我有一个从套接字读取xml文档的程序。我将xml文档存储在一个字符串中，我希望将其直接转换为Python字典，就像在Django的simplejson库中完成一样。
举个例子：
str ="<?xml version="1.0" ?><person><name>john</name><age>20</age></person"
dic_xml = convert_to_dic(str)
然后dic_xml看起来像{'person' : { 'name' : 'john', 'age' : 20 } }
答案 0 :(得分：229)
xmltodict（完全披露：我写的）确实如此：
xmltodict.parse("""
<?xml version="1.0" ?>
<person>
<name>john</name>
<age>20</age>
</person>""")
# {u'person': {u'age': u'20', u'name': u'john'}}
答案 1 :(得分：42)
这是某人创建的一个很棒的模块。我已经好几次使用它了。 http://code.activestate.com/recipes/410469-xml-as-dictionary/
以下是网站上的代码，以防链接变坏。
import cElementTree as ElementTree
class XmlListConfig(list):
def __init__(self, aList):
for element in aList:
if element:
# treat like dict
if len(element) == 1 or element[0].tag != element[1].tag:
self.append(XmlDictConfig(element))
# treat like list
elif element[0].tag == element[1].tag:
self.append(XmlListConfig(element))
elif element.text:
text = element.text.strip()
if text:
self.append(text)
class XmlDictConfig(dict):
'''
Example usage:
>>> tree = ElementTree.parse('your_file.xml')
>>> root = tree.getroot()
>>> xmldict = XmlDictConfig(root)
Or, if you want to use an XML string:
>>> root = ElementTree.XML(xml_string)
>>> xmldict = XmlDictConfig(root)
And then use xmldict for what it is... a dict.
'''
def __init__(self, parent_element):
if parent_element.items():
self.update(dict(parent_element.items()))
for element in parent_element:
if element:
# treat like dict - we assume that if the first two tags
# in a series are different, then they are all different.
if len(element) == 1 or element[0].tag != element[1].tag:
aDict = XmlDictConfig(element)
# treat like list - we assume that if the first two tags
# in a series are the same, then the rest are the same.
else:
# here, we put the list in dictionary; the key is the
# tag name the list elements all share in common, and
# the value is the list itself
aDict = {element[0].tag: XmlListConfig(element)}
# if the tag has attributes, add those to the dict
if element.items():
aDict.update(dict(element.items()))
self.update({element.tag: aDict})
# this assumes that if you've got an attribute in a tag,
# you won't be having any text. This may or may not be a
# good idea -- time will tell. It works for the way we are
# currently doing XML configuration files...
elif element.items():
self.update({element.tag: dict(element.items())})
# finally, if there are no child tags and no attributes, extract
# the text
else:
self.update({element.tag: element.text})
使用示例：
tree = ElementTree.parse('your_file.xml')
root = tree.getroot()
xmldict = XmlDictConfig(root)
//或者，如果你想使用XML字符串：
root = ElementTree.XML(xml_string)
xmldict = XmlDictConfig(root)
答案 2 :(得分：37)
以下XML-to-Python-dict片段解析实体以及this XML-to-JSON "specification"之后的属性。它是处理所有XML案例的最通用的解决方案。
from collections import defaultdict
def etree_to_dict(t):
d = {t.tag: {} if t.attrib else None}
children = list(t)
if children:
dd = defaultdict(list)
for dc in map(etree_to_dict, children):
for k, v in dc.items():
dd[k].append(v)
d = {t.tag: {k:v[0] if len(v) == 1 else v for k, v in dd.items()}}
if t.attrib:
