Python如何使用ElementTree解析xml

<?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>

try:
  import xml.etree.celementtree as et
except importerror:
  import xml.etree.elementtree as et

tree = et.parse("country.xml") # <class 'xml.etree.elementtree.elementtree'>
root = tree.getroot()      # 获取根节点 <element 'data' at 0x02bf6a80>

import xml.etree.elementtree as et

tree = et.parse("country.xml")
root = tree.getroot()
print(root.tag, ":", root.attrib) # 打印根元素的tag和属性
# 遍历xml文档的第二层
for child in root:
  # 第二层节点的标签名称和属性
  print(child.tag,":", child.attrib) 
  # 遍历xml文档的第三层
  for children in child:
    # 第三层节点的标签名称和属性
    print(children.tag, ":", children.attrib)

# 将所有的rank值加1,并添加属性updated为yes
for rank in root.iter("rank"):
  new_rank = int(rank.text) + 1
  rank.text = str(new_rank) # 必须将int转为str
  rank.set("updated", "yes") # 添加属性

# 再终端显示整个xml
et.dump(root)
# 注意 修改的内容存在内存中 尚未保存到文件中
# 保存修改后的内容
tree.write("output.xml")

import xml.etree.elementtree as et

tree = et.parse("output.xml")
root = tree.getroot()

for rank in root.iter("rank"):
  # attrib为属性字典
  # 删除对应的属性updated
  del rank.attrib['updated'] 

et.dump(root)

import xml.etree.elementtree as et

tree = et.parse("country.xml")
root = tree.getroot()

# 删除rank大于50的国家
for country in root.iter("country"):
  rank = int(country.find("rank").text)
  if rank > 50:
    # remove()方法 删除子元素
    root.remove(country)

et.dump(root)

import xml.etree.elementtree as et

tree = et.parse("country.xml")
root = tree.getroot()

country = root[0]
last_ele = country[len(list(country))-1]
last_ele.tail = '\n\t\t'
# 创建新的元素, tag为test_append
elem1 = et.element("test_append")
elem1.text = "elem 1"
# elem.tail = '\n\t'
country.append(elem1)

# subelement() 其实内部调用的时append()
elem2 = et.subelement(country, "test_subelement")
elem2.text = "elem 2"

# extend()
elem3 = et.element("test_extend")
elem3.text = "elem 3"
elem4 = et.element("test_extend")
elem4.text = "elem 4"
country.extend([elem3, elem4])

# insert()
elem5 = et.element("test_insert")
elem5.text = "elem 5"
country.insert(5, elem5)

et.dump(country)

import xml.etree.elementtree as et


def subelement(root, tag, text):
  ele = et.subelement(root, tag)
  ele.text = text
  ele.tail = '\n'


root = et.element("note")

to = root.makeelement("to", {})
to.text = "peter"
to.tail = '\n'
root.append(to)

subelement(root, "from", "marry")
subelement(root, "heading", "reminder")
subelement(root, "body", "don't forget the meeting!")

tree = et.elementtree(root)
tree.write("note.xml", encoding="utf-8", xml_declaration=true)

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("note")

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

subelement(root, "from", "marry")
subelement(root, "heading", "reminder")
subelement(root, "body", "don't forget the meeting!")

# 保存xml文件
savexml(root, "note.xml")