cat an_xml.py
#!/usr/bin/python3import xml.saxclass 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
War, Thriller DVD 2003 PG 10 Talk about a US-Japan war Anime, Science Fiction DVD 1989 R 8 A schientific fiction Anime, Action DVD 4 PG 10 Vash the Stampede! Comedy VHS PG 2 Viewable boredom
运行结果python3 an_xml.py：
*****Movie*****Title: Enemy BehindType: War, ThrillerFormat: DVDYear: 2003Rating: PGStars: 10Description: Talk about a US-Japan war*****Movie*****Title: TransformersType: Anime, Science FictionFormat: DVDYear: 1989Rating: RStars: 8Description: A schientific fiction*****Movie*****Title: TrigunType: Anime, ActionFormat: DVDRating: PGStars: 10Description: Vash the Stampede!*****Movie*****Title: IshtarType: ComedyFormat: VHSRating: PGStars: 2Description: 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