Python解析XML的三种核心方法：DOM、ElementTree与SAX详解

<collection shelf="New Arrivals">
<movie title="Enemy Behind">
  <type>War, Thriller</type>
  <format>DVD</format>
  <year>2003</year>
  <rating>PG</rating>
  <stars>10</stars>
  <description>Talk about a US-Japan war</description>
</movie>
<movie title="Transformers">
  <type>Anime, Science Fiction</type>
  <format>DVD</format>
  <year>1989</year>
  <rating>R</rating>
  <stars>8</stars>
  <description>A schientific fiction</description>
</movie>
  <movie title="Trigun">
  <type>Anime, Action</type>
  <format>DVD</format>
  <episodes>4</episodes>
  <rating>PG</rating>
  <stars>10</stars>
  <description>Vash the Stampede!</description>
</movie>
<movie title="Ishtar">
  <type>Comedy</type>
  <format>VHS</format>
  <rating>PG</rating>
  <stars>2</stars>
  <description>Viewable boredom</description>
</movie>
</collection>

# !/usr/bin/python
# -*- coding: UTF-8 -*-

from xml.dom.minidom import parse
import xml.dom.minidom

# 使用minidom解析器打开 XML 文档
DOMTree = xml.dom.minidom.parse("movie.xml")
#得到元素对象
collection = DOMTree.documentElement
if collection.hasAttribute("shelf"):
  print("Root element : %s" % collection.getAttribute("shelf"))
  #获取标签名
  #print(collection.nodeName)

# 在集合中获取所有电影
movies = collection.getElementsByTagName("movie")

# 打印每部电影的详细信息
for movie in movies:
  print("*****Movie*****")
  if movie.hasAttribute("title"):
    print("Title: %s" % movie.getAttribute("title"))

  type = movie.getElementsByTagName('type')[0]
  print("Type: %s" % type.childNodes[0].data)
  format = movie.getElementsByTagName('format')[0]
  print("Format: %s" % format.childNodes[0].data)
  year=movie.getElementsByTagName("year")
  if len(year)>0:
    print("Year: %s" % year[0].firstChild.data)
    #父节点 parentNode
    #print(year[0].parentNode.nodeName)
  rating = movie.getElementsByTagName('rating')[0]
  print("Rating: %s" % rating.childNodes[0].data)
  description = movie.getElementsByTagName('description')[0]
  # 显示标签对之间的数据
  print("Description: %s" % description.childNodes[0].data)
  #print("Description: %s" % description.firstChild.data)

Root element : New Arrivals
*****Movie*****
Title: Enemy Behind
Type: War, Thriller
Format: DVD
Year: 2003
Rating: PG
Description: Talk about a US-Japan war
*****Movie*****
Title: Transformers
Type: Anime, Science Fiction
Format: DVD
Year: 1989
Rating: R
Description: A schientific fiction
*****Movie*****
Title: Trigun
Type: Anime, Action
Format: DVD
Rating: PG
Description: Vash the Stampede!
*****Movie*****
Title: Ishtar
Type: Comedy
Format: VHS
Rating: PG
Description: Viewable boredom

import xml.etree.ElementTree as ET
import sys
import os.path

def traverseXml(element):
  #print (len(element))
  if len(element) > 0:
    for child in element:
      print("********Movie********")
      print("Title：",child.get("title"))
      for childchild in child:
        print(childchild.tag,"：",childchild.text)
      #traverseXml(child)
  #else:
  #  print (element.tag, "----", element.attrib)

def readXml(xmlFile):
  try:
    tree = ET.parse(xmlFile)
    #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 ***.xml fail!")
    sys.exit()
  #print("root type:", type(root))
  #root.attrib访问root属性,root.tag标签
  #print(root.tag, "：", root.attrib)
  return root

if __name__ == "__main__":
  xmlFilePath = os.path.abspath("movie.xml")
  root=readXml(xmlFilePath)

  # # 使用下标访问
  # print(root[0][0].text)
  # print(root[1][2].text)
  #根据标签名查找root下的所有标签
  # movies=root.findall("movie")
  #遍历子标签
  # print(len(movies))
  # for movie in movies:
  #   type=movie.find("type")
  #   print(type.text)

  # 遍历xml文件
  traverseXml(root)

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import xml.sax

class MovieHandler(xml.sax.ContentHandler):
  def __init__(self):
    self.CurrentData = ""
    self.type = ""
    self.format = ""
    self.year = ""
    self.rating = ""
    self.stars = ""
    self.description = ""

  # 元素开始事件处理
  def startElement(self, tag, attributes):
    self.CurrentData = tag
    if tag == "movie":
      print("*****Movie*****")
      title = attributes["title"]
      print("Title:", title)

  # 元素结束事件处理
  def endElement(self, tag):
    if self.CurrentData == "type":
      print("Type:", self.type)
    elif self.CurrentData == "format":
      print("Format:", self.format)
    elif self.CurrentData == "year":
      print("Year:", self.year)
    elif self.CurrentData == "rating":
      print("Rating:", self.rating)
    elif self.CurrentData == "stars":
      print("Stars:", self.stars)
    elif self.CurrentData == "description":
      print("Description:", self.description)
    self.CurrentData = ""

  # 内容事件处理
  def characters(self, content):
    if self.CurrentData == "type":
      self.type = content
    elif self.CurrentData == "format":
      self.format = content
    elif self.CurrentData == "year":
      self.year = content
    elif self.CurrentData == "rating":
      self.rating = content
    elif self.CurrentData == "stars":
      self.stars = content
    elif self.CurrentData == "description":
      self.description = content

if (__name__ == "__main__"):
  # 创建一个 XMLReader
  parser = xml.sax.make_parser()
  # turn off namepsaces
  parser.setFeature(xml.sax.handler.feature_namespaces, 0)

  # 重写 ContextHandler
  Handler = MovieHandler()
  parser.setContentHandler(Handler)

  parser.parse("movie.xml")