python_way.day7
1、模块
configparser，xml，shutil，subprocess， schedule
1、模块
a、configparser
用于处理特定格式的文件，其本职上使用open来操作，只能是 [test1] 特定的格式
[test1] k1 = 123 k2 = True [test2] k1 = 123 k2 = v1
1、获取
import configparser #打开文件找到文件下的所有的项目标签 config = configparser.ConfigParser() #创建configparser对象 config.read("file1",encoding="utf-8") #将文件读入 ret = config.sections() #找到所有的标签 print(ret) ['test1', 'test2'] #获取到test1节点下对应的 key & velvet ret1 = config.items("test1") print(ret1) [('k1', '123'), ('k2', 'v1')] #获取test1节点下所有的key ret2 = config.options("test1") print(ret2) ['k1', 'k2'] #获取节点下所有的velue ret3 = config.get("test1","k1") #获取字符串 print(ret3,type(ret3)) 123 <class 'str'> 以下获取这些类型个的数据首先必须可以转换成相对应的类型才能转换 ret3 = config.getint("test1","k1") #获取整数型 print(ret3,type(ret3)) 123 <class 'int'> ret3 = config.getfloat("test1","k1") #获取浮点型 print(ret3,type(ret3)) 123.0 <class 'float'> ret3 = config.getboolean("test1","k2") #获取布尔值 print(ret3,type(ret3))True <class 'bool'>
2、检查、删除、添加节点
import configparser config = configparser.configParser() config.read("file1",encoding="utf-8") #检查 has_ses = config.has_section("test1") print(has_ses) True #添加节点 -- 如果节点名已经存在报错 config.add_section("test3") config.write(open("file1","w")) #删除节点 -- 如果没有此节点不会报错 config.remove_section("test3") config.write(open("file1","w"))
3、检查，删除，设置指定组内的键值对
import configparser
config.configparser.configParser()
config.read("file1",encoding="utf-8")
检查
config.has_option("test1","k1) #检查test1下有没有k1这个键
删除
config.remove_option("test1","k1") #删除指定节点下的k1
config.write("open(file1","w")) #将删除后的结果存入文件，删除后自动将文件
设置
config.set("test2","k1","234") #将test2中的 k1和234 存到配置文件中去，如果已经存在不报错。
config.write(open("file1"),"w")
b、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>
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()
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()
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
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。
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')
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') 复制代码
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)
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")
c、subprocess
python中有众多的执行命令的模块，python3中为了更方便的使用系统命令，就有了一个subprocess这个模块，这个模块封装了众多的命令的功能。
subprocess.call
执行命令，返回状态码
两种写法：
ret = subprocess.call(["ls", "-l"], shell=False)
ret = subprocess.call("ls -l", shell=True) #如果命令想当成字符串传入，shell就要为True
subprocess.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_output
ret = subprocess.check_output("dir", shell=True)
print(type(ret))
rets = str(ret,"gbk") #因为ret是bytes类型的，所以需要转换一下。
print(rets)
驱动器 D 中的卷是 数据资料
卷的序列号是 5CAF-B40D
D:\资料\python\oldboy13\jobs\day9\myftp 的目录
2016/07/04 13:32 <DIR> .
2016/07/04 13:32 <DIR> ..
2016/07/04 09:25 <DIR> bin
2016/07/04 09:25 <DIR> conf
2016/07/04 09:40 <DIR> db
2016/07/04 10:23 <DIR> module
2016/07/04 13:32 175 test.py
1 个文件 175 字节
6 个目录 21,768,052,736 可用字节
subprocess.Popen
执行复杂命令
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
普通命令
#操作复杂命令，cwd 就是在那个目录下面做操作
obj = subprocess.Popen("mkdir t3", shell=True, cwd='/home/han')
需要交互的命令
import subprocess
obj = subprocess.Popen(["python"], stdin=subprocess.PIPE（定义输入的管道）, stdout=subprocess.PIPE（定义输出的管道））, stderr=subprocess.PIPE（定义错误信息的管道）, universal_newlines=True)
obj.stdin.write("print(1)\n") #输入一个命令 print（1）换行
obj.stdin.write("print(2)") #输入第二个命令 print（2）
obj.stdin.close() #关闭输入
cmd_out = obj.stdout.read() #读取输出结果
obj.stdout.close() #关闭
cmd_error = obj.stderr.read() #查看错误信息
obj.stderr.close() #关闭
print(cmd_out) #打印输出结果
print(cmd_error) #打印错误结果
上面的另一种写法
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() #这个命令会自动帮你去正确输出，和错误输出中各自取一下结果，结果是一个列表
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")') #这里也可以执行简单的命令
D , schedule 定时执行
import schedule
每多少分钟做什么事
schedule.every(7200).seconds.do(run_threaded, set_test_data_to_redis)
while True:
schedule.run_pending()
time.sleep(1)