Day6 反射、模块、正则表达式和算法

递归完成阶乘

def func(num):
    if num == 1:
        return 1
    return num * func(num - 1)

x = func(7)

print(x)

反射

commons.py

def login():
    print("炫酷登录页面")

def logout():
    print("炫酷退出页面")

def home():
    print("炫酷主页面")

index.py

import commons

def run():
    inp = input('请输入要访问的url：')
    #inp字符串类型 inp = "login"
    #commons.inp    #commons.login
    #反射：利用字符串的形式去对象（模块）中操作（寻找/检查/删除/设置）成员，都是在内存中操作
    #delattr()
    #setattr()
    if hasattr(commons, inp):
        func = getattr(commons, inp)
        func()
    else:
        print('404')

if __name__ == '__main__':
    run()

以字符串形式导入模块

account.py

def login():
    print("炫酷登录页面")

manager.py

def order():
    print("炫酷的订单页面")

commons.py

def logout():
    print("炫酷退出页面")

index.py

def run():
    inp = input('请输入要访问的url：')
    #inp字符串类型 inp = "login"
    #commons.inp    #commons.login
    #反射：利用字符串的形式去对象（模块）中操作（寻找/检查/删除/设置）成员，都是在内存中操作
    #delattr()
    #setattr()
    m, f = inp.split('/')
    #__import__导入模块传入__import__("commons")
    obj = __import__(m)
    if hasattr(obj, f):
        func = getattr(obj, f)
        func()
    else:
        print('404')

if __name__ == '__main__':
    run()

导入lib目录中的模块

def run():
    inp = input('请输入要访问的url：')
    #inp字符串类型 inp = "login"
    #commons.inp    #commons.login
    #反射：利用字符串的形式去对象（模块）中操作（寻找/检查/删除/设置）成员，都是在内存中操作
    #delattr()
    #setattr()
    m, f = inp.split('/')
    #__import__导入模块传入__import__("commons")
    #obj = __import__(m)
    obj = __import__("lib." + m, fromlist=True)
    if hasattr(obj, f):
        func = getattr(obj, f)
        func()
    else:
        print('404')

if __name__ == '__main__':
    run()

总结

实例：伪造Web框架的路由系统

反射：基于字符串的形式取去对象（模块）中操作其成员

     getattr,delattr,setattr,hasattr

扩展：导入模块

     import xxx

     from xxx import lll

     obj = __import__("xxx")

     obj = __import__("xxx.lll.ddd", fromlist=True)

模块中的特殊变量

import sys
import os
"""
我是注释
"""
#获取注释
print(__doc__)
#__cached__:字节码所在路径
#当前py文件所在路径
print(__file__)
#文件的绝对路径
ret = os.path.abspath(__file__)
print(ret)
#找到文件的上级目录
ret1 = os.path.dirname(ret)
print(ret1)
ret2 = os.path.dirname(ret1)
print(ret2)

from bin import admin

print(__package__)
print(admin.__package__)
#只有执行当前文件时，当前文件的特殊变量__name__==“__main__”
print(__name__)

sys模块

sys.argv           #命令行参数List，第一个元素是程序本身路径
sys.exit(n)        #退出程序，正常退出时exit(0)
sys.version        #获取Python解释程序的版本信息
sys.maxint         #最大的Int值
sys.path           #返回模块的搜索路径，初始化时使用PYTHONPATH环境变量的值
sys.platform       #返回操作系统平台名称
sys.stdin          #输入相关
sys.stdout         #输出相关
sys.stderror       #错误相关

进度条

import sys
import time

def view_bar(num, total):
    rate = num / total
    rate_num = int(rate * 100)

    #‘\r’：回到当前行的首个位置

    r = '\r%s>%d%%' % ("="*num, rate_num)

    #输出不加换行符
    sys.stdout.write(r)
    #输出清空
    sys.stdout.flush()

if __name__ == '__main__':
    for i in range(0, 101):
        time.sleep(0.1)
        view_bar(i, 100)

os模块

os.getcwd()                 #获取当前工作目录，即当前python脚本工作的目录路径
os.chdir("dirname")         #改变当前脚本工作目录；相当于shell下cd
os.curdir                   #返回当前目录: ('.')
os.pardir                   #获取当前目录的父目录字符串名：('..')
os.makedirs('dir1/dir2')    #可生成多层递归目录
os.removedirs('dirname1')   #若目录为空，则删除，并递归到上一级目录，如若也为空，则删除，依此类推
os.mkdir('dirname')         #生成单级目录；相当于shell中mkdir dirname
os.rmdir('dirname')         #删除单级空目录，若目录不为空则无法删除，报错；相当于shell中rmdir dirname
os.listdir('dirname')       #列出指定目录下的所有文件和子目录，包括隐藏文件，并以列表方式打印
os.remove()                 #删除一个文件
os.rename("oldname","new")  #重命名文件/目录
os.stat('path/filename')    #获取文件/目录信息
os.sep                      #操作系统特定的路径分隔符，win下为"\\",Linux下为"/"
os.linesep                  #当前平台使用的行终止符，win下为"\t\n",Linux下为"\n"
os.pathsep                  #用于分割文件路径的字符串
os.name                     #字符串指示当前使用平台。win->'nt'; Linux->'posix'
os.system("bash command")   #运行shell命令，直接显示
os.environ                  #获取系统环境变量

