-
文件内置函数
Pyhon文件里面自带一些函数，打开一个文件print(vars())，就可以查看文件自带的函数
__doc__ # py文件的注释 __file__ # 当前文件路径 __package__ # 当前文件 None # 导入的其他文件：指定文件所在包，用 . 分隔， __cached__ #作缓存使用 # 当前文件 None # 导入的其他文件 __name__ # 如果是主文件， __name__ == "__main__" 否则，等于模块名
注：
调用主函数前，必须加：
if __name__ == "__main__":
当前文件路径：__file__
在当前文件操作将lib文件添加到sys.path[]中
#需要使用os sys模块 import os import sys print(__file__) p1 = os.path.dirname(__file__) print(p1) p2 = "lib" p3 = os.path.join(p1,p2) sys.path.append(p3) print(sys.path) #打印结果： E:/Python-study/week05/day011/demo.py E:/Python-study/week05/day011 ['E:\Python-study\week05\day011', 'E:\Python-study', 'D:\myProgram\Python35\python35.zip', 'D:\myProgram\Python35\DLLs', 'D:\myProgram\Python35\lib', 'D:\myProgram\Python35', 'D:\myProgram\Python35\lib\site-packages', 'E:/Python-study/week05/day011\lib']
存放内置函数：__builtins__
-
如何安装第三方模块
# 1、安装 # 软件管理工具 pip3 # pip3路径添加到环境变量 # pip3路径： C:Python35Scripts # 添加环境变量：【右键计算机】—》【属性】—》【高级系统设置】—》【高级】—》【环境变量】—》【在第二个内容框中找到 变量名为Path 的一行，双击】 —> 【Python安装目录追加到变值值中，用 ； 分割】 # pip3 install requests # 2、源码安装 # 下载代码，安装 #1 先下载 # https://github.com/kennethreitz/requests/tarball/master # 2、解压 # 3、进入目录 # 4、执行python setup.py install
-
XML
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
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 ret = open('first.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(ret)
利用ElementTree.parse将文件解析成xml对象：
from xml.etree import ElementTree as ET # 获取xml文件内容 tree = ET.parse("xo.xml") # .getroot()获取xml文件的根节点 root = tree.getroot()
2、操作XML
XML格式类型是节点嵌套节点，对于每一个节点都有一些功能，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
常用操作：
.tag()：获取标签名
.attrib()：获取标签属性
.text()：标签内容
.find()：找到标签
.iter()：遍历XML中的某一节点
.get()：获取属性
.set()：设置属性
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
修改时是在内存中进行，不会影响文件中的内容。所以，如果想要修改，就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')
d、删除节点：.remove(标签名)
解析字符串方式打开，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')
解析文件方式打开，删除，保存：
from xml.etree import ElementTree as ET ############ 解析文件方式 ############ # 直接解析xml文件 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')
3、创建XML文档
ET.Element(标签名，{属性})
.makeelement(标签名，{属性})
ET.SubElement(标签名，{属性})
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)
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)
设置缩进
由于原生保存的XML时默认没有缩进，会显得格式混乱。so，为了有一个好看的格式，我们就要设置缩进，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=" ") # 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
说明连接：http://www.w3school.com.cn/xml/xml_namespaces.asp
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")
-
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。
白话：用Python模拟浏览器浏览网页
下面用requests来实现浏览网页：
import requests #导入requests模块 res = requests.get("http://www.weather.com.cn/adat/sk/101010500.html") #发送请求 res.encoding = "utf-8" result = res.text #.text表示返回内容 print(result) #打印结果：{"weatherinfo":{"city":"怀柔","cityid":"101010500","temp":"9","WD":"南风","WS":"1级","SD":"29%","WSE":"1","time":"10:25","isRadar":"1","Radar":"JC_RADAR_AZ9010_JB","njd":"暂无实况","qy":"1007"}}
示例：检查QQ在线状态
import requests #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=761505506') result = r.text #字符串类型 from xml.etree import ElementTree as ET #解析XML格式内容 #XML接受一个参数：字符串，格式化为特殊的对象 node = ET.XML(result) #获取内容 if node.text == "Y": print("在线") else: print("离线")
示例：获取列车时刻表
