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('dirname1/dirname2') 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","newname") 重命名文件/目录
os.stat('path/filename') 获取文件/目录信息
os.sep 输出操作系统特定的路径分隔符，win下为"\\",Linux下为"/"
os.linesep 输出当前平台使用的行终止符，win下为"\t\n",Linux下为"\n"
os.pathsep 输出用于分割文件路径的字符串
os.name 输出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
2、sys用于提供对解释器相关的操作
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.stdout.write('please:')
val = sys.stdin.readline()[:-1]
3.hashlib #加密
文件中对密码进行加密
import hashlib
def md5(pwd):
hash=hashlib.md5(bytes('xx7',encoding='utf-8'))
hash.update(bytes(pwd,encoding='utf-8'))
return hash.hexdigest()
def login(usr,pwd): #登陆
with open('db','r') as f:
for line in f:
u,p=line.strip().split('|')
if u==usr and p==md5(pwd): #和加密后的密码进行比较
return True
else:
return False
def register(usr,pwd): #注册
with open('db','a') as f:
temp=usr+'|'+md5(pwd) #写入加密后的密码
f.write(temp)
usr=input('usr:')
pwd=input('pwd:')
inp=input('1.register 2.login')
if inp=='1':
register(usr,pwd)
elif inp=='2':
r=login(usr,pwd)
if r:
print('ok')
else:
print('no')
4.json & pickle 模块
Python中用于序列化的两个模块
- json 用于【字符串】和 【python基本数据类型】 间进行转换
- pickle 用于【python特有的类型】 和 【python基本数据类型】间进行转换
Json模块提供了四个功能：dumps、dump、loads、load
pickle模块提供了四个功能：dumps、dump、loads、load
json.loads()#将字符串 转换成 python基本数据类型 便于读取 #注意：json.loads() 如果内容是字典，里面必须是双引号
json.dumps#将python的基本数据类型 转换成 字符串 便于写入文件
import json
li = "[11,22,33,44,55,66,77,88,99]"
dic = '{"5":"inviload"}' #中间必须是双引号
print(json.loads(li))
print(json.loads(dic))
dic1 = {"5":"inviload"}
print(json.dumps(dic1),type(json.dumps(dic1)))
5.系统自带的全局变量
__doc__ 文件注释
__file__ 当前文件路径
__package__ 指定文件所在的包，用.分割 当前文件None
__cached__ 缓存 当前文件None
__name__ 主文件 __name__=="__main__",否则，等于模块名
目录的拼接，添加同一级文件夹到path
添加bin目录到path
6.第三方模块的安装
下载安装：1.将pip目录添加在系统环境变量中
2.pip3 install requests
源码安装：1.下载，解压，终端进入目录，执行python setup.py install
7.requests 模块
import requests
r=requests.get('http://www.weather.com.cn/adat/sk/101010500.html') #获取文件内容
r.encoding='utf-8'
result=r.text #提取文件内容
print(result)
# 1、无参数实例
import requests
ret = requests.get('https://github.com/timeline.json')
print(ret.url)
print(ret.text)
# 2、有参数实例
import requests
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.get("http://httpbin.org/get", params=payload)
print(ret.url)
print(ret.text)
GET请求
# 1、基本POST实例
import requests
payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.post("http://httpbin.org/post", data=payload)
print(ret.text)
# 2、发送请求头和数据实例
import requests
import json
url = 'https://api.github.com/some/endpoint'
payload = {'some': 'data'}
headers = {'content-type': 'application/json'}
ret = requests.post(url, data=json.dumps(payload), headers=headers)
print(ret.text)
print(ret.cookies)
POST请求
requests.get(url, params=None, **kwargs) requests.post(url, data=None, json=None, **kwargs) requests.put(url, data=None, **kwargs) requests.head(url, **kwargs) requests.delete(url, **kwargs) requests.patch(url, data=None, **kwargs) requests.options(url, **kwargs) # 以上方法均是在此方法的基础上构建 requests.request(method, url, **kwargs) 其他请求
8.Http请求和XML实例
实例：检测QQ账号是否在线
import urllib
import requests
from xml.etree import ElementTree as ET
# 使用内置模块urllib发送HTTP请求，或者XML格式内容
"""
f = urllib.request.urlopen('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
result = f.read().decode('utf-8') #结果为字符串