d[t.tag].update(('@' + k, v) for k, v in t.attrib.items())
if t.text:
text = t.text.strip()
if children or t.attrib:
if text:
d[t.tag]['#text'] = text
else:
d[t.tag] = text
return d
使用：
from xml.etree import cElementTree as ET
e = ET.XML('''
<root>
<e />
<e>text</e>
<e name="value" />
<e name="value">text</e>
<e> <a>text</a> <b>text</b> </e>
<e> <a>text</a> <a>text</a> </e>
<e> text <a>text</a> </e>
</root>
''')
from pprint import pprint
pprint(etree_to_dict(e))
此示例的输出（按照上面链接的“规范”）应为：
{'root': {'e': [None,
'text',
{'@name': 'value'},
{'#text': 'text', '@name': 'value'},
{'a': 'text', 'b': 'text'},
{'a': ['text', 'text']},
{'#text': 'text', 'a': 'text'}]}}
不一定很漂亮，但它是明确的，更简单的XML输入导致更简单的JSON。 ：）
如果您要执行反向，从JSON / dict 发出 XML字符串，您可以使用：
try:
basestring
except NameError: # python3
basestring = str
def dict_to_etree(d):
def _to_etree(d, root):
if not d:
pass
elif isinstance(d, basestring):
root.text = d
elif isinstance(d, dict):
for k,v in d.items():
assert isinstance(k, basestring)
if k.startswith('#'):
assert k == '#text' and isinstance(v, basestring)
root.text = v
elif k.startswith('@'):
assert isinstance(v, basestring)
root.set(k[1:], v)
elif isinstance(v, list):
for e in v:
_to_etree(e, ET.SubElement(root, k))
else:
_to_etree(v, ET.SubElement(root, k))
else:
raise TypeError('invalid type: ' + str(type(d)))
assert isinstance(d, dict) and len(d) == 1
tag, body = next(iter(d.items()))
node = ET.Element(tag)
_to_etree(body, node)
return ET.tostring(node)
pprint(dict_to_etree(d))
答案 3 :(得分：22)
这个轻量级版本虽然不可配置，但很容易根据需要进行定制，并且适用于旧的蟒蛇。它也很严格 - 意味着无论属性是否存在，结果都是相同的。
import xml.etree.ElementTree as ET
from copy import copy
def dictify(r,root=True):
if root:
return {r.tag : dictify(r, False)}
d=copy(r.attrib)
if r.text:
d["_text"]=r.text
for x in r.findall("./*"):
if x.tag not in d:
d[x.tag]=[]
d[x.tag].append(dictify(x,False))
return d
所以：
root = ET.fromstring("<erik><a x='1'>v</a><a y='2'>w</a></erik>")
dictify(root)
结果：
{'erik': {'a': [{'x': '1', '_text': 'v'}, {'y': '2', '_text': 'w'}]}}
答案 4 :(得分：6)
最新版本的PicklingTools库（1.3.0和1.3.1）支持从XML转换为Python dict的工具。
可从此处下载：PicklingTools 1.3.1
转换器here有相当多的文档：文档详细描述了在XML和Python词典之间进行转换时会出现的所有决策和问题（有许多边缘情况：属性，列表，匿名列表，匿名dicts，eval等，大多数转换器不处理）。但总的来说， 转换器易于使用。如果'example.xml'包含：
<top>
<a>1</a>
<b>2.2</b>
<c>three</c>
</top>
然后将其转换为字典：
>>> from xmlloader import *
>>> example = file('example.xml', 'r') # A document containing XML
>>> xl = StreamXMLLoader(example, 0) # 0 = all defaults on operation
>>> result = xl.expect XML()
>>> print result
{'top': {'a': '1', 'c': 'three', 'b': '2.2'}}
在C ++和Python中都有转换工具：C ++和Python进行转换，但C ++的转换速度提高了60倍
答案 5 :(得分：3)
声明： 这个修改过的XML解析器的灵感来自于Adam Clark 原始XML解析器适用于大多数简单情况。但是，它不适用于某些复杂的XML文件。我逐行调试代码，最后解决了一些问题。如果您发现了一些错误，请告诉我。我很乐意解决它。
class XmlDictConfig(dict):
'''
Note: need to add a root into if no exising
Example usage:
>>> tree = ElementTree.parse('your_file.xml')
>>> root = tree.getroot()
>>> xmldict = XmlDictConfig(root)
Or, if you want to use an XML string:
>>> root = ElementTree.XML(xml_string)
>>> xmldict = XmlDictConfig(root)
And then use xmldict for what it is... a dict.
