本章内容：
- 模块介绍
- time & datetime
- random
- os
- sys
- json & picle
- hashlib
- XML
- requests
- ConfigParser
- logging
- shutil
- subprocess
- argparse
- email （smtplib)
- Excel文件（xlrd,xlsxwriter）
- hashids
| 模块介绍 |
Python Module(模块)，就是一个保存了Python代码的文件。模块能定义函数，类和变量。模块里也能包含可执行的代码。
文件名就是模块名加上后缀.py，在模块内部，模块名存储在全局变量__name__中，是一个string，可以直接在module中通过__name__引用到module name。
模块分为三种：
- 自定义模块
- 内置标准模块（又称标准库）
- 开源模块
导入模块：
- import: 使客户端（导入者）以一个整体获取一个模块。
- from:容许客户端从一个模块文件中获取特定的变量名。
- reload:在不中止Python程序的情况下，提供了一个重新载入模块文件代码的方法。
|
1
2
3
4
|
import module
from module.xx.xx import xx
from module.xx.xx import xx as rename
from module.xx.xx import *
|
模块路径：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
#获取路径import sys
for i in sys.path:
print(i)
#输出结果：S:\MyprojectS:\Python 3.5.1\python35.zip
S:\Python 3.5.1\DLLs
S:\Python 3.5.1\lib #存放标准库
S:\Python 3.5.1
S:\Python 3.5.1\lib\site-packages #存放第三方库，扩充库
#添加路径import sys
import os
pre_path = os.path.abspath('../')
sys.path.append(pre_path) |
开源模块：
| time & datetime 模块 |
时间相关的操作，时间有三种表示方式：
- 时间戳 1970年1月1日之后的秒，即：time.time()
- 格式化的字符串 2014-11-11 11:11， 即：time.strftime('%Y-%m-%d')
- 结构化时间 元组包含了：年、日、星期等... time.struct_time 即：time.localtime()
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
|
import time
print(time.time()) #返回当前系统时间戳（1970年1月1日0时0分0秒开始）
print(time.ctime()) #输出Tue May 17 16:07:11 2016，当前系统时间
print(time.ctime(time.time() - 86400)) #将时间戳转换为字符串格式
print(time.gmtime(time.time() - 86400)) #将时间戳转换为struct_time格式
print(time.localtime(time.time() - 86400)) #将时间戳转换为struct_time格式，返回本地时间
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(5) #sleep停顿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("2016-05-17","%Y-%m-%d")) #将字符串格式转换成struct_time格式
print("----------------------------------------------------------------")
import datetime
print(datetime.date.today()) #输出格式 2016-05-17
print(datetime.date.fromtimestamp(time.time() - 86400)) #2016-05-16 将时间戳转成日期格式
current_time = datetime.datetime.now()
print(current_time) #输出2016-05-17 16:18:28.737561
print(current_time.timetuple()) #返回struct_time格式
print(current_time.replace(2008,8,8)) #输出2008-08-08 16:21:34.798203,返回当前时间,但指定的值将被替换
str_to_date = datetime.datetime.strptime("28/7/08 11:20","%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)
|
| random 模块 |
随机数：
|
1
2
3
4
5
6
7
8
9
10
11
12
|
import random
print(random.random()) #用于生成一个0到1的随机符点数: 0 <= n < 1.0
print(random.randint(1,2)) #用于生成一个指定范围内的整数
print(random.randrange(1,10)) #从指定范围内，按指定基数递增的集合中获取一个随机数
print(random.uniform(1,10)) #用于生成一个指定范围内的随机符点数
print(random.choice('nick')) #从序列中获取一个随机元素
li = ['nick','jenny','car',]
random.shuffle(li) #用于将一个列表中的元素打乱
print(li)
li_new = random.sample(li,2) #从指定序列中随机获取指定长度的片断(从li中随机获取2个元素，作为一个片断返回)
print(li_new)
|
生成随机验证码：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
|
########## 随机验证码 ############import random
temp = ''
for i in range(4):
num = random.randrange(0,4)
if num == 0 or num == 3: #一半的概率
rad2 = random.randrange(0,10)
temp = temp + str(rad2)
else:
rad1 = random.randrange(65,91)
c1 = chr(rad1)
temp = temp + c1
print(temp)
|
| os模块 |
os模块用于提供系统级别的操作
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
|
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 |
| sys模块 |
用于提供对解释器相关的操作
|
1
2
3
4
5
6
7
8
9
|
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 |
# 手写进度条
import sys,time
for ii in range(101):
sys.stdout.write('\r') #每一次清空原行。