os.path.abspath(path) #返回path规范化的绝对路径

os.path.split(path)         #将path分割成目录和文件名二元组返回

os.path.dirname(path) #返回path的目录。其实就是os.path.split(path)的第一个元素

os.path.basename(path)      #返回path最后的文件名。如何path以／或\结尾，那么就会返回空值。即os.path.split(path)的第二个元素
os.path.exists(path)        #如果path存在，返回True；如果path不存在，返回False
os.path.isabs(path)         #如果path是绝对路径，返回True
os.path.isfile(path)        #如果path是一个存在的文件，返回True。否则返回False
os.path.isdir(path)         #如果path是一个存在的目录，则返回True。否则返回False

os.path.join(path1[, path2[, ...]]) #将多个路径组合后返回，第一个绝对路径之前的参数将被忽略

os.path.getatime(path)      #返回path所指向的文件或者目录的最后存取时间
os.path.getmtime(path)      #返回path所指向的文件或者目录的最后修改时间

MD5

import hashlib
#自定义加密key
obj = hashlib.md5(bytes(bytes('wnddnxnsnxsjnxueldoekcemckkaslkmadlkcecene', encoding='utf-8')))
obj.update(bytes('Radar', encoding='utf-8'))
#加密后的结果
ret = obj.hexdigest()
print(ret)

configparser

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import configparser
#只对应指定的格式操作，如下readme.txt：
"""
[section1]
k1 = 123
k2 = v2

[section2]
k1 = 567
"""
#获取所有节点
config = configparser.ConfigParser()
config.read('readme.txt', encoding='utf-8')
ret = config.sections()
print(ret)

#获取指定节点下所有的键值对
ret1 = config.items('section1')
print(ret1)

#获取指定节点下所有的键
ret2 = config.options('section1')
print(ret2)

#获取指定节点下指定key的值
v = config.get('section1', 'k1')
# v = config.getint('section1', 'k1')
#v = config.getfloat('section1', 'k1')
#v = config.getboolean('section1', 'k1')
print(v)

#检查、删除、添加节点(均在内存中操作)
# 检查
has_sec = config.has_section('section1')
print(has_sec)

# 添加节点
config.add_section("SEC_1")
config.write(open('readme.txt', 'w'))

# 删除节点
config.remove_section("SEC_1")
config.write(open('readme.txt', 'w'))

#检查、删除、设置指定组内的键值对
# 检查
has_opt = config.has_option('section1', 'k1')
print(has_opt)

# 删除
config.remove_option('section1', 'k1')
config.write(open('readme.txt', 'w'))

# 设置
config.set('section1', 'k10', "")
config.write(open('readme.txt', 'w'))

XML模块

xml格式如下：

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2026</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>

xml节点功能

class Element:
    """An XML element.

    This class is the reference implementation of the Element interface.

    An element's length is its number of subelements.  That means if you
    want to check if an element is truly empty, you should check BOTH
    its length AND its text attribute.

    The element tag, attribute names, and attribute values can be either
    bytes or strings.

    *tag* is the element name.  *attrib* is an optional dictionary containing
    element attributes. *extra* are additional element attributes given as
    keyword arguments.

    Example form:
        <tag attrib>text<child/>...</tag>tail

    """

    当前节点的标签名
    tag = None
    """The element's name."""

    当前节点的属性

    attrib = None
    """Dictionary of the element's attributes."""

    当前节点的内容
    text = None
    """
    Text before first subelement. This is either a string or the value None.
    Note that if there is no text, this attribute may be either
    None or the empty string, depending on the parser.

    """

    tail = None
    """
    Text after this element's end tag, but before the next sibling element's
    start tag.  This is either a string or the value None.  Note that if there
    was no text, this attribute may be either None or an empty string,
    depending on the parser.

    """

    def __init__(self, tag, attrib={}, **extra):
        if not isinstance(attrib, dict):
            raise TypeError("attrib must be dict, not %s" % (
                attrib.__class__.__name__,))
        attrib = attrib.copy()
        attrib.update(extra)
        self.tag = tag
        self.attrib = attrib
        self._children = []

    def __repr__(self):
        return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self))

    def makeelement(self, tag, attrib):
        创建一个新节点
        """Create a new element with the same type.

        *tag* is a string containing the element name.
        *attrib* is a dictionary containing the element attributes.

        Do not call this method, use the SubElement factory function instead.

        """
        return self.__class__(tag, attrib)

    def copy(self):
        """Return copy of current element.

        This creates a shallow copy. Subelements will be shared with the
        original tree.

