Python使用sax模块解析XML文件示例

<?xml version="1.0"?>
<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>

from xml import sax
class moviehandler(sax.contenthandler):
  def __init__(self):
    # 初始化数据，并增加一个当前数据
    self.currentdata = ""
    self.type = ""
    self.format = ""
    self.year = ""
    self.rating = ""
    self.stars = ""
    self.description = ""
  # 文档启动的时候调用
  def startdocument(self):
    print('xml开始解析中...')
  # 元素开始事件处理
  def startelement(self, name, attrs):
    self.currentdata=name
    if self.currentdata=='movie':
      print('*********movie*********')
      title=attrs['title']
      print('title:{0}'.format(title))
  # 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
  # 元素结束事件处理
  def endelement(self, name):
    if self.currentdata=='type':
      print('type:{0}'.format(self.type))
    elif self.currentdata=='format':
      print('format:{0}'.format(self.format))
    elif self.currentdata=='year':
      print('year:{0}'.format(self.year))
    elif self.currentdata == 'rating':
      print('rating:{0}'.format(self.rating))
    elif self.currentdata == 'stars':
      print('stars:{0}'.format(self.stars))
    elif self.currentdata == 'description':
      print('description:{0}'.format(self.description))
    self.currentdata = ""
  # 文档结束的时候调用
  def enddocument(self):
    print('xml文档解析结束!')
if __name__=='__main__':
  handler=moviehandler()
  parser = sax.make_parser()
  # parser.setfeature(sax.handler.feature_namespaces, 0)
  parser.setcontenthandler(handler)
  parser.parse("sax_test.xml")