sys.stdout.write("%s%% |%s|"%(int(int(ii)/100*100),int(int(ii)/100*100) * '#')) #一共次数除当前次数算进度
sys.stdout.flush() #强制刷新到屏幕
time.sleep(0.05)
手写进度条
| json & picle 模块 |
用于序列化的两个模块
- json，用于字符串 和 python数据类型间进行转换
- pickle，用于python特有的类型 和 python的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
dump()函数接受一个文件句柄和一个数据对象作为参数，把数据对象以特定的格式保存 到给定的文件中。当我们使用load()函数从文件中取出已保存的对象时，pickle知道如何恢复这些对象到它们本来的格式。
dumps()函数执行和dump() 函数相同的序列化。取代接受流对象并将序列化后的数据保存到磁盘文件，这个函数简单的返回序列化的数据。
loads()函数执行和load() 函数一样的反序列化。取代接受一个流对象并去文件读取序列化后的数据，它接受包含序列化后的数据的str对象, 直接返回的对象。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
|
##### json.loads 将字符串转换为python基本数据类型 列表字典 #####import json
l = '["nick","jenny","car"]'
print(l,type(l))
l = json.loads(l)
print(l,type(l))
l = '{"k1":"nick","k2:":"jenny"}'
print(l,type(l))
l = json.loads(l)
print(l,type(l))
##### json.dumps 将python的数据类型列表字典转换为字符串 ######import json
l = ["nick","jenny","car"]
print(l,type(l))
l = json.dumps(l)
print(l,type(l))
l = {"k1":"nick","k2:":"jenny"}
print(l,type(l))
l = json.dumps(l)
print(l,type(l))
##### json dump、load 文件相关 #####import json
l = {"k1":"nick","k2:":"jenny"}
json.dump(l,open('db','w'))
ret = json.load(open('db'))
print(ret)
|
| hashlib 模块 |
用于加密相关的操作，代替了md5模块和sha模块，主要提供md5(), sha1(), sha224(), sha256(), sha384(), and sha512()算法
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
|
import hashlib
# ######## md5 ########hash = hashlib.md5()
# help(hash.update)hash.update(bytes('admin', encoding='utf-8'))
print(hash.hexdigest())
print(hash.digest())
######## sha1 ########hash = hashlib.sha1()
hash.update(bytes('admin', encoding='utf-8'))
print(hash.hexdigest())
# ######## sha256 ########hash = hashlib.sha256()
hash.update(bytes('admin', encoding='utf-8'))
print(hash.hexdigest())
# ######## sha384 ########hash = hashlib.sha384()
hash.update(bytes('admin', encoding='utf-8'))
print(hash.hexdigest())
# ######## sha512 ########hash = hashlib.sha512()
hash.update(bytes('admin', encoding='utf-8'))
print(hash.hexdigest())
##### 加盐 ####### ######## md5 ########hash = hashlib.md5(bytes('898oaFs09f',encoding="utf-8"))
hash.update(bytes('admin',encoding="utf-8"))
print(hash.hexdigest())
#python内置还有一个 hmac 模块，它内部对我们创建 key 和 内容 进行进一步的处理然后再加密import hmac
h = hmac.new(bytes('898oaFs09f',encoding="utf-8"))
h.update(bytes('admin',encoding="utf-8"))
print(h.hexdigest())
|
| XML 模块 |
XML是实现不同语言或程序之间进行数据交换的协议，XML文件格式如下：
<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>
1、解析XML
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
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
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
源码
|
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 ############ b、遍历XML中指定的节点 from xml.etree import ElementTree as ET ############ 解析方式一 ############ 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。 from xml.etree import ElementTree as ET ############ 解析方式一 ############ # 打开文件，读取XML内容 解析字符串方式，修改，保存 from xml.etree import ElementTree as ET ############ 解析方式二 ############ # 直接解析xml文件 解析文件方式，修改，保存 d、删除节点 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 解析字符串方式打开，删除，保存 from xml.etree import ElementTree as ET ############ 解析文件方式 ############ # 直接解析xml文件 解析文件方式打开，删除，保存 |
3、创建XML文档
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）
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）
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）
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()
写入缩进
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": ""})
