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"
                      }
                    ]
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
]

lxml。物化真的很简单。

以示例文本为例:

from lxml import objectify
from collections import defaultdict

count = defaultdict(int)

root = objectify.fromstring(text)

for item in root.bar.type:
    count[item.attrib.get("foobar")] += 1

print dict(count)

输出:

{'1': 1, '2': 1}

XML:

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

Python代码:

import xml.etree.cElementTree as ET

tree = ET.parse("foo.xml")
root = tree.getroot() 
root_tag = root.tag
print(root_tag) 

for form in root.findall("./bar/type"):
    x=(form.attrib)
    z=list(x)
    for i in z:
        print(x[i])

输出:

foo
1
2

为了增加另一种可能性，可以使用untangle，因为它是一个简单的xml-to-python-object库。这里有一个例子:

安装:

pip install untangle

用法:

你的XML文件(有一点变化):

<foo>
   <bar name="bar_name">
      <type foobar="1"/>
   </bar>
</foo>

使用untangle访问属性:

import untangle

obj = untangle.parse('/path_to_xml_file/file.xml')

print obj.foo.bar['name']
print obj.foo.bar.type['foobar']

输出将是:

bar_name
1

更多关于untangle的信息可以在“untangle”中找到。

此外，如果您感兴趣，可以在“Python和XML”中找到使用XML和Python的工具列表。您还将看到前面的答案中提到的最常见的问题。

你可以使用BeautifulSoup:

from bs4 import BeautifulSoup

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

y=BeautifulSoup(x)
>>> y.foo.bar.type["foobar"]
u'1'

>>> y.foo.bar.findAll("type")
[<type foobar="1"></type>, <type foobar="2"></type>]

>>> y.foo.bar.findAll("type")[0]["foobar"]
u'1'
>>> y.foo.bar.findAll("type")[1]["foobar"]
u'2'

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”。