SAX将dd.xml解析成html。当然啦，如果得到了xml对应的xsl文件可以直接用libxml2将其转换成html。
代码如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#---------------------------------------
# 程序：XML解析器
# 版本：01.0
# 作者：mupeng
# 日期：2013-12-18
# 语言：Python 2.7
# 功能：将xml解析成对应的html
# 注解：该程序用xml.sax模块的parse函数解析XML，并生成事件
# 继承ContentHandler并重写其事件处理函数
# Dispatcher主要用于相应标签的起始、结束事件的派发
#---------------------------------------
from xml.sax.handler import ContentHandler
from xml.sax import parse
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()
def startElement(self, name, attrs):
self.dispatch('start', name, attrs)
def endElement(self, name):
self.dispatch('end', name)
class Website(Dispatcher, ContentHandler):
def __init__(self):
self.fout = open('ddt_SAX.html', 'w')
self.imagein = False
self.desflag = False
self.item = False
self.title = ''
self.link = ''
self.guid = ''
self.url = ''
self.pubdate = ''
self.description = ''
self.temp = ''
self.prx = ''
def startChannel(self):
self.fout.write('''\n
\n
RSS-''')<p> def endChannel(self):<BR> self.fout.write('''<BR> <tr><td height="20"></td></tr><BR> </table><BR> </center><BR> <BR> function GetTimeDiff(str)<BR> {<BR> if(str == '')<BR> {<BR> return '';<BR> }</P>
<P> var pubDate = new Date(str);<BR> var nowDate = new Date();<BR> var diffMilSeconds = nowDate.valueOf()-pubDate.valueOf();<BR> var days = diffMilSeconds/800000;<BR> days = parseInt(days);</P>
<P> diffMilSeconds = diffMilSeconds-(days*800000);<BR> var hours = diffMilSeconds/3600000;<BR> hours = parseInt(hours);</P>
<P> diffMilSeconds = diffMilSeconds-(hours*3600000);<BR> var minutes = diffMilSeconds/60000;<BR> minutes = parseInt(minutes);</P>
<P> diffMilSeconds = diffMilSeconds-(minutes*60000);<BR> var seconds = diffMilSeconds/1000;<BR> seconds = parseInt(seconds);<p> var returnStr = "±±¾©·¢²¼Ê±¼ä£º" + pubDate.toLocaleString();</P>
<P> if(days > 0)<BR> {<BR> returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + days + "Ìì" + hours + "Сʱ" + minutes + "·ÖÖÓ£©";<BR> }<BR> else if (hours > 0)<BR> {<BR> returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + hours + "Сʱ" + minutes + "·ÖÖÓ£©";<BR> }<BR> else if (minutes > 0)<BR> {<BR> returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + minutes + "·ÖÖÓ£©";<BR> }</P>
<P> return returnStr;</P>
<P> }</P>
<P> function GetSpanText()<BR> {<BR> var pubDate;<BR> var pubDateArray;<BR> var spanArray = document.getElementsByTagName("span");</P>
<P> for(var i = 0; i < spanArray.length; i++)<BR> {<BR> pubDate = spanArray[i].innerHTML;<BR> document.getElementsByTagName("span")[i].innerHTML = GetTimeDiff(pubDate); <BR> }<BR> }</P>
<P> GetSpanText();<BR> </ script><BR> <div style="display:none;"><script>var _hmt = _hmt || [];(function() {var hm = document.createElement("script");hm.src = "https://hm.baidu.com/hm.js?de973f4fc4fc27c651135a4cd7781c2b";var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s);})();</script></div></body><BR> </html><BR> ''')<BR> self.fout.close()</P>
<P> def characters(self, chars):<BR> if chars.strip():<BR> #chars = chars.strip()<BR> self.temp += chars<BR> #print self.temp<p> <BR> def startTitle(self):<p> if self.item:<BR> self.fout.write('''<BR> <tr bgcolor="#eeeeee">\n<td style="padding-top:5px;padding-left:5px;" height="30">\n<B><BR> ''')<p> def endTitle(self):<p> if not self.imagein and not self.item:<BR> self.title = self.temp<BR> self.temp = ''<BR> self.fout.write(self.title.encode('gb2312'))<p> #self.title = self.temp<BR> self.fout.write('''<BR> \n\n\n
\n
\n
function copyLink()
{
clipboardData.setData("Text",window.location.href);
alert("RSSÁ´½ÓÒѾ¸´ÖƵ½¼ôÌù°å");
}
function subscibeLink()
{
var str = window.location.pathname;
while(str.match(/^\//))
{
str = str.replace(/^\//,"");
}
window.open("http://rss.sina.com.cn/my_sina_web_rss_news.html?url=" + str,"_self");
}
\n
\n
\n
\n
''') if self.item:
self.title = self.temp
self.temp = ''
self.fout.write(self.title.encode('gb2312'))
self.fout.write('''
|
''')
def startImage(self):
self.imagein = True
def endImage(self):
self.imagein = False def startLink(self):
if self.imagein:
self.fout.write('''
def endLink(self):
self.link = self.temp
self.temp = ''
if self.imagein:
self.fout.write(self.link.encode('gb2312'))
self.fout.write('''" target="_blank">\n ''')
elif self.item:
#self.link = self.temp
pass
else:
self.fout.write(self.link)
self.fout.write(''' " target="
_blank
"> ''')
self.fout.write(self.title.encode('gb2312'))
self.fout.write(''' |
''')
self.fout.write(self.description.encode('gb2312'))
self.fout.write('''
|
| ¸´ÖÆ´ËÒ³Á´½Ó ÎÒҪǶÈë¸ÃÐÂÎÅÁÐ±íµ½ÎÒµÄÒ³Ã棨¼òµ¥¡¢¿ìËÙ¡¢ÊµÊ±¡¢Ãâ·Ñ£© |
''')
def startUrl(self):
if self.imagein:
self.fout.write('''<BR> def endUrl(self):<BR> self.url = self.temp<BR> self.temp = ''<BR> if self.imagein:<BR> self.fout.write(self.url.encode('gb2312'))<BR> self.fout.write(''')
\n
''')
if self.item:
#self.url = self.temp
pass
def defaultStart(self):
pass
def defaultEnd(self):
self.temp = ''
def startDescription(self):
pass
def endDescription(self):
self.description = self.temp
self.temp = ''
if self.item:
#self.fout.write('¡¡¡¡')
self.fout.write(self.description.encode('gb2312')) def endGuid(self):
self.guid = self.temp
def endPubdate(self):
if not self.temp.startswith('http'):
self.pubdate = self.temp
self.temp = ''
else:
self.pubdate = ''
def startItem(self):
self.item = True
def endItem(self):
self.item = False
self.fout.write('''
|
self.fout.write(self.link)
self.fout.write(''' " target="_blank"> ''')
self.fout.write(self.guid)
self.fout.write('''
|
''')
self.fout.write(self.pubdate)
self.fout.write(''' |
|
''')
#程序入口
if __name__ == '__main__':
parse('ddt.xml', Website())
下载本文
显示全文
