循序渐进Python3（二） -- 数据类型

数据类型

一、数字（int）

　　Python可以处理任意大小的正负整数，但是实际中跟我们计算机的内存有关，在32位机器上，整数的位数为32位，取值范围为 -2**31～2**31-1，在64位系统上，整数的位数为64位，取值范围为-2**63～2**63-1。对于int类型，需要掌握的方法不多，看 下面的几个例子：

二、字符串（str）

　　字符串的常用功能很多，下面就列举一下：

capitalize # 如果字符串中的第一个字符是字母，将其变为大写，其余字母变为小写

>>> a = '123,HELLO,world!'
>>> a.capitalize()
'123,hello,world!'

>>> a = 'hELLO,World!'
>>> a.capitalize()
'Hello,world!'

casefold # 将字符串中的大写变成小写，和lower 类似。casefold对其他语言更有效。

总结来说，汉语 & 英语环境下面，继续用

lower()

没问题；要处理其它语言且存在大小写情况的时候再用

casefold()

>>> a = 'hELLO,World!'
>>> print(a.casefold())
hello,world!
>>>

s = 'ß' #德语
a=s.lower() #  'ß'
b=s.casefold() # 'ss'
print(a,b)
ß ss

center(self, width, fillchar=None) # 把字符串居中，两边补齐fillchar，最终字符串总长度为width

>>> a = 'li'
>>> print(a.center(40,'-'))
-------------------li-------------------

count(self, sub, start=None, end=None) # 查看子字符串在字符串中的数量

>>> a = 'my name is han meimei'
>>> print(a.count(' '))
4
>>> print(a.count(' ',3,8))
1
>>> print(a.count('m',3,8))
1
>>> print(a.count('m'))
4

endode #

pass

endswith(self, suffix, start=None, end=None) # 查看字符串从start位置到end位置这一段的结尾是不是suffix

>>> a = 'my name is han meimei'
>>> b = a.endswith('meimei')
>>> print(b)
True
>>> if a.endswith('meimei'):
...   print('你好')
...
你好
>>> print(a.endswith('is',3,9))
False
>>> print(a.endswith('is',3,10)) #顾头不顾尾原则
True

def capitalize(self): # real signature unknown; restored from __doc__
"""
S.capitalize() -> str

Return a capitalized version of S, i.e. make the first character
have upper case and the rest lower case.
"""
return ""

def casefold(self): # real signature unknown; restored from __doc__
"""
S.casefold() -> str

Return a version of S suitable for caseless comparisons.
"""
return ""

def center(self, width, fillchar=None): # real signature unknown; restored from __doc__
"""
S.center(width[, fillchar]) -> str

Return S centered in a string of length width. Padding is
done using the specified fill character (default is a space)
"""
return ""

def count(self, sub, start=None, end=None): # real signature unknown; restored from __doc__
"""
S.count(sub[, start[, end]]) -> 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.
"""
return 0

def encode(self, encoding='utf-8', errors='strict'): # real signature unknown; restored from __doc__
"""
S.encode(encoding='utf-8', errors='strict') -> bytes

Encode S using the codec registered for encoding. Default encoding
is 'utf-8'. errors may be given to set a different error
handling scheme. 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.
"""
return b""

def endswith(self, suffix, start=None, end=None): # real signature unknown; restored from __doc__
"""
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.
"""
return False

def expandtabs(self, tabsize=8): # real signature unknown; restored from __doc__
"""
S.expandtabs(tabsize=8) -> str

Return a copy of S where all tab characters are expanded using spaces.
If tabsize is not given, a tab size of 8 characters is assumed.
"""
return ""

def find(self, sub, start=None, end=None): # real signature unknown; restored from __doc__
"""
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.
"""
return 0

def format(*args, **kwargs): # known special case of str.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 '}').
"""
pass

def format_map(self, mapping): # real signature unknown; restored from __doc__
"""
S.format_map(mapping) -> str