        """
        elem = self.makeelement(self.tag, self.attrib)
        elem.text = self.text
        elem.tail = self.tail
        elem[:] = self
        return elem

    def __len__(self):
        return len(self._children)

    def __bool__(self):
        warnings.warn(
            "The behavior of this method will change in future versions.  "
            "Use specific 'len(elem)' or 'elem is not None' test instead.",
            FutureWarning, stacklevel=2
            )
        return len(self._children) != 0 # emulate old behaviour, for now

    def __getitem__(self, index):
        return self._children[index]

    def __setitem__(self, index, element):
        # if isinstance(index, slice):
        #     for elt in element:
        #         assert iselement(elt)
        # else:
        #     assert iselement(element)
        self._children[index] = element

    def __delitem__(self, index):
        del self._children[index]

    def append(self, subelement):
        为当前节点追加一个子节点
        """Add *subelement* to the end of this element.

        The new element will appear in document order after the last existing
        subelement (or directly after the text, if it's the first subelement),
        but before the end tag for this element.

        """
        self._assert_is_element(subelement)
        self._children.append(subelement)

    def extend(self, elements):
        为当前节点扩展 n 个子节点
        """Append subelements from a sequence.

        *elements* is a sequence with zero or more elements.

        """
        for element in elements:
            self._assert_is_element(element)
        self._children.extend(elements)

    def insert(self, index, subelement):
        在当前节点的子节点中插入某个节点，即：为当前节点创建子节点，然后插入指定位置
        """Insert *subelement* at position *index*."""
        self._assert_is_element(subelement)
        self._children.insert(index, subelement)

    def _assert_is_element(self, e):
        # Need to refer to the actual Python implementation, not the
        # shadowing C implementation.
        if not isinstance(e, _Element_Py):
            raise TypeError('expected an Element, not %s' % type(e).__name__)

    def remove(self, subelement):
        在当前节点在子节点中删除某个节点
        """Remove matching subelement.

        Unlike the find methods, this method compares elements based on
        identity, NOT ON tag value or contents.  To remove subelements by
        other means, the easiest way is to use a list comprehension to
        select what elements to keep, and then use slice assignment to update
        the parent element.

        ValueError is raised if a matching element could not be found.

        """
        # assert iselement(element)
        self._children.remove(subelement)

    def getchildren(self):
        获取所有的子节点（废弃）
        """(Deprecated) Return all subelements.

        Elements are returned in document order.

        """
        warnings.warn(
            "This method will be removed in future versions.  "
            "Use 'list(elem)' or iteration over elem instead.",
            DeprecationWarning, stacklevel=2
            )
        return self._children

    def find(self, path, namespaces=None):
        获取第一个寻找到的子节点
        """Find first matching element by tag name or path.

        *path* is a string having either an element tag or an XPath,
        *namespaces* is an optional mapping from namespace prefix to full name.

        Return the first matching element, or None if no element was found.

        """
        return ElementPath.find(self, path, namespaces)

    def findtext(self, path, default=None, namespaces=None):
        获取第一个寻找到的子节点的内容
        """Find text for first matching element by tag name or path.

        *path* is a string having either an element tag or an XPath,
        *default* is the value to return if the element was not found,
        *namespaces* is an optional mapping from namespace prefix to full name.

        Return text content of first matching element, or default value if
        none was found.  Note that if an element is found having no text
        content, the empty string is returned.

        """
        return ElementPath.findtext(self, path, default, namespaces)

    def findall(self, path, namespaces=None):
        获取所有的子节点
        """Find all matching subelements by tag name or path.

        *path* is a string having either an element tag or an XPath,
        *namespaces* is an optional mapping from namespace prefix to full name.

        Returns list containing all matching elements in document order.

        """
        return ElementPath.findall(self, path, namespaces)

    def iterfind(self, path, namespaces=None):
        获取所有指定的节点，并创建一个迭代器（可以被for循环）
        """Find all matching subelements by tag name or path.

        *path* is a string having either an element tag or an XPath,
        *namespaces* is an optional mapping from namespace prefix to full name.

        Return an iterable yielding all matching elements in document order.

        """
        return ElementPath.iterfind(self, path, namespaces)

    def clear(self):
        清空节点
        """Reset element.

        This function removes all subelements, clears all attributes, and sets
        the text and tail attributes to None.

        """
        self.attrib.clear()
        self._children = []
        self.text = self.tail = None

    def get(self, key, default=None):
        获取当前节点的属性值
        """Get element attribute.

        Equivalent to attrib.get, but some implementations may handle this a
        bit more efficiently.  *key* is what attribute to look for, and
        *default* is what to return if the attribute was not found.

        Returns a string containing the attribute value, or the default if
        attribute was not found.

        """
        return self.attrib.get(key, default)

    def set(self, key, value):
        为当前节点设置属性值
        """Set element attribute.

        Equivalent to attrib[key] = value, but some implementations may handle
        this a bit more efficiently.  *key* is what attribute to set, and
        *value* is the attribute value to set it to.

        """
        self.attrib[key] = value

    def keys(self):
        获取当前节点的所有属性的 key

        """Get list of attribute names.

        Names are returned in an arbitrary order, just like an ordinary
        Python dict.  Equivalent to attrib.keys()

        """
        return self.attrib.keys()

    def items(self):
        获取当前节点的所有属性值，每个属性都是一个键值对
        """Get element attributes as a sequence.

