Python 2 or Python 3 ?
看代码之前先欣赏一下美女舒缓一下内心
Python编码
转码思路
字符串在Python内部的表示是unicode编码,在编码转换时通常需要以unicode作为中间编码。
先将其他编码的字符串解码(decode)成unicode,再从unicode编码(encode)成另一种编码。
转码举例
s.decode('utf-8', 'ignore').encode('gbk', 'ignore')
先由utf-8转为unicode,再由unicode转为gbk,ignore表示忽略非法字符
s = u'中文' # s为unicode print isinstance(s, unicode) # True print s.encode('utf-8', 'ignore') # 中文 # 由unicode转为utf-8,ignore表示忽略非法字符
异常处理
try-except-finall结构
import traceback try: xxx except Exception, e: print e print traceback.format_exc() raise finally: print 'end'
记录错误
import logging except StandardError, e: logging.exception(e)
字符串
不可变类型
>>> a = 'abc' >>> a 'abc' >>> b = a.replace('a', 'A') >>> a 'abc' >>> b 'Abc'
带关键字与不带关键字的格式化
>>> 'Hello %(name)s !' % {'name': 'James'} 'Hello James !' >>> 'Hello %s !' % 'James' 'Hello James !' >>> 'Hello {name} !'.format(name='James') 'Hello James !' >>> 'Hello {} !'.format('James') 'Hello James !'
列表
列表是由一系列元素组成的有序的序列。
append与extend
list1.append(xxx) # 表示在list1后添加元素xxx list1.extend(list2) # 表示在list1后添加序列list2
zip函数
>>> list1 = ['a', 'b'] >>> list2 = ['1', '2'] >>> zip(list1, list2) [('a', '1'), ('b', '2')] >>> zip(*[list1, list2]) [('a', '1'), ('b', '2')]
enumerate函数:把list变成'索引-元素'对
>>> word = ['c', 'b', 'd', 'a'] >>> word.sort() >>> word ['a', 'b', 'c', 'd'] >>> for i, value in enumerate(word): print i, value 0 a 1 b 2 c 3 d
enumerate函数实现
def enumerate(sequence, start=0): n = start for elem in sequence: yield n, elem n += 1
列表去重
>>> l = [1, 2, 4, 7, 2, 1, 8, 6, 1] >>> list(set(l)) # 不保证顺序 [1, 2, 4, 6, 7, 8] >>> sorted(list(set(l)), reverse=True) # 顺序 [8, 7, 6, 4, 2, 1] >>> {}.fromkeys(l).keys() # 不保证顺序 [1, 2, 4, 6, 7, 8] >>> from collections import OrderedDict >>> OrderedDict().fromkeys(l).keys() # 按照原有序列顺序 [1, 2, 4, 7, 8, 6]
列表推导式
>>> [x*x for x in range(10)] # 一层循环 [0, 1, 4, 9, 16, 25, 36, 49, 64, 81] >>> [m + n for m in 'ABC' for n in 'XYZ'] # 两层循环 ['AX', 'AY', 'AZ', 'BX', 'BY', 'BZ', 'CX', 'CY', 'CZ']
引用、浅复制、深复制
>>> import copy >>> l = [0, [1, 2], 3] >>> l1 = l # 引用 >>> l2 = l[:] # 浅复制 >>> l3 = copy.copy(l) # 浅复制 >>> l4 = copy.deepcopy(l) # 深复制 >>> l [0, [1, 2], 3] >>> l1, l2, l3, l4 ([0, [1, 2], 3], [0, [1, 2], 3], [0, [1, 2], 3], [0, [1, 2], 3]) >>> l[0] = 9 >>> l [9, [1, 2], 3] >>> l1, l2, l3, l4 ([9, [1, 2], 3], [0, [1, 2], 3], [0, [1, 2], 3], [0, [1, 2], 3]) >>> l[1][1] = 9 >>> l [9, [1, 9], 3] >>> l1, l2, l3, l4 ([9, [1, 9], 3], [0, [1, 9], 3], [0, [1, 9], 3], [0, [1, 2], 3])
is 与 ==
is 比较两个对象的标识(引用)
== 比较两个对象的值(内容)
>>> a = [1, 2, 3] >>> b = a >>> b is a True >>> b == a True >>> b = a[:] >>> b is a False >>> b == a True def fib1(max_num): L = [] n, a, b = 0, 0, 1 while n < max_num: L.append(b) a, b = b, a + b n += 1 return L
迭代器 iterator
__iter__()方法:返回迭代器对象本身。
next()方法:返回迭代器的下一个对象。
生成器 generator
g = (x*x for x in range(5)) # generator
yield