Return a formatted version of S, using substitutions from mapping.
The substitutions are identified by braces ('{' and '}').
"""
return ""

def index(self, sub, start=None, end=None): # real signature unknown; restored from __doc__
"""
S.index(sub[, start[, end]]) -> int

Like S.find() but raise ValueError when the substring is not found.
"""
return 0

def isalnum(self): # real signature unknown; restored from __doc__
"""
S.isalnum() -> bool

Return True if all characters in S are alphanumeric
and there is at least one character in S, False otherwise.
"""
return False

def isalpha(self): # real signature unknown; restored from __doc__
"""
S.isalpha() -> bool

Return True if all characters in S are alphabetic
and there is at least one character in S, False otherwise.
"""
return False

def isdecimal(self): # real signature unknown; restored from __doc__
"""
S.isdecimal() -> bool

Return True if there are only decimal characters in S,
False otherwise.
"""
return False

def isdigit(self): # real signature unknown; restored from __doc__
"""
S.isdigit() -> bool

Return True if all characters in S are digits
and there is at least one character in S, False otherwise.
"""
return False

def isidentifier(self): # real signature unknown; restored from __doc__
"""
S.isidentifier() -> bool

Return True if S is a valid identifier according
to the language definition.

Use keyword.iskeyword() to test for reserved identifiers
such as "def" and "class".
"""
return False

def islower(self): # real signature unknown; restored from __doc__
"""
S.islower() -> bool

Return True if all cased characters in S are lowercase and there is
at least one cased character in S, False otherwise.
"""
return False

def isnumeric(self): # real signature unknown; restored from __doc__
"""
S.isnumeric() -> bool

Return True if there are only numeric characters in S,
False otherwise.
"""
return False

def isprintable(self): # real signature unknown; restored from __doc__
"""
S.isprintable() -> bool

Return True if all characters in S are considered
printable in repr() or S is empty, False otherwise.
"""
return False

def isspace(self): # real signature unknown; restored from __doc__
"""
S.isspace() -> bool

Return True if all characters in S are whitespace
and there is at least one character in S, False otherwise.
"""
return False

def istitle(self): # real signature unknown; restored from __doc__
"""
S.istitle() -> bool

Return True if S is a titlecased string and there is at least one
character in S, i.e. upper- and titlecase characters may only
follow uncased characters and lowercase characters only cased ones.
Return False otherwise.
"""
return False

def isupper(self): # real signature unknown; restored from __doc__
"""
S.isupper() -> bool

Return True if all cased characters in S are uppercase and there is
at least one cased character in S, False otherwise.
"""
return False

def join(self, iterable): # real signature unknown; restored from __doc__
"""
S.join(iterable) -> str

Return a string which is the concatenation of the strings in the
iterable.  The separator between elements is S.
"""
return ""

def ljust(self, width, fillchar=None): # real signature unknown; restored from __doc__
"""
S.ljust(width[, fillchar]) -> str

Return S left-justified in a Unicode string of length width. Padding is
done using the specified fill character (default is a space).
"""
return ""

def lower(self): # real signature unknown; restored from __doc__
"""
S.lower() -> str

Return a copy of the string S converted to lowercase.
"""
return ""

def lstrip(self, chars=None): # real signature unknown; restored from __doc__
"""
S.lstrip([chars]) -> str

Return a copy of the string S with leading whitespace removed.
If chars is given and not None, remove characters in chars instead.
"""
return ""

def maketrans(self, *args, **kwargs): # real signature unknown
"""
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.
"""
pass

def partition(self, sep): # real signature unknown; restored from __doc__
"""
S.partition(sep) -> (head, sep, tail)

Search for the separator sep in S, and return the part before it,
the separator itself, and the part after it.  If the separator is not
found, return S and two empty strings.
"""
pass

def replace(self, old, new, count=None): # real signature unknown; restored from __doc__
"""
S.replace(old, new[, count]) -> str

Return a copy of S with all occurrences of substring
old replaced by new.  If the optional argument count is
given, only the first count occurrences are replaced.
"""
return ""

def rfind(self, sub, start=None, end=None): # real signature unknown; restored from __doc__
"""
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.
"""
return 0

def rindex(self, sub, start=None, end=None): # real signature unknown; restored from __doc__
"""
S.rindex(sub[, start[, end]]) -> int

