Python基础之文件处理、函数、内置函数 (三)

内置函数 一

详细见python文档,请点击

文件操作

操作文件时,一般需要经历如下步骤:

  • 打开文件
  • 操作文件

一、打开文件

文件句柄 = file('文件路径', '模式')

:python中打开文件有两种方式,即:open(...) 和  file(...) ,本质上前者在内部会调用后者来进行文件操作,推荐使用 open。

打开文件时,需要指定文件路径和以何等方式打开文件,打开后,即可获取该文件句柄,日后通过此文件句柄对该文件操作。

打开文件的模式有:

  • r,只读模式(默认)。
  • w,只写模式。【不可读;不存在则创建;存在则删除内容;】
  • a,追加模式。【可读;   不存在则创建;存在则只追加内容;】

"+" 表示可以同时读写某个文件

  • r+,可读写文件。【可读;可写;可追加】
  • w+,写读
  • a+,同a

"U"表示在读取时,可以将 自动转换成 (与 r 或 r+ 模式同使用)

  • rU
  • r+U

"b"表示处理二进制文件(如:FTP发送上传ISO镜像文件,linux可忽略,windows处理二进制文件时需标注)

  • rb
  • wb
  • ab

二、操作操作

class file(object):
  
    def close(self): # real signature unknown; restored from __doc__
        关闭文件
        """
        close() -> None or (perhaps) an integer.  Close the file.
         
        Sets data attribute .closed to True.  A closed file cannot be used for
        further I/O operations.  close() may be called more than once without
        error.  Some kinds of file objects (for example, opened by popen())
        may return an exit status upon closing.
        """
 
    def fileno(self): # real signature unknown; restored from __doc__
        文件描述符  
         """
        fileno() -> integer "file descriptor".
         
        This is needed for lower-level file interfaces, such os.read().
        """
        return 0    
 
    def flush(self): # real signature unknown; restored from __doc__
        刷新文件内部缓冲区
        """ flush() -> None.  Flush the internal I/O buffer. """
        pass
 
 
    def isatty(self): # real signature unknown; restored from __doc__
        判断文件是否是同意tty设备
        """ isatty() -> true or false.  True if the file is connected to a tty device. """
        return False
 
 
    def next(self): # real signature unknown; restored from __doc__
        获取下一行数据,不存在,则报错
        """ x.next() -> the next value, or raise StopIteration """
        pass
 
    def read(self, size=None): # real signature unknown; restored from __doc__
        读取指定字节数据
        """
        read([size]) -> read at most size bytes, returned as a string.
         
        If the size argument is negative or omitted, read until EOF is reached.
        Notice that when in non-blocking mode, less data than what was requested
        may be returned, even if no size parameter was given.
        """
        pass
 
    def readinto(self): # real signature unknown; restored from __doc__
        读取到缓冲区,不要用,将被遗弃
        """ readinto() -> Undocumented.  Don't use this; it may go away. """
        pass
 
    def readline(self, size=None): # real signature unknown; restored from __doc__
        仅读取一行数据
        """
        readline([size]) -> next line from the file, as a string.
         
        Retain newline.  A non-negative size argument limits the maximum
        number of bytes to return (an incomplete line may be returned then).
        Return an empty string at EOF.
        """
        pass
 
    def readlines(self, size=None): # real signature unknown; restored from __doc__
        读取所有数据,并根据换行保存值列表
        """
        readlines([size]) -> list of strings, each a line from the file.
         
        Call readline() repeatedly and return a list of the lines so read.
        The optional size argument, if given, is an approximate bound on the
        total number of bytes in the lines returned.
        """
        return []
 
    def seek(self, offset, whence=None): # real signature unknown; restored from __doc__
        指定文件中指针位置
        """
        seek(offset[, whence]) -> None.  Move to new file position.
         
        Argument offset is a byte count.  Optional argument whence defaults to
        0 (offset from start of file, offset should be >= 0); other values are 1
        (move relative to current position, positive or negative), and 2 (move
        relative to end of file, usually negative, although many platforms allow
        seeking beyond the end of a file).  If the file is opened in text mode,
        only offsets returned by tell() are legal.  Use of other offsets causes
        undefined behavior.
        Note that not all file objects are seekable.
        """
        pass
 
    def tell(self): # real signature unknown; restored from __doc__
        获取当前指针位置
        """ tell() -> current file position, an integer (may be a long integer). """
        pass
 
    def truncate(self, size=None): # real signature unknown; restored from __doc__
        截断数据,仅保留指定之前数据
        """
        truncate([size]) -> None.  Truncate the file to at most size bytes.
         
