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。
复制代码 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 RSS-''')<br><br> def endChannel(self):<br> self.fout.write('''<br> <tr><td height="20"></td></tr>
<br> <br> <br> <script><BR> function GetTimeDiff(str)<BR> {<BR> if(str == '')<BR> {<BR> return '';<BR> }
<P> var pubDate = new Date(str);<BR> var nowDate = new Date();<BR> var diffMilSeconds = nowDate.valueOf()-pubDate.valueOf();<BR> var days = diffMilSeconds/86400000;<BR> days = parseInt(days);
<P> diffMilSeconds = diffMilSeconds-(days*86400000);<BR> var hours = diffMilSeconds/3600000;<BR> hours = parseInt(hours);
<P> diffMilSeconds = diffMilSeconds-(hours*3600000);<BR> var minutes = diffMilSeconds/60000;<BR> minutes = parseInt(minutes);
<P> diffMilSeconds = diffMilSeconds-(minutes*60000);<BR> var seconds = diffMilSeconds/1000;<BR> seconds = parseInt(seconds);<br><br> var returnStr = "±±¾©·¢²¼Ê±¼ä£º" + pubDate.toLocaleString();
<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> return returnStr;
<P> }
<P> function GetSpanText()<BR> {<BR> var pubDate;<BR> var pubDateArray;<BR> var spanArray = document.getElementsByTagName("span");
<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> GetSpanText();<BR> </script><br> <br> <br> ''')<br> self.fout.close()
<p> def characters(self, chars):<br> if chars.strip():<br> #chars = chars.strip()<br> self.temp += chars<br> #print self.temp<br><br> <br> def startTitle(self):<br><br> if self.item:<br> self.fout.write('''<br> </p>
<tr bgcolor="#eeeeee">\n<td style="padding-top:5px;padding-left:5px;" height="30">\n<b><br> ''')<br><br> def endTitle(self):<br><br> if not self.imagein and not self.item:<br> self.title = self.temp<br> self.temp = ''<br> self.fout.write(self.title.encode('gb2312'))<br><br> #self.title = self.temp<br> self.fout.write('''<br> \n\n\n</b><center>\n<br> <script>\n
<P> function copyLink()<BR> {<BR> clipboardData.setData("Text",window.location.href);<BR> alert("RSSÁ´½ÓÒѾ­¸´ÖƵ½¼ôÌù°å");<BR> }
<P> function subscibeLink()<BR> {<BR> var str = window.location.pathname;<BR> while(str.match(/^\//))<BR> {<BR> str = str.replace(/^\//,"");<BR> }<BR> window.open("http://rss.sina.com.cn/my_sina_web_rss_news.html?url=" + str,"_self");
<P> }<BR> </script>\n<br> <table width="750" cellpadding="0" cellspacing="0">\n<br> <tr>\n<br> <td align="right" style="padding-right:15px;" valign="bottom">\n<br> ''')<br><br> if self.item:<br> self.title = self.temp<br> self.temp = ''<br> self.fout.write(self.title.encode('gb2312'))<br> self.fout.write('''<br> <br> </td>
<br> </tr>
<br> <tr bgcolor="#eeeeee">
<br> <td style="padding-left:5px;">
<br> ''')
<p> def startImage(self):<br> self.imagein = True</p>
<p> def endImage(self):<br> self.imagein = False<br><br> def startLink(self):<br> if self.imagein:<br> self.fout.write('''<a href="''')<br><br>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20<BR>%C2%A0%C2%A0%C2%A0%20def%20endLink(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.link%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.temp%20=%20''<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20if%20self.imagein:<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write(self.link.encode('gb2312'))<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write('''" target="_blank">\n ''')<br> elif self.item:<br> #self.link = self.temp<br> pass<br> else:<br> self.fout.write(self.link)<br> self.fout.write(''' " target="<br> _blank<br> "> ''')<br> self.fout.write(self.title.encode('gb2312'))<br> self.fout.write(''' </a></p>
</td>
<br> </tr>
<br> <tr><td colspan="2" align="center">
<br> ''')<br> self.fout.write(self.description.encode('gb2312'))<br> self.fout.write('''<br> </td></tr>
<br> <tr style="font-size:12px;" bgcolor="#eeeeff"><td colspan="2" style="font-size:14px;padding-top:5px;padding-bottom:5px;"><b><a href="javascript:copyLink();">¸´ÖÆ´ËÒ³Á´½Ó</a> <a href="javascript:subscibeLink();">ÎÒҪǶÈë¸ÃÐÂÎÅÁÐ±íµ½ÎÒµÄÒ³Ã棨¼òµ¥¡¢¿ìËÙ¡¢ÊµÊ±¡¢Ãâ·Ñ£©</a></b></td></tr>
<br> </table>
<br> <table width="750" cellpadding="0" cellspacing="0">
<br> ''')
<p> def startUrl(self):<br> if self.imagein:<br> self.fout.write('''<img src="''')<BR>%C2%A0%C2%A0%C2%A0%20def%20endUrl(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.url%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.temp%20=%20''<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20if%20self.imagein:<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write(self.url.encode('gb2312'))<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write('''" border="0" alt="使用python解析xml成对应的html示例分享" >\n<br> <br> <br> </p>
<td align="left" valign="bottom" style="padding-bottom:8px;"><b><a href="<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20''')<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20if%20self.item:<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20#self.url%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20pass</P>%0A<P>%C2%A0%C2%A0%C2%A0%20def%20defaultStart(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20pass<BR>%C2%A0%C2%A0%C2%A0%20def%20defaultEnd(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.temp%20=%20''<BR>%C2%A0%C2%A0%C2%A0%20def%20startDescription(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20pass<BR>%C2%A0%C2%A0%C2%A0%20def%20endDescription(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.description%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.temp%20=%20''<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20if%20self.item:<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20#self.fout.write('%C2%A1%C2%A1%C2%A1%C2%A1')<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write(self.description.encode('gb2312'))<br><br>%C2%A0%C2%A0%C2%A0%20def%20endGuid(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.guid%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%20def%20endPubdate(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20if%20not%20self.temp.startswith('http'):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.pubdate%20=%20self.temp<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.temp%20=%20''<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20else:<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.pubdate%20=%20''<BR>%C2%A0%C2%A0%C2%A0%20def%20startItem(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.item%20=%20True<BR>%C2%A0%C2%A0%C2%A0%20def%20endItem(self):<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.item%20=%20False<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write('''<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20</td><BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20</tr><BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20<tr%20bgcolor="><br> </a></b></td>
<td style="padding-top:5px;padding-left:5px;">
<br> <a href="''')<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write(self.link)<BR>%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%C2%A0%20self.fout.write('''%20" target="_blank"> ''')<br> self.fout.write(self.guid)<br> self.fout.write('''<br> </a><br> </td>
<br> <br> <tr bgcolor="#eeeeee">
<br> <td style="padding-top:5px;padding-left:5px;padding-bottom:5px;"><span>''')<br> self.fout.write(self.pubdate)<br> self.fout.write('''</span></td>
<br> </tr>
<br> <tr height="10"><td></td></tr>''')
<p>#程序入口<br>if __name__ == '__main__':<br> parse('ddt.xml', Website())<br></p>
</table>
</center>
</td>
</tr>
#!/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