import requests r= requests.get('http://www.webxml.com.cn/WebServices/TrainTimeWebService.asmx/getDetailInfoByTrainCode?TrainCode=K234&UserID=') ret = r.text from xml.etree import ElementTree as ET result = ET.XML(ret) #找到TrainDetailInfo标签，进行循环 for i in result.iter('TrainDetailInfo'): #打印标签里面TrainDetailInfo标签和StartTime标签的内容 print(i.find('TrainStation').text,i.find('StartTime').text)
#打印结果： 上海（车次：K234K235） 11:12:00 昆山 11:48:00 苏州 12:16:00 无锡 12:55:00 常州 13:26:00 镇江 14:16:00 南京 15:16:00 蚌埠 17:50:00 徐州 19:58:00 商丘 22:17:00 开封 23:53:00 郑州 01:14:00 新乡 02:22:00 鹤壁 03:03:00 安阳 03:36:00 邯郸 04:16:00 邢台 04:51:00 石家庄 None
-
configparser模块
configparser是用于处理特定格式的文件，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
示例：文件名：ini
[zou] age = 1 xxx = woman [zhao] age = 2 xxx = man
1、获取所有节点：.sections()
import configparser con = configparser.ConfigParser() #con对象的read功能，打开文件读取文件，放进内容 con.read("ini",encoding="utf-8") #con对象的sections，在内存中寻找所有的[节点] ret = con.sections() print(ret) #打印结果：['zou', 'zhao']
注：获取节点以列表形式打印出来
2、获取指定节点下所有的键值对：.items(节点名)
import configparser con = configparser.ConfigParser() con.read("ini",encoding="utf-8") ret = con.items("zou") print(ret) #打印结果：[('age', '1'), ('xxx', 'woman')]
3、获取指定节点下所有的键：.options(节点名)
import configparser con = configparser.ConfigParser() con.read("ini",encoding="utf-8") ret = con.options("zou") print(ret) #打印结果：['age', 'xxx']
4、获取指定节点下指定KEY的值：.get(节点名，键)
import configparser con = configparser.ConfigParser() con.read("ini",encoding="utf-8") ret = con.get("zou","age") print(ret) #打印结果：1 # ret1 = con.getint('zou', 'age') # ret2 = con.getfloat('zou', 'age') # ret3 = con.getboolean('zou', 'age') # print(ret1) #打印结果：1 # print(ret2) #打印结果：1.0 # print(ret3) #打印结果：True
5、检查、删除、添加节点：
检查节点：.has_section(节点名)
添加节点：add_section(节点名)
.write(open(文件名，打开方式w))
删除节点：.remove_section(节点名)
.write(open(文件名，打开方式w))
import configparser con = configparser.ConfigParser() con.read("ini",encoding="utf-8") #检查节点 ret = con.has_section("zou") #如果含有节点就返回True，没有节点就返回False print(ret)#打印结果：True #添加节点 con.add_section("li") con.write(open("ini",'w')) #删除节点 con.remove_section("li") con.write(open("ini",'w'))
6、检查、删除、设置 指定组内的键值对：
检查键值对：.has_option(节点名,键)
删除键值对：.remove_option(节点名,键)
.write(open(文件名，打开方式w))
设置键值对：.set(节点名,键，值)
.write(open(文件名，打开方式w))
import configparser con = configparser.ConfigParser() con.read("ini",encoding="utf-8") #检查指定键值对 ret = con.has_option("zou","age") #如果含有指定键值对就返回True，没有指定键值对就返回False print(ret) #删除指定键值对 con.remove_option("zou","age") con.write(open("ini","w")) #设置键值对 con.set("zou","age","1") con.write(open("ini","w"))
-
shutil模块
shutil模块是针对高级的文件、文件夹、压缩包处理的模块
shutil.copyfileobj(fsrc,fdst,[length]):将文件内容拷贝到另一个文件中
import shutil #将f1文件内容拷贝到f2文件中，清空f2文件，写入f1文件内容 shutil.copyfileobj(open("f1",'r'),open("f2",'w')) #将f1文件内容拷贝到f2文件中，在f2文件末尾追加f1文件内容 shutil.copyfileobj(open("f1",'r'),open("f2",'a'))
shutil.copyfile(src,dst)：拷贝文件
#用f1文件内容覆盖f2文件 shutil.copyfile("f1","f2")
shutil.copymode(src,dst)：仅拷贝权限。内容、组、用户均不变
shutil.copymode("f1","f2")
shutil.copystat(src,dst)：拷贝状态的信息，包括：mode bits,atime,mtime,flags
shutil.copystat("f1","f2")
shutil.copy(src,dst)：拷贝文件和权限
shutil.copy("f1","f2")
shutil.copy2(src,dst)：拷贝文件和状态信息
shutil.copy2("f1","f2")
shutil.ignore_patterns(*patterns)
shutil.copytree(src,dst,symlinks=False,ignore=None)
import shutil shutil.copytree('f1', 'f2', symlinks=True, ignore=shutil.ignore_patterns('*.pyc', 'tmp*'))
shutil.rmtree(path,[ignore_errors,[onerror]])：递归地去删除文件
shutil.rmtree('f1')
shutil.move(src,dst)：递归地去移动文件，它类似mv命令，其实就是重命名
shutil.move('f1', 'f2')
shutil.make_archive(base_name,format,...)