        The attributes are returned in arbitrary order.  Equivalent to
        attrib.items().

        Return a list of (name, value) tuples.

        """
        return self.attrib.items()

    def iter(self, tag=None):
        在当前节点的子孙中根据节点名称寻找所有指定的节点，并返回一个迭代器（可以被for循环）。
        """Create tree iterator.

        The iterator loops over the element and all subelements in document
        order, returning all elements with a matching tag.

        If the tree structure is modified during iteration, new or removed
        elements may or may not be included.  To get a stable set, use the
        list() function on the iterator, and loop over the resulting list.

        *tag* is what tags to look for (default is to return all elements)

        Return an iterator containing all the matching elements.

        """
        if tag == "*":
            tag = None
        if tag is None or self.tag == tag:
            yield self
        for e in self._children:
            yield from e.iter(tag)

    # compatibility
    def getiterator(self, tag=None):
        # Change for a DeprecationWarning in 1.4
        warnings.warn(
            "This method will be removed in future versions.  "
            "Use 'elem.iter()' or 'list(elem.iter())' instead.",
            PendingDeprecationWarning, stacklevel=2
        )
        return list(self.iter(tag))

    def itertext(self):
        在当前节点的子孙中根据节点名称寻找所有指定的节点的内容，并返回一个迭代器（可以被for循环）。
        """Create text iterator.

        The iterator loops over the element and all subelements in document
        order, returning all inner text.

        """
        tag = self.tag
        if not isinstance(tag, str) and tag is not None:
            return
        if self.text:
            yield self.text
        for e in self:
            yield from e.itertext()
            if e.tail:
                yield e.tail

节点功能一览表

遍历xml文件中的所有内容

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#浏览器返回的字符串
#1.html
#2.json
#3.xml:页面展示（字符串类型的一个XML格式数据）、配置文件（文件、内部数据XML格式）

from xml.etree import ElementTree as ET
tree = ET.parse('read.xml')
root = tree.getroot()

for child in root:
    print(child.tag, child.attrib)
    for gradechild in child:
        print(gradechild.tag, gradechild.text)

打开xml的两种方式

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#浏览器返回的字符串
#1.html
#2.json
#3.xml:页面展示（字符串类型的一个XML格式数据）、配置文件（文件、内部数据XML格式）

from xml.etree import ElementTree as ET

#第一种方式：利用ElementTree.XML将字符串解析成xml对象
# 打开文件，读取XML内容
str_xml = open('read.xml', 'r').read()

# 将字符串解析成xml特殊对象，root代指xml文件的根节点
root = ET.XML(str_xml)
print(root)

#第二种方式：利用ElementTree.parse将文件直接解析成xml对象
# 直接解析xml文件
tree = ET.parse("read.xml")

# 获取xml文件的根节点
root = tree.getroot()
print(root)

修改节点

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#浏览器返回的字符串
#1.html
#2.json
#3.xml:页面展示（字符串类型的一个XML格式数据）、配置文件（文件、内部数据XML格式）

from xml.etree import ElementTree as ET

############ 解析方式一 ############
#解析字符串方式，修改，保存
# 打开文件，读取XML内容
str_xml = open('read.xml', 'r').read()

# 将字符串解析成xml特殊对象，root代指xml文件的根节点
root = ET.XML(str_xml)

############ 操作 ############

# 顶层标签
print(root.tag)

# 循环所有的year节点
for node in root.iter('year'):
    # 将year节点中的内容自增一
    new_year = int(node.text) + 1
    node.text = str(new_year)

    # 设置属性
    node.set('name', 'alex')
    node.set('age', '')
    # 删除属性
    del node.attrib['name']

############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("newnew.xml", encoding='utf-8')

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#浏览器返回的字符串
#1.html
#2.json
#3.xml:页面展示（字符串类型的一个XML格式数据）、配置文件（文件、内部数据XML格式）

from xml.etree import ElementTree as ET

############ 解析方式二 ############
#解析文件方式，修改，保存
# 直接解析xml文件
tree = ET.parse("read.xml")

# 获取xml文件的根节点
root = tree.getroot()

############ 操作 ############

# 顶层标签
print(root.tag)

# 循环所有的year节点
for node in root.iter('year'):
    # 将year节点中的内容自增一
    new_year = int(node.text) + 1
    node.text = str(new_year)

    # 设置属性
    node.set('name', 'alex')
    node.set('age', '')
    # 删除属性
    del node.attrib['name']

############ 保存文件 ############
tree.write("newnew2.xml", encoding='utf-8')

创建XML

方式一：

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

from xml.etree import ElementTree as ET
#创建方式（一）

# 创建根节点
root = ET.Element("famliy")

# 创建节点大儿子
son1 = ET.Element('son', {'name': '儿1'})
# 创建小儿子
son2 = ET.Element('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
grandson1 = ET.Element('grandson', {'name': '儿11'})
grandson2 = ET.Element('grandson', {'name': '儿12'})
son1.append(grandson1)
son1.append(grandson2)

