用python解析xml的几种方法

Xml：

1. 标签成对出现

2. 区分大小写

3. 标签要正确嵌套

4.开始部分：

5.只能有一个根节点

6.节点可以有属性

DTD：约束XML文件的节点

Xml解析：

1. dom（文档对象模型）：把解析的xml整个加载到内存，组织成object树。

w3cDom dom4j

from xml.dom.minidom import parse
doc=parse("students.xml")   得到整个DOM文档树
root=doc.documentElement     得到根节点
students=root.getElementsByTagName("student")
class Student:
    def __init__(self,name,age,sex,score):
        self.name=name
        self.age=age
        self.sex=sex
        self.score=score
    def __str__(self):
        return "姓名：{0}，年龄：{1}，性别：{2}，成绩：{3}".format(self.name,self.age,self.sex,self.score)
people=[]
for p in students:
    student = Student(p.getElementsByTagName("name")[0].childNodes[0].data,p.getElementsByTagName("age")[0].childNodes[0].data,p.getElementsByTagName("sex")[0].childNodes[0].data,p.getElementsByTagName("score")[0].childNodes[0].data)
    people.append(student)
for p in people:
    print(p)

 

2. Sax:事件驱动式解析，不会在内存中加载整个文档，只会根据自己编写的事件保存数据

from xml.sax import ContentHandler
from xml.sax import parse
class Student:
    def __init__(self,name=None,age=None,sex=None,score=None):
        self.name=name
        self.age=age
        self.sex=sex
        self.score=score
    def __str__(self):
        return "姓名：{0}，年龄：{1}，性别：{2}，成绩：{3}".format(self.name,self.age,self.sex,self.score)
student=[]
class mysax(ContentHandler):
    def __init__(self):
        self.tag=None
        self.student=None
    def startDocument(self):
        pass
    def startElement(self, name, attrs):
        self.tag = name
        if name=="student":
            self.student=Student()
    def characters(self, content):
        if self.tag=="name":
            self.student.name=content
        if self.tag=="age":
            self.student.age=content
        if self.tag=="sex":
            self.student.sex=content
        if self.tag=="score":
            self.student.score=content
    def endElement(self, name):
        if name=="student":
            student.append(self.student)
            self.student = None
        self.tag = None
    def endDocument(self):
        pass
students=mysax()
parse("students.xml",students)
for p in student:
    print(p)

3. 元素树解析(ElmentTree)

from xml.etree.ElementTree import*
class Student:
    def __init__(self,name=None,age=None,sex=None,score=None):
        self.name=name
        self.age=age
        self.sex=sex
        self.score=score
    def __str__(self):
        return "姓名：{0}，年龄：{1}，性别：{2}，成绩：{3}".format(self.name,self.age,self.sex,self.score)
people=[]
root=parse("students.xml")
student1=root.findall("student")
for p in student1:
    student=Student()
    student.name=p.find("name").text
    student.age = p.find("age").text
    student.sex = p.find("sex").text
    student.score = p.find("score").text
    people.append(student)
for p in people:
    print(p)