py3 字符串 字典 列表 元组 集合
目录
字符串
列表
元组
字典
集合
基本数据类型总结
数据类型转换
Python 字符串
字符串是 Python 中最常用的数据类型。我们可以使用引号('或")来创建字符串。
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'. """ def capitalize(self, *args, **kwargs): # real signature unknown """首字母大写 """ """ Return a capitalized version of the string. More specifically, make the first character have upper case and the rest lower case. """ pass def casefold(self, *args, **kwargs): # real signature unknown """类似于lower(),但是lower只能小写化英文,此方法还能小写化别的语言类似于德文 """ """ Return a version of the string suitable for caseless comparisons. """ pass def center(self, *args, **kwargs): # real signature unknown """ 内容居中，args：总长度；kwargs：空白处填充内容，默认" " """ """ Return a centered string of length width. Padding is done using the specified fill character (default is a space). """ pass def count(self, sub, start=None, end=None): # real signature unknown; restored from __doc__ """ 返回括号内的子序列个数 """ """ 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 decode(self, encoding=None, errors=None): """ 解码 """ """ S.decode([encoding[,errors]]) -> object Decodes S using the codec registered for encoding. encoding defaults to the default encoding. errors may be given to set a different error handling scheme. Default is 'strict' meaning that encoding errors raise a UnicodeDecodeError. Other possible values are 'ignore' and 'replace' as well as any other name registered with codecs.register_error that is able to handle UnicodeDecodeErrors. """ return object def encode(self, *args, **kwargs): # real signature unknown """ 编码，Unicode转别的编码 """ """ 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. """ pass def endswith(self, suffix, start=None, end=None): # real signature unknown; restored from __doc__ """ 判断字符串是否以子串结尾 """ """ 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, *args, **kwargs): # real signature unknown """ 将tab转换成空格，默认一个tab转换成8个空格 """ """ Return a copy where all tab characters are expanded using spaces. If tabsize is not given, a tab size of 8 characters is assumed. """ pass def find(self, sub, start=None, end=None): # real signature unknown; restored from __doc__ """ 寻找子序列位置，如果没找到，返回 -1 """ """ 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(self, *args, **kwargs): # known special case of str.format """ 字符串格式化，动态参数 """ """ 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__ """ 子序列位置，如果没找到，报错 """ """ 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. """ return 0 def isalnum(self, *args, **kwargs): # real signature unknown """ 是否是字母和数字 """ """ 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. """ pass def isalpha(self, *args, **kwargs): # real signature unknown """ 是否是字母 """ """ 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. """ pass def isascii(self, *args, **kwargs): # real signature unknown """ 是否所有字符都在ASCII表中 """ """ 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. """ pass def isdecimal(self, *args, **kwargs): # real signature unknown """ 是否是十进制数 """ """ 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. """ pass def isdigit(self, *args, **kwargs): # real signature unknown """ 是否是数字 """ """ 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. """ pass def isidentifier(self, *args, **kwargs): # real signature unknown """ 判断是否是合法的标识符 """ """ 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". """ pass def islower(self, *args, **kwargs): # real signature unknown """ 判断是否是小写 """ """ 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. """ pass def isnumeric(self, *args, **kwargs): # real signature unknown """ 是否是数字 """ """ 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. """ pass def isprintable(self, *args, **kwargs): # real signature unknown """ 是否可打印 """ """ 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. """ pass def isspace(self, *args, **kwargs): # real signature unknown """ 是否全是空格 """ """ 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. """ pass def istitle(self, *args, **kwargs): # real signature unknown """ 是否是标题华 """ """ 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. """ pass def isupper(self, *args, **kwargs): # real signature unknown """ 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. """ pass def join(self, ab=None, pq=None, rs=None): # real signature unknown; restored from __doc__ """ 字符串连接 """ """ 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' """ pass def ljust(self, *args, **kwargs): # real signature unknown """ 内容左对齐，右侧默认填充’ ‘ """ """ Return a left-justified string of length width. Padding is done using the specified fill character (default is a space). """ pass def lower(self, *args, **kwargs): # real signature unknown """ 变小写 """ """ Return a copy of the string converted to lowercase. """ pass def lstrip(self, *args, **kwargs): # real signature unknown """ 移除左侧空白 """ """ Return a copy of the string with leading whitespace removed. If chars is given and not None, remove characters in chars instead. """ pass def maketrans(self, *args, **kwargs): # real signature unknown """创建字符映射的转换表，对于接受两个参数的最简单的调用方式，第一个参数是字符串，表示需要转换的字符，第二个参数也是字符串表示转换的目标。""" """ 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, *args, **kwargs): # real signature unknown """ 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. """ pass def replace(self, *args, **kwargs): # real signature unknown """ 字符串中的 str1 替换成 str2,如果 max 指定，则替换不超过 max 次。 """ """ 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. """ pass 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 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. """ return 0 def rjust(self, *args, **kwargs): # real signature unknown """ Return a right-justified string of length width. Padding is done using the specified fill character (default is a space). """ pass def rpartition(self, *args, **kwargs): # real signature unknown """ 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. """ pass def rsplit(self, *args, **kwargs): # real signature unknown """ 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. """ pass def rstrip(self, *args, **kwargs): # real signature unknown """ Return a copy of the string with trailing whitespace removed. If chars is given and not None, remove characters in chars instead. """ pass def split(self, *args, **kwargs): # real signature unknown """ 分割， maxsplit最多分割几次 """ """ 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. """ pass def splitlines(self, *args, **kwargs): # real signature unknown """按照行('\r', '\r\n', \n')分隔，返回一个包含各行作为元素的列表，如果参数 keepends 为 False，不包含换行符，如果为 True，则保留换行符。""" """ 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. """ pass def startswith(self, prefix, start=None, end=None): # real signature unknown; restored from __doc__ """ 是否起始 """ """ 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, *args, **kwargs): # real signature unknown """ 移除两段空白 """ """ Return a copy of the string with leading and trailing whitespace remove. If chars is given and not None, remove characters in chars instead. """ pass def swapcase(self, *args, **kwargs): # real signature unknown """ 大写变小写，小写变大写 """ """ Convert uppercase characters to lowercase and lowercase characters to uppercase. """ pass def title(self, *args, **kwargs): # real signature unknown """ 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. """ pass def translate(self, *args, **kwargs): # real signature unknown """转换，需要先做一个对应表，最后一个表示删除字符集合""" """ 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. """ pass def upper(self, *args, **kwargs): # real signature unknown """ 小写变大写 """ """ Return a copy of the string converted to uppercase. """ pass def zfill(self, *args, **kwargs): # real signature unknown """方法返回指定长度的字符串，原字符串右对齐，前面填充0。""" """ Pad a numeric string with zeros on the left, to fill a field of the given width. The string is never truncated. """ pass def __add__(self, *args, **kwargs): # real signature unknown """ Return self+value. """ pass def __contains__(self, *args, **kwargs): # real signature unknown """ Return key in self. """ pass def __eq__(self, *args, **kwargs): # real signature unknown """ Return self==value. """ pass def __format__(self, *args, **kwargs): # real signature unknown """ Return a formatted version of the string as described by format_spec. """ pass def __getattribute__(self, *args, **kwargs): # real signature unknown """ Return getattr(self, name). """ pass def __getitem__(self, *args, **kwargs): # real signature unknown """ Return self[key]. """ pass def __getnewargs__(self, *args, **kwargs): # real signature unknown pass def __ge__(self, *args, **kwargs): # real signature unknown """ Return self>=value. """ pass def __gt__(self, *args, **kwargs): # real signature unknown """ Return self>value. """ pass def __hash__(self, *args, **kwargs): # real signature unknown """ Return hash(self). """ pass def __init__(self, value='', encoding=None, errors='strict'): # known special case of str.__init__ """ 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'. # (copied from class doc) """ pass def __iter__(self, *args, **kwargs): # real signature unknown """ Implement iter(self). """ pass def __len__(self, *args, **kwargs): # real signature unknown """ Return len(self). """ pass def __le__(self, *args, **kwargs): # real signature unknown """ Return self<=value. """ pass def __lt__(self, *args, **kwargs): # real signature unknown """ Return self<value. """ pass def __mod__(self, *args, **kwargs): # real signature unknown """ Return self%value. """ pass def __mul__(self, *args, **kwargs): # real signature unknown """ Return self*value. """ pass @staticmethod # known case of __new__ def __new__(*args, **kwargs): # real signature unknown """ Create and return a new object. See help(type) for accurate signature. """ pass def __ne__(self, *args, **kwargs): # real signature unknown """ Return self!