
 |  rjust(self, width, fillchar=' ', /)
 |      Return a right-justified string of length width.
 |      
 |      Padding is done using the specified fill character (default is a space).
 |  
 |  rpartition(self, sep, /)
 |      Partition the string into three parts using the given separator.
 |      
 |      This will search for the separator in the string, starting at the end. If
 |      the separator is found, returns a 3-tuple containing the part before the
 |      separator, the separator itself, and the part after it.
 |      
 |      If the separator is not found, returns a 3-tuple containing two empty strings
 |      and the original string.
 |  
 |  rsplit(self, /, sep=None, maxsplit=-1)
 |      Return a list of the words in the string, using sep as the delimiter string.
 |      
 |        sep
 |          The delimiter according which to split the string.
 |          None (the default value) means split according to any whitespace,
 |          and discard empty strings from the result.
 |        maxsplit
 |          Maximum number of splits to do.
 |          -1 (the default value) means no limit.
 |      
 |      Splits are done starting at the end of the string and working to the front.
 |  
 |  rstrip(self, chars=None, /)
 |      Return a copy of the string with trailing whitespace removed.
 |      
 |      If chars is given and not None, remove characters in chars instead.
 |  
 |  split(self, /, sep=None, maxsplit=-1)
 |      Return a list of the words in the string, using sep as the delimiter string.
 |      
 |      sep
 |        The delimiter according which to split the string.
 |        None (the default value) means split according to any whitespace,
 |        and discard empty strings from the result.
 |      maxsplit
 |        Maximum number of splits to do.
 |        -1 (the default value) means no limit.
 |  
 |  splitlines(self, /, keepends=False)
 |      Return a list of the lines in the string, breaking at line boundaries.
 |      
 |      Line breaks are not included in the resulting list unless keepends is given and
 |      true.
 |  
 |  startswith(...)
 |      S.startswith(prefix[, start[, end]]) -> bool
 |      
 |      Return True if S starts with the specified prefix, False otherwise.
 |      With optional start, test S beginning at that position.
 |      With optional end, stop comparing S at that position.
 |      prefix can also be a tuple of strings to try.
 |  
 |  strip(self, chars=None, /)
 |      Return a copy of the string with leading and trailing whitespace removed.
 |      
 |      If chars is given and not None, remove characters in chars instead.
 |  
 |  swapcase(self, /)
 |      Convert uppercase characters to lowercase and lowercase characters to uppercase.
 |  
 |  title(self, /)
 |      Return a version of the string where each word is titlecased.
 |      
 |      More specifically, words start with uppercased characters and all remaining
 |      cased characters have lower case.
 |  
 |  translate(self, table, /)
 |      Replace each character in the string using the given translation table.
 |      
 |        table
 |          Translation table, which must be a mapping of Unicode ordinals to
 |          Unicode ordinals, strings, or None.
 |      
 |      The table must implement lookup/indexing via __getitem__, for instance a
 |      dictionary or list.  If this operation raises LookupError, the character is
 |      left untouched.  Characters mapped to None are deleted.
 |  
 |  upper(self, /)
 |      Return a copy of the string converted to uppercase.
 |  
 |  zfill(self, width, /)
 |      Pad a numeric string with zeros on the left, to fill a field of the given width.
 |      
 |      The string is never truncated.
 |  
 |  ----------------------------------------------------------------------
 |  Static methods defined here:
 |  
 |  __new__(*args, **kwargs) from builtins.type
 |      Create and return a new object.  See help(type) for accurate signature.
 |  
 |  maketrans(x, y=None, z=None, /)
 |      Return a translation table usable for str.translate().
 |      
 |      If there is only one argument, it must be a dictionary mapping Unicode
 |      ordinals (integers) or characters to Unicode ordinals, strings or None.
 |      Character keys will be then converted to ordinals.
 |      If there are two arguments, they must be strings of equal length, and
 |      in the resulting dictionary, each character in x will be mapped to the
 |      character at the same position in y. If there is a third argument, it
 |      must be a string, whose characters will be mapped to None in the result.