'''
def __init__(self, parent_element):
if parent_element.items():
self.updateShim( dict(parent_element.items()) )
for element in parent_element:
if len(element):
aDict = XmlDictConfig(element)
# if element.items():
# aDict.updateShim(dict(element.items()))
self.updateShim({element.tag: aDict})
elif element.items(): # items() is specialy for attribtes
elementattrib= element.items()
if element.text:
elementattrib.append((element.tag,element.text )) # add tag:text if there exist
self.updateShim({element.tag: dict(elementattrib)})
else:
self.updateShim({element.tag: element.text})
def updateShim (self, aDict ):
for key in aDict.keys(): # keys() includes tag and attributes
if key in self:
value = self.pop(key)
if type(value) is not list:
listOfDicts = []
listOfDicts.append(value)
listOfDicts.append(aDict[key])
self.update({key: listOfDicts})
else:
value.append(aDict[key])
self.update({key: value})
else:
self.update({key:aDict[key]}) # it was self.update(aDict)
答案 6 :(得分：3)
您可以使用lxml轻松完成此操作。首先安装它：
[sudo] pip install lxml
这是我写的一个递归函数，它可以帮助你解决这个问题：
from lxml import objectify as xml_objectify
def xml_to_dict(xml_str):
""" Convert xml to dict, using lxml v3.4.2 xml processing library """
def xml_to_dict_recursion(xml_object):
dict_object = xml_object.__dict__
if not dict_object:
return xml_object
for key, value in dict_object.items():
dict_object[key] = xml_to_dict_recursion(value)
return dict_object
return xml_to_dict_recursion(xml_objectify.fromstring(xml_str))
xml_string = """<?xml version="1.0" encoding="UTF-8"?><Response><NewOrderResp>
<IndustryType>Test</IndustryType><SomeData><SomeNestedData1>1234</SomeNestedData1>
<SomeNestedData2>3455</SomeNestedData2></SomeData></NewOrderResp></Response>"""
print xml_to_dict(xml_string)
以下变体保留父键/元素：
def xml_to_dict(xml_str):
""" Convert xml to dict, using lxml v3.4.2 xml processing library, see http://lxml.de/ """
def xml_to_dict_recursion(xml_object):
dict_object = xml_object.__dict__
if not dict_object: # if empty dict returned
return xml_object
for key, value in dict_object.items():
dict_object[key] = xml_to_dict_recursion(value)
return dict_object
xml_obj = objectify.fromstring(xml_str)
return {xml_obj.tag: xml_to_dict_recursion(xml_obj)}
如果您只想返回一个子树并将其转换为dict，您可以使用 Element.find（）来获取子树然后转换它：
xml_obj.find('.//') # lxml.objectify.ObjectifiedElement instance
请参阅lxml docs here。我希望这有帮助！
答案 7 :(得分：2)
最容易使用的Python XML解析器是ElementTree（从2.5x及更高版本开始，它位于标准库xml.etree.ElementTree中）。我认为没有任何东西可以完全满足您的需求。使用ElementTree写一些你想要的东西是非常简单的，但为什么要转换为字典，为什么不直接使用ElementTree。
答案 8 :(得分：2)
def xml_to_dict(node):
u'''
@param node:lxml_node
@return: dict
'''
return {'tag': node.tag, 'text': node.text, 'attrib': node.attrib, 'children': {child.tag: xml_to_dict(child) for child in node}}
答案 9 :(得分：2)
来自@ K3 --- rnc response（对我而言最好）我已经添加了一些小的修改来从XML文本中获取OrderedDict（有时候是有序的事情）：
sys.argv关注@ K3 --- rnc示例，您可以使用它：
def etree_to_ordereddict(t):
d = OrderedDict()
d[t.tag] = OrderedDict() if t.attrib else None
children = list(t)
if children:
dd = OrderedDict()
for dc in map(etree_to_ordereddict, children):
for k, v in dc.iteritems():
if k not in dd:
dd[k] = list()
dd[k].append(v)
d = OrderedDict()
d[t.tag] = OrderedDict()
for k, v in dd.iteritems():
if len(v) == 1:
d[t.tag][k] = v[0]
else:
d[t.tag][k] = v
if t.attrib:
d[t.tag].update(('@' + k, v) for k, v in t.attrib.iteritems())
if t.text:
text = t.text.strip()
if children or t.attrib:
if text:
d[t.tag]['#text'] = text
else:
d[t.tag] = text
return d
希望它有所帮助;）
答案 10 :(得分：2)
来自http://code.activestate.com/recipes/410469-xml-as-dictionary/的代码效果很好，但如果层次结构中的给定位置有多个相同的元素，则只会覆盖它们。
我在self.update（）之前添加了一个垫片，看看该元素是否已经存在。如果是，则弹出现有条目并创建现有和新的列表。任何后续重复项都会添加到列表中。
不确定这是否可以更优雅地处理，但它有效：
import xml.etree.ElementTree as ElementTree
class XmlDictConfig(dict):
def __init__(self, parent_element):
if parent_element.items():
self.updateShim(dict(parent_element.items()))
for element in parent_element:
if len(element):
aDict = XmlDictConfig(element)
if element.items():
aDict.updateShim(dict(element.items()))
self.updateShim({element.tag: aDict})
elif element.items():
self.updateShim({element.tag: dict(element.items())})
else:
self.updateShim({element.tag: element.text.strip()})
def updateShim (self, aDict ):
for key in aDict.keys():
if key in self:
value = self.pop(key)
if type(value) is not list:
listOfDicts = []
listOfDicts.append(value)
listOfDicts.append(aDict[key])
self.update({key: listOfDicts})
else:
value.append(aDict[key])
self.update({key: value})
else:
self.update(aDict)
答案 11 :(得分：1)
以下是指向ActiveState solution的链接 - 以及代码，以防它再次消失。
==================================================
xmlreader.py:
==================================================
from xml.dom.minidom import parse
class NotTextNodeError:
pass
def getTextFromNode(node):
"""
scans through all children of node and gathers the
text. if node has non-text child-nodes, then
NotTextNodeError is raised.