=value. """ pass def __repr__(self, *args, **kwargs): # real signature unknown """ Return repr(self). """ pass def __rmod__(self, *args, **kwargs): # real signature unknown """ Return value%self. """ pass def __rmul__(self, *args, **kwargs): # real signature unknown """ Return value*self. """ pass def __sizeof__(self, *args, **kwargs): # real signature unknown """ Return the size of the string in memory, in bytes. """ pass def __str__(self, *args, **kwargs): # real signature unknown """ Return str(self). """ pass
访问字符串中的值（切片）
Python不支持单字符类型（char），单字符在 Python 中也是作为一个字符串使用。
Python访问子字符串，可以使用方括号来截取字符串，如下实例：（顾头不顾尾）
var1 = 'Hello World!' var2 = "Python Runoob" print "var1[0]: ", var1[0] print "var2[1:5]: ", var2[1:5] # var1[0]: H # var2[1:5]: ytho
转义字符
在需要在字符中使用特殊字符时，python用反斜杠(\)转义字符。如下表：
| 转义字符 | 描述 |
|---|---|
| \(在行尾时) | 续行符 |
| \\ | 反斜杠符号 |
| \' | 单引号 |
| \" | 双引号 |
| \a | 响铃 |
| \b | 退格(Backspace) |
| \e | 转义 |
| \000 | 空 |
| \n | 换行 |
| \v | 纵向制表符 |
| \t | 横向制表符 |
| \r | 回车 |
| \f | 换页 |
| \oyy | 八进制数，yy代表的字符，例如：\o12代表换行 |
| \xyy | 十六进制数，yy代表的字符，例如：\x0a代表换行 |
| \other | 其它的字符以普通格式输出 |
字符串运算符
下表实例变量 a 值为字符串 "Hello"，b 变量值为 "Python"：
| 操作符 | 描述 | 实例 |
|---|---|---|
| + | 字符串连接 |
>>>a + b 'HelloPython'
|
| * | 重复输出字符串 |
>>>a * 2 'HelloHello'
|
| [] | 通过索引获取字符串中字符 |
>>>a[1] 'e'
|
| [ : ] | 截取字符串中的一部分 |
>>>a[1:4] 'ell'
|
| in | 成员运算符 - 如果字符串中包含给定的字符返回 True |
>>>"H" in a True
|
| not in | 成员运算符 - 如果字符串中不包含给定的字符返回 True |
>>>"M" not in a True
|
| r/R | 原始字符串 - 原始字符串：所有的字符串都是直接按照字面的意思来使用，没有转义特殊或不能打印的字符。 原始字符串除在字符串的第一个引号前加上字母"r"（可以大小写）以外，与普通字符串有着几乎完全相同的语法。 |
>>>print r'\n' \n >>> print R'\n' \n
|
| % | 格式字符串 | 请看下一点 |
格式化字符串
推荐使用第二种
name = input("name:") age = input("age:") job = input("job:") salary = input("salary:") print(type(job)) print(type(int(age))) # 爱人割让 info = ''' -------info of %s------ name:%s age:%s job:%s salary:%s ''' % (name, name, age, job, salary) info2 = ''' -------info of {_name}------ name:{_name} age:{_age} job:{_job} salary:{_salary} '''.format(_name=name, _age=age, _job=job, _salary=salary) info3 = ''' -------info of {0}------ name:{0} age:{1} job:{2} salary:{3} '''.format(name, age, job, salary) print(info2)
格式化字符串%还是format
皇城PK
Python中格式化字符串目前有两种阵营：%和format，我们应该选择哪种呢？
自从Python2.6引入了format这个格式化字符串的方法之后，我认为%还是format这根本就不算个问题。不信你往下看。
# 定义一个坐标值 c = (250, 250) # 使用%来格式化 s1 = "敌人坐标：%s" % c
上面的代码很明显会抛出一个如下的TypeError：
TypeError: not all arguments converted during string formatting
像这类格式化的需求我们需要写成下面丑陋的格式才行：
# 定义一个坐标值 c = (250, 250) # 使用%丑陋的格式化... s1 = "敌人坐标：%s" % (c,)
而使用format就不会存在上面的问题：
# 定义一个坐标值
c = (250, 250)
# 使用format格式化
s2 = "敌人坐标：{}".format(c)
很显然，上面这一个理由就已经足够让你在以后的项目中使用format了。
新特性
在Python3.6中加入了f-strings：
In[1]: name = "Q1mi"
In[2]: age = 18
In[3]: f"My name is {name}.I'm {age}"
Out[3]: "My name is Q1mi.I'm 18"
常用的format用法
通过位置
In[1]: data = ["Q1mi", 18]
In[2]: "Name:{0}, Age:{1}".format(*data)
Out[2]: 'Name:Q1mi, Age:18'
通过关键字
In[1]: data = {"name": "Q1mi", "age": 18}
In[2]: "Name:{name}, Age:{age}".format(**data)
Out[2]: 'Name:Q1mi, Age:18'
通过对象属性
In[1]: class Person(object):
...: def __init__(self, name, age):
...: self.name = name
...: self.age = age
...: def __str__(self):
...: return "This guy is {self.name}, {self.age} years old.".format(self=self)
...:
In[2]: p = Person("Q1mi", 18)
In[3]: str(p)
Out[3]: 'This guy is Q1mi, 18 years old.'
通过下标
In[1]: "{0[0]} is {0[1]} years old.".format(data)
Out[1]: 'Q1mi is 18 years old.'
填充与对齐
填充常跟对齐一起使用
^、<、>分别是居中、左对齐、右对齐，后面带宽度
:号后面带填充的字符，只能是一个字符，不指定的话默认是用空格填充。
In[1]: "{:>10}".format('18')
Out[1]: ' 18'
In[2]: "{:0>10}".format('18')
Out[2]: '0000000018'
In[3]: "{:A>10}".format('18')
Out[3]: 'AAAAAAAA18
补充一个字符串自带的zfill()方法：
Python zfill()方法返回指定长度的字符串，原字符串右对齐，前面填充0。
zfill()方法语法：str.zfill(width)
参数width指定字符串的长度。原字符串右对齐，前面填充0。
返回指定长度的字符串。
In[1]: "18".zfill(10) Out[1]: '0000000018'
精度与类型f
精度常跟类型f一起使用。
In[1]: "{:.2f}".format(3.1415926)
Out[1]: '3.14'
其中.2表示长度为2的精度，f表示float类型。
其他进制
主要就是进制了，b、d、o、x分别是二进制、十进制、八进制、十六进制。
In[1]: "{:b}".format(18)
Out[1]: '10010'
In[2]: "{:d}".format(18)
Out[2]: '18'
In[3]: "{:o}".format(18)
Out[3]: '22'
In[4]: "{:x}".format(18)
Out[4]: '12'
千位分隔符
In[1]: "{:,}".format(1234567890)
Out[1]: '1,234,567,890'
列表
列表内置函数