迭代器实现Fibonacci数列
class fib2(object): def __init__(self, max_num): self.max_num = max_num self.n, self.a, self.b = 0, 0, 1 def __iter__(self): return self def next(self): if self.n < self.max_num: r = self.b self.a, self.b = self.b, self.a + self.b self.n += 1 return r raise StopIteration()
生成器实现Fibonacci数列
def fib3(max_num): n, a, b = 0, 0, 1 while n < max_num: yield b a, b = b, a + b n += 1 >>> g_gen = fib3(10) >>> g_gen <generator object fib3 at 0x0000000002716678> >>> for i in g_gen: print i 1 1 2 3 5 8 13 21 34 55
协程 coroutine
生成器是数据的生产者,协程则是数据的消费者。
def my_coroutine(a=None): print 'coroutine start...' while True: f = (yield a) print 'result: {}'.format(f) >>> c = my_coroutine() >>> next(c) coroutine start... >>> c.send('first') result: first >>> c.send('second') result: second >>> c.close()
元组
元组是只读的列表,不能对其修改。
定义一个只有1个元素的tuple:
建议
t = ('xxx',)
不建议,为什么?
t = ('xxx')
字典
字典是由键key和值value的对应组合成的无序的序列。
字典构造
>>> dict([('a', '1'), ('b', '2')]) {'a': '1', 'b': '2'} >>> dict.fromkeys(['a', 'b'], 1) {'a': 1, 'b': 1} >>> dict.fromkeys('ab', 1) {'a': 1, 'b': 1} >>> {'a':'1', 'b':'2'} {'a': '1', 'b': '2'} >>> dict(zip(['a', 'b'], ['1', '2'])) {'a': '1', 'b': '2'} >>> dict([('a', '1'), ('b', '2')]) {'a': '1', 'b': '2'} >>> dict(a='1', b='2') {'a': '1', 'b': '2'} >>> dict(a=1, b=2) {'a': 1, 'b': 2}
判断一个字典是否有某个key
key in Dict Dict.has_key(key)
获得指定key的值
Dict.get(key, default) # 如果没有key,返回default值,在Dict中不添加该键值。 Dict.setdefault(key, default) # 如果没有key,返回default值,并且在Dict中添加该键值。 Dict[key] # 如果没有key,返回error。
items(), keys(), values()
>>> Dict = {'a':1, 'b':2, 'c':3, 'd':4} >>> Dict.items() [('a', 1), ('c', 3), ('b', 2), ('d', 4)] >>> Dict.keys() ['a', 'c', 'b', 'd'] >>> Dict.values() [1, 3, 2, 4] >>> Dict.iteritems() <dictionary-itemiterator object at 0x0000000002BBACC8> >>> for k, v in Dict.iteritems(): print k, v a 1 c 3 b 2 d 4 >>> Dict.iterkeys() <dictionary-keyiterator object at 0x0000000002BBACC8> >>> Dict.itervalues() <dictionary-valueiterator object at 0x0000000002BBAD18> >>> dct = dict() >>> dct['foo'] Traceback (most recent call last): File "<pyshell#55>", line 1, in <module> dct['foo'] KeyError: 'foo'
特殊方法 __missing__
class Dict(dict): def __missing__(self, key): ## 当查找不到key的时候,会执行该方法 self[key] = [] return self[key] >>> dct = Dict() >>> dct['foo'] []
按照values值进行降序排列
>>> x = {'a': 2, 'b': 4, 'c': 3, 'd': 1, 'e': 0} >>> x.items() [('a', 2), ('c', 3), ('b', 4), ('e', 0), ('d', 1)]
方法1
>>> sorted_x = sorted(x.items(), key=lambda xx:xx[1], reverse=True) >>> sorted_x [('b', 4), ('c', 3), ('a', 2), ('d', 1), ('e', 0)]
方法2
>>> sorted_x = x.items() >>> sorted_x.sort(key=lambda xx:xx[1], reverse=True) >>> sorted_x [('b', 4), ('c', 3), ('a', 2), ('d', 1), ('e', 0)]
合并字典
