使用python解析xml成对应的html示例分享



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\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(''' 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

''')

#程序入口
if __name__ == '__main__':
parse('ddt.xml', Website())

Copyright © 2019- otar.cn 版权所有

违法及侵权请联系：TEL:199 18 7713 E-MAIL:2724546146@qq.com

本站由北京市万商天勤律师事务所王兴未律师提供法律服务

''') 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('''