        Size defaults to the current file position, as returned by tell().
        """
        pass
 
    def write(self, p_str): # real signature unknown; restored from __doc__
        写内容
        """
        write(str) -> None.  Write string str to file.
         
        Note that due to buffering, flush() or close() may be needed before
        the file on disk reflects the data written.
        """
        pass
 
    def writelines(self, sequence_of_strings): # real signature unknown; restored from __doc__
        将一个字符串列表写入文件
        """
        writelines(sequence_of_strings) -> None.  Write the strings to the file.
         
        Note that newlines are not added.  The sequence can be any iterable object
        producing strings. This is equivalent to calling write() for each string.
        """
        pass
 
    def xreadlines(self): # real signature unknown; restored from __doc__
        可用于逐行读取文件,非全部
        """
        xreadlines() -> returns self.
         
        For backward compatibility. File objects now include the performance
        optimizations previously implemented in the xreadlines module.
        """
        pass
View Code

三、with

为了避免打开文件后忘记关闭,可以通过管理上下文,即:

with open('log','r') as f:
     
    ...

如此方式,当with代码块执行完毕时,内部会自动关闭并释放文件资源。

在Python 2.7 后,with又支持同时对多个文件的上下文进行管理,即:

with open('log1') as obj1, open('log2') as obj2:
    pass

四、那么问题来了...

1、如何在线上环境优雅的修改配置文件?

global       
        log 127.0.0.1 local2
        daemon
        maxconn 256
        log 127.0.0.1 local2 info
defaults
        log global
        mode http
        timeout connect 5000ms
        timeout client 50000ms
        timeout server 50000ms
        option  dontlognull

listen stats :8888
        stats enable
        stats uri       /admin
        stats auth      admin:1234

frontend aa.org
        bind 0.0.0.0:80
        option httplog
        option httpclose
        option  forwardfor
        log global
        acl www hdr_reg(host) -i www.aa.org
        use_backend www.aa.org if www

backend www.aa.org
        server 100.1.7.9 100.1.7.9 weight 20 maxconn 3000

原配置文件
原配置文件
1、查
    输入:www.aa.org
    获取当前backend下的所有记录

2、新建
    输入:
        arg = {
            'bakend': 'www.aa.org',
            'record':{
                'server': '100.1.7.9',
                'weight': 20,
                'maxconn': 30
            }
        }

3、删除
    输入:
        arg = {
            'bakend': 'www.aa.org',
            'record':{
                'server': '100.1.7.9',
                'weight': 20,
                'maxconn': 30
            }
        }

需求
需求
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import json
import os


def fetch(backend):
    backend_title = 'backend %s' % backend
    record_list = []
    with open('ha') as obj:
        flag = False
        for line in obj:
            line = line.strip()
            if line == backend_title:
                flag = True
                continue
            if flag and line.startswith('backend'):
                flag = False
                break

            if flag and line:
                record_list.append(line)

    return record_list


def add(dict_info):
    backend = dict_info.get('backend')
    record_list = fetch(backend)
    backend_title = "backend %s" % backend
    current_record = "server %s %s weight %d maxconn %d" % (dict_info['record']['server'], dict_info['record']['server'], dict_info['record']['weight'], dict_info['record']['maxconn'])
    if not record_list:
        record_list.append(backend_title)
        record_list.append(current_record)
        with open('ha') as read_file, open('ha.new', 'w') as write_file:
            flag = False
            for line in read_file:
                write_file.write(line)
            for i in record_list:
                if i.startswith('backend'):
                    write_file.write(i+'
')
                else:
                    write_file.write("%s%s
" % (8*" ", i))
    else:
        record_list.insert(0, backend_title)
        if current_record not in record_list:
            record_list.append(current_record)