"""
# 使用第三方模块requests发送HTTP请求，或者XML格式内容
r = requests.get('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
result = r.text
# 解析XML格式内容
node = ET.XML(result)
# 获取内容
if node.text == "Y":
print("在线")
else:
print("离线")
实例：查看火车停靠信息
import urllib
import requests
from xml.etree import ElementTree as ET
# 使用内置模块urllib发送HTTP请求，或者XML格式内容
"""
f = urllib.request.urlopen('http://www.webxml.com.cn/WebServices/TrainTimeWebService.asmx/getDetailInfoByTrainCode?TrainCode=G666&UserID=')
result = f.read().decode('utf-8')
"""
# 使用第三方模块requests发送HTTP请求，或者XML格式内容
r = requests.get('http://www.webxml.com.cn/WebServices/TrainTimeWebService.asmx/getDetailInfoByTrainCode?TrainCode=G666&UserID=')
result = r.text
# 解析XML格式内容
root = ET.XML(result)
for node in root.iter('TrainDetailInfo'): #.iter遍历每一个节点
print(node.find('TrainStation').text,node.find('StartTime').text,node.tag,node.attrib) #.text提取值 .tag获取标签名 .attrib 获取标签属性
set 添加属性 del 删除属性
import requests
from xml.etree import ElementTree
tree=ElementTree.parse('fist.xml') #一种可以保存的打开方式
root=tree.getroot() #获取根节点
print(root.get) # 获取元素属性
for node in root.iter('year'):
new_year=int(node.text)+1
node.text=str(new_year)
node.set('name','alex') #设置属性
del node.attrib['name'] #删除属性
tree.write('fist.xml') #重新写入文件
创建XML文档
from xml.etree import ElementTree as ET
# 创建根节点
new_xml = ET.Element("namelist")
# 创建根节点的子节点
name1 = ET.SubElement(new_xml, "name", attrib={"enrolled": "yes"})
age1 = ET.SubElement(name1, "age", attrib={"checked": "no"})
sex1 = ET.SubElement(name1, "sex")
sex1.text = '33'
# 创建根节点的子节点
name2 = ET.SubElement(new_xml, "name", attrib={"enrolled": "no"})
age2 = ET.SubElement(name2, "age")
age2.text = '19'
et = ET.ElementTree(new_xml) #生成文档对象
et.write("test.xml", encoding="utf-8", xml_declaration=True)
创建结果
<namelist>
<name enrolled="yes">
<age checked="no" />
<sex>33</sex>
</name>
<name enrolled="no">
<age>19</age>
</name>
</namelist>
XML补充
8.1、解析XML
利用ElementTree.xml将 字符串 解析成xml对象
from xml.etree import ElementTree as ET
# 打开文件，读取XML内容
str_xml = open('xo.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)
利用ElementTree.XML将字符串解析成xml对象
利用ElementTree.parse将 文件 直接解析成xml对象
from xml.etree import ElementTree as ET
# 直接解析xml文件
tree = ET.parse("xo.xml")
# 获取xml文件的根节点
root = tree.getroot()
利用ElementTree.parse将文件直接解析成xml对象
8.2 操作XML
XML格式类型是节点嵌套节点，对于每一个节点均有以下功能，以便对当前节点进行操作：
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
由于 每个节点 都具有以上的方法，并且在上一步骤中解析时均得到了root（xml文件的根节点），so 可以利用以上方法进行操作xml文件。
a. 遍历XML文档的所有内容
from xml.etree import ElementTree as ET
############ 解析方式一 ############
"""
# 打开文件，读取XML内容
str_xml = open('xo.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)
"""
############ 解析方式二 ############
# 直接解析xml文件
tree = ET.parse("xo.xml")
# 获取xml文件的根节点
root = tree.getroot()
### 操作
# 顶层标签
print(root.tag)
# 遍历XML文档的第二层
for child in root:
# 第二层节点的标签名称和标签属性
print(child.tag, child.attrib)
# 遍历XML文档的第三层
for i in child:
# 第二层节点的标签名称和内容
print(i.tag,i.text)
b、遍历XML中指定的节点
from xml.etree import ElementTree as ET
############ 解析方式一 ############
"""
# 打开文件，读取XML内容
str_xml = open('xo.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)
"""
############ 解析方式二 ############
# 直接解析xml文件
tree = ET.parse("xo.xml")
# 获取xml文件的根节点
root = tree.getroot()
### 操作
# 顶层标签
print(root.tag)
# 遍历XML中所有的year节点
for node in root.iter('year'):
# 节点的标签名称和内容
print(node.tag, node.text)