class list(object): """ list() -> new empty list list(iterable) -> new list initialized from iterable's items """ def append(self, p_object): # real signature unknown; restored from __doc__ """ L.append(object) -- append object to end """ pass 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) -- 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) -- 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, cmp=None, key=None, reverse=False): # real signature unknown; restored from __doc__ """ L.sort(cmp=None, key=None, reverse=False) -- stable sort *IN PLACE*; cmp(x, y) -> -1, 0, 1 """ pass def __add__(self, y): # real signature unknown; restored from __doc__ """ x.__add__(y) <==> x+y """ pass def __contains__(self, y): # real signature unknown; restored from __doc__ """ x.__contains__(y) <==> y in x """ pass def __delitem__(self, y): # real signature unknown; restored from __doc__ """ x.__delitem__(y) <==> del x[y] """ pass def __delslice__(self, i, j): # real signature unknown; restored from __doc__ """ x.__delslice__(i, j) <==> del x[i:j] Use of negative indices is not supported. """ pass def __eq__(self, y): # real signature unknown; restored from __doc__ """ x.__eq__(y) <==> x==y """ pass def __getattribute__(self, name): # real signature unknown; restored from __doc__ """ x.__getattribute__('name') <==> x.name """ pass def __getitem__(self, y): # real signature unknown; restored from __doc__ """ x.__getitem__(y) <==> x[y] """ pass def __getslice__(self, i, j): # real signature unknown; restored from __doc__ """ x.__getslice__(i, j) <==> x[i:j] Use of negative indices is not supported. """ pass def __ge__(self, y): # real signature unknown; restored from __doc__ """ x.__ge__(y) <==> x>=y """ pass def __gt__(self, y): # real signature unknown; restored from __doc__ """ x.__gt__(y) <==> x>y """ pass def __iadd__(self, y): # real signature unknown; restored from __doc__ """ x.__iadd__(y) <==> x+=y """ pass def __imul__(self, y): # real signature unknown; restored from __doc__ """ x.__imul__(y) <==> x*=y """ pass def __init__(self, seq=()): # known special case of list.__init__ """ list() -> new empty list list(iterable) -> new list initialized from iterable's items # (copied from class doc) """ pass def __iter__(self): # real signature unknown; restored from __doc__ """ x.__iter__() <==> iter(x) """ pass def __len__(self): # real signature unknown; restored from __doc__ """ x.__len__() <==> len(x) """ pass def __le__(self, y): # real signature unknown; restored from __doc__ """ x.__le__(y) <==> x<=y """ pass def __lt__(self, y): # real signature unknown; restored from __doc__ """ x.__lt__(y) <==> x<y """ pass def __mul__(self, n): # real signature unknown; restored from __doc__ """ x.__mul__(n) <==> x*n """ pass @staticmethod # known case of __new__ def __new__(S, *more): # real signature unknown; restored from __doc__ """ T.__new__(S, ...) -> a new object with type S, a subtype of T """ pass def __ne__(self, y): # real signature unknown; restored from __doc__ """ x.__ne__(y) <==> x!=y """ pass def __repr__(self): # real signature unknown; restored from __doc__ """ x.__repr__() <==> repr(x) """ pass def __reversed__(self): # real signature unknown; restored from __doc__ """ L.__reversed__() -- return a reverse iterator over the list """ pass def __rmul__(self, n): # real signature unknown; restored from __doc__ """ x.__rmul__(n) <==> n*x """ pass def __setitem__(self, i, y): # real signature unknown; restored from __doc__ """ x.__setitem__(i, y) <==> x[i]=y """ pass def __setslice__(self, i, j, y): # real signature unknown; restored from __doc__ """ x.__setslice__(i, j, y) <==> x[i:j]=y Use of negative indices is not supported. """ pass def __sizeof__(self): # real signature unknown; restored from __doc__ """ L.__sizeof__() -- size of L in memory, in bytes """ pass __hash__ = None list
定义列表
Python已经内置确定序列的长度以及确定最大和最小的元素的方法。
列表是最常用的Python数据类型，它可以作为一个方括号内的逗号分隔值出现。
列表的数据项不需要具有相同的类型
创建一个列表，只要把逗号分隔的不同的数据项使用方括号括起来即可。如下所示：
names = ['Alex',"Tenglan",'Eric', 123]
通过下标访问列表中的元素，下标从0开始计数
>>> names[0] 'Alex' >>> names[2] 'Eric' >>> names[-1] 123 >>> names[-2] #还可以倒着取 'Eric'
切片（顾头不顾尾）
>>> names = ["Alex","Tenglan","Eric","Rain","Tom","Amy"] >>> names[1:4] #取下标1至下标4之间的数字，包括1，不包括4 ['Tenglan', 'Eric', 'Rain'] >>> names[1:-1] #取下标1至-1的值，不包括-1 ['Tenglan', 'Eric', 'Rain', 'Tom'] >>> names[0:3] ['Alex', 'Tenglan', 'Eric'] >>> names[:3] #如果是从头开始取，0可以忽略，跟上句效果一样 ['Alex', 'Tenglan', 'Eric'] >>> names[:] #取所有 ["Alex", "Tenglan", "Eric", "Rain", "Tom", "Amy"] >>> names[3:] #如果想取最后一个，必须不能写-1，只能这么写 ['Rain', 'Tom', 'Amy'] >>> names[3:-1] #这样-1就不会被包含了 ['Rain', 'Tom'] >>> names[0::2] #后面的2是代表，每隔一个元素，就取一个 ['Alex', 'Eric', 'Tom'] >>> names[::2] #和上句效果一样 ['Alex', 'Eric', 'Tom']
追加
>>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy'] >>> names.append("我是新来的") >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的']
插入