        with open('ha') as read_file, open('ha.new', 'w') as write_file:
            flag = False
            has_write = False
            for line in read_file:
                line_strip = line.strip()
                if line_strip == backend_title:
                    flag = True
                    continue
                if flag and line_strip.startswith('backend'):
                    flag = False
                if not flag:
                    write_file.write(line)
                else:
                    if not has_write:
                        for i in record_list:
                            if i.startswith('backend'):
                                write_file.write(i+'
')
                            else:
                                write_file.write("%s%s
" % (8*" ", i))
                    has_write = True
    os.rename('ha','ha.bak')
    os.rename('ha.new','ha')


def remove(dict_info):
    backend = dict_info.get('backend')
    record_list = fetch(backend)
    backend_title = "backend %s" % backend
    current_record = "server %s %s weight %d maxconn %d" % (dict_info['record']['server'], dict_info['record']['server'], dict_info['record']['weight'], dict_info['record']['maxconn'])
    if not record_list:
        return
    else:
        if current_record not in record_list:
            return
        else:
            del record_list[record_list.index(current_record)]
            if len(record_list) > 0:
                record_list.insert(0, backend_title)
        with open('ha') as read_file, open('ha.new', 'w') as write_file:
            flag = False
            has_write = False
            for line in read_file:
                line_strip = line.strip()
                if line_strip == backend_title:
                    flag = True
                    continue
                if flag and line_strip.startswith('backend'):
                    flag = False
                if not flag:
                    write_file.write(line)
                else:
                    if not has_write:
                        for i in record_list:
                            if i.startswith('backend'):
                                write_file.write(i+'
')
                            else:
                                write_file.write("%s%s
" % (8*" ", i))
                    has_write = True
    os.rename('ha','ha.bak')
    os.rename('ha.new','ha')

if __name__ == '__main__':
    """
    print '1、获取;2、添加;3、删除'
    num = raw_input('请输入序号:')
    data = raw_input('请输入内容:')
    if num == '1':
        fetch(data)
    else:
        dict_data = json.loads(data)
        if num == '2':
            add(dict_data)
        elif num == '3':
            remove(dict_data)
        else:
            pass
    """
    #data = "www.aa.org"
    #fetch(data)
    #data = '{"backend": "tettst.aa.org","record":{"server": "100.1.7.90","weight": 20,"maxconn": 30}}'
    #dict_data = json.loads(data)
    #add(dict_data)
    #remove(dict_data)

demo
demo

2、文件处理中xreadlines的内部是如何实现的呢?

自定义函数

一、背景

在学习函数之前,一直遵循:面向过程编程,即:根据业务逻辑从上到下实现功能,其往往用一长段代码来实现指定功能,开发过程中最常见的操作就是粘贴复制,也就是将之前实现的代码块复制到现需功能处,如下

while True:
    if cpu利用率 > 90%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接
  
    if 硬盘使用空间 > 90%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接
  
    if 内存占用 > 80%:
        #发送邮件提醒
        连接邮箱服务器
        发送邮件
        关闭连接

定眼一看上述代码,if条件语句下的内容可以被提取出来公用,如下:

def 发送邮件(内容)
    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接
  
while True:
  
    if cpu利用率 > 90%:
        发送邮件('CPU报警')
  
    if 硬盘使用空间 > 90%:
        发送邮件('硬盘报警')
  
    if 内存占用 > 80%:

对于上述的两种实现方式,第二次必然比第一次的重用性和可读性要好,其实这就是函数式编程和面向过程编程的区别:

  • 函数式:将某功能代码封装到函数中,日后便无需重复编写,仅调用函数即可
  • 面向对象:对函数进行分类和封装,让开发“更快更好更强...”

函数式编程最重要的是增强代码的重用性和可读性

二、 函数的定义和使用

def 函数名(参数):
     
    ...
    函数体
    ...

函数的定义主要有如下要点:

  • def:表示函数的关键字
  • 函数名:函数的名称,日后根据函数名调用函数
  • 函数体:函数中进行一系列的逻辑计算,如:发送邮件、计算出 [11,22,38,888,2]中的最大数等...
  • 参数:为函数体提供数据
  • 返回值:当函数执行完毕后,可以给调用者返回数据。

以上要点中,比较重要有参数和返回值:

1、返回值

函数是一个功能块,该功能到底执行成功与否,需要通过返回值来告知调用者。

def 发送短信():
     
    发送短信的代码...
 
    if 发送成功:
        return True
    else:
        return False
 
 
while True:
     
    # 每次执行发送短信函数,都会将返回值自动赋值给result
    # 之后,可以根据result来写日志,或重发等操作
 
    result = 发送短信()
    if result == False:
        记录日志,短信发送失败...

