如果您不想使用任何外部库或第三方工具，请尝试下面的代码。

这将把xml解析成python字典 这也将解析xml属性 这也将解析空标签，如<tag/>和只有属性的标签，如<tag var=val/>

Code

import re

def getdict(content):
    res=re.findall("<(?P<var>\S*)(?P<attr>[^/>]*)(?:(?:>(?P<val>.*?)</(?P=var)>)|(?:/>))",content)
    if len(res)>=1:
        attreg="(?P<avr>\S+?)(?:(?:=(?P<quote>['\"])(?P<avl>.*?)(?P=quote))|(?:=(?P<avl1>.*?)(?:\s|$))|(?P<avl2>[\s]+)|$)"
        if len(res)>1:
            return [{i[0]:[{"@attributes":[{j[0]:(j[2] or j[3] or j[4])} for j in re.findall(attreg,i[1].strip())]},{"$values":getdict(i[2])}]} for i in res]
        else:
            return {res[0]:[{"@attributes":[{j[0]:(j[2] or j[3] or j[4])} for j in re.findall(attreg,res[1].strip())]},{"$values":getdict(res[2])}]}
    else:
        return content

with open("test.xml","r") as f:
    print(getdict(f.read().replace('\n','')))

样例输入

<details class="4b" count=1 boy>
    <name type="firstname">John</name>
    <age>13</age>
    <hobby>Coin collection</hobby>
    <hobby>Stamp collection</hobby>
    <address>
        <country>USA</country>
        <state>CA</state>
    </address>
</details>
<details empty="True"/>
<details/>
<details class="4a" count=2 girl>
    <name type="firstname">Samantha</name>
    <age>13</age>
    <hobby>Fishing</hobby>
    <hobby>Chess</hobby>
    <address current="no">
        <country>Australia</country>
        <state>NSW</state>
    </address>
</details>

输出(美化)

[
  {
    "details": [
      {
        "@attributes": [
          {
            "class": "4b"
          },
          {
            "count": "1"
          },
          {
            "boy": ""
          }
        ]
      },
      {
        "$values": [
          {
            "name": [
              {
                "@attributes": [
                  {
                    "type": "firstname"
                  }
                ]
              },
              {
                "$values": "John"
              }
            ]
          },
          {
            "age": [
              {
                "@attributes": []
              },
              {
                "$values": "13"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Coin collection"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Stamp collection"
              }
            ]
          },
          {
            "address": [
              {
                "@attributes": []
              },
              {
                "$values": [
                  {
                    "country": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "USA"
                      }
                    ]
                  },
                  {
                    "state": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "CA"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": [
          {
            "empty": "True"
          }
        ]
      },
      {
        "$values": ""
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": []
      },
      {
        "$values": ""
      }
    ]
  },
  {
    "details": [
      {
        "@attributes": [
          {
            "class": "4a"
          },
          {
            "count": "2"
          },
          {
            "girl": ""
          }
        ]
      },
      {
        "$values": [
          {
            "name": [
              {
                "@attributes": [
                  {
                    "type": "firstname"
                  }
                ]
              },
              {
                "$values": "Samantha"
              }
            ]
          },
          {
            "age": [
              {
                "@attributes": []
              },
              {
                "$values": "13"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Fishing"
              }
            ]
          },
          {
            "hobby": [
              {
                "@attributes": []
              },
              {
                "$values": "Chess"
              }
            ]
          },
          {
            "address": [
              {
                "@attributes": [
                  {
                    "current": "no"
                  }
                ]
              },
              {
                "$values": [
                  {
                    "country": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "Australia"
                      }
                    ]
                  },
                  {
                    "state": [
                      {
                        "@attributes": []
                      },
                      {
                        "$values": "NSW"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
]

这里有一个使用cElementTree的非常简单但有效的代码。

try:
    import cElementTree as ET
except ImportError:
  try:
    # Python 2.5 need to import a different module
    import xml.etree.cElementTree as ET
  except ImportError:
    exit_err("Failed to import cElementTree from any known place")      

def find_in_tree(tree, node):
    found = tree.find(node)
    if found == None:
        print "No %s in file" % node
        found = []
    return found  

# Parse a xml file (specify the path)
def_file = "xml_file_name.xml"
try:
    dom = ET.parse(open(def_file, "r"))
    root = dom.getroot()
except:
    exit_err("Unable to open and parse input definition file: " + def_file)

# Parse to find the child nodes list of node 'myNode'
fwdefs = find_in_tree(root,"myNode")

这是来自“python xml解析”。

如果你使用python-benedict，就不需要使用lib特定的API。只需从XML初始化一个新实例并轻松管理它，因为它是dict子类。

安装很简单:pip install python-benedict

from benedict import benedict as bdict

# data-source can be an url, a filepath or data-string (as in this example)
data_source = """
<foo>
   <bar>
      <type foobar="1"/>
      <type foobar="2"/>
   </bar>
</foo>"""

data = bdict.from_xml(data_source)
t_list = data['foo.bar'] # yes, keypath supported
for t in t_list:
   print(t['@foobar'])