Like S.rfind() but raise ValueError when the substring is not found.
"""
return 0

def rjust(self, width, fillchar=None): # real signature unknown; restored from __doc__
"""
S.rjust(width[, fillchar]) -> str

Return S right-justified in a string of length width. Padding is
done using the specified fill character (default is a space).
"""
return ""

def rpartition(self, sep): # real signature unknown; restored from __doc__
"""
S.rpartition(sep) -> (head, sep, tail)

Search for the separator sep in S, starting at the end of S, and return
the part before it, the separator itself, and the part after it.  If the
separator is not found, return two empty strings and S.
"""
pass

def rsplit(self, sep=None, maxsplit=-1): # real signature unknown; restored from __doc__
"""
S.rsplit(sep=None, maxsplit=-1) -> list of strings

Return a list of the words in S, using sep as the
delimiter string, starting at the end of the string and
working to the front.  If maxsplit is given, at most maxsplit
splits are done. If sep is not specified, any whitespace string
is a separator.
"""
return []

def rstrip(self, chars=None): # real signature unknown; restored from __doc__
"""
S.rstrip([chars]) -> str

Return a copy of the string S with trailing whitespace removed.
If chars is given and not None, remove characters in chars instead.
"""
return ""

def split(self, sep=None, maxsplit=-1): # real signature unknown; restored from __doc__
"""
S.split(sep=None, maxsplit=-1) -> list of strings

Return a list of the words in S, using sep as the
delimiter string.  If maxsplit is given, at most maxsplit
splits are done. If sep is not specified or is None, any
whitespace string is a separator and empty strings are
removed from the result.
"""
return []

def splitlines(self, keepends=None): # real signature unknown; restored from __doc__
"""
S.splitlines([keepends]) -> list of strings

Return a list of the lines in S, breaking at line boundaries.
Line breaks are not included in the resulting list unless keepends
is given and true.
"""
return []

def startswith(self, prefix, start=None, end=None): # real signature unknown; restored from __doc__
"""
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.
"""
return False

def strip(self, chars=None): # real signature unknown; restored from __doc__
"""
S.strip([chars]) -> str

Return a copy of the string S with leading and trailing
whitespace removed.
If chars is given and not None, remove characters in chars instead.
"""
return ""

def swapcase(self): # real signature unknown; restored from __doc__
"""
S.swapcase() -> str

Return a copy of S with uppercase characters converted to lowercase
and vice versa.
"""
return ""

def title(self): # real signature unknown; restored from __doc__
"""
S.title() -> str

Return a titlecased version of S, i.e. words start with title case
characters, all remaining cased characters have lower case.
"""
return ""

def translate(self, table): # real signature unknown; restored from __doc__
"""
S.translate(table) -> str

Return a copy of the string S in which each character has been mapped
through the given translation table. The table must implement
lookup/indexing via __getitem__, for instance a dictionary or list,
mapping Unicode ordinals to Unicode ordinals, strings, or None. If
this operation raises LookupError, the character is left untouched.
Characters mapped to None are deleted.
"""
return ""

def upper(self): # real signature unknown; restored from __doc__
"""
S.upper() -> str

Return a copy of S converted to uppercase.
"""
return ""

def zfill(self, width): # real signature unknown; restored from __doc__
"""
S.zfill(width) -> str

Pad a numeric string S with zeros on the left, to fill a field
of the specified width. The string S is never truncated.
"""
return ""

　　