c、修改节点内容
由于修改的节点时，均是在内存中进行，其不会影响文件中的内容。所以，如果想要修改，则需要重新将内存中的内容写到文件。
解析字符串方式，修改，保存
from xml.etree import ElementTree as ET
############ 解析方式一 ############
# 打开文件，读取XML内容
str_xml = open('xo.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', '18')
# 删除属性
del node.attrib['name']
############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("newnew.xml", encoding='utf-8')
解析字符串方式，修改，保存
解析文件方式，修改，保存
from xml.etree import ElementTree as ET
############ 解析方式二 ############
# 直接解析xml文件
tree = ET.parse("xo.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', '18')
# 删除属性
del node.attrib['name']
############ 保存文件 ############
tree.write("newnew.xml", encoding='utf-8')
解析文件方式，修改，保存
d、删除节点
解析 字符串 方式，删除，保存
from xml.etree import ElementTree as ET
############ 解析字符串方式打开 ############
# 打开文件，读取XML内容
str_xml = open('xo.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)
# 遍历data下的所有country节点
for country in root.findall('country'):
# 获取每一个country节点下rank节点的内容
rank = int(country.find('rank').text)
if rank > 50:
# 删除指定country节点
root.remove(country)
############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("newnew.xml", encoding='utf-8')
解析字符串方式打开，删除，保存
解析 文件 方式，删除，保存
from xml.etree import ElementTree as ET
############ 解析文件方式 ############
# 直接解析xml文件
tree = ET.parse("xo.xml")
# 获取xml文件的根节点
root = tree.getroot()
############ 操作 ############
# 顶层标签
print(root.tag)
# 遍历data下的所有country节点
for country in root.findall('country'):
# 获取每一个country节点下rank节点的内容
rank = int(country.find('rank').text)
if rank > 50:
# 删除指定country节点
root.remove(country)
############ 保存文件 ############
tree.write("newnew.xml", encoding='utf-8')
解析文件方式打开，删除，保存
3、创建XML文档
方式一：
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.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('oooo.xml',encoding='utf-8', short_empty_elements=False)
创建方式（一）
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)
创建方式（二）
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)
创建方式（三）
设置缩进
由于原生保存的XML时默认无缩进，如果想要设置缩进的话， 需要修改保存方式：
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("xxxoo.xml",'w',encoding='utf-8')
f.write(raw_str)
f.close()
4、命名空间
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": "123"})
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")
命名空间
9.time & datetime模块
#_*_coding:utf-8_*_
import time
import datetime
print(time.clock()) #返回处理器时间,3.3开始已废弃
print(time.process_time()) #返回处理器时间,3.3开始已废弃
print(time.time()) #返回当前系统时间戳
print(time.ctime()) #输出Tue Jan 26 18:23:48 2016 ,当前系统时间
print(time.ctime(time.time()-86640)) #将时间戳转为字符串格式
print(time.gmtime(time.time()-86640)) #将时间戳转换成struct_time格式
print(time.localtime(time.time()-86640)) #将时间戳转换成struct_time格式,但返回 的本地时间
print(time.mktime(time.localtime())) #与time.localtime()功能相反,将struct_time格式转回成时间戳格式
#time.sleep(4) #sleep
print(time.strftime("%Y-%m-%d %H:%M:%S",time.gmtime()) ) #将struct_time格式转成指定的字符串格式
print(time.strptime("2016-01-28","%Y-%m-%d") ) #将字符串格式转换成struct_time格式
#datetime module
print(datetime.date.today()) #输出格式 2016-01-26
print(datetime.date.fromtimestamp(time.time()-864400) ) #2016-01-16 将时间戳转成日期格式
current_time = datetime.datetime.now() #
print(current_time) #输出2016-01-26 19:04:30.335935
print(current_time.timetuple()) #返回struct_time格式
#datetime.replace([year[, month[, day[, hour[, minute[, second[, microsecond[, tzinfo]]]]]]]])
