首先,我先给出一段xml文档:
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<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>
然后,用Python中的xml模块对上面的xml文本进行操作:
# Author : XueFeng
# 传统的系统接口多使用XML
import xml.etree.ElementTree as ET
tree = ET.parse("xml_t.xml")
root = tree.getroot()
print(root)
print(root.tag)
# 遍历xml文档
# tag---------->标签名
# attrib------->属性
# text--------->文本信息
for child in root:
print(child.tag, child.attrib)
for i in child:
print(i.tag, i.text, i.attrib)
# 只遍历year的文本信息
for node in root.iter('year'):
print(node.attrib, node.text)
# 修改xml文件
for node in root.iter("year"):
Nyear = int(node.text)+1
node.text = str(Nyear)
node.set("updated", "yes")
tree.write('xml_t.xml')
# 删除节点
for country in root.findall('country'):
rank = int(country.find('rank').text)
if rank > 50:
root.remove(country)
tree.write('output.xml')
# 创建xml文件
new_xml = ET.Element('namelist')
name = ET.SubElement(new_xml, "name", attrib={"enrolled": "yes"})
age = ET.SubElement(name, "age", attrib={"checked": "no"})
sex = ET.SubElement(name, "sex")
sex.text = '33'
name2 = ET.SubElement(new_xml, "name", attrib={"enrolled": "no"})
age = ET.SubElement(name2, "age")
age.text = '19'
et = ET.ElementTree(new_xml)
et.write("test.xml", encoding="utf-8", xml_declaration=True)
ET.dump(new_xml)