>>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.insert(2,"强行从Eric前面插入") >>> names ['Alex', 'Tenglan', '强行从Eric前面插入', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.insert(5,"从eric后面插入试试新姿势") >>> names ['Alex', 'Tenglan', '强行从Eric前面插入', 'Eric', 'Rain', '从eric后面插入试试新姿势', 'Tom', 'Amy', '我是新来的']
修改
>>> names ['Alex', 'Tenglan', '强行从Eric前面插入', 'Eric', 'Rain', '从eric后面插入试试新姿势', 'Tom', 'Amy', '我是新来的'] >>> names[2] = "该换人了" >>> names ['Alex', 'Tenglan', '该换人了', 'Eric', 'Rain', '从eric后面插入试试新姿势', 'Tom', 'Amy', '我是新来的']
删除
>>> del names[2] >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', '从eric后面插入试试新姿势', 'Tom', 'Amy', '我是新来的'] >>> del names[4] >>> names ['Alex', 'Tenglan', 'Eric', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> >>> names.remove("Eric") #删除指定元素 >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', '我是新来的'] >>> names.pop() #删除列表最后一个值 '我是新来的' >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy']
扩展
>>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy'] >>> b = [1,2,3] >>> names.extend(b) >>> names ['Alex', 'Tenglan', 'Rain', 'Tom', 'Amy', 1, 2, 3]
统计
>>> names ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] >>> names.count("Amy") 2
排序&翻转
>>> names ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] >>> names.sort() #排序 Traceback (most recent call last): File "<stdin>", line 1, in <module> TypeError: unorderable types: int() < str() #3.0里不同数据类型不能放在一起排序了，擦 >>> names[-3] = '1' >>> names[-2] = '2' >>> names[-1] = '3' >>> names ['Alex', 'Amy', 'Amy', 'Tenglan', 'Tom', '1', '2', '3'] >>> names.sort() >>> names ['1', '2', '3', 'Alex', 'Amy', 'Amy', 'Tenglan', 'Tom'] >>> names.reverse() #反转 >>> names ['Tom', 'Tenglan', 'Amy', 'Amy', 'Alex', '3', '2', '1']
获取下标
>>> names ['Tom', 'Tenglan', 'Amy', 'Amy', 'Alex', '3', '2', '1'] >>> names.index("Amy") 2 #只返回找到的第一个下标
拷贝（深浅copy）
浅copy三种实现方式
import copy p = ['alex', 'oldbody', ['tom', 'jack']] p1 = copy.copy(p) p2 = p[:] p3 = list(p)
import copy __date__ = '2018/5/23 11:57' a = 10 b = a a = 200 aa = 'asdf' bb = aa aa = 'qwer' print(a, b) # 200 10 print(aa, bb) # qwer asdf names = ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] name2 = names.copy() # 浅copy,第一层是复制的一份，但是列表内嵌列表存的是地址，浅copy复制的也是地址 print(names) # ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] print(name2) # ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] name2[1] = 'wlx' print(names) # ['Alex', 'Tenglan', 'Amy', 'Tom', 'Amy', 1, 2, 3] print(name2) # ['Alex', 'wlx', 'Amy', 'Tom', 'Amy', 1, 2, 3] name3 = ['Alex', 'Tenglan', 'Amy', ['jack', 'alice'], 'Tom', 'Amy', 1, 2, 3] # 列表内部的列表存的是指针，复制的也是地址 name4 = name3.copy() # 浅copy,第一层是复制的一份，但是列表内嵌列表存的是地址，浅copy复制的也是地址 name3[3][0] = 'JACK chen' print(name3) # ['Alex', 'Tenglan', 'Amy', ['JACK chen', 'alice'], 'Tom', 'Amy', 1, 2, 3] print(name4) # ['Alex', 'Tenglan', 'Amy', ['JACK chen', 'alice'], 'Tom', 'Amy', 1, 2, 3] name3[2] = 'AMY' print(name3) # ['Alex', 'Tenglan', 'AMY', ['JACK chen', 'alice'], 'Tom', 'Amy', 1, 2, 3] print(name4) # ['Alex', 'Tenglan', 'Amy', ['JACK chen', 'alice'], 'Tom', 'Amy', 1, 2, 3] name5 = ['Alex', 'Tenglan', 'Amy', ['jack', 'alice'], 'Tom', 'Amy', 1, 2, 3] name6 = copy.copy(name5) # 也是浅copy，和name5.copy效果一样 name5[3][0] = 'JACK chen' name5[2] = 'AMY' print(name6) # ['Alex', 'Tenglan', 'Amy', ['JACK chen', 'alice'], 'Tom', 'Amy', 1, 2, 3] name7 = ['Alex', 'Tenglan', 'Amy', ['jack', 'alice'], 'Tom', 'Amy', 1, 2, 3] name8 = copy.deepcopy(name7) # 深copy完全复制一封独立的 name7[3][0] = 'JACK chen' name7[2] = 'AMY' print(name8) # ['Alex', 'Tenglan', 'Amy', ['jack', 'alice'], 'Tom', 'Amy', 1, 2, 3]
列表脚本操作符
列表对 + 和 * 的操作符与字符串相似。+ 号用于组合列表，* 号用于重复列表。如下所示：
| Python 表达式 | 结果 | 描述 |
|---|---|---|
| len([1, 2, 3]) | 3 | 长度 |
| [1, 2, 3] + [4, 5, 6] | [1, 2, 3, 4, 5, 6] | 组合 |
| ['Hi!'] * 4 | ['Hi!', 'Hi!', 'Hi!', 'Hi!'] | 重复 |
| 3 in [1, 2, 3] | True | 元素是否存在于列表中 |
| for x in [1, 2, 3]: print x, | 1 2 3 | 迭代 |
python内置函数的列表使用效果
| 序号 | 函数 |
|---|---|
| 1 | cmp(list1, list2) 比较两个列表的元素 |
| 2 | len(list) 列表元素个数 |
| 3 | max(list) 返回列表元素最大值 |
| 4 | min(list) 返回列表元素最小值 |
| 5 | list(seq) 将元组转换为列表 |
元组
Python的元组与列表类似，不同之处在于元组的元素不能修改。（有序）
单纯的元组不能修改，但是元组内部若是有列表等，元素的元素如果是可变的就可以修改可变的元素
a = (1,['alex', 'abc123', '24' ]) >>> type(a) <class 'tuple'> >>> a[1][0] = 'ALEX' >>> print(a) (1, ['ALEX', 'abc123', '24']) >>> a[0] = 122 Traceback (most recent call last): File "<stdin>", line 1, in <module> TypeError: 'tuple' object does not support item assignment
元组使用小括号，列表使用方括号。
元组创建很简单，只需要在括号中添加元素，并使用逗号隔开即可。