# 把儿子添加到根节点中
root.append(son1)
root.append(son1)

tree = ET.ElementTree(root)
tree.write('new_create1.xml',encoding='utf-8', short_empty_elements=False)

方式二

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("famliy")

# 创建大儿子
# son1 = ET.Element('son', {'name': '儿1'})
son1 = root.makeelement('son', {'name': '儿1'})
# 创建小儿子
# son2 = ET.Element('son', {"name": '儿2'})
son2 = root.makeelement('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
# grandson1 = ET.Element('grandson', {'name': '儿11'})
grandson1 = son1.makeelement('grandson', {'name': '儿11'})
# grandson2 = ET.Element('grandson', {'name': '儿12'})
grandson2 = son1.makeelement('grandson', {'name': '儿12'})

son1.append(grandson1)
son1.append(grandson2)

# 把儿子添加到根节点中
root.append(son1)
root.append(son1)

tree = ET.ElementTree(root)
tree.write('oooo.xml',encoding='utf-8', short_empty_elements=False)

方式三

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("famliy")

# 创建节点大儿子
son1 = ET.SubElement(root, "son", attrib={'name': '儿1'})
# 创建小儿子
son2 = ET.SubElement(root, "son", attrib={"name": "儿2"})

# 在大儿子中创建一个孙子
grandson1 = ET.SubElement(son1, "age", attrib={'name': '儿11'})
grandson1.text = '孙子'

et = ET.ElementTree(root)  #生成文档对象
et.write("test.xml", encoding="utf-8", xml_declaration=True, short_empty_elements=False)

带缩进功能创建xml

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

from xml.etree import ElementTree as ET
from xml.dom import minidom

def prettify(elem):
    """将节点转换成字符串，并添加缩进。
    """
    rough_string = ET.tostring(elem, 'utf-8')
    reparsed = minidom.parseString(rough_string)
    return reparsed.toprettyxml(indent="\t")

# 创建根节点
root = ET.Element("famliy")

# 创建大儿子
# son1 = ET.Element('son', {'name': '儿1'})
son1 = root.makeelement('son', {'name': '儿1'})
# 创建小儿子
# son2 = ET.Element('son', {"name": '儿2'})
son2 = root.makeelement('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
# grandson1 = ET.Element('grandson', {'name': '儿11'})
grandson1 = son1.makeelement('grandson', {'name': '儿11'})
# grandson2 = ET.Element('grandson', {'name': '儿12'})
grandson2 = son1.makeelement('grandson', {'name': '儿12'})

son1.append(grandson1)
son1.append(grandson2)

# 把儿子添加到根节点中
root.append(son1)
root.append(son1)

raw_str = prettify(root)

f = open("new_create2.xml",'w',encoding='utf-8')
f.write(raw_str)
f.close()

命名空间

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

from xml.etree import ElementTree as ET

ET.register_namespace('com',"http://www.company.com") #some name

# build a tree structure
root = ET.Element("{http://www.company.com}STUFF")
body = ET.SubElement(root, "{http://www.company.com}MORE_STUFF", attrib={"{http://www.company.com}hhh": ""})
body.text = "STUFF EVERYWHERE!"

# wrap it in an ElementTree instance, and save as XML
tree = ET.ElementTree(root)

tree.write("page.xml",
           xml_declaration=True,
           encoding='utf-8',
           method="xml")

shutil：高级的 文件、文件夹、压缩包 处理模块

1.将文件内容拷贝到另一个文件中

shutil.copyfileobj(fsrc, fdst[, length])

import shutil

shutil.copyfileobj(open('old.xml','r'), open('new.xml', 'w'))

2.拷贝文件

shutil.copyfile(src, dst)

shutil.copyfile('f1.log', 'f2.log')

3.仅拷贝权限。内容、组、用户均不变

shutil.copymode(src, dst)

shutil.copymode('f1.log', 'f2.log')

4.仅拷贝状态的信息，包括：mode bits, atime, mtime, flags

shutil.copystat(src, dst)

shutil.copystat('f1.log', 'f2.log')

5.拷贝文件和权限

shutil.copy(src, dst)

import shutil

shutil.copy('f1.log', 'f2.log')

6.拷贝文件和状态信息

shutil.copy2(src, dst)

import shutil

shutil.copy2('f1.log', 'f2.log')

7.递归的去拷贝文件夹

shutil.ignore_patterns(*patterns)
shutil.copytree(src, dst, symlinks=False, ignore=None)

import shutil

shutil.copytree('folder1', 'folder2', ignore=shutil.ignore_patterns('*.pyc', 'tmp*'))

import shutil

shutil.copytree('f1', 'f2', symlinks=True, ignore=shutil.ignore_patterns('*.pyc', 'tmp*'))

8.递归的去删除文件

shutil.rmtree(path[, ignore_errors[, onerror]])

import shutil

shutil.rmtree('folder1')

9.递归的去移动文件，它类似mv命令，其实就是重命名

shutil.move(src, dst)

import shutil

shutil.move('folder1', 'folder3')

10.创建压缩包并返回文件路径，例如：zip、tar

shutil.make_archive(base_name, format,...)