print(current_time.replace(2014,9,12)) #输出2014-09-12 19:06:24.074900,返回当前时间,但指定的值将被替换
str_to_date = datetime.datetime.strptime("21/11/06 16:30", "%d/%m/%y %H:%M") #将字符串转换成日期格式
new_date = datetime.datetime.now() + datetime.timedelta(days=10) #比现在加10天
new_date = datetime.datetime.now() + datetime.timedelta(days=-10) #比现在减10天
new_date = datetime.datetime.now() + datetime.timedelta(hours=-10) #比现在减10小时
new_date = datetime.datetime.now() + datetime.timedelta(seconds=120) #比现在+120s
print(new_date)
| Directive | Meaning | Notes |
|---|---|---|
%a |
Locale’s abbreviated weekday name. | |
%A |
Locale’s full weekday name. | |
%b |
Locale’s abbreviated month name. | |
%B |
Locale’s full month name. | |
%c |
Locale’s appropriate date and time representation. | |
%d |
Day of the month as a decimal number [01,31]. | |
%H |
Hour (24-hour clock) as a decimal number [00,23]. | |
%I |
Hour (12-hour clock) as a decimal number [01,12]. | |
%j |
Day of the year as a decimal number [001,366]. | |
%m |
Month as a decimal number [01,12]. | |
%M |
Minute as a decimal number [00,59]. | |
%p |
Locale’s equivalent of either AM or PM. | (1) |
%S |
Second as a decimal number [00,61]. | (2) |
%U |
Week number of the year (Sunday as the first day of the week) as a decimal number [00,53]. All days in a new year preceding the first Sunday are considered to be in week 0. | (3) |
%w |
Weekday as a decimal number [0(Sunday),6]. | |
%W |
Week number of the year (Monday as the first day of the week) as a decimal number [00,53]. All days in a new year preceding the first Monday are considered to be in week 0. | (3) |
%x |
Locale’s appropriate date representation. | |
%X |
Locale’s appropriate time representation. | |
%y |
Year without century as a decimal number [00,99]. | |
%Y |
Year with century as a decimal number. | |
%z |
Time zone offset indicating a positive or negative time difference from UTC/GMT of the form +HHMM or -HHMM, where H represents decimal hour digits and M represents decimal minute digits [-23:59, +23:59]. | |
%Z |
Time zone name (no characters if no time zone exists). | |
%% |
A literal '%' character. |
十、logging 模块
用于便捷记录日志且线程安全的模块
1、单文件日志
import logging logging.basicConfig(filename='log.log', format='%(asctime)s - %(name)s - %(levelname)s -%(module)s: %(message)s', datefmt='%Y-%m-%d %H:%M:%S %p', level=10) #一般写 level=logging.INFO
logging.debug('debug')
logging.info('info')
logging.warning('warning')
logging.error('error')
logging.critical('critical')
logging.log(10,'log')
日志等级：
CRITICAL = 50 FATAL = CRITICAL ERROR = 40 WARNING = 30 WARN = WARNING INFO = 20 DEBUG = 10 NOTSET = 0
注：只有【当前写等级】大于【日志等级】时，日志文件才被记录。
日志记录格式：
2、多文件日志
对于上述记录日志的功能，只能将日志记录在单文件中，如果想要设置多个日志文件，logging.basicConfig将无法完成，需要自定义文件和日志操作对象。
日志1：
# 定义文件
file_1_1 = logging.FileHandler('l1_1.log', 'a')
fmt = logging.Formatter(fmt="%(asctime)s - %(name)s - %(levelname)s -%(module)s: %(message)s")
file_1_1.setFormatter(fmt)
file_1_2 = logging.FileHandler('l1_2.log', 'a')
fmt = logging.Formatter()
file_1_2.setFormatter(fmt)
# 定义日志
logger1 = logging.Logger('s1', level=logging.ERROR)
logger1.addHandler(file_1_1)
logger1.addHandler(file_1_2)
# 写日志
logger1.critical('1111')
日志（一）
日志2：
# 定义文件
file_2_1 = logging.FileHandler('l2_1.log', 'a')
fmt = logging.Formatter()
file_2_1.setFormatter(fmt)
# 定义日志
logger2 = logging.Logger('s2', level=logging.INFO)
