xml处理模块

假如有下面这样简单的xml内容：

<?xml version="1.0" encoding="UTF-8"?>
<data>
    <person name="LiPanHui">
        <age>28</age>
        <sex>man</sex>
        <like name="WuTao"/>
    </person>
    <person name="XuQianHua">
        <age>30</age>
        <sex>man</sex>
        <like name="ChenWeiMeng"/>
    </person>
</data>

读文档的内容

>>> import xml.etree.ElementTree as ET                                                                                  
>>> tree = ET.parse("test.xml")                                                                                         
>>> root = tree.getroot()                                                                                               
>>> print(root.tag)                                                                                                     
data    
                                                                                                              
>>> for child in root:                  # 遍历xml文档                                                                                
...   print(child.tag, child.attrib)                                                                                    
...   for i in child:                                                                                                   
...     print(i.tag, i.text)                                                                                            
...                                                                                                                     
person {'name': 'LiPanHui'}                                                                                             
age 28                                                                                                                  
sex man                                                                                                                 
like None                                                                                                               
person {'name': 'XuQianHua'}                                                                                            
age 30                                                                                                                  
sex man                                                                                                                 
like None      
                                                                                                       
>>> for node in root.iter('age'):       # 只遍历age节点                                                                                
...   print(node.tag, node.text)                                                                                        
...                                                                                                                     
age 28                                                                                                                  
age 30   

修改和删除xml文档的内容

# 修改
>>> tree = ET.parse("test.xml")                                                                                         
>>> root = tree.getroot()                                                                                                                                                                                          
>>> for node in root.iter('age'):                                                                                       
...   new_age = int(node.text) + 1                                                                                      
...   node.text = str(new_age)                                                                                          
...   node.set('updated', 'yes')                                                                                        
...                                                                                                                     
>>> tree                                                                                                                
<xml.etree.ElementTree.ElementTree object at 0x000001B5F29BCD68>                                                        
>>> tree.write('test2.xml')

新生成了文件test2.xml

<data>
    <person name="LiPanHui">
        <age updated="yes">29</age>
        <sex>man</sex>
        <like name="WuTao" />
    </person>
    <person name="XuQianHua">
        <age updated="yes">31</age>
        <sex>man</sex>
        <like name="ChenWeiMeng" />
    </person>
</data>

# 删除
>>> tree = ET.parse("test.xml")
>>> root = tree.getroot()
>>> for person in root.findall('person'):
...   age = int(person.find('age').text)
...   if age < 29:
...     root.remove(person)
...
>>> tree.write("test.xml")

文件test.xml被修改成：

<data>
    <person name="XuQianHua">
        <age>30</age>
        <sex>man</sex>
        <like name="ChenWeiMeng" />
    </person>
</data>

新增xml文件

>>> new_xml = ET.Element("hobbies")
>>> name = ET.SubElement(new_xml, "singing", attrib={'very_like': 'yes'})
>>> is_usually = ET.SubElement(name, "is_usually")
>>> is_usually.text = 'yes'
>>> name2 = ET.SubElement(new_xml, "play_game", attrib={'very_like': 'no'})
>>> is_usually = ET.SubElement(name2, "is_usually")
>>> is_usually.text = 'no'
>>> et = ET.ElementTree(new_xml)
>>> et.write("test.xml", encoding="utf-8", xml_declaration=True)
>>> ET.dump(new_xml)# 打印生成的内容
<hobbies><singing very_like="yes"><is_usually>yes</is_usually></singing><play_game very_like="no"><is_usually>no</is_usually></play_game></hobbies>

生成的内容：

<?xml version='1.0' encoding='utf-8'?>
<hobbies>
    <singing very_like="yes">
        <is_usually>yes</is_usually>
    </singing>
    <play_game very_like="no">
        <is_usually>no</is_usually>
    </play_game>
</hobbies>