lass tuple(object): """ tuple() -> empty tuple tuple(iterable) -> tuple initialized from iterable's items If the argument is a tuple, the return value is the same object. """ 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 def __add__(self, y): # real signature unknown; restored from __doc__ """ x.__add__(y) <==> x+y """ pass def __contains__(self, y): # real signature unknown; restored from __doc__ """ x.__contains__(y) <==> y in x """ pass def __eq__(self, y): # real signature unknown; restored from __doc__ """ x.__eq__(y) <==> x==y """ pass def __getattribute__(self, name): # real signature unknown; restored from __doc__ """ x.__getattribute__('name') <==> x.name """ pass def __getitem__(self, y): # real signature unknown; restored from __doc__ """ x.__getitem__(y) <==> x[y] """ pass def __getnewargs__(self, *args, **kwargs): # real signature unknown pass def __getslice__(self, i, j): # real signature unknown; restored from __doc__ """ x.__getslice__(i, j) <==> x[i:j] Use of negative indices is not supported. """ pass def __ge__(self, y): # real signature unknown; restored from __doc__ """ x.__ge__(y) <==> x>=y """ pass def __gt__(self, y): # real signature unknown; restored from __doc__ """ x.__gt__(y) <==> x>y """ pass def __hash__(self): # real signature unknown; restored from __doc__ """ x.__hash__() <==> hash(x) """ pass def __init__(self, seq=()): # known special case of tuple.__init__ """ tuple() -> empty tuple tuple(iterable) -> tuple initialized from iterable's items If the argument is a tuple, the return value is the same object. # (copied from class doc) """ pass def __iter__(self): # real signature unknown; restored from __doc__ """ x.__iter__() <==> iter(x) """ pass def __len__(self): # real signature unknown; restored from __doc__ """ x.__len__() <==> len(x) """ pass def __le__(self, y): # real signature unknown; restored from __doc__ """ x.__le__(y) <==> x<=y """ pass def __lt__(self, y): # real signature unknown; restored from __doc__ """ x.__lt__(y) <==> x<y """ pass def __mul__(self, n): # real signature unknown; restored from __doc__ """ x.__mul__(n) <==> x*n """ pass @staticmethod # known case of __new__ def __new__(S, *more): # real signature unknown; restored from __doc__ """ T.__new__(S, ...) -> a new object with type S, a subtype of T """ pass def __ne__(self, y): # real signature unknown; restored from __doc__ """ x.__ne__(y) <==> x!=y """ pass def __repr__(self): # real signature unknown; restored from __doc__ """ x.__repr__() <==> repr(x) """ pass def __rmul__(self, n): # real signature unknown; restored from __doc__ """ x.__rmul__(n) <==> n*x """ pass def __sizeof__(self): # real signature unknown; restored from __doc__ """ T.__sizeof__() -- size of T in memory, in bytes """ pass tuple
创建元组
tup1 = ('physics', 'chemistry', 1997, 2000) tup2 = (1, 2, 3, 4, 5 ) tup3 = "a", "b", "c", "d #创建空元组 tup1 = () # 元组中只包含一个元素时，需要在元素后面添加逗号 tup1 = (50,)
字典
字典的每个键值 key=>value 对用冒号 : 分割，每个键值对之间用逗号 , 分割，整个字典包括在花括号 {} 中
键一般是唯一的，如果重复最后的一个键值对会替换前面的，值不需要唯一。
值可以取任何数据类型，但键必须是不可变的，如字符串，数字或元组。
dir1 = {'a': '1', 'b': '2', 'c': '3', 'a': '3'}
print(dir1)
person = dict({"name": "mr.wu", 'age': 18})
class dict(object): """ dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2) """ def clear(self): # real signature unknown; restored from __doc__ """ 清除内容 """ """ D.clear() -> None. Remove all items from D. """ pass def copy(self): # real signature unknown; restored from __doc__ """ 浅拷贝 """ """ D.copy() -> a shallow copy of D """ pass @staticmethod # known case def fromkeys(S, v=None): # real signature unknown; restored from __doc__ """ dict.fromkeys(S[,v]) -> New dict with keys from S and values equal to v. v defaults to None. """ pass def get(self, k, d=None): # real signature unknown; restored from __doc__ """ 根据key获取值，d是默认值 """ """ D.get(k[,d]) -> D[k] if k in D, else d. d defaults to None. """ pass def has_key(self, k): # real signature unknown; restored from __doc__ """ 是否有key """ """ D.has_key(k) -> True if D has a key k, else False """ return False def items(self): # real signature unknown; restored from __doc__ """ 所有项的列表形式 """ """ D.items() -> list of D's (key, value) pairs, as 2-tuples """ return [] def iteritems(self): # real signature unknown; restored from __doc__ """ 项可迭代 """ """ D.iteritems() -> an iterator over the (key, value) items of D """ pass def iterkeys(self): # real signature unknown; restored from __doc__ """ key可迭代 """ """ D.iterkeys() -> an iterator over the keys of D """ pass def itervalues(self): # real signature unknown; restored from __doc__ """ value可迭代 """ """ D.itervalues() -> an iterator over the values of D """ pass def keys(self): # real signature unknown; restored from __doc__ """ 所有的key列表 """ """ D.keys() -> list of D's keys """ return [] def pop(self, k, d=None): # real signature unknown; restored from __doc__ """ 获取并在字典中移除 """ """ 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__ """ 获取并在字典中移除 """ """ 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__ """ 如果key不存在，则创建，如果存在，则返回已存在的值且不修改 """ """ 