Student.xml
<?xml version="1.0" encoding="utf-8" ?>
<School>
<Teacher desc="PythonTeacher" score="good">
<Name>LiuDana</Name>
<Age_1 Detail="Age for year 2010">18</Age_1>
<Mobile>13260446055</Mobile>
</Teacher>
<Student>
<Name Other="他是班长">ZhangSan</Name>
<Age Detail="The yongest boy in class">14</Age>
</Student>
<Student>
<Name>LiSi</Name>
<Age>19</Age>
<Mobile>15578875040</Mobile>
</Student>
<!-- 这是北京图灵学院的一个例子而已 -->
</School>
# XML访问
## 读取
- XML读取分两个主要技术,SAX, DOM
- SAX(Simple API for XML):
- 基于事件驱动的API
- 利用SAX解析文档设计到解析器和事件处理两部分
- 特点:
- 快
- 流式读取
- DOM
- 是W3C规定的XML编程接口
- 一个XML文件在缓存中以树形结构保存,读取
- 用途
- 定位浏览XML任何一个节点信息
- 添加删除相应内容
- minidom
- minidom.parse(filename):加载读取的xml文件, filename也可以是xml代码
- doc.documentElement:获取xml文档对象,一个xml文件只有一个对应的文档对象
- node.getAttribute(attr_name):获取xml节点的属性值
- node.getElementByTagName(tage_name):得到一个节点对象集合
- node.childNodes:得到所有孩子节点
- node.childNodes[index].nodeValue:获取单个节点值
- node.firstNode:得到第一个节点,等价于node.childNodes[0]
- node.attributes[tage_name] 返回元素所有可能属性的集合
-
import xml.dom.minidom
from xml.dom.minidom import parse
#使用parse 打开xml 文件
DOMTREE = xml.dom.minidom.parse("Student.xml")
#得到文档对象
doc = DOMTREE.documentElement
print(type(doc))
#显示子元素
for ele in doc.childNodes:
if ele.nodeName == 'Teacher':
print("------------Node:{0}--------------".format(ele.nodeName))
childs = ele.childNodes
print(childs)
for child in childs:
if child.nodeName == 'Name':
# data 是本节点的一个属性,表示值
print("Name:{0}".format(child.childNodes[0].data))
if child.nodeName == "Mobile":
print("Mobile:{0}".format(child.childNodes[0].nodeValue))
if child.nodeName =="Age_1":
print("Age:{0}".format(child.childNodes[0].data))
if child.hasAttribute("Detail"):
print("age_detail :{0}".format(child.getAttribute("Detail")))
- etree
- 以树形结构来表示xml
- root.getiterator:得到相应的可迭代的node集合
- root.iter
- find(node_name):查找指定node_name的节点,返回一个node
- root.findall(node_name):返回多个node_name的节点
- node.tag: node对应的tagename
- node.text:node的文本值
- node.attrib: 是node的属性的字典类型的内容
-
import xml.etree.ElementTree
root = xml.etree.ElementTree.parse("Student.xml")
print("利用getiterator 访问...")
nodes = root.getiterator()
for node in nodes:
print("...{}...{}...".format(node.tag,node.text))
print("利用find 和findall 方法...")
ele_teacher = root.find("Teacher")
print(type(ele_teacher))
print("----{}---{}---".format(ele_teacher.tag,ele_teacher.text))
ele_stu = root.findall("Student")
print(type(ele_stu))
for ele in ele_stu:
print("======={}===={}==".format(ele.tag,ele.text))
for sub in ele.getiterator():
print(sub.tag,">>>",sub.text)
if sub.tag == "Name":
print(sub.attrib.keys(),"<<<<",sub.text)
<School>
<Teacher>
<Name>LiuYing</Name>
<Age detail="Age for year 2010">18</Age>
<Mobile>13260446056</Mobile>
</Teacher>
<Student>
<Name Other="他是班长" test="ZhangSanZhangSan">ZhangSan</Name>
<Age Detail="The yongest boy in class">14</Age>
<Student>
<Name test="luodayouluodayou">luodayou</Name>
<Age>59</Age>
<Mobile>1387878776787</Mobile>
</Student>
<Student>
<Name test="LiSiLiSi">LiSi</Name>
<Age>19</Age>
<Mobile>13240484187</Mobile>
</Student>
</School>
-------------to_edit.xml
- xml文件写入
- 更改
- ele.set:修改属性
- ele.append: 添加子元素
- ele.remove:删除元素
import xml.etree.ElementTree as et
tree = et.parse(r'to_edit.xml')
root = tree.getroot()
print(root)
for e in root.iter('Name'):
print(e.text)
for stu in root.iter("Student"):
name = stu.find("Name")
print("name===",name.text)
# if name != None:
# name.set('test',name.text*2)
stu = root.find("Student")
# 生成一个新额元素
e = et.Element("Adder")
e.attrib = {'a':"b"}
e.text="我家的"
stu.append(e)
tree.write("to_edit.xml")
- 生成创建
- SubElement,
import xml.etree.ElementTree as et
stu = et.Element("Student1")
name = et.SubElement(stu,"Name")
name.attrib ={"lang":"en"}
name.text="aimmon"
age = et.SubElement(stu,"Age")
age.text ='19' #int 会提示不能序列化
et.dump(stu)
<Student1><Name lang="en">aimmon</Name><Age>19</Age></Student1>
- minidom 写入,
import xml.dom.minidom
#在内存中创建一个空的文档
doc = xml.dom.minidom.Document()
#创建一个根节点Managers对象
root = doc.createElement('Managers')
#设置根节点的属性
root.setAttribute('company', 'xx科技')
root.setAttribute('address', '科技软件园')
#将根节点添加到文档对象中
doc.appendChild(root)
managerList = [{'name' : 'joy', 'age' : 27, 'sex' : '女'},
{'name' : 'tom', 'age' : 30, 'sex' : '男'},
{'name' : 'ruby', 'age' : 29, 'sex' : '女'}
]
for i in managerList :
nodeManager = doc.createElement('Manager')
nodeName = doc.createElement('name')
#给叶子节点name设置一个文本节点,用于显示文本内容
nodeName.appendChild(doc.createTextNode(str(i['name'])))
nodeAge = doc.createElement("age")
nodeAge.appendChild(doc.createTextNode(str(i["age"])))
nodeSex = doc.createElement("sex")
nodeSex.appendChild(doc.createTextNode(str(i["sex"])))
#将各叶子节点添加到父节点Manager中,
#最后将Manager添加到根节点Managers中
nodeManager.appendChild(nodeName)
nodeManager.appendChild(nodeAge)
nodeManager.appendChild(nodeSex)
root.appendChild(nodeManager)
#开始写xml文档
fp = open('Manager.xml', 'w')
doc.writexml(fp, indent='\t', addindent='\t', newl='\n', encoding="utf-8")
- etree创建,
import xml.etree.ElementTree as et
#在内存中创建一个空的文档
etree = et.ElementTree()
e = et.Element('Student')
etree._setroot(e)
e_name = et.SubElement(e, 'Name')
e_name.text = "hahahah"
etree.write('v06.xml')
<Student><Name>hahaaa</Name></Student> --v07.xml