三、列表（list）

　　列表是Python内置的一种数据类型是列表，是一种有序的集合，可以随时添加和删除其中的元素。

def append(self, p_object): # real signature unknown; restored from __doc__
""" L.append(object) -> None -- append object to end """
pass

def clear(self): # real signature unknown; restored from __doc__
""" L.clear() -> None -- remove all items from L """
pass

def copy(self): # real signature unknown; restored from __doc__
""" L.copy() -> list -- a shallow copy of L """
return []

def count(self, value): # real signature unknown; restored from __doc__
""" L.count(value) -> integer -- return number of occurrences of value """
return 0

def extend(self, iterable): # real signature unknown; restored from __doc__
""" L.extend(iterable) -> None -- extend list by appending elements from the iterable """
pass

def index(self, value, start=None, stop=None): # real signature unknown; restored from __doc__
"""
L.index(value, [start, [stop]]) -> integer -- return first index of value.
Raises ValueError if the value is not present.
"""
return 0

def insert(self, index, p_object): # real signature unknown; restored from __doc__
""" L.insert(index, object) -- insert object before index """
pass

def pop(self, index=None): # real signature unknown; restored from __doc__
"""
L.pop([index]) -> item -- remove and return item at index (default last).
Raises IndexError if list is empty or index is out of range.
"""
pass

def remove(self, value): # real signature unknown; restored from __doc__
"""
L.remove(value) -> None -- remove first occurrence of value.
Raises ValueError if the value is not present.
"""
pass

def reverse(self): # real signature unknown; restored from __doc__
""" L.reverse() -- reverse *IN PLACE* """
pass

def sort(self, key=None, reverse=False): # real signature unknown; restored from __doc__
""" L.sort(key=None, reverse=False) -> None -- stable sort *IN PLACE* """
pass

　　

四、元组（tuple）

　　tuple和list非常类似，但是tuple一旦初始化就不能修改，tuple也是有序的，tuple使用的是小括号标识。

def count(self, value): # real signature unknown; restored from __doc__
""" T.count(value) -> integer -- return number of occurrences of value """
return 0

def index(self, value, start=None, stop=None): # real signature unknown; restored from __doc__
"""
T.index(value, [start, [stop]]) -> integer -- return first index of value.
Raises ValueError if the value is not present.
"""
return 0

　　

五、字典（dict）

　　字典是无序的，使用键-值（key-value）存储，具有极快的查找速度。

def clear(self): # real signature unknown; restored from __doc__
""" D.clear() -> None.  Remove all items from D. """
pass

def copy(self): # real signature unknown; restored from __doc__
""" D.copy() -> a shallow copy of D """
pass

@staticmethod # known case
def fromkeys(*args, **kwargs): # real signature unknown
""" Returns a new dict with keys from iterable and values equal to value. """
pass

def get(self, k, d=None): # real signature unknown; restored from __doc__
""" D.get(k[,d]) -> D[k] if k in D, else d.  d defaults to None. """
pass

def items(self): # real signature unknown; restored from __doc__
""" D.items() -> a set-like object providing a view on D's items """
pass

def keys(self): # real signature unknown; restored from __doc__
""" D.keys() -> a set-like object providing a view on D's keys """
pass

def pop(self, k, d=None): # real signature unknown; restored from __doc__
"""
D.pop(k[,d]) -> v, remove specified key and return the corresponding value.
If key is not found, d is returned if given, otherwise KeyError is raised
"""
pass

def popitem(self): # real signature unknown; restored from __doc__
"""
D.popitem() -> (k, v), remove and return some (key, value) pair as a
2-tuple; but raise KeyError if D is empty.
"""
pass

def setdefault(self, k, d=None): # real signature unknown; restored from __doc__
""" D.setdefault(k[,d]) -> D.get(k,d), also set D[k]=d if k not in D """
pass

def update(self, E=None, **F): # known special case of dict.update
"""
D.update([E, ]**F) -> None.  Update D from dict/iterable E and F.
If E is present and has a .keys() method, then does:  for k in E: D[k] = E[k]
If E is present and lacks a .keys() method, then does:  for k, v in E: D[k] = v
In either case, this is followed by: for k in F:  D[k] = F[k]
"""
pass

def values(self): # real signature unknown; restored from __doc__
""" D.values() -> an object providing a view on D's values """
pass

　　

