python的xml模块

cat an_xml.py 

#!/usr/bin/python3

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 = ""

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

   # 元素结束调用
   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 = ""

   # 读取字符时调用
   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("movies.xml")

cat movies.xml 

<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>

运行结果python3 an_xml.py：

*****Movie*****
Title: Enemy Behind
Type: War, Thriller
Format: DVD
Year: 2003
Rating: PG
Stars: 10
Description: Talk about a US-Japan war
*****Movie*****
Title: Transformers
Type: Anime, Science Fiction
Format: DVD
Year: 1989
Rating: R
Stars: 8
Description: A schientific fiction
*****Movie*****
Title: Trigun
Type: Anime, Action
Format: DVD
Rating: PG
Stars: 10
Description: Vash the Stampede!
*****Movie*****
Title: Ishtar
Type: Comedy
Format: VHS
Rating: PG
Stars: 2
Description: Viewable boredom

中间发生错误是因为文件名用xml命名，导致：

No module named 'xml.sax'; 'xml' is not a package

还有一个文件拷贝的格式问题：

-bash: ./xml.py: /usr/bin/python3^M: bad interpreter: No such file or directory

解决：

dos2unix  an_xml.py