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
| requests 模块 |
Python标准库中提供了：urllib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务。
import urllib.request
f=urllib.request.urlopen('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
result = f.read().decode('utf-8')
发送GET请求
import urllib.request
req = urllib.request.Request('http://www.example.com/')
req.add_header('Referer', 'http://www.python.org/')
r = urllib.request.urlopen(req)
result = f.read().decode('utf-8')
发送携带请求头的GET请求
注：更多见Python官方文档：https://docs.python.org/3.5/library/urllib.request.html#module-urllib.request
Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在Python内置模块的基础上进行了高度的封装，从而使得Pythoner进行网络请求时，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。
1、安装模块
|
1
|
pip3 install requests |
2、使用模块
# 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
更多requests模块相关的文档见：http://cn.python-requests.org/zh_CN/latest/
3、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=630571017')
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/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")
检测QQ账号是否在线
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'):
print(node.find('TrainStation').text,node.find('StartTime').text,node.tag,node.attrib)
查看火车停靠信息
实例：查看天气信息
import requests
response = requests.get("http://www.weather.com.cn/data/sk/101010100.html")
response.encoding = "utf-8"
result = response.text
print(result)
查看天气信息
| configparser 模块 |
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
;注释2 [nick] #节点
age = 18 #值
gender = ning #值
dearm = girl #值 [jenny] #节点
age = 21 #值
gender = jia #值
1、获取所有节点
|
1
2
3
4
5
6
7
|
import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
result = con.sections()
print(result)
|
2、获取指定节点下所有的键值对
|
1
2
3
4
5
6
7
|
import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
result = con.items("nick")
print(result)
|
3、获取指定节点下所有的键
|
1
2
3
4
5
6
7
|
import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
ret = con.options("nick")
print(ret)
|
4、获取指定节点下指定key的值
|
1
2
3
4
5
6
7
8
9
10
|
import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
v = con.get("nick","age")
v = con.get("nick","gender")
v = con.get("jenny","age")
v = con.get("jenny","gender")
print(v)
|
5、检查、删除、添加节点
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
#检查、删除、添加节点import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
#检查has_sec = con.has_section("nick")
print(has_sec)
#添加节点con.add_section("car")
con.write(open("ini","w"))
#删除节点con.remove_section("car")
con.write(open("ini","w"))
|
6、检查、删除、设置指定组内的键值对
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
|
#检查、删除、设置指定组内的键值对import configparser
con = configparser.ConfigParser()
con.read("ini",encoding="utf-8")
#检查hac_opt = con.has_option("nick","age")
print(hac_opt)
#删除con.remove_option("nick","dearm")
con.write(open("ini","w"))
#设置con.set("nick","dearm","girl")
con.write(open("ini","w"))
|
| logging 模块 |
用于便捷记录日志且线程安全的模块
1、单日志文件
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
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=logging.INFO)
logging.critical("critical")
logging.fatal("fatal")
logging.error("error")
logging.warn("warn")
logging.warning("warning")
logging.info("info")
logging.debug("debug")
logging.log(8,"log")
|
日志等级
""" |
注：只有【当前写等级】大于【日志等级】时，日志文件才被记录。
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。
# 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('')
日志（一）