logger2.addHandler(file_2_1)
日志（二）
如上述创建的两个日志对象
- 当使用【logger1】写日志时，会将相应的内容写入 l1_1.log 和 l1_2.log 文件中
- 当使用【logger2】写日志时，会将相应的内容写入 l2_1.log 文件中
十一、系统命令 subprocess 模块
call 执行命令，返回状态码：正常返回0
ret = subprocess.call(["ls", "-l"], shell=False)
ret = subprocess.call("ls -l", shell=True)
check_call 执行命令，如果执行状态码是 0 ，则返回0，否则抛异常
subprocess.check_call(["ls", "-l"])
subprocess.check_call("exit 1", shell=True)
check_output 执行命令，如果状态码是 0 ，则返回执行结果，否则抛异常
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
执行普通命令：
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)")
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)
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)
out_error_list = obj.communicate('print("hello")')
print(out_error_list)
十二、shutil
高级的 文件、文件夹、压缩包 处理模块
shutil.copyfileobj(fsrc, fdst[, length])
将文件内容拷贝到另一个文件中，可指定长度，复制模式w和a模式
import shutil
shutil.copyfileobj(open('old.xml','r'), open('new.xml', 'w'))
shutil.copyfile(src, dst)
拷贝文件
shutil.copyfile('f1.log', 'f2.log')
shutil.copymode(src, dst)
仅拷贝权限。内容、组、用户均不变
shutil.copymode('f1.log', 'f2.log')
shutil.copystat(src, dst)
拷贝状态的信息，包括：mode bits, atime, mtime, flags
shutil.copystat('f1.log', 'f2.log')
shutil.copy(src, dst)
拷贝文件和权限
import shutil
shutil.copy('f1.log', 'f2.log')
shutil.copy2(src, dst)
拷贝文件和状态信息
import shutil
shutil.copy2('f1.log', 'f2.log')
shutil.ignore_patterns(*patterns)
shutil.copytree(src, dst, symlinks=False, ignore=None)
递归的去拷贝文件夹
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*'))
shutil.rmtree(path[, ignore_errors[, onerror]])
递归的去删除文件
import shutil
shutil.rmtree('folder1')
shutil.move(src, dst)
递归的去移动文件，它类似mv命令，其实就是重命名
import shutil
shutil.move('folder1', 'folder3')
shutil.make_archive(base_name, format,...)
创建压缩包并返回文件路径，例如：zip、tar
创建压缩包并返回文件路径，例如：zip、tar
- 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：
zipfile 解压缩
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.close()
zipfile解压缩
tarfile 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
tar.close()
tarfile解压缩
十三、configparser 配置文件处理
configparser用于处理特定格式的文件，其本质上是利用open来操作文件。
指定格式：
# 注释1 ; 注释2 [section1] # 节点 k1 = v1 # 值 k2:v2 # 值 [section2] # 节点 k1 = v1 # 值 指定格式
1、获取所有节点
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
ret = config.sections()
print(ret)
2、获取指定节点下所有的键值对
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
ret = config.items('section1')
print(ret)
3.获取指定节点下所有的建
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
ret = config.options('section1')
print(ret)
4.获取指定节点下指定key的值
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
v = config.get('section1', 'k1')
# v = config.getint('section1', 'k1')
# v = config.getfloat('section1', 'k1')
# v = config.getboolean('section1', 'k1')
print(v)
5.检查、删除、添加节点
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
# 检查
has_sec = config.has_section('section1')
print(has_sec)
# 添加节点
config.add_section("SEC_1")
config.write(open('xxxooo', 'w'))
# 删除节点
config.remove_section("SEC_1")
config.write(open('xxxooo', 'w'))
6.检查、删除、设置指定组内的键值对
import configparser
config = configparser.ConfigParser()
config.read('xxxooo', encoding='utf-8')
# 检查
has_opt = config.has_option('section1', 'k1')
print(has_opt)
# 删除
config.remove_option('section1', 'k1')
config.write(open('xxxooo', 'w'))
# 设置
config.set('section1', 'k10', "123")
config.write(open('xxxooo', 'w'))