"""
t = ""
for n in node.childNodes:
if n.nodeType == n.TEXT_NODE:
t += n.nodeValue
else:
raise NotTextNodeError
return t
def nodeToDic(node):
"""
nodeToDic() scans through the children of node and makes a
dictionary from the content.
three cases are differentiated:
- if the node contains no other nodes, it is a text-node
and {nodeName:text} is merged into the dictionary.
- if the node has the attribute "method" set to "true",
then it's children will be appended to a list and this
list is merged to the dictionary in the form: {nodeName:list}.
- else, nodeToDic() will call itself recursively on
the nodes children (merging {nodeName:nodeToDic()} to
the dictionary).
"""
dic = {}
for n in node.childNodes:
if n.nodeType != n.ELEMENT_NODE:
continue
if n.getAttribute("multiple") == "true":
# node with multiple children:
# put them in a list
l = []
for c in n.childNodes:
if c.nodeType != n.ELEMENT_NODE:
continue
l.append(nodeToDic(c))
dic.update({n.nodeName:l})
continue
try:
text = getTextFromNode(n)
except NotTextNodeError:
# 'normal' node
dic.update({n.nodeName:nodeToDic(n)})
continue
# text node
dic.update({n.nodeName:text})
continue
return dic
def readConfig(filename):
dom = parse(filename)
return nodeToDic(dom)
def test():
dic = readConfig("sample.xml")
print dic["Config"]["Name"]
print
for item in dic["Config"]["Items"]:
print "Item's Name:", item["Name"]
print "Item's Value:", item["Value"]
test()
==================================================
sample.xml:
==================================================
<?xml version="1.0" encoding="UTF-8"?>
<Config>
<Name>My Config File</Name>
<Items multiple="true">
<Item>
<Name>First Item</Name>
<Value>Value 1</Value>
</Item>
<Item>
<Name>Second Item</Name>
<Value>Value 2</Value>
</Item>
</Items>
</Config>
==================================================
output:
==================================================
My Config File
Item's Name: First Item
Item's Value: Value 1
Item's Name: Second Item
Item's Value: Value 2
答案 12 :(得分：0)
@dibrovsd：如果xml有多个具有相同名称的标签，解决方案将无效
根据您的想法，我已经修改了一些代码并将其写入一般节点而不是root：
from collections import defaultdict
def xml2dict(node):
d, count = defaultdict(list), 1
for i in node:
d[i.tag + "_" + str(count)]['text'] = i.findtext('.')[0]
d[i.tag + "_" + str(count)]['attrib'] = i.attrib # attrib gives the list
d[i.tag + "_" + str(count)]['children'] = xml2dict(i) # it gives dict
return d
答案 13 :(得分：0)
有一次，我不得不解析并编写只包含没有属性的元素的XML，因此可以轻松实现从XML到dict的1：1映射。这就是我提出的，以防其他人也不需要属性：
def xmltodict(element):
if not isinstance(element, ElementTree.Element):
raise ValueError("must pass xml.etree.ElementTree.Element object")
def xmltodict_handler(parent_element):
result = dict()
for element in parent_element:
if len(element):
obj = xmltodict_handler(element)
else:
obj = element.text
if result.get(element.tag):
if hasattr(result[element.tag], "append"):
result[element.tag].append(obj)
else:
result[element.tag] = [result[element.tag], obj]
else:
result[element.tag] = obj
return result
return {element.tag: xmltodict_handler(element)}
def dicttoxml(element):
if not isinstance(element, dict):
raise ValueError("must pass dict type")
if len(element) != 1:
raise ValueError("dict must have exactly one root key")
def dicttoxml_handler(result, key, value):