def merge(ds): r = {} for d in ds: for k in d: if k in r: r[k] += d.get(k) else: r[k] = d.get(k) return r >>> d1 = {'a':1, 'b':2, 'c':3} >>> d2 = {'b':4, 'd':5, 'e':6} >>> d3 = {'b':3, 'c':1, 'e':1} >>> d = merge([d1, d2, d3]) >>> d {'a': 1, 'c': 4, 'b': 9, 'e': 7, 'd': 5}
集合
集合与字典类似,也是一组key的集合,但不存储value。
集合构造
>>> set(['a', 'b', 'c']) set(['a', 'c', 'b']) >>> set('abc') set(['a', 'c', 'b']) >>> {'a', 'b', 'c'} set(['a', 'c', 'b'])
交集、并集、差集、对称差集
x.intersection(y) 或 x&y x.union(y) 或 x|y x.difference(y) 或 x-y x.symmetric_difference(y) 或 x^y
类与对象
普通继承
class Bird(object): def __init__(self): self.hungry = True def eat(self): if self.hungry: print 'Aaaah...' self.hungry = False else: print 'No, thanks!' class SongBird(Bird): def sing(self): pass >>> s = SongBird() >>> s.sing() >>> s.eat() Aaaah... >>> s.eat() No, thanks!
super继承
class SongBird(Bird): def __init__(self): self.sound = 'Squawk!' def sing(self): print self.sound >>> s = SongBird() >>> s.sing() Squawk! >>> s.eat() Traceback (most recent call last): File "<pyshell#67>", line 1, in <module> s.eat() File "<pyshell#53>", line 5, in eat if self.hungry: AttributeError: 'SongBird' object has no attribute 'hungry'
super继承
class SongBird(Bird): def __init__(self): # Bird.__init__(self) super(SongBird, self).__init__() self.sound = 'Squawk!' def sing(self): print self.sound >>> s = SongBird() >>> s.sing() Squawk! >>> s.eat() Aaaah... >>> s.eat() No, thanks!
直接调用内部属性
class Student(object): def __init__(self, name, score): self.name = name self.score = score >>> s = Student('Bart', 59) >>> s.score 59 >>> s.score = 60 >>> '%s: %s' % (s.name, s.score) 'Bart: 60'
通过类成员访问内部属性
class Student(object): def __init__(self, name, score): self._name = name self._score = score def get_score(self): return self._score def set_score(self, value): self._score = value def print_score(self): print '%s: %s' % (self._name, self._score) >>> s = Student('Bart', 59) >>> s.get_score() 59 >>> s.set_score(60) >>> s.print_score() Bart: 60
@property与property()
class Student(object): def __init__(self, name, score): self._name = name self._score = score @property def score(self): return self._score @score.setter def score(self, value): self._score = value @score.deleter def score(self): del self._score >>> s = Student('Bart', 59) >>> s.score 59 >>> s.score = 60 >>> s.score 60 >>> del s.score
@property与property()
class Student(object): def __init__(self, name, score): self._name = name self._score = score def get_score(self): return self._score def set_score(self, value): self._score = value def del_score(self): del self._score score = property(get_score, set_score, del_score) >>> s = Student('Bart', 59) >>> s.score 59 >>> s.score = 60 >>> s.score 60 >>> del s.score
动态绑定
