Python——day3_基础1_集合,文件操作,字符编码与转码

s = set([3,5,9,10])      #创建一个数值集合  
  
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

f = open(‘lyrics‘) #打开文件
first_line = f.readline()
print(‘first line:‘,first_line) #读一行
print(‘我是分隔线‘.center(50,‘-‘))
data = f.read()# 读取剩下的所有内容,文件大时不要用
print(data) #打印文件
 
f.close() #关闭文件

def close(self): # real signature unknown; restored from __doc__
        """
        Close the file.
        
        A closed file cannot be used for further I/O operations.  close() may be
        called more than once without error.
        """
        pass

    def fileno(self, *args, **kwargs): # real signature unknown
        """ Return the underlying file descriptor (an integer). """
        pass

    def isatty(self, *args, **kwargs): # real signature unknown
        """ True if the file is connected to a TTY device. """
        pass

    def read(self, size=-1): # known case of _io.FileIO.read
        """
        注意，不一定能全读回来
        Read at most size bytes, returned as bytes.
        
        Only makes one system call, so less data may be returned than requested.
        In non-blocking mode, returns None if no data is available.
        Return an empty bytes object at EOF.
        """
        return ""

    def readable(self, *args, **kwargs): # real signature unknown
        """ True if file was opened in a read mode. """
        pass

    def readall(self, *args, **kwargs): # real signature unknown
        """
        Read all data from the file, returned as bytes.
        
        In non-blocking mode, returns as much as is immediately available,
        or None if no data is available.  Return an empty bytes object at EOF.
        """
        pass

    def readinto(self): # real signature unknown; restored from __doc__
        """ Same as RawIOBase.readinto(). """
        pass #不要用,没人知道它是干嘛用的

    def seek(self, *args, **kwargs): # real signature unknown
        """
        Move to new file position and return the file position.
        
        Argument offset is a byte count.  Optional argument whence defaults to
        SEEK_SET or 0 (offset from start of file, offset should be >= 0); other values
        are SEEK_CUR or 1 (move relative to current position, positive or negative),
        and SEEK_END or 2 (move relative to end of file, usually negative, although
        many platforms allow seeking beyond the end of a file).
        
        Note that not all file objects are seekable.
        """
        pass

    def seekable(self, *args, **kwargs): # real signature unknown
        """ True if file supports random-access. """
        pass

    def tell(self, *args, **kwargs): # real signature unknown
        """
        Current file position.
        
        Can raise OSError for non seekable files.
        """
        pass

    def truncate(self, *args, **kwargs): # real signature unknown
        """
        Truncate the file to at most size bytes and return the truncated size.
        
        Size defaults to the current file position, as returned by tell().
        The current file position is changed to the value of size.
        """
        pass

    def writable(self, *args, **kwargs): # real signature unknown
        """ True if file was opened in a write mode. """
        pass

    def write(self, *args, **kwargs): # real signature unknown
        """
        Write bytes b to file, return number written.
        
        Only makes one system call, so not all of the data may be written.
        The number of bytes actually written is returned.  In non-blocking mode,
        returns None if the write would block.
        """
        pass

1 with open(‘log‘,‘r‘) as f:
2      
3     ...

1 with open(‘log1‘) as obj1, open(‘log2‘) as obj2:
2     pass

需知:

1.在python2默认编码是ASCII, python3里默认是unicode

2.unicode 分为 utf-32(占4个字节),utf-16(占两个字节)，utf-8(占1-4个字节)， so utf-16就是现在最常用的unicode版本， 不过在文件里存的还是utf-8，因为utf8省空间

3.在py3中encode,在转码的同时还会把string 变成bytes类型，decode在解码的同时还会把bytes变回string

#-*-coding:utf-8-*-
__author__ = ‘Alex Li‘

import sys
print(sys.getdefaultencoding())


msg = "我爱北京天安门"
msg_gb2312 = msg.decode("utf-8").encode("gb2312")
gb2312_to_gbk = msg_gb2312.decode("gbk").encode("gbk")

print(msg)
print(msg_gb2312)
print(gb2312_to_gbk)

in python2

#-*-coding:gb2312 -*-   #这个也可以去掉
__author__ = ‘Alex Li‘

import sys
print(sys.getdefaultencoding())


msg = "我爱北京天安门"
#msg_gb2312 = msg.decode("utf-8").encode("gb2312")
msg_gb2312 = msg.encode("gb2312") #默认就是unicode,不用再decode,喜大普奔
gb2312_to_unicode = msg_gb2312.decode("gb2312")
gb2312_to_utf8 = msg_gb2312.decode("gb2312").encode("utf-8")

print(msg)
print(msg_gb2312)
print(gb2312_to_unicode)
print(gb2312_to_utf8)

in python3