XML处理模块
xml是实现不同语言或程序之间进行数据交换的协议，跟json差不多，但json使用起来更简单，不过，古时候，在json还没诞生的黑暗年代，大家只能选择用xml呀，至今很多传统公司如金融行业的很多系统的接口还主要是xml。
xml文件格式是早期的文件格式，早期的文件格式是xml文件接口，文件之间的交互都是用xml格式。
xml的格式如下，就是通过<>节点来区别数据结构的，下面来看看xml的格式：
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 __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):
为当前子节点扩展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):
在当前节点的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
t = self.text
if t:
yield t
for e in self:
yield from e.itertext()
t = e.tail
if t:
yield t
def parse(source, parser=None):
"""Parse XML document into element tree.
*source* is a filename or file object containing XML data,
*parser* is an optional parser instance defaulting to XMLParser.
Return an ElementTree instance.
"""
tree = ElementTree()
tree.parse(source, parser)
return tree
下面来看看XML的文件格式：
<?xml version="1.0" encoding="utf-8" ?> <data> <country name="Liechtenstein"> <rank updated="yes">2</rank> <year>2008</year> <gdppc>141100</gdppc> <neighbor name="Austria" direction="E"/> <neighbor name="Switzerland" direction="W"/> </country> <country name="Singapore"> <rank updated="yes">5</rank> <year>2011</year> <gdppc>59900</gdppc> <neighbor name="Malaysia" direction="N"/> </country> <country name="Panama"> <rank updated="yes">69</rank> <year>2011</year> <gdppc>13660</gdppc> <neighbor name="Costa Rica" direction="W"/> <neighbor name="Colombia" direction="E"/> </country> </data>
xml协议在各个语言里的都 是支持的，在python中可以用以下模块操作xml：
（1）遍历XML文件
import xml.etree.ElementTree as ET tree = ET.parse("xml_data") #获取根节点，根节点的名字 root = tree.getroot() print(root.tag) #遍历xml文档 for child in root: print(child.tag,child.attrib) for i in child: print("result:",i.tag,i.text) #只遍历year节点 for node in root.iter("year"): print(node.tag,node.text)
（二）修改XML文件的内容
import xml.etree.ElementTree as ET tree = ET.parse("xml_data") root = tree.getroot() #修改 for node in root.iter("year"): new_year = int(node.text) + 1 #每个年的值加1 node.text = str(new_year) #把新的年份设置 node.set("updated","yes") #修改updated的属性 tree.write("xml_data") 修改后的XML文件如下： <data> <country name="Liechtenstein"> <rank updated="yes">2</rank> <year updated="yes">2009</year> <gdppc>141100</gdppc> <neighbor direction="E" name="Austria" /> <neighbor direction="W" name="Switzerland" /> </country> <country name="Singapore"> <rank updated="yes">5</rank> <year updated="yes">2012</year> <gdppc>59900</gdppc> <neighbor direction="N" name="Malaysia" /> </country> <country name="Panama"> <rank updated="yes">69</rank> <year updated="yes">2012</year> <gdppc>13660</gdppc> <neighbor direction="W" name="Costa Rica" /> <neighbor direction="E" name="Colombia" /> </country> </data>
（三）删除XML文件中的内容：
import xml.etree.ElementTree as ET tree = ET.parse("xml_data") #首先解析XML文件 root = tree.getroot() #删除文件信息 for country in root.findall("country"): rank = int(country.find("rank").text) if rank > 50: root.remove(country) tree.write("output.xml")
删除后的XML文件格式如下：
<data>
<country name="Liechtenstein">
<rank updated="yes">2</rank>
<year updated="yes">2009</year>
<gdppc>141100</gdppc>
<neighbor direction="E" name="Austria" />
<neighbor direction="W" name="Switzerland" />
</country>
<country name="Singapore">
<rank updated="yes">5</rank>
<year updated="yes">2012</year>
<gdppc>59900</gdppc>
<neighbor direction="N" name="Malaysia" />
</country>
</data>
（四）XML文件的创建
友情链接：http://www.cnblogs.com/wupeiqi/articles/5501365.html
友情链接：http://www.cnblogs.com/alex3714/articles/5161349.html
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