http://feeds.feedburner.com/YouLookNiceToday?format=xml

#!/usr/bin/env python

import sys

from xml.sax import make_parser, handler
from xml.sax.saxutils import DefaultHandler

from email.Utils import parsedate
import time
#
import os
import urllib

# --- The ContentHandler

class RSSHandler(DefaultHandler):

    def __init__(self, pc):
        self._pc=pc
        self._text = ""
        self._parent = None
        self._title = None
        self._link = None
        self._encURL=None
        self._date = None
        self._xml_stack = ['Root']
        self._pc._parseFail=False

    def ReadIn(self, xml):
        self._xml=xml
        parser=make_parser()
        parser.setContentHandler(self)
        try:
           parser.parse(self._xml)
        except:
           print "XML Parse fail"
           self._pc._parseFail=True

    # ContentHandler methods
    def startElement(self, name, attrs):
        self._xml_stack.append(name)
        self._text = ""
        if name=="enclosure" and self._xml_stack[-2]=="item":
          self._encURL=attrs.get("url")
        

    def endElement(self, name):
        self._xml_stack.pop()
        #self._parent=self._xml_stack[len(self._xml_stack)-1]
        self._parent=self._xml_stack[-1]
        if self._parent == "channel":
            if name == "title":
		self._pc._Title=self._text
            elif name == "description":
	        self._pc._Desc=self._text
            elif name == "lastBuildDate":
                self._pc._RSSDate=parsedate(self._text)
            elif name == "pubDate":
                self._pc._RSSDate=parsedate(self._text)

        elif self._parent == "item":
            if name == "title":
                self._title = self._text
            elif name == "link":
                self._link = self._text
            elif name == "pubDate":
                self._date = parsedate(self._text)
            elif name == "description":
                self._descr = self._text

        if name == "item":
            self._pc._Episodes.append([self._encURL, self._title,self._date])
            self._title = None
	    self._date=None
            self._link = None
            self._descr = ""

    def characters(self, content):
        self._text = self._text + content

class PodcastClass():
    def __init__(self):
        self._Title=""
        self._Episodes=[]
        self._Desc=""
        self._RSSDate=None
        self._machineName=""
        self._prevRSSDate=None
        self._parseFail=False

    def upDated(self):
        if self._RSSDate==None:
          for ee in self._Episodes:
            if ee[2]>self._RSSDate or self._RSSDate==None:
              self._RSSDate=ee[2]
        return self._RSSDate

    def newEpisodes(self):
        g=[]
        if self._prevRSSDate==None:
          g=self._Episodes
        else:
          for ee in self._Episodes:
            if ee[2]>self._prevRSSDate:
              g.append(ee)
        return g
          
    def shortName(self):                                                   
        if self._machineName=="":                                           
           for c in self._Title.lower():                                                               
             if c.isalnum():
                self._machineName=self._machineName+c 
        return self._machineName

    def newest(self):
        re=None
        for gg in self.newEpisodes():
          if re==None or re[2]<gg[2]:
            re=gg

        return re
        

def myReportHook(count, blockSize, totalSize):
    print count, count*blockSize, totalSize, int(100 *  count*blockSize/totalSize),"\r",


def uncracklink(urlfile):
    f=open(urlfile,"r")
    u=f.readline()                                                                                                                
    f.close()
    return u

#---+----+---+---+

sDir="/media/mmc1/podcasts/"

d=os.listdir(sDir)
for f in d:
   if f.lower().endswith(".url"):
     print "Reading file", f.lower()
     sPodCast=f[:-4]
     sURL=uncracklink(sDir+"/"+f)
     if not os.path.isdir(sDir+"/"+sPodCast):
       os.mkdir(sDir+"/"+sPodCast)
       print "NB: creating podcast directory"

     prevPC=PodcastClass()
     if sPodCast+".xml" in d: 
       print "Reading previous XML"
       prevPCr=RSSHandler(prevPC)
       prevPCr.ReadIn(sDir+"/"+sPodCast+".xml") 
       if prevPC.upDated()!=None:
         print "Podcast", prevPC._Title, time.strftime("%Y-%m-%d %H:%M:%S",prevPC.upDated())
     else:
       print "No previous XML"

     print "Downloading newest RSS XML"
     try:
       x=urllib.urlretrieve(sURL,sDir+"/"+sPodCast+".1.xml",myReportHook)
     except urllib.ContentTooShortError:
       print "retrieve fail"

     if x[0]!=None:   
       newPC=PodcastClass()
       newPCr=RSSHandler(newPC)
       newPCr.ReadIn(x[0])
       newPC._prevRSSDate=prevPC.upDated()
       if newPC.upDated()!=None:
         print "retrieved", newPC._Title, time.strftime("%Y-%m-%d %H:%M:%S",