使用python解析xml成对应的html示例分享
作者：
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。
#!/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('''<html>\n<head>\n<title> RSS-''')
def endChannel(self):
self.fout.write('''
<tr><td height="20"></td></tr>
</table>
</center>
<script>
function GetTimeDiff(str)
{
if(str == '')
{
return '';
}
var pubDate = new Date(str);
var nowDate = new Date();
var diffMilSeconds = nowDate.valueOf()-pubDate.valueOf();
var days = diffMilSeconds/86400000;
days = parseInt(days);
diffMilSeconds = diffMilSeconds-(days*86400000);
var hours = diffMilSeconds/3600000;
hours = parseInt(hours);
diffMilSeconds = diffMilSeconds-(hours*3600000);
var minutes = diffMilSeconds/60000;
minutes = parseInt(minutes);
diffMilSeconds = diffMilSeconds-(minutes*60000);
var seconds = diffMilSeconds/1000;
seconds = parseInt(seconds);
var returnStr = "±±¾©·¢²¼Ê±¼ä£º" + pubDate.toLocaleString();
if(days > 0)
{
returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + days + "Ìì" + hours + "Сʱ" + minutes + "·ÖÖÓ£©";
}
else if (hours > 0)
{
returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + hours + "Сʱ" + minutes + "·ÖÖÓ£©";
}
else if (minutes > 0)
{
returnStr = returnStr + " £¨¾àÀëÏÖÔÚ" + minutes + "·ÖÖÓ£©";
}
return returnStr;
}
function GetSpanText()
{
var pubDate;
var pubDateArray;
var spanArray = document.getElementsByTagName("span");
for(var i = 0; i < spanArray.length; i++)
{
pubDate = spanArray[i].innerHTML;
document.getElementsByTagName("span")[i].innerHTML = GetTimeDiff(pubDate);
}
}
GetSpanText();
</script>
</body>
</html>
''')
self.fout.close()
def characters(self, chars):
if chars.strip():
#chars = chars.strip()
self.temp += chars
#print self.temp
def startTitle(self):
if self.item:
self.fout.write('''
<tr bgcolor="#eeeeee">\n<td style="padding-top:5px;padding-left:5px;" height="30">\n<B>
''')
def endTitle(self):
if not self.imagein and not self.item:
self.title = self.temp
self.temp = ''
self.fout.write(self.title.encode('gb2312'))
#self.title = self.temp
self.fout.write('''
</title>\n</head>\n<body>\n<center>\n
<script>\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");
}
</script>\n
<table width="750" cellpadding="0" cellspacing="0">\n
<tr>\n
<td align="right" style="padding-right:15px;" valign="bottom">\n
''')
if self.item:
self.title = self.temp
self.temp = ''
self.fout.write(self.title.encode('gb2312'))
self.fout.write('''
</B>
</td>
</tr>
<tr bgcolor="#eeeeee">
<td style="padding-left:5px;">
''')
def startImage(self):
self.imagein = True
def endImage(self):
self.imagein = False
def startLink(self):
if self.imagein:
self.fout.write('''<A href=" ''')
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(''' </A></B></td>
</tr>
<tr><td colspan="2" align="center">
''')
self.fout.write(self.description.encode('gb2312'))
self.fout.write('''
</td></tr>
<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>
</table>
<table width="750" cellpadding="0" cellspacing="0">
''')
def startUrl(self):
if self.imagein:
self.fout.write('''<IMG src=" ''')
def endUrl(self):
self.url = self.temp
self.temp = ''
if self.imagein:
self.fout.write(self.url.encode('gb2312'))
self.fout.write('''" border="0">\n
</A>
</td>
<td align="left" valign="bottom" style="padding-bottom:8px;"><B><A href="
''')
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('''
</td>
</tr>
<tr bgcolor="#eeeeee">
<td style="padding-top:5px;padding-left:5px;">
<A href="''')
self.fout.write(self.link)
self.fout.write(''' " target="_blank"> ''')
self.fout.write(self.guid)
self.fout.write('''
</A>
</td>
</tr>
<tr bgcolor="#eeeeee">
<td style="padding-top:5px;padding-left:5px;padding-bottom:5px;"><span>''')
self.fout.write(self.pubdate)
self.fout.write('''</span></td>
</tr>
<tr height="10"><td></td></tr>''')
#程序入口
if __name__ == '__main__':
parse('ddt.xml', Website())