2、参数

为什么要有参数?

def CPU报警邮件()
    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接

def 硬盘报警邮件()
    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接

def 内存报警邮件()
    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接
 
while True:
 
    if cpu利用率 > 90%:
        CPU报警邮件()
 
    if 硬盘使用空间 > 90%:
        硬盘报警邮件()
 
    if 内存占用 > 80%:
        内存报警邮件()

上例,无参数实现
上例,无参数实现
def 发送邮件(邮件内容)

    #发送邮件提醒
    连接邮箱服务器
    发送邮件
    关闭连接

 
while True:
 
    if cpu利用率 > 90%:
        发送邮件("CPU报警了。")
 
    if 硬盘使用空间 > 90%:
        发送邮件("硬盘报警了。")
 
    if 内存占用 > 80%:
        发送邮件("内存报警了。")

上列,有参数实现
上列,有参数实现

函数的有三中不同的参数:

  • 普通参数
  • 默认参数
  • 动态参数
# ######### 定义函数 ######### 

# name 叫做函数func的形式参数,简称:形参
def func(name):
    print name

# ######### 执行函数 ######### 
#  'wupeiqi' 叫做函数func的实际参数,简称:实参
func('wupeiqi')

普通参数
普通参数
def func(*args):

    print args


# 执行方式一
func(11,33,4,4454,5)

# 执行方式二
li = [11,2,2,3,3,4,54]
func(*li)

动态参数一
动态参数一
def func(**kwargs):

    print args


# 执行方式一
func(name='wupeiqi',age=18)

# 执行方式二
li = {'name':'wupeiqi', age:18, 'gender':'male'}
func(**li)

动态参数二
动态参数二
def func(*args, **kwargs):

    print args
    print kwargs
动态参数三

扩展:发送邮件实例

import smtplib
from email.mime.text import MIMEText
from email.utils import formataddr
 
 
msg = MIMEText('邮件内容', 'plain', 'utf-8')
msg['From'] = formataddr(["xs",'xs@126.com'])
msg['To'] = formataddr(["走人",'123456789@qq.com'])
msg['Subject'] = "主题"
 
server = smtplib.SMTP("smtp.126.com", 25)
server.login("xs@126.com", "邮箱密码")
server.sendmail('xs@126.com', ['123456789@qq.com',], msg.as_string())
server.quit()
发邮件

lambda表达式

学习条件运算时,对于简单的 if else 语句,可以使用三元运算来表示,即:

# 普通条件语句
if 1 == 1:
    name = 'weibinf'
else:
    name = 'xs'
  
# 三元运算
name = 'weibinf' if 1 == 1 else 'xs'
View Code

对于简单的函数,也存在一种简便的表示方式,即:lambda表达式

# ###################### 普通函数 ######################
# 定义函数(普通方式)
def func(arg):
    return arg + 1
  
# 执行函数
result = func(123)
  
# ###################### lambda ######################
  
# 定义函数(lambda表达式)
my_lambda = lambda arg : arg + 1
  
# 执行函数
result = my_lambda(123)

lambda存在意义就是对简单函数的简洁表示

内置函数 二

一、map

遍历序列,对序列中每个元素进行操作,最终获取新的序列。

li = [11, 22, 33]

new_list = map(lambda a: a + 100, li)
每个元素增加100
li = [11, 22, 33]
sl = [1, 2, 3]
new_list = map(lambda a, b: a + b, li, sl)
两个列表对应元素相加

二、filter

对于序列中的元素进行筛选,最终获取符合条件的序列

li = [11, 22, 33]

new_list = filter(lambda arg: arg > 22, li)

#filter第一个参数为空,将获取原来序列
获取列表中大于12的所有元素集合

三、reduce

对于序列内所有元素进行累计操作

li = [11, 22, 33]

result = reduce(lambda arg1, arg2: arg1 + arg2, li)

# reduce的第一个参数,函数必须要有两个参数
# reduce的第二个参数,要循环的序列
# reduce的第三个参数,初始值

获取序列所有元素的和
获取序列所有元素的和

yield生成器

1、对比range 和 xrange 的区别

>>> print range(10)
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
>>> print xrange(10)
xrange(10)

