BioHackersNetXML Parsing을 위한 간단한 인터페이스. callback-based, stream-based API.
사용예)
1 from xml.sax.handler import ContentHandler
2
3 class ArticleHandler(ContentHandler):
4 """
5 A handler to deal with articles in XML
6 """
7 inArticle = False
8 inBody = False
9 isMatch = False
10 title = ""
11 body = ""
12
13 def startElement(self, name, attrs):
14 if name == "webArticle":
15 subcat = attrs.get("subcategory", "")
16 if subcat.find("tech") > -1:
17 self.inArticle = True
18 self.isMatch = True
19 elif self.inArticle:
20 if name == "header":
21 self.title = attrs.get("title","")
22 if name == "body":
23 self.inBody = True
24
25 def characters(self, chars):
26 if self.inBody:
27 if len(self.body) < 80:
28 self.body += chars
29 if len(self.body) > 80:
30 self.body = self.body[:78] + "..."
31 self.inBody = False
32
33 def endElement(self, name):
34 if name == "body":
35 self.inBody = False
article.xml
<?xml version="1.0"?>
<webArticle category="news" subcategory="technical">
<header title="NASA Builds Warp Drive"
length="3k"
autohr="Joe Reporter"
distribution="all"/>
<body>Seattle, WA - Today an anonymous individual
announced that NASA has completed building a
Wrap Drive and has parked a ship that uses
claims that although he hasn't been contacted by
NASA concerning the parked space vessel, he assumes
that he will be launching it later this week to
mount an exhibition to the Andromeda Galaxy.
</body>
</webArticle>