# 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
import os
import logging
from logging.handlers import TimedRotatingFileHandler base = os.path.abspath(os.path.dirname(__file__))
logfile = os.path.join(base, 'test', 'testlog')
handler = TimedRotatingFileHandler(filename=logfile, when='MIDNIGHT',
interval=1, backupCount=365)
handler.suffix = "%Y%m%d.log"
handler.setFormatter(logging.Formatter('%(asctime)s\t%(levelname)-8s\t%(message)s'))
handler.setLevel(logging.DEBUG)
apipartnerlogger = logging.getLogger(logfile)
apipartnerlogger.addHandler(handler)
apipartnerlogger.setLevel(logging.INFO)
记录日志及按天切割实例
| shutil 模块 |
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
|
1
2
3
|
import shutil
shutil.copyfileobj(open('old.xml','r'), open('new.xml', 'w'))
|
shutil.copyfile(src, dst)
拷贝文件
|
1
|
shutil.copyfile('f1.log', 'f2.log')
|
shutil.copymode(src, dst)
仅拷贝权限。内容、组、用户均不变
|
1
|
shutil.copymode('f1.log', 'f2.log')
|
shutil.copystat(src, dst)
拷贝状态的信息，包括：mode bits, atime, mtime, flags
|
1
|
shutil.copystat('f1.log', 'f2.log')
|
shutil.copy(src, dst)
拷贝文件和权限
|
1
2
3
|
import shutil
shutil.copy('f1.log', 'f2.log')
|
shutil.copy2(src, dst)
拷贝文件和状态信息
|
1
2
3
|
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
|
1
2
3
|
import shutil
shutil.copytree('folder1', 'folder2', ignore=shutil.ignore_patterns('*.pyc', 'tmp*'))
|
shutil.rmtree(path[, ignore_errors[, onerror]])
递归的去删除文件
|
1
2
3
|
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。
|
1
2
3
|
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
|
1
2
3
4
5
6
7
8
|
#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
z = zipfile.ZipFile("ini.zip","w")
z.write("ini")
z.write("pip")
z.close()
#压缩包里追加内容（打开模式变为a）
#z = zipfile.ZipFile("ini.zip","a")
#z.write("db")
z.close()
#解压
z = zipfile.ZipFile("ini.zip","r")
z.extractall() #解压全部
# z.extract("pip") #解压指定文件
z.close()
zipfile解压缩
import tarfile #压缩
tar = tarfile.open("ini.zip","w")
tar.add("S:\stud\ini",arcname="iiini.txt") #路径、重命名
tar.add("./pip",arcname="pip.log")
tar.close() #解压
tar = tarfile.open("ini.zip","r")
tar.extractall() #可设置解压地址
tar.close()
tarfile解压缩
| subprocess |
可以执行shell命令的相关模块和函数有：
- os.system
- os.spawn*
- os.popen* --废弃
- popen2.* --废弃
- commands.* --废弃，3.x中被移除
import commands
result = commands.getoutput('cmd')
result = commands.getstatus('cmd')
result = commands.getstatusoutput('cmd')
commands
以上执行shell命令的相关的模块和函数的功能均在 subprocess 模块中实现，并提供了更丰富的功能。
call
执行命令，返回状态码
|
1
2
|
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
|
1
2
|
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
|
1
2
|
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)
执行普通命令
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)
Argparse
argparse — 命令行选项、参数和子命令的解析器， 官方文档
# -*- coding: utf-8 -*-
__author__ = 'suoning' import argparse
parser = argparse.ArgumentParser() parser.add_argument("echo", help="echo the String you ues here")
parser.add_argument("num", help="echo the String you ues here", type=int) parser.add_argument("-v", "--version", help="--version", action="store_true")
parser.add_argument("-c", help="all_count", action="count", default=95) args = parser.parse_args() print "Hello, %s." % args.echo
if args.num > 9:
print "The num ori is %s, *10 after change %s" % (args.num, args.num * 10)
else:
print "The num ori is %s, not change" % args.num
if args.version:
print "version 0.1.520"
print args.c """
use:
python me_argparse.py nick 10 -v -ccccc
ret:
Hello, nick.
