使用python3.4解析xml文件(sax、dom、etree)

清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>

调用sax模块处理xml文件。

#重载了三个方法
#处理xml,主要就是写自己的事件处理类

from xml.sax import *

class DengHandler(ContentHandler):
    def startDocument(self):
        print("----开始解析xml文档----")
    def endDocument(self):
        print("----xml文档解析完毕----")
    def startElement(self,name,attrs):
        if name == "author":
            print("名字:",attrs['name']," 日期:",attrs["birth"])

parse("deng.xml",DengHandler())
        



deng.xml


<?xml version = "1.0" encoding = "utf-8"?>
	<author name = "dengjingdong" birth = "19920517"></author>
</people>



调用dom模块中的minidom处理xml文件。


from xml.dom.minidom import *
#scannode函数打印xml文件的结构
def scannode(doc,level = 0):
    ret = doc.__class__.__name__
    if doc.nodeType == Node.ELEMENT_NODE:
        ret += ",标签:" + doc.tagName
    print(" "*4*level,ret)
    if doc.hasChildNodes:
        for child in doc.childNodes:
            scannode(child,level+1)
#----scannode-----
xin = parse("book.xml")
print(xin)
scannode(xin)
#----scannode-----

x = parse("domtest.xml")
nx = x.getElementsByTagName("author")

print(nx[0].getAttribute("birth"))
print(nx[0].childNodes[0].data)

print(nx[1].getAttribute("birth"))
print(nx[1].childNodes[0].data)



book.xml


<?xml version = "1.0" encoding = "utf-8" ?>
<book>
	<title>the book title</title>
	<author>
		<name>jingdong</name>
		<boy>true</boy>
	</author>
	<chapter number = "1">
		<title> first chapter </title>
		<para>
			I love python.
		</para>
	</chapter>
</book>

domtest.xml



<?xml version = "1.0" encoding = "utf-8" ?>
<people>
	<author name = "dengjingdong" birth = "1990517">dongdong</author>
	<author name = "wushengnan" birth = "19920520">nannan</author>
</people>



调用etree模块中的ElementTree生成所需的xml文件。


import xml.etree.ElementTree as et
x = et.Element("name")
x.text = "dengjingdong"
x.set("boy","true")
sx = et.tostring(x)
print(sx)