Python模块——xml

xml模块

xml是实现不同语言或程序之间进行数据交换的协议，跟json差不多，但json使用起来更简单，

不过，古时候，在json还没诞生的黑暗年代，大家只能选择用xml呀，至今很多传统公司如金融行业的很多系统的接口还主要是xml。

xml的格式如下，就是通过<>节点来区别数据结构的:

<?xml version="1.0"?>
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2011</year>
        <gdppc>13600</gdppc>
        <neighbor name="Costa Rica" direction="W"/>
        <neighbor name="Colombia" direction="E"/>
    </country>
</data>

xml协议在各个语言里的都 是支持的，在python中可以用以下模块操作xml

遍历

import xml.etree.ElementTree as ET

tree = ET.parse("xml test")  # 打开xml文件
root = tree.getroot()  # 得到根节点
# print(dir(root))
print(root.tag)
# 遍历xml文档
for child in root:
    print('----------',child.tag, child.attrib)  # 打印country节点
    for i in child:
        print(i.tag,i.text)

修改和删除xml文档内容

import xml.etree.ElementTree as ET

tree = ET.parse("xml_test")
root = tree.getroot() #f.seek(0)

# 修改
for node in root.iter('year'):
    new_year = int(node.text) + 5
    node.text = str(new_year) # 修改内容
    node.set("attr_test","false")
tree.write('output.xml') # 写入文件

# #删除node
for country in root.findall('country'):
   rank = int(country.find('rank').text)
   if rank > 50:
     root.remove(country)

tree.write('output.xml')

新建xml

import xml.etree.ElementTree as ET

root = ET.Element("namelist")  # 创建root

name = ET.SubElement(root,"name",attrib={"enrolled":"yes"})  # 创建child--name
age = ET.SubElement(name,"age",attrib={"checked":"no"}) # 创建name child--age,sex,name
sex = ET.SubElement(name,"sex")
n = ET.SubElement(name,"name")
n.text = "Alex Li"
sex.text = 'male'

name2 = ET.SubElement(root,"name",attrib={"enrolled":"no"})
age = ET.SubElement(name2,"age")
age.text = ''

et = ET.ElementTree(root)  # 生成文档对象
et.write("build_out.xml", encoding="utf-8",xml_declaration=True)

 由于原生保存的XML时默认无缩进，如果想要设置缩进的话， 需要修改保存方式

import xml.etree.ElementTree as ET
from xml.dom import minidom

def subElement(root, tag, text):
    ele = ET.SubElement(root, tag)
    ele.text = text

def saveXML(root, filename, indent="\t", newl="\n", encoding="utf-8"):
    rawText = ET.tostring(root)
    dom = minidom.parseString(rawText)
    with open(filename, 'w') as f:
        dom.writexml(f, "", indent, newl, encoding)

root = ET.Element("namelist")

to = root.makeelement("to", {})
to.text = "peter"
root.append(to)

name = ET.SubElement(root,"name",attrib={"enrolled":"yes"})  # 创建child--name
age = ET.SubElement(name,"age",attrib={"checked":"no"}) # 创建name child--age,sex,name
sex = ET.SubElement(name,"sex")
n = ET.SubElement(name,"name")
n.text = "Alex Li"
sex.text = 'male'

name2 = ET.SubElement(root,"name",attrib={"enrolled":"no"})
age = ET.SubElement(name2,"age")
age.text = ''

# et = ET.ElementTree(root)  # 生成文档对象

# 保存xml文件
saveXML(root, "note.xml")