• base_name： 压缩包的文件名，也可以是压缩包的路径。只是文件名时，则保存至当前目录，否则保存至指定路径，
  如：www                        =>保存至当前路径
  如：/Users/wupeiqi/www =>保存至/Users/wupeiqi/
• format： 压缩包种类，“zip”, “tar”, “bztar”，“gztar”
• root_dir： 要压缩的文件夹路径（默认当前目录）
• owner： 用户，默认当前用户
• group： 组，默认当前组
• logger： 用于记录日志，通常是logging.Logger对象

#将 /Users/wupeiqi/Downloads/test 下的文件打包放置当前程序目录
import shutil
ret = shutil.make_archive("wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test')

#将 /Users/wupeiqi/Downloads/test 下的文件打包放置 /Users/wupeiqi/目录
import shutil
ret = shutil.make_archive("/Users/wupeiqi/wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test')

shutil 对压缩包的处理是调用 ZipFile 和 TarFile 两个模块来进行的，详细：

import zipfile

# 压缩
z = zipfile.ZipFile('laxi.zip', 'w')
z.write('a.log')
z.write('data.data')
z.close()

# 解压
z = zipfile.ZipFile('laxi.zip', 'r')
z.extractall()
#z.namelist()获取压缩包中的对象

z.namelist()

z.close() zipfile解压缩

import tarfile

# 压缩
tar = tarfile.open('your.tar','w')
tar.add('/Users/wupeiqi/PycharmProjects/bbs2.log', arcname='bbs2.log')
tar.add('/Users/wupeiqi/PycharmProjects/cmdb.log', arcname='cmdb.log')
tar.close()

# 解压
tar = tarfile.open('your.tar','r')
tar.extractall()  # 可设置解压地址
#obj = tar.getmember("bbs2.log")
#tar.extractall(obj)

tar.close()

tarfile解压缩

subprocess

1.执行命令，返回状态码

call 

ret = subprocess.call(["ls", "-l"], shell=False)
ret = subprocess.call("ls -l", shell=True)

2.执行命令，如果执行状态码是 0 ，则返回0，否则抛异常

check_call

subprocess.check_call(["ls", "-l"])
subprocess.check_call("exit 1", shell=True)

3.执行命令，如果状态码是 0 ，则返回执行结果，否则抛异常

check_output

subprocess.check_output(["echo", "Hello World!"])
subprocess.check_output("exit 1", shell=True)

subprocess.Popen(...)

用于执行复杂的系统命令

参数：

• args：shell命令，可以是字符串或者序列类型（如：list，元组）
• bufsize：指定缓冲。0 无缓冲,1 行缓冲,其他 缓冲区大小,负值 系统缓冲
• stdin, stdout, stderr：分别表示程序的标准输入、输出、错误句柄
• preexec_fn：只在Unix平台下有效，用于指定一个可执行对象（callable object），它将在子进程运行之前被调用
• close_sfs：在windows平台下，如果close_fds被设置为True，则新创建的子进程将不会继承父进程的输入、输出、错误管道。
  所以不能将close_fds设置为True同时重定向子进程的标准输入、输出与错误(stdin, stdout, stderr)。
• shell：同上
• cwd：用于设置子进程的当前目录
• env：用于指定子进程的环境变量。如果env = None，子进程的环境变量将从父进程中继承。
• universal_newlines：不同系统的换行符不同，True -> 同意使用 \n
• startupinfo与createionflags只在windows下有效
  将被传递给底层的CreateProcess()函数，用于设置子进程的一些属性，如：主窗口的外观，进程的优先级等等

import subprocess
ret1 = subprocess.Popen(["mkdir","t1"])
ret2 = subprocess.Popen("mkdir t2", shell=True)

终端输入的命令分为两种：

• 输入即可得到输出，如：ifconfig
• 输入进行某环境，依赖再输入，如：python

import subprocess

obj = subprocess.Popen("mkdir t3", shell=True, cwd='/home/dev',)

import subprocess

obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
obj.stdin.write("print(1)\n")
obj.stdin.write("print(2)")
obj.stdin.close()

cmd_out = obj.stdout.read()
obj.stdout.close()
cmd_error = obj.stderr.read()
obj.stderr.close()

print(cmd_out)
print(cmd_error)

import subprocess

obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
obj.stdin.write("print(1)\n")
obj.stdin.write("print(2)")

out_error_list = obj.communicate()
print(out_error_list)

import subprocess

obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
out_error_list = obj.communicate('print("hello")')
print(out_error_list)

正则表达式

特殊字符：

#".":匹配除换行外的任意字符，只能匹配一个字符
#"^":起始位置匹配
#"$":末尾位置匹配
#"*":匹配*前的字符，0到多次
#"+"：匹配+前的字符，1到多次
#"?":匹配？前的字符，0到1次
#"{}"：re.findall('aa.{1,5}b','aaddbbssbbbaajjddseeaall')#匹配aa与b直接的字符1到5次
#"[]":re.findall('a[a-z]b','aaddbbssbbbaajjddseeaall')
#re.findall('a[0-9]b','aaddbbssbbbaajjddseeaall')
#re.findall('a[^asd]b','aaddbbssbbbaajjddseeaall')#^代表非
#"\":\d数字，\跟元字符去除特殊功能，\s任何空白字符，\w字母数字[a-z0-9A-Z_]，\b匹配位置信息re.findall(r'I\b','I& am abcId')
#"()":
#"|":

