- 论坛徽章:
- 0
|
from xml.sax.handler import ContentHandler
from xml.sax import parse
import os
class Dispatcher:
def dispatch(self, prefix, name, attrs=None):
mname = prefix + name.capitalize()
dname = 'default' + prefix.capitalize()
method = getattr(self, mname, None)
if callable(method): args = ()
else:
method = getattr(self, dname, None)
args = name,
if prefix == 'start': args += attrs,
if callable(method): method(*args)
def startElement(self, name, attrs):
self.dispatch('start', name, attrs)
def endElement(self, name):
self.dispatch('end', name)
class WebsiteConstructor(Dispatcher, ContentHandler):
passthrough = False
def __init__(self, directory):
self.directory = [directory]
self.ensureDirectory()
def ensureDirectory(self):
path = os.path.join(*self.directory)
print path
print '----'
if not os.path.isdir(path): os.makedirs(path)
def characters(self, chars):
if self.passthrough: self.out.write(chars)
def defaultStart(self, name, attrs):
if self.passthrough:
self.out.write('<' + name)
for key, val in attrs.items():
self.out.write(' %s="%s"' %(key, val))
self.out.write('>')
def defaultEnd(self, name):
if self.passthrough:
self.out.write('</%s>' % name)
def startDirectory(self, attrs):
self.directory.append(attrs['name'])
self.ensureDirectory()
def endDirectory(self):
print 'endDirectory'
self.directory.pop()
def startPage(self, attrs):
print 'startPage'
filename = os.path.join(*self.directory + [attrs['name']+'.html'])
self.out = open(filename, 'w')
self.writeHeader(attrs['title'])
self.passthrough = True
def endPage(self):
print 'endPage'
self.passthrough = False
self.writeFooter()
self.out.close()
def writeHeader(self, title):
self.out.write('<html>\n <head>\n <title>')
self.out.write(title)
self.out.write('</title>\n </head>\n <body>\n')
def writeFooter(self):
self.out.write('\n </body>\n</html>\n')
parse('website.xml',WebsiteConstructor('public_html'))
流程大概就是
1.首先创建一个public_html的文件,存放整个网站,然后读xml的节点,通过startElement和endElement调用dispatch进行处理。
2.然后就是dispatch怎么调用具体的处理函数了
小弟的疑问就是:
是因为startElement和endElement函数在前面,所以传递进来的html标签以及xml节点就会先被这两个函数调用,而不会被下面的函数直接调用吗? |
|