if isinstance(value, list):
for e in value:
dicttoxml_handler(result, key, e)
elif isinstance(value, basestring):
elem = ElementTree.Element(key)
elem.text = value
result.append(elem)
elif isinstance(value, int) or isinstance(value, float):
elem = ElementTree.Element(key)
elem.text = str(value)
result.append(elem)
elif value is None:
result.append(ElementTree.Element(key))
else:
res = ElementTree.Element(key)
for k, v in value.items():
dicttoxml_handler(res, k, v)
result.append(res)
result = ElementTree.Element(element.keys()[0])
for key, value in element[element.keys()[0]].items():
dicttoxml_handler(result, key, value)
return result
def xmlfiletodict(filename):
return xmltodict(ElementTree.parse(filename).getroot())
def dicttoxmlfile(element, filename):
ElementTree.ElementTree(dicttoxml(element)).write(filename)
def xmlstringtodict(xmlstring):
return xmltodict(ElementTree.fromstring(xmlstring).getroot())
def dicttoxmlstring(element):
return ElementTree.tostring(dicttoxml(element))
答案 14 :(得分：0)
我修改了我的口味的答案之一，并使用具有相同标签的多个值，例如考虑保存在XML.xml文件中的以下xml代码
<A>
<B>
<BB>inAB</BB>
<C>
<D>
<E>
inABCDE
</E>
<E>value2</E>
<E>value3</E>
</D>
<inCout-ofD>123</inCout-ofD>
</C>
</B>
<B>abc</B>
<F>F</F>
</A>
和python
import xml.etree.ElementTree as ET
class XMLToDictionary(dict):
def __init__(self, parentElement):
self.parentElement = parentElement
for child in list(parentElement):
child.text = child.text if (child.text != None) else ' '
if len(child) == 0:
self.update(self._addToDict(key= child.tag, value = child.text.strip(), dict = self))
else:
innerChild = XMLToDictionary(parentElement=child)
self.update(self._addToDict(key=innerChild.parentElement.tag, value=innerChild, dict=self))
def getDict(self):
return {self.parentElement.tag: self}
class _addToDict(dict):
def __init__(self, key, value, dict):
if not key in dict:
self.update({key: value})
else:
identical = dict[key] if type(dict[key]) == list else [dict[key]]
self.update({key: identical + [value]})
tree = ET.parse('./XML.xml')
root = tree.getroot()
parseredDict = XMLToDictionary(root).getDict()
print(parseredDict)
输出为
{'A': {'B': [{'BB': 'inAB', 'C': {'D': {'E': ['inABCDE', 'value2', 'value3']}, 'inCout-ofD': '123'}}, 'abc'], 'F': 'F'}}
答案 15 :(得分：0)
我编写了一个简单的递归函数来完成这项工作：
from xml.etree import ElementTree
root = ElementTree.XML(xml_to_convert)
def xml_to_dict_recursive(root):
if len(root.getchildren()) == 0:
return {root.tag:root.text}
else:
return {root.tag:list(map(xml_to_dict_recursive, root.getchildren()))}
答案 16 :(得分：0)
另一种方法（为层次结构中的相同标签构建列表）：
from xml.etree import cElementTree as ElementTree
def xml_to_dict(xml, result):
for child in xml:
if len(child) == 0:
result[child.tag] = child.text
else:
if child.tag in result:
if not isinstance(result[child.tag], list):
result[child.tag] = [result[child.tag]]
result[child.tag].append(xml_to_dict(child, {}))
else:
result[child.tag] = xml_to_dict(child, {})
return result
xmlTree = ElementTree.parse('my_file.xml')
xmlRoot = xmlTree.getroot()
dictRoot = xml_to_dict(xmlRoot, {})
result = {xmlRoot.tag: dictRoot}
答案 17 :(得分：-1)
我有一个递归方法从lxml元素
获取字典 def recursive_dict(element):
return (element.tag.split('}')[1],
dict(map(recursive_dict, element.getchildren()),
**element.attrib))