Sax parses the dd.xml into HTML. Of course, if you get the XSL file for XML, you can convert it to HTML directly with LIBXML2.
Copy the Code code as follows:
#!/usr/bin/env python
#-*-Coding:utf-8-*-
#---------------------------------------
# Program: XML Parser
# version: 01.0
# Author: Mupeng
# Date: 2013-12-18
# language: Python 2.7
# function: Parse XML into corresponding HTML
# Note: The program parses the XML with the parse function of the Xml.sax module and generates an event
# Inherit ContentHandler and override its event handler function
# Dispatcher is mainly used to distribute the starting and ending events of the corresponding labels.
#---------------------------------------
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-") <br><br> def endchannel (self):<br> self.fout.write (" ' <BR> &L T;TR><TD height= "></td></tr><BR> </table><BR> </center><BR> <BR> </body><BR> </ptm L><br> ") <BR> Self.fout.close () </P><P> def characters (self, chars): &L t;br> if Chars.strip ():<br> #chars = Chars.strip () <BR> self.temp + = Chars<b R> #print self.temp<br><br> <BR> def starttitle (self):<br><br> If self.item:<br> self.fout.write ("<BR> <tr bgcolor=" #eeeeee ">\n< TD style= "PADDING-TOP:5PX;PADDING-LEFT:5PX;" height= ">\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. titl E = self.temp<br> self.fout.write ("<BR>\ n\ n\ n
\ n
\ 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´½óîòòªç¶èë¸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 ())
''')
") If Self.item: #self. url = Self.temp Pass def defaultstart (self): Pass def defaultend (self): Self.temp = ' def STARTD Escription: 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.t EMP 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 ("' |
|
''')