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 """ 更新 {'name':'alex', 'age': 18000} [('name','sbsbsb'),] """ """ D.update([E, ]**F) -> None. Update D from dict/iterable E and F. If E present and has a .keys() method, does: for k in E: D[k] = E[k] If E present and lacks .keys() method, 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__ """ 所有的值 """ """ D.values() -> list of D's values """ return [] def viewitems(self): # real signature unknown; restored from __doc__ """ 所有项，只是将内容保存至view对象中 """ """ D.viewitems() -> a set-like object providing a view on D's items """ pass def viewkeys(self): # real signature unknown; restored from __doc__ """ D.viewkeys() -> a set-like object providing a view on D's keys """ pass def viewvalues(self): # real signature unknown; restored from __doc__ """ D.viewvalues() -> an object providing a view on D's values """ pass def __cmp__(self, y): # real signature unknown; restored from __doc__ """ x.__cmp__(y) <==> cmp(x,y) """ pass def __contains__(self, k): # real signature unknown; restored from __doc__ """ D.__contains__(k) -> True if D has a key k, else False """ return False def __delitem__(self, y): # real signature unknown; restored from __doc__ """ x.__delitem__(y) <==> del x[y] """ pass def __eq__(self, y): # real signature unknown; restored from __doc__ """ x.__eq__(y) <==> x==y """ pass def __getattribute__(self, name): # real signature unknown; restored from __doc__ """ x.__getattribute__('name') <==> x.name """ pass def __getitem__(self, y): # real signature unknown; restored from __doc__ """ x.__getitem__(y) <==> x[y] """ pass def __ge__(self, y): # real signature unknown; restored from __doc__ """ x.__ge__(y) <==> x>=y """ pass def __gt__(self, y): # real signature unknown; restored from __doc__ """ x.__gt__(y) <==> x>y """ pass def __init__(self, seq=None, **kwargs): # known special case of dict.__init__ """ dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object's (key, value) pairs dict(iterable) -> new dictionary initialized as if via: d = {} for k, v in iterable: d[k] = v dict(**kwargs) -> new dictionary initialized with the name=value pairs in the keyword argument list. For example: dict(one=1, two=2) # (copied from class doc) """ pass def __iter__(self): # real signature unknown; restored from __doc__ """ x.__iter__() <==> iter(x) """ pass def __len__(self): # real signature unknown; restored from __doc__ """ x.__len__() <==> len(x) """ pass def __le__(self, y): # real signature unknown; restored from __doc__ """ x.__le__(y) <==> x<=y """ pass def __lt__(self, y): # real signature unknown; restored from __doc__ """ x.__lt__(y) <==> x<y """ pass @staticmethod # known case of __new__ def __new__(S, *more): # real signature unknown; restored from __doc__ """ T.__new__(S, ...) -> a new object with type S, a subtype of T """ pass def __ne__(self, y): # real signature unknown; restored from __doc__ """ x.__ne__(y) <==> x!=y """ pass def __repr__(self): # real signature unknown; restored from __doc__ """ x.__repr__() <==> repr(x) """ pass def __setitem__(self, i, y): # real signature unknown; restored from __doc__ """ x.__setitem__(i, y) <==> x[i]=y """ pass def __sizeof__(self): # real signature unknown; restored from __doc__ """ D.__sizeof__() -> size of D in memory, in bytes """ pass __hash__ = None dict
字典的特性：
- dict是无序的
- key必须是唯一的,so 天生去重
- 字典值可以没有限制地取任何python对象，既可以是标准的对象，也可以是用户定义的，但键不行。
增加
info = {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1101': 'wutenglan'}
info['stu1104'] = "武藤兰"
info.setdefault('stu1101', 'wusir') # setdefault() 如果key原来有，则不变原来的值，否则加一个键值对
info.setdefault('stu1105', 'wusir1')
print(info)
修改
>>> info['stu1101'] = "武藤兰" >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1101': '武藤兰'}
删除
>>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya', 'stu1101': '武藤兰'} >>> info.pop("stu1101") #标准删除姿势 '武藤兰' >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} >>> del info['stu1103'] #换个姿势删除 >>> info {'stu1102': 'LongZe Luola'} >>> >>> >>> >>> info = {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} >>> info {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'} #随机删除 >>> info.popitem() ('stu1102', 'LongZe Luola') >>> info {'stu1103': 'XiaoZe Maliya'}
查找
>>> info = {'stu1102': 'LongZe Luola', 'stu1103': 'XiaoZe Maliya'}
>>>
>>> "stu1102" in info #标准用法
True
>>> info.get("stu1102") #获取
'LongZe Luola'
>>> info["stu1102"] #同上，但是看下面
'LongZe Luola'
>>> info["stu1105"] #如果一个key不存在，就报错，get不会，不存在只返回None
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
KeyError: 'stu1105'
多级字典嵌套
