最近感觉自己的工作中可能用到python，这语言实在是太强大了所以再次开始python的学习
通过联系小项目的形式练练手，下面是第一个项目，万能的XML
要使用python解析xml文件，我们需要用到SAX语法分分析器，这样我们就可以把xml解析的工作交给分析器取工作了。
本项目的主要工作：
- 整个网站用一个XML文件描述，其中包括独立的网页和文件目录的描述
- 程序能根据XML信息创建对应的html和目录文件
- 能轻松地改变整个网站的设计，并以新的设计为基础重新生成新的网页和目录结构
自定一的xml文件如下：
<website> <page name="index" title="Home Page"> <h1>Welcome to my Home Page</h1> <p>Hi. there. My name is Zeus. And this is my home page .Here are some of my interests:</p> <ul> <li><a href="interests/shouting.html">Shouting</a></li> <li><a href="interests/sleeping.html">Sleeping</a></li> <li><a href="interests/eating.html">Eating</a></li> </ul> </page> <directory name="interests"> <page name="shouting" title="shouting"> <h1>Mr. Zeus's Shouting Page</h1> <p>...</p> </page> <page name="sleeping" title="sleeping"> <h1>Mr. Hello's Sleeping Page</h1> <p>...</p> </page> <page name="eating" title="eating"> <h1>Mr. World's Eating Page</h1> <p>...</p> </page> </directory> </website>
对应的python解析xml代码如下：
#coding=utf-8
#!/usr/bin/python
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)
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):
self.directory.pop()
def startPage(self, attrs):
filename = os.path.join(*self.directory+[attrs['name']+'.html'])
self.out = open(filename, 'w')
self.writeHeader(attrs['title'])
self.passthrough = True
def endPage(self):
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'))