Python解析XML的三种主流方法：DOM、ElementTree与SAX详解

<?xml version="1.0" encoding="utf-8"?>
<catalog>
  <maxid>4</maxid>
  <login username="pytest" passwd='123456'>
    <caption>Python</caption>
    <item id="4">
      <caption>测试</caption>
    </item>
  </login>
  <item id="2">
    <caption>Zope</caption>
  </item>
</catalog>

#coding=utf-8

#通过minidom解析xml文件
import xml.dom.minidom as xmldom
import os
''' 
XML文件读取 
<?xml version="1.0" encoding="utf-8"?>
<catalog>
  <maxid>4</maxid>
  <login username="pytest" passwd='123456'>dasdas
    <caption>Python</caption>
    <item id="4">
      <caption>测试</caption>
    </item>
  </login>
  <item id="2">
    <caption>Zope</caption>
  </item>
</catalog>

'''

xmlfilepath = os.path.abspath("test.xml")
print ("xml文件路径：", xmlfilepath)

# 得到文档对象
domobj = xmldom.parse(xmlfilepath)
print("xmldom.parse:", type(domobj))
# 得到元素对象
elementobj = domobj.documentElement
print ("domobj.documentElement:", type(elementobj))

#获得子标签
subElementObj = elementobj.getElementsByTagName("login")
print ("getElementsByTagName:", type(subElementObj))

print (len(subElementObj))
# 获得标签属性值
print (subElementObj[0].getAttribute("username"))
print (subElementObj[0].getAttribute("passwd"))

#区分相同标签名的标签
subElementObj1 = elementobj.getElementsByTagName("caption")
for i in range(len(subElementObj1)):
  print ("subElementObj1[i]:", type(subElementObj1[i]))
  print (subElementObj1[i].firstChild.data) #显示标签对之间的数据

#coding=utf-8

#通过解析xml文件
'''
try:
  import xml.etree.CElementTree as ET
except:
  import xml.etree.ElementTree as ET

从Python3.3开始ElementTree模块会自动寻找可用的C库来加快速度  
'''
import xml.etree.ElementTree as ET
import os
import sys
''' 
XML文件读取 
<?xml version="1.0" encoding="utf-8"?>
<catalog>
  <maxid>4</maxid>
  <login username="pytest" passwd='123456'>dasdas
    <caption>Python</caption>
    <item id="4">
      <caption>测试</caption>
    </item>
  </login>
  <item id="2">
    <caption>Zope</caption>
  </item>
</catalog>
'''

#遍历xml文件
def traverseXml(element):
  #print (len(element))
  if len(element)>0:
    for child in element:
      print (child.tag, "----", child.attrib)
      traverseXml(child)
  #else:
    #print (element.tag, "----", element.attrib)
    

if __name__ == "__main__":
  xmlFilePath = os.path.abspath("test.xml")
  print(xmlFilePath)
  try:
    tree = ET.parse(xmlFilePath)
    print ("tree type:", type(tree))
  
    # 获得根节点
    root = tree.getroot()
  except Exception as e: #捕获除与程序退出sys.exit()相关之外的所有异常
    print ("parse test.xml fail!")
    sys.exit()
  print ("root type:", type(root))  
  print (root.tag, "----", root.attrib)
  
  #遍历root的下一层
  for child in root:
    print ("遍历root的下一层", child.tag, "----", child.attrib)

  #使用下标访问
  print (root[0].text)
  print (root[1][1][0].text)

  print (20 * "*")
  #遍历xml文件
  traverseXml(root)
  print (20 * "*")

  #根据标签名查找root下的所有标签
  captionList = root.findall("item") #在当前指定目录下遍历
  print (len(captionList))
  for caption in captionList:
    print (caption.tag, "----", caption.attrib, "----", caption.text)

  #修改xml文件，将passwd修改为999999
  login = root.find("login")
  passwdValue = login.get("passwd")
  print ("not modify passwd:", passwdValue)
  login.set("passwd", "999999")  #修改，若修改text则表示为login.text
  print ("modify passwd:", login.get("passwd"))

#coding=utf-8

'''
  XML解析类
  @功能-结点的增删改查
'''
import xml.etree.ElementTree as ET
import sys
import os.path

class XmlParse:
  def __init__(self, file_path):
    self.tree = None
    self.root = None
    self.xml_file_path = file_path

  def ReadXml(self):
    try:
      print("xmlfile:", self.xml_file_path)
      self.tree = ET.parse(self.xml_file_path)
      self.root = self.tree.getroot()
    except Exception as e:
      print ("parse xml faild!")
      sys.exit()
    else:
      print ("parse xml success!")      
    finally: 
      return self.tree
        
  def CreateNode(self, tag, attrib, text):
    element = ET.Element(tag, attrib)
    element.text = text
    print ("tag:%s;attrib:%s;text:%s" %(tag, attrib, text))
    return element
       
  def AddNode(self, Parent, tag, attrib, text):
    element = self.CreateNode(tag, attrib, text)
    if Parent:
      Parent.append(element)
      el = self.root.find("lizhi")
      print (el.tag, "----", el.attrib, "----", el.text)
    else:
      print ("parent is none")

  def WriteXml(self, destfile):
    dest_xml_file = os.path.abspath(destfile)
    self.tree.write(dest_xml_file, encoding="utf-8",xml_declaration=True)
    

if __name__ == "__main__":
  xml_file = os.path.abspath("test.xml")
  parse = XmlParse(xml_file)
  tree = parse.ReadXml()
  root = tree.getroot()
  print (root)
  parse.AddNode(root, "Python", {"age":"22", "hello":"world"}, "YES")
  
  parse.WriteXml("testtest.xml")