补充

深浅copy

为什么要拷贝？

数字字符串 和 集合 在修改时的差异？（深浅拷贝不同的终极原因）

对于集合，如何保留其修改前和修改后的数据？

对于集合，如何拷贝其n层元素同时拷贝？

1 浅copy
2 >>> dict = {"a":("apple",),"bo":{"b":"banna","o":"orange"},"g":["grape","grapefruit"]}
3 >>> dict = {"a":("apple",),"bo":{"b":"banna","o":"orange"},"g":["grape","grapefruit"]}
4 >>> dict2 = dict.copy()
5
6
7 >>> dict["g"][0] = "shuaige"  #第一次我修改的是第二层的数据
8 >>> print dict
9 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
10 >>> print dict2
11 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
12 >>> id(dict["g"][0]),id(dict2["g"][0])
13 (140422980581296, 140422980581296)  #从这里可以看出第二层他们是用的内存地址
14 >>>
15
16
17 >>> dict["a"] = "dashuaige"  #注意第二次这里修改的是第一层
18 >>> print dict
19 {'a': 'dashuaige', 'bo': {'b': 'banna', 'o': 'orange'}, 'g':['shuaige','grapefruit']}'g': ['shuaige', 'grapefruit']}'g': ['shuaige', 'grapefruit']}'g': ['shuaige', 'grapefruit']}
20 >>> print dict2
21 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
22 >>>
23 >>> id(dict["a"]),id(dict2["a"])
24 (140422980580816, 140422980552272)  #从这里看到第一层他们修改后就不会是相同的内存地址了！
25 >>>
26
27
28 #这里看下，第一次我修改了dict的第二层的数据，dict2也跟着改变了，但是我第二次我修改了dict第一层的数据dict2没有修改。
29 说明：浅copy只是第一层是独立的，其他层面是公用的！作用节省内存
30
31 深copy
32
33 >>> import copy  #深copy需要导入模块
34 >>> dict = {"a":("apple",),"bo":{"b":"banna","o":"orange"},"g":["grape","grapefruit"]}
35 >>> dict2 = copy.deepcopy(dict)
36 >>> print dict
37 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
38 >>> print dict2
39 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
40 >>> dict["g"][0] = "shuaige"   #修改第二层数据
41 >>> print dict

42 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
43 >>> print dict2
44 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
45 >>> id(dict["g"][0]),id(dict2["g"][0])
46 (140422980580816, 140422980580288)  #从这里看到第二个数据现在也不是公用了
47
48 # 通过这里可以看出他们现在是一个完全独立的，当你修改dict时dict2是不会改变的因为是两个独立的字典！

'g': ['shuaige', 'grapefruit']}
20 >>> print dict2
21 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
22 >>>
23 >>> id(dict["a"]),id(dict2["a"])
24 (140422980580816, 140422980552272)  #从这里看到第一层他们修改后就不会是相同的内存地址了！
25 >>>
26
27
28 #这里看下，第一次我修改了dict的第二层的数据，dict2也跟着改变了，但是我第二次我修改了dict第一层的数据dict2没有修改。
29 说明：浅copy只是第一层是独立的，其他层面是公用的！作用节省内存
30
31 深copy
32
33 >>> import copy  #深copy需要导入模块
34 >>> dict = {"a":("apple",),"bo":{"b":"banna","o":"orange"},"g":["grape","grapefruit"]}
35 >>> dict2 = copy.deepcopy(dict)
36 >>> print dict
37 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
38 >>> print dict2
39 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
40 >>> dict["g"][0] = "shuaige"   #修改第二层数据
41 >>> print dict
42 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['shuaige', 'grapefruit']}
43 >>> print dict2
44 {'a': ('apple',), 'bo': {'b': 'banna', 'o': 'orange'}, 'g': ['grape', 'grapefruit']}
45 >>> id(dict["g"][0]),id(dict2["g"][0])
46 (140422980580816, 140422980580288)  #从这里看到第二个数据现在也不是公用了
47
48 # 通过这里可以看出他们现在是一个完全独立的，当你修改dict时dict2是不会改变的因为是两个独立的字典！