from types import MethodType class Student(object): pass def set_age(self, age): self.age = age def set_score(self, score): self.score = score >>> s = Student() >>> s.name = 'Michael' >>> s.name 'Michael' >>> s.set_age = MethodType(set_age, s, Student) >>> s.set_age(25) >>> s.age 25 >>> Student.set_score = MethodType(set_score, None, Student) >>> s.set_score(100) >>> s.score 100
限制变量 __slots__
from types import MethodType class Student(object): __slots__ = ('name', 'age', 'set_age') >>> s = Student() >>> s.name = 'Michael' >>> s.name 'Michael' >>> s.set_age = MethodType(set_age, s, Student) >>> s.set_age(25) >>> s.age 25 >>> Student.set_score = MethodType(set_score, None, Student) >>> s.set_score(100) Traceback (most recent call last): File "<pyshell#136>", line 1, in <module> s.set_score(100) File "<pyshell#120>", line 2, in set_score self.score = score AttributeError: 'Student' object has no attribute 'score'
type 动态创建类
def __init__(cls, func): cls.func = func def hello(cls): print 'hello world' Hello = type('Hello', (object,), {'__init__':__init__, 'hello':hello}) >>> h = Hello(lambda a, b: a+b) >>> h.hello() hello world >>> type(Hello) <type 'type'> >>> type(h) <class '__main__.Hello'>
元类 __metaclass__ 动态创建类
class HelloMeta(type): def __new__(cls, name, bases, dct): def __init__(cls, func): cls.func = func def hello(cls): print 'hello world' # t = type.__new__(cls, name, bases, dct) t = super(HelloMeta, cls).__new__(cls, name, bases, dct) t.__init__ = __init__ t.hello = hello return t class New_Hello(object): __metaclass__ = HelloMeta >>> h = New_Hello(lambda a, b: a+b) >>> h.hello() hello world >>> type(New_Hello) <class '__main__.HelloMeta'> >>> type(h) <class '__main__.New_Hello'>
魔法方法 Magic Method
会话管理器
enter:定义当使用with语句定义一个代码块时会话管理器应该做什么。
exit:定义当一个代码块被执行或者终止后会话管理器应该做什么。
class FileObject(object): def __init__(self, filepath='sample.txt'): self.file = open(filepath, 'r+') def __enter__(self): # 与with语句对应 return self.file def __exit__(self, exc_type, exc_val, exc_tb): self.file.close() del self.file with FileObject() as fp: print fp.read()
对象的魔法方法
getattr:查询不在dict系统中的对象属性或者对象方法。
class A(object): def __getattr__(self, attr): def _(*args, **kw): print args, kw return _ pass >>> a = A() >>> a.xxx <function _ at 0x0000000002C05F28> >>> a.xxx1(1, 2, key='ssss') (1, 2) {'key': 'ssss'} >>> a.xxx2(1, 2) (1, 2) {} >>> a.xxx3(1, 2, 3) (1, 2, 3) {}
魔法方法举例
class Student(object): def __init__(self, name): self.name = name def __str__(self): return 'Student object (name: %s)' % self.name def __call__(self): print 'Student object (name: %s)' % self.name def __getattr__(self, attr): if attr == 'score': return 99 else: def func(*args, **kw): return args, kw return func
魔法方法举例
>>> print(s) # 调用__str__方法 Student object (name: Michael) >>> s() # 调用__call__方法 Student object (name: Michael) >>> s.name # 调用存在的属性name 'Michael' >>> s.score # 调用不存在的属性score 99 >>> s.score1 # 调用不存在的属性score1 <function func at 0x0000000002B3E9E8> >>> s.function(1, 2, 3) # 调用不存在的方法function ((1, 2, 3), {})