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：f1 ==>保存至当前路径
如：/User/F1/f1 ==>保存至/User/F1/
- 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/F1/Downloads/test 下的文件打包放置当前程序目录 import shutil ret = shutil.make_archive("f1", 'gztar', root_dir='/Users/F1/Downloads/test') #将 /Users/F1/Downloads/test 下的文件打包放置 /Users/zouqian/目录 import shutil ret = shutil.make_archive("/Users/zouqian/f1", 'gztar', root_dir='/Users/F1/Downloads/test')
shutil对压缩包的处理是调用ZipFile 和 TarFile 两个模块来进行的：
ZipFile解压缩：
import zipfile # 压缩 z = zipfile.ZipFile('log.zip', 'w') #将文件添加到压缩包进行压缩 z.write('a.log') z.write('data.data') z.close() # 解压 z = zipfile.ZipFile('log.zip', 'r') z.extractall() z.close()
TarFile解压缩：
import tarfile # 压缩 tar = tarfile.open('log.tar','w') tar.add('/Users/F1/PycharmProjects/log1.log', arcname='log1.log') tar.add('/Users/F1/PycharmProjects/log2.log', arcname='log2.log') tar.close() # 解压 tar = tarfile.open('log.tar','r') tar.extractall() # 可设置解压地址 tar.close()
-
subprocess系统命令
subprocess专门用于Python执行系统命令
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')
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
#shell=False时，分开写命令然后放入列表 ret = subprocess.call(["ls", "-l"], shell=False) #默认情况下shell=True，命令是字符串 ret = subprocess.call("ls -l", shell=True)
check_call：执行命令，如果执行状态是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
- 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
- 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',)
stdin：输入管道 stdout：输出管道 stderr：输出错误管道
universal_newllines：换行符
import subprocess obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True) obj.stdin.write("print(1) ") 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) #打印结果：1 2 print(cmd_error)
下面是针对上面代码的一个简化，用.communicate() 替换 .read() .close()
import subprocess obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True) obj.stdin.write("print(1) ") obj.stdin.write("print(2)") out_error_list = obj.communicate() print(out_error_list)
对于单条命令，输入时也有更简化的方式，直接在.communiacte（）括号里面写print（）
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)
-
logging模块
用于便捷记了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) 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（level）大于 日志等级 时，日志文件才被记录。
2、多文件日志
要想设置多个文件，logging.basicConfig将无法完成，需要自定义文件和日志操作对象。
import logging
#创建文件 file_1_1 = logging.FileHandler('f1_1.log','a') #创建格式 fmt = logging.Formatter(fmt='%(asctime)s - %(name)s -%(levelname)s -%(module)s: %(message)s') #应用格式 file_1_1.setFormatter(fmt) #创建第二个文件 file_1_2 = logging.FileHandler('f1_2.log','a') fmt1 = logging.Formatter() file_1_2.setFormatter(fmt1) logger1 = logging.Logger('s2',level=logging.ERROR) logger1.addHandler(file_1_1) logger1.addHandler(file_1_2) #写日志 logger1.critical('11111')