import xml.dom.minidom document = """\ <slideshow> <title>Demo slideshow</title> <slide><title>Slide title</title> <point>This is a demo</point> <point>Of a program for processing slides</point> </slide> <slide><title>Another demo slide</title> <point>It is important</point> <point>To have more than</point> <point>one slide</point> </slide> </slideshow> """ dom = xml.dom.minidom.parseString(document) def getText(nodelist): rc = [] for node in nodelist: if node.nodeType == node.TEXT_NODE: rc.append(node.data) return ''.join(rc) def handleSlideshow(slideshow): print "<html>" handleSlideshowTitle(slideshow.getElementsByTagName("title")[0]) slides = slideshow.getElementsByTagName("slide") handleToc(slides) handleSlides(slides) print "</html>" def handleSlides(slides): for slide in slides: handleSlide(slide) def handleSlide(slide): handleSlideTitle(slide.getElementsByTagName("title")[0]) handlePoints(slide.getElementsByTagName("point")) def handleSlideshowTitle(title): print "<title>%s</title>" % getText(title.childNodes) def handleSlideTitle(title): print "<h2>%s</h2>" % getText(title.childNodes) def handlePoints(points): print "<ul>" for point in points: handlePoint(point) print "</ul>" def handlePoint(point): print "<li>%s</li>" % getText(point.childNodes) def handleToc(slides): for slide in slides: title = slide.getElementsByTagName("title")[0] print "<p>%s</p>" % getText(title.childNodes) handleSlideshow(dom)
运行结果:
<html>
<title>Demo slideshow</title>
<p>Slide title</p>
<p>Another demo slide</p>
<h2>Slide title</h2>
<ul>
<li>This is a demo</li>
<li>Of a program for processing slides</li>
</ul>
<h2>Another demo slide</h2>
<ul>
<li>It is important</li>
<li>To have more than</li>
<li>one slide</li>
</ul>
</html>