函数的参数传递
参数定义
在函数调用的时候,Python解释器自动按照参数位置和参数名把对应的参数传进去。
def func(a, b, c=0, *args, **kw): print 'a =', a, 'b =', b, 'c =', c, \ 'args =', args, 'kw =', kw >>> func(1, 2) a = 1 b = 2 c = 0 args = () kw = {} >>> func(1, 2, c=3) a = 1 b = 2 c = 3 args = () kw = {} >>> func(1, 2, 3, 'a', 'b') a = 1 b = 2 c = 3 args = ('a', 'b') kw = {} >>> func(1, 2, 3, 'a', 'b', x=99) a = 1 b = 2 c = 3 args = ('a', 'b') kw = {'x': 99} >>> args = (1, 2, 3, 4) >>> kw = {'x': 99} >>> func(*args, **kw) a = 1 b = 2 c = 3 args = (4,) kw = {'x': 99}
默认参数
默认参数必须为不可变对象,如None,string,tuple,不可为list类型。
def add_end(L=[]): L.append('END') return L >>> add_end() ['END'] >>> add_end() ['END', 'END'] >>> add_end() ['END', 'END', 'END']
改为
def add_end(L=None): if L is None: L = [] L.append('END') return L
可变参数
任意函数都可以表示成func(*args, **kw)形式。
def func(a, b, c): print a, b, c >>> l = [1, 2, 3] >>> d = {'a':1, 'b':2, 'c':3} >>> func(*l) 1 2 3 >>> func(**d) 1 2 3
函数式编程
lambda函数
可以动态生成一个函数对象,但该函数只能有一个表达式。
f = lambda x: x*x def f(x): return x*x
map(), reduce(), filter()
>>> range(0,10) [0, 1, 2, 3, 4, 5, 6, 7, 8, 9] >>> map(lambda x:x*2, range(0,10)) [0, 2, 4, 6, 8, 10, 12, 14, 16, 18] >>> reduce(lambda x,y:x*10+y, range(0,10)) 123456789 >>> filter(lambda x:x%2==0, range(0,10)) [0, 2, 4, 6, 8]
偏函数 partial
不需要定义新的函数,把函数的某些参数固定,返回一个新的函数。
实现sequence的加法和乘法
>>> from functools import partial >>> import operator >>> l = [i for i in range(1, 10)] >>> l [1, 2, 3, 4, 5, 6, 7, 8, 9] >>> sum = partial(reduce, operator.add) >>> sum(l) 45 >>> product = partial(reduce, operator.mul) >>> product(l) 362880
闭包 closure
指延伸了作用域的函数,它能访问定义体之外定义的环境变量,这个函数和它的环境变量合在一起,就构成了一个闭包。
def lazy_sum(*args): def sum(x=0): # sum函数和变量args构成闭包 ax = x for n in args: # 闭包变量args是只读的,不能修改 ax = ax + n return ax return sum >>> f = lazy_sum(1, 3, 5, 7, 9) >>> >>> f <function sum at 0x0000000002B3E208> >>> f() 25 >>> f(1) 26
装饰器 decorator
不修改函数的定义,在代码运行期间动态增加功能的方式。
函数装饰器
def decorator(func): def wrapper(*args, **kw): print 'input:', args, kw return func(*args, **kw) return wrapper @decorator def square_sum(*args, **kw): sum = 0 for i in args: sum += i**2 for j in kw.values(): sum += j**2 return sum >>> square_sum(3, 4, key=5) input: (3, 4) {'key': 5} 50
类装饰器
class decorator(object): def __init__(self, func): self.func = func def __call__(self, *args, **kw): print 'input:', args, kw return self.func(*args, **kw) @decorator def square_sum(*args, **kw): sum = 0 for i in args: sum += i**2 for j in kw.values(): sum += j**2 return sum >>> square_sum(3, 4, key=5) input: (3, 4) {'key': 5}
带参数的装饰器
def decorator(*args, **kw): text = args def _(func): def wrapper(*args, **kw): print 'text: %s' % text print 'input:', args, kw return func(*args, **kw) return wrapper return _
注意:decorator中的(*args, **kw) vs wrapper中的(*args, **kw)
最后再欣赏一下美女吧~