如上代码所示,range会在内存中创建所有指定的数字,而xrange不会立即创建,只有在迭代循环时,才去创建每个数组。

def nrange(num):
    temp = -1
    while True:
        temp = temp + 1
        if temp >= num:
            return
        else:
            yield temp

自定义生成器nrange
自定义生成器nrange

2、文件操作的 read 和 xreadlinex 的的区别

read会读取所有内容到内存
xreadlines则只有在循环迭代时才获取
def NReadlines():
    with open('log','r') as f:
        while True:
            line = f.next()
            if line:
                yield line
            else:
                return

for i in NReadlines():
    print i

基于next自定义生成器NReadlines
基于next自定义生成器NReadlines
def NReadlines():
    with open('log','r') as f:
        seek = 0
        while True:
            f.seek(seek)
            data = f.readline()
            if data:
                seek = f.tell()
                yield data
            else:
                return

for item in NReadlines():
    print item

基于seek和tell自定义生成器NReadlines
基于seek和tell自定义生成器NReadlines

装饰器

装饰器是函数,只不过该函数可以具有特殊的含义,装饰器用来装饰函数或类,使用装饰器可以在函数执行前和执行后添加相应操作。

def wrapper(func):
    def result():
        print 'before'
        func()
        print 'after'
    return result
 
@wrapper
def foo():
    print 'foo'
import functools


def wrapper(func):
    @functools.wraps(func)
    def wrapper():
        print 'before'
        func()
        print 'after'
    return wrapper

@wrapper
def foo():
    print 'foo'
View Code
#!/usr/bin/env python
#coding:utf-8
 
def Before(request,kargs):
    print 'before'
     
def After(request,kargs):
    print 'after'
 
 
def Filter(before_func,after_func):
    def outer(main_func):
        def wrapper(request,kargs):
             
            before_result = before_func(request,kargs)
            if(before_result != None):
                return before_result;
             
            main_result = main_func(request,kargs)
            if(main_result != None):
                return main_result;
             
            after_result = after_func(request,kargs)
            if(after_result != None):
                return after_result;
             
        return wrapper
    return outer
     
@Filter(Before, After)
def Index(request,kargs):
    print 'index'
     
     
if __name__ == '__main__':
    Index(1,2)
View Code

冒泡算法

需求:请按照从小到大对列表 [13, 22, 6, 99, 11] 进行排序

思路:相邻两个值进行比较,将较大的值放在右侧,依次比较!

li = [13, 22, 6, 99, 11]

for m in range(4):     # 等价于 #for m in range(len(li)-1):
    if li[m]> li[m+1]:
        temp = li[m+1]
        li[m+1] = li[m]
        li[m] = temp

第一步
第一步
li = [13, 22, 6, 99, 11]

for m in range(4):     # 等价于 #for m in range(len(li)-1):
    if li[m]> li[m+1]:
        temp = li[m+1]
        li[m+1] = li[m]
        li[m] = temp

for m in range(3):     # 等价于 #for m in range(len(li)-2):
    if li[m]> li[m+1]:
        temp = li[m+1]
        li[m+1] = li[m]
        li[m] = temp

for m in range(2):     # 等价于 #for m in range(len(li)-3):
    if li[m]> li[m+1]:
        temp = li[m+1]
        li[m+1] = li[m]
        li[m] = temp

for m in range(1):     # 等价于 #for m in range(len(li)-4):
    if li[m]> li[m+1]:
        temp = li[m+1]
        li[m+1] = li[m]
        li[m] = temp
print li

第二步
第二步
li = [13, 22, 6, 99, 11]

for i in range(1,5):
    for m in range(len(li)-i): 
        if li[m] > li[m+1]:
            temp = li[m+1]
            li[m+1] = li[m]
            li[m] = temp

第三步
第三步

递归

利用函数编写如下数列:

斐波那契数列指的是这样一个数列 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233,377,610,987,1597,2584,4181,6765,10946,17711,28657,46368
def func(arg1,arg2):
    if arg1 == 0:
        print arg1, arg2
    arg3 = arg1 + arg2
    print arg3
    func(arg2, arg3)

func(0,1)

demo
demo
原文地址:https://www.cnblogs.com/fanweibin/p/5028590.html