av_catalog = { "欧美":{ "www.youporn.com": ["很多免费的,世界最大的","质量一般"], "www.pornhub.com": ["很多免费的,也很大","质量比yourporn高点"], "letmedothistoyou.com": ["多是自拍,高质量图片很多","资源不多,更新慢"], "x-art.com":["质量很高,真的很高","全部收费,屌比请绕过"] }, "日韩":{ "tokyo-hot":["质量怎样不清楚,个人已经不喜欢日韩范了","听说是收费的"] }, "大陆":{ "1024":["全部免费,真好,好人一生平安","服务器在国外,慢"] } } av_catalog["大陆"]["1024"][1] += ",可以用爬虫爬下来" print(av_catalog["大陆"]["1024"]) #ouput ['全部免费,真好,好人一生平安', '服务器在国外,慢,可以用爬虫爬下来']
循环字典
#方法1 for key in info: print(key,info[key]) #方法2 for k,v in info.items(): #会先把dict转成list,数据里大时莫用 print(k,v)
字典的访问：dic.get() 方法和 dic[key] 方法的不同，建议使用dic.get()
这两种方法都是用来获取字典中 key 对应的 value，一般情况下似乎没有什么区别：
但是若是不知道字典中有哪些key，用dic[key]访问时，若key不存在会报错，而dic.get() 不会报错
如果程序中抛出了任何 Error 就意味着一件件事情，我们的程序要停止运行了。这在正式程序中是大家都不愿意看到的。
而且在时间上尽管dic.get() 会慢一些，但是并不明显
注意，get方法返回值是可能int或者字符串常量，不能对get的返回值进行赋值操作，用get要先将返回值赋值给变量
集合
可以使用大括号 { } 或者 set() 函数创建集合，注意：创建一个空集合必须用 set() 而不是 { }，因为 { } 是用来创建一个空字典。
创建格式：
集合是一个无序的，不重复的数据组合，它的主要作用如下：
- 去重，把一个列表变成集合，就自动去重了
- 关系测试，测试两组数据之前的交集、差集、并集等关系
常用操作
s = set([3,5,9,10]) #创建一个数值集合 >>> type(s) <class 'set'> t = set("Hello") #创建一个唯一字符的集合 a = t | s # t 和 s的并集 b = t & s # t 和 s的交集 c = t – s # 求差集（项在t中，但不在s中） d = t ^ s # 对称差集（项在t或s中，但不会同时出现在二者中） 基本操作： t.add('x') # 添加一项 s.update([10,37,42]) # 在s中添加多项 使用remove()可以删除一项： t.remove('H') len(s) set 的长度 x in s 测试 x 是否是 s 的成员 x not in s 测试 x 是否不是 s 的成员 s.issubset(t) s <= t 测试是否 s 中的每一个元素都在 t 中 s.issuperset(t) s >= t 测试是否 t 中的每一个元素都在 s 中 s.union(t) s | t 返回一个新的 set 包含 s 和 t 中的每一个元素 s.intersection(t) s & t 返回一个新的 set 包含 s 和 t 中的公共元素 s.difference(t) s - t 返回一个新的 set 包含 s 中有但是 t 中没有的元素 s.symmetric_difference(t) s ^ t 返回一个新的 set 包含 s 和 t 中不重复的元素 s.copy() 返回 set “s”的一个浅复制
基本数据类型总结
列表：有序，可重复，[ ]括起来
元组：原则上不可修改，有序，可重复，（）括起来
字典：无序，不可重复，{ }键值对
集合：无序，不重复，{1，2，3}表示
数据类型转换
元组转列表
tuple(seq)将列表转换为元组。>>> list1= ['Google', 'Taobao', 'Runoob', 'Baidu'] >>> tuple1=tuple(list1) >>> tuple1 ('Google', 'Taobao', 'Runoob', 'Baidu')
列表转元组
list(seq)将元组转换为列表aTuple = (123, 'Google', 'Runoob', 'Taobao') list1 = list(aTuple) print ("列表元素 : ", list1) #[123, 'Google', 'Runoob', 'Taobao']
列表转字符串
>>> list1=['ak','uk',4] >>> list2=[str(i) for i in list1] #使用列表推导式把列表中的单个元素全部转化为str类型 # 不转化会报错，join只能连字符串 >>> list2 #查看转化后的列表 ['ak', 'uk', '4'] >>> list3=' '.join(list2) #把列表中的元素放在空串中，元素间用空格隔开 >>> list3 #查看生成的长串 'ak uk 4'
字符串转列表
str="Hello World" list2=list(str) print ("列表元素 : ", list2) # ['H', 'e', 'l', 'l', 'o', ' ', 'W', 'o', 'r', 'l', 'd']
法2
str1 = "hi hello world"
print(str1.split(" "))
输出：
['hi', 'hello', 'world']
字典转字符串
mydic = {"俄罗斯": {"1":"圣彼得堡", "2":"叶卡捷琳堡", "3":"莫斯科", "4":"喀山"}}
mystr = str(mydic)
print (type(mystr))
输出结果如下：
字符串转字典
在工作中遇到一个小问题，需要将一个 python 的字符串转为字典，比如字符串：
user_info = '{"name" : "john", "gender" : "male", "age": 28}'
我们想把它转为下面的字典：
user_dict = {"name" : "john", "gender" : "male", "age": 28}
有以下几种方法：
1、通过 json 来转换
>>> import json
>>> user_info= '{"name" : "john", "gender" : "male", "age": 28}'
>>> user_dict = json.loads(user_info)
>>> user_dict
{u'gender': u'male', u'age': 28, u'name': u'john'}
但是使用 json 进行转换存在一个潜在的问题。
由于 json 语法规定 数组或对象之中的字符串必须使用双引号，不能使用单引号 (官网上有一段描述是 “A string is a sequence of zero or more Unicode characters, wrapped in double quotes, using backslash escapes” )，因此下面的转换是错误的：
>>> import json
>>> user_info = "{'name' : 'john', 'gender' : 'male', 'age': 28}"
# 由于字符串使用单引号，会导致运行出错
>>> user_dict = json.loads(user_info)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/__init__.py", line 339, in loads
return _default_decoder.decode(s)
File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 364, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/usr/local/Cellar/python/2.7.11/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 380, in raw_decode
obj, end = self.scan_once(s, idx)
ValueError: Expecting property name: line 1 column 2 (char 1)
2、通过 eval
>>> user_info = '{"name" : "john", "gender" : "male", "age": 28}'
>>> user_dict = eval(user_info)
>>> user_dict
{'gender': 'male', 'age': 28, 'name': 'john'}
>>> user_info = "{'name' : 'john', 'gender' : 'male', 'age': 28}"
>>> user_dict = eval(user_info)
>>> user_dict
{'gender': 'male', 'age': 28, 'name': 'john'}
通过 eval 进行转换就不存在上面使用 json 进行转换的问题。但是，使用 eval 却存在安全性的问题，比如下面的例子:
# 让用户输入 `user_info`
>>> user_info = raw_input('input user info: ')
# 输入 {"name" : "john", "gender" : "male", "age": 28}，没问题
>>> user_dict = eval(user_info)
# 输入 __import__('os').system('dir')，user_dict 会列出当前的目录文件！
# 再输入一些删除命令，则可以把整个目录清空了！
>>> user_dict = eval(user_info)
3、通过 literal_eval
>>> import ast
>>> user = '{"name" : "john", "gender" : "male", "age": 28}'
>>> user_dict = ast.literal_eval(user)
>>> user_dict
{'gender': 'male', 'age': 28, 'name': 'john'}
user_info = "{'name' : 'john', 'gender' : 'male', 'age': 28}"
>>> user_dict = ast.literal_eval(user)
>>> user_dict
{'gender': 'male', 'age': 28, 'name': 'john'}
使用 ast.literal_eval 进行转换既不存在使用 json 进行转换的问题，也不存在使用 eval 进行转换的 安全性问题，因此推荐使用 ast.literal_eval。
