如何在Python中将xml字符串转换为字典？

Question

我有一个程序从套接字读取xml文档.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 } }

Answer 1

xmltodict(完全披露:我写的)完全是这样的:

xmltodict.parse("""
<?xml version="1.0" ?>
<person>
  <name>john</name>
  <age>20</age>
</person>""")
# {u'person': {u'age': u'20', u'name': u'john'}}

Answer 2

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/

这是网站上的代码,以防链接变坏.

from xml.etree 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})

用法示例:

tree = ElementTree.parse('your_file.xml')
root = tree.getroot()
xmldict = XmlDictConfig(root)

//或者,如果要使用XML字符串:

root = ElementTree.XML(xml_string)
xmldict = XmlDictConfig(root)

Answer 3

以下XML-to-Python-dict片段解析实体以及遵循此XML-to-JSON"规范"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

它用于:

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")应该是:

{'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.:)

更新

如果你想反过来,从JSON/dict发出一个XML字符串,你可以使用:

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))

Answer 4

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)

结果是:

{'erik': {'a': [{'x': '1', '_text': 'v'}, {'y': '2', '_text': 'w'}]}}

Answer 5

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

没有为转换颇有几分文档在这里:文档中详细介绍了所有的XML和Python字典之间转换时将产生的决定和问题(有一些边缘情况:属性,列表,匿名列表,匿名大多数转换器无法处理的dicts,eval等).但是,一般而言,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++的转换速度提高了约60倍

Answer 6

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，它为你做了繁重的工作：

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)

以下变体保留了父键/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)}

如果只想返回一个子树并将其转换为 dict，则可以使用Element.find()获取子树，然后将其转换：

xml_obj.find('.//')  # lxml.objectify.ObjectifiedElement instance

请参阅此处的 lxml 文档。我希望这有帮助！

Answer 7

免责声明：此经过修改的XML解析器受到Adam Clark 的启发。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。我逐行调试了代码，最后解决了一些问题。如果您发现一些错误，请告诉我。我很高兴修复它。

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)    

Answer 8

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()))}