The num ori is 10, *10 after change 100
version 0.1.520
100
"""
smtplib
# -*- coding: utf-8 -*-
__author__ = 'suoning' import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText me = '发送的邮箱@net263.com'
you = '接收的邮箱@net263.com' try:
s = smtplib.SMTP()
s.connect('smtp.263.net')
s.login(me, 'me's password') msg = MIMEMultipart('alternative')
msg['Subject'] = "Alert 主题"
msg['From'] = me
msg['To'] = you html = '<html><body><p>Hi, I have the following alerts for you!</p></body></html>'
part2 = MIMEText(html, 'html')
msg.attach(part2) s.sendmail(me, you, msg.as_string())
s.quit() except Exception, e:
print e
Excel文件（xlrd,xlsxwriter）
# -*- coding: utf-8 -*-
__author__ = 'suoning' import xlrd data = xlrd.open_workbook('F:\\message\\test.xlsx') # 获取一个工作表
# table = data.sheets()[0]
# table = data.sheet_by_index(0)
table = data.sheet_by_name(u'Sheet1') # 获取行数和列数
nrows = table.nrows
# nrows = table.ncols # 使用行列索引
cell_A1 = table.row(0)[0].value
cell_A2 = table.col(1)[0].value
print cell_A1, cell_A2 # 单元格
cell_C1 = table.cell(0, 0).value
cell_C2 = table.cell(2, 1).value
print cell_C1, cell_C2 for i in range(nrows):
print table.row_values(i)
# # 获取整行和整列的值(数组)
# table.row_values(i)
# table.col_values(i) # 写入 import xlsxwriter # 建立文件
workbook = xlsxwriter.Workbook('F:\\message\\test.xlsx')
# 建立sheet， 可以work.add_worksheet('employee')来指定sheet名，但中文名会报UnicodeDecodeErro的错误
worksheet = workbook.add_worksheet()
# 向A1写入
worksheet.write('A1', 'Hello world')
worksheet.write('B1', '2017-02-13') workbook.close()
hashids
JavaScript hashids实现的python端口。它从一个或多个数字生成类似于tubea的散列。当您不想向用户公开数据库id时使用hashids。
pip install hashids
>>> from hashids import Hashids
>>>
>>> Hashids().encode(5201314)
'zpAmDO'
>>> Hashids("suoning").encode(5201314)
'QEgpxq'
>>>
>>> Hashids("suoning").encode(5201314)
'QEgpxq'
>>>
Encode a single integer:
hashid = hashids.encode(123) # 'Mj3'
Decode a hash:
ints = hashids.decode('xoz') # (456,)
To encode several integers, pass them all at once:
hashid = hashids.encode(123, 456, 789) # 'El3fkRIo3'
Decoding is done the same way:
ints = hashids.decode('1B8UvJfXm') # (517, 729, 185)
Using A Custom Salt
Hashids supports salting hashes by accepting a salt value. If you don’t want others to decode your hashes, provide a unique string to the constructor.
hashids = Hashids(salt='this is my salt 1')
hashid = hashids.encode(123) # 'nVB'
The generated hash changes whenever the salt is changed:
hashids = Hashids(salt='this is my salt 2')
hashid = hashids.encode(123) # 'ojK'
Controlling Hash Length
By default, hashes are going to be the shortest possible. One reason you might want to increase the hash length is to obfuscate how large the integer behind the hash is.
This is done by passing the minimum hash length to the constructor. Hashes are padded with extra characters to make them seem longer.
hashids = Hashids(min_length=16)
hashid = hashids.encode(1) # '4q2VolejRejNmGQB' Using A Custom Alphabet
It’s possible to set a custom alphabet for your hashes. The default alphabet is 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890'.
To have only lowercase letters in your hashes, pass in the following custom alphabet:
hashids = Hashids(alphabet='abcdefghijklmnopqrstuvwxyz')
hashid = hashids.encode(123456789) # 'kekmyzyk'Randomness
The primary purpose of hashids is to obfuscate ids. It’s not meant or tested to be used for security purposes or compression. Having said that, this algorithm does try to make these hashes unguessable and unpredictable:
Repeating numbers
There are no repeating patterns that might show that there are 4 identical numbers in the hash:
hashids = Hashids("this is my salt")
hashids.encode(5, 5, 5, 5) # '1Wc8cwcE'
The same is valid for incremented numbers:
hashids.encode(1, 2, 3, 4, 5, 6, 7, 8, 9, 10) # 'kRHnurhptKcjIDTWC3sx'
hashids.encode(1) # 'NV' hashids.encode(2) # '6m' hashids.encode(3) # 'yD' hashids.encode(4) # '2l' hashids.encode(5) # 'rD'