函数：

#只匹配起始位置
re.match('com', 'comwwww.eeiiem')
#匹配到一个就结束
re.search('com', 'comwwww.eeicomiem')
#finditer,匹配到后需要循环才能取值
#sub、subn
re.sub("g.t", "have", 'I get A, I got B, I got C',2)#最后的2为替换次数
re.sub("g.t", "have", 'I get A, I got B, I got C')#替换后会返回替换的次数
re.split('\d+', 'one1two2three3four4')#['one', 'two', 'three', 'four', '']

re.findall('\\\\com', 'asssss\comssssaaa')

re.findall(r'\\com', 'asssss\comssssaaa')

re.findall(r'\bam', 'I asssss\comsss am saaa')#匹配时都加上r

正则表达式分组

#分组：去已经提取的的内容中提取数据
import re
origin = "has sddflklfsdkfd4562125121"
r = re.match("h(?P<name>\w+)", origin)#设置匹配到的key值
print(r.group())
#分组
print(r.groups())
print(r.groupdict())

# 无分组
r = re.findall("a\w+", origin)
print(r)
# 有分组
origin = "hello alex bcd abcd lge acd 19"
r = re.findall("a((\w*)c)(d)", origin)
print(r)

# 与分组无关
origin = "hello alex bcd alex lge alex acd 19"
r = re.sub("a\w+", "999", origin, 2)
print(r)

常用正则匹配

IP：
^(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}$
手机号：
^1[3|4|5|8][0-9]\d{8}$
邮箱：
[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+(\.[a-zA-Z0-9_-]+)

match

import re
#macth只从头开始匹配
m = re.match("abc", "abcefg")
m = re.match("[0-9][0-9]", "885467saawswwcc")
m = re.match("[0-9]{0,10}", "885467saawswwcc")

if m:
    print(m)
    print(m.group())

findall

#匹配所有的数字
m = re.findall("[0-9]{1,15}", "885467saawsw4561w2c2c3")
#匹配所有字母
m = re.findall("[a-zA-Z]{1,15}", "885467saawsw4561w1c2c3")
#匹配所有字符
m = re.findall(".+", "885467saawsw4561w1c2c3")
#匹配任意非空
m = re.findall("\S+", "885467s aaw~s%w4&5!61w1c2c3")

if m:
    print(m)

search

#找到第一个匹配的就返回
m = re.search("\d+", "885467s aaw~s%w4&5!61w1c2c3")

if m:
    print(m)
    print(m.group())

sub

#替换
m = re.sub("^\d+", "|", "4saa885467s aaw~s%w4&5!61w1c2c3",count=2)
if m:
    print(m)

对于文件特别大，需要进行正则匹配时，建议先编译再匹配

import re

p = re.compile("^[0-9]")
m = p.match('14534Abc')

print(m.group())

算法

冒泡算法

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#冒泡排序属于简单排序
#时间复杂度O(n),小循环增加了循环的时间，成指数增长，O(n)**2
import random
import time

def bubble_sort(array):
    for i in range(len(array)):
        for j in range(len(array)-1-i):
            #升序排列
            if array[j] > array[j+1]:
                temp = array[j]
                array[j] = array[j+1]
                array[j+1] = temp
    print(array)

if __name__ == '__main__':
    array = []
    for i in range(50000):
        array.append(random.randrange(100000))
    print(array)
    time_start = time.time()
    bubble_sort(array)
    time_end = time.time()
    print(time_end - time_start)

选择排序

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

#循环整个列表，找最小的值，找到后最小值和第一个值交换，
# 接着在剩下的列表中找最小值，与剩下列表中的第一个值交换，直到完成
#时间复杂度，
import random
import time

def selection_sort(array):
    for i in range(len(array)):
        smallest_index = i
        for j in range(i, len(array)):
            #比较时不交换，只更新下标
            if array[smallest_index] > array[j]:
                smallest_index = j
        tmp = array[i]
        array[i] = array[smallest_index]
        array[smallest_index] = tmp
    print(array)

if __name__ == '__main__':
    array = []
    for i in range(50000):
        array.append(random.randrange(100000))
    #print(array)
    time_start = time.time()
    selection_sort(array)
    time_end = time.time()
    print(time_end - time_start)

快速排序

　　

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

"""
设要排序的数组是A[0]……A[N-1]，首先任意选取一个数据（通常选用数组的第一个数）作为关键数据，
然后将所有比它小的数都放到它前面，所有比它大的数都放到它后面，这个过程称为一趟快速排序。
值得注意的是，快速排序不是一种稳定的排序算法，也就是说，多个相同的值的相对位置也许会在算法结束时产生变动　　