它支持并规范化多种格式的I/O操作:Base64, CSV, JSON, TOML, XML, YAML和查询字符串。

它在GitHub上经过了很好的测试和开源。披露:我是作者。

我建议使用declxml。

完全公开:我编写这个库是因为我正在寻找一种在XML和Python数据结构之间转换的方法，而不需要用ElementTree编写数十行强制解析/序列化代码。

使用declxml，您可以使用处理器声明性地定义XML文档的结构以及如何在XML和Python数据结构之间进行映射。处理器用于序列化和解析，也用于基本级别的验证。

解析成Python数据结构很简单:

import declxml as xml

xml_string = """
<foo>
   <bar>
      <type foobar="1"/>
      <type foobar="2"/>
   </bar>
</foo>
"""

processor = xml.dictionary('foo', [
    xml.dictionary('bar', [
        xml.array(xml.integer('type', attribute='foobar'))
    ])
])

xml.parse_from_string(processor, xml_string)

它产生输出:

{'bar': {'foobar': [1, 2]}}

还可以使用同一处理器将数据序列化为XML

data = {'bar': {
    'foobar': [7, 3, 21, 16, 11]
}}

xml.serialize_to_string(processor, data, indent='    ')

哪个产生以下输出

<?xml version="1.0" ?>
<foo>
    <bar>
        <type foobar="7"/>
        <type foobar="3"/>
        <type foobar="21"/>
        <type foobar="16"/>
        <type foobar="11"/>
    </bar>
</foo>

如果希望使用对象而不是字典，则可以定义处理器来在对象之间转换数据。

import declxml as xml

class Bar:

    def __init__(self):
        self.foobars = []

    def __repr__(self):
        return 'Bar(foobars={})'.format(self.foobars)


xml_string = """
<foo>
   <bar>
      <type foobar="1"/>
      <type foobar="2"/>
   </bar>
</foo>
"""

processor = xml.dictionary('foo', [
    xml.user_object('bar', Bar, [
        xml.array(xml.integer('type', attribute='foobar'), alias='foobars')
    ])
])

xml.parse_from_string(processor, xml_string)

哪个产生以下输出

{'bar': Bar(foobars=[1, 2])}

有很多选择。如果速度和内存使用是一个问题，cElementTree看起来很棒。与简单地使用readline读取文件相比，它的开销非常小。

相关指标可以在下表中找到，复制自cElementTree网站:

library                         time    space
xml.dom.minidom (Python 2.1)    6.3 s   80000K
gnosis.objectify                2.0 s   22000k
xml.dom.minidom (Python 2.4)    1.4 s   53000k
ElementTree 1.2                 1.6 s   14500k  
ElementTree 1.2.4/1.3           1.1 s   14500k  
cDomlette (C extension)         0.540 s 20500k
PyRXPU (C extension)            0.175 s 10850k
libxml2 (C extension)           0.098 s 16000k
readlines (read as utf-8)       0.093 s 8850k
cElementTree (C extension)  --> 0.047 s 4900K <--
readlines (read as ascii)       0.032 s 5050k   

正如@jfs所指出的，cElementTree是与Python捆绑在一起的:

Python 2:来自xml。etree导入cElementTree作为ElementTree。 Python 3:从xml。导入ElementTree(自动使用加速的C版本)。

如果源文件是一个xml文件，就像这个示例一样

<pa:Process xmlns:pa="http://sssss">
        <pa:firsttag>SAMPLE</pa:firsttag>
    </pa:Process>

您可以尝试下面的代码

from lxml import etree, objectify
metadata = 'C:\\Users\\PROCS.xml' # this is sample xml file the contents are shown above
parser = etree.XMLParser(remove_blank_text=True) # this line removes the  name space from the xml in this sample the name space is --> http://sssss
tree = etree.parse(metadata, parser) # this line parses the xml file which is PROCS.xml
root = tree.getroot() # we get the root of xml which is process and iterate using a for loop
for elem in root.getiterator():
    if not hasattr(elem.tag, 'find'): continue  # (1)
    i = elem.tag.find('}')
    if i >= 0:
        elem.tag = elem.tag[i+1:]

dict={}  # a python dictionary is declared
for elem in tree.iter(): #iterating through the xml tree using a for loop
    if elem.tag =="firsttag": # if the tag name matches the name that is equated then the text in the tag is stored into the dictionary
        dict["FIRST_TAG"]=str(elem.text)
        print(dict)

输出将是

{'FIRST_TAG': 'SAMPLE'}