注：在待排序的文件中，若存在多个关键字相同的记录，经过排序后这些具有相同关键字的记录之间的相对次序保持不变，
该排序方法是稳定的；若具有相同关键字的记录之间的相对次序发生改变，则称这种排序方法是不稳定的。
要注意的是，排序算法的稳定性是针对所有输入实例而言的。即在所有可能的输入实例中，
只要有一个实例使得算法不满足稳定性要求，则该排序算法就是不稳定的。
"""
import time,random

def quick_sort(array, start, end):
 if start >= end:
  return
 k = array[start]
 #左边标记
 left_flag = start
 #右边标记
 right_flag = end
 #左右旗子不相等
 while left_flag < right_flag:
  #右边的大于左边的，代表继续往左移动旗子
  while left_flag < right_flag and array[right_flag] > k:
   right_flag -= 1
  tmp = array[left_flag]
  array[left_flag] = array[right_flag]
  array[right_flag] = tmp
  #只要交换后，接着左边的旗子开始向右移动
  while left_flag < right_flag and array[left_flag] <= k:
   left_flag += 1
   #上面的loop一跳出，代表左边的旗子现在所在位置的值小于
  tmp = array[left_flag]
  array[left_flag] = array[right_flag]
  array[right_flag] = tmp
  print(array)
  #把问题分两半
  #排左边一半的列表
 quick_sort(array, start, left_flag-1)
 #排右边一半的列表
 quick_sort(array, left_flag+1, end)

if __name__ == '__main__':
 array = []
 for i in range(50000):
  array.append(random.randrange(100000))
 #array = [96, 14, 10, 9, 6, 99, 16, 5, 1, 3, 2, 4, 1, 13, 26, 18, 2, 45, 34, 23, 1, 7, 3, 22, 19, 2]
 #print(array)
 time_start = time.time()
 quick_sort(array, 0, len(array)-1)
 time_end = time.time()
 print(time_end - time_start)

collections系列

counter:对字典进行处理，用于计算元素出现的个数

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections
#计数器,Counter
obj = collections.Counter("asdfghjgioccvbnjrtubvg6782bnsh2bn")
print(obj)
#取前4个数，排序按照从多到少
ret = obj.most_common(4)
print(ret)
#obj:处理完的数据
for k,v in obj.items():
    print(k, v)

#elements：原生的值，未经过加工处理的
for i in obj.elements():
    print(i)

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections
obj = collections.Counter(['11', '22', '33', '44', '55'])
print(obj)
#增加
obj.update(['eric', '11', '11'])
print(obj)
#删除
obj.subtract(['eric', '11', '11'])
print(obj)

有序字典

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections
#列表+字典=有序字典，key取列表中的元素
dic = collections.OrderedDict()
dic['k1'] = 'v1'
dic['k2'] = 'v2'
dic['k3'] = 'v3'
dic['k4'] = 'v4'
dic['k5'] = 'v5'
dic['k6'] = 'v6'
dic['k7'] = 'v7'
dic['k8'] = 'v8'
print(dic)

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections
#列表+字典=有序字典，key取列表中的元素
dic = collections.OrderedDict()
dic['k1'] = 'v1'
dic['k2'] = 'v2'
dic['k3'] = 'v3'
dic['k4'] = 'v4'
dic['k5'] = 'v5'
dic['k6'] = 'v6'
dic['k7'] = 'v7'
dic['k8'] = 'v8'
print(dic)
#移动到最后
dic.move_to_end('k1')
print(dic)
#后进先出
dic.popitem()
print(dic)
#指定取数，pop将取出的数据为己有
ret = dic.pop('k3')
print(dic)
print(ret)
#设置默认值,如果存在不做任何操作，如果不存在则增加
dic.setdefault('k9','22')
print(dic)
#更新
dic.update({'k1':'v1', 'k10':'v10'})
print(dic)

默认字典

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections
values = [11, 22, 33, 44, 55, 66, 77, 88]
my_dict = collections.defaultdict(list)

for value in values:
    if value > 33:
        my_dict['k1'].append(value)
    else:
        my_dict['k2'].append(value)

print(my_dict)

可命名元祖

#创建类,defaultdict
MytupleClass = collections.namedtuple('MytupleClass',['x', 'y', 'z'])
print(help(MytupleClass))
obj = MytupleClass(11, 22, 33)
print(obj.x)
print(obj.y)
print(obj.z)

双向队列

#！/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: wanghuafeng

import collections

d = collections.deque()
#增加一个
d.append('1')
#往左增加
d.appendleft('10')
d.appendleft('1')
print(d)
#统计个数
ret = d.count('1')
print(ret)
#扩展，右边增加
d.extend(['yy', 'qq', '11'])
print(d)
#扩展，左边增加
d.extendleft(['y1y', 'q2q', '131'])

print(d)

#从右取数插入左边
d.rotate(3)
print(d)

单向队列

import queue

#创建单向队列
q = queue.Queue()
#增加数据
q.put('123')
q.put('456')
print(q.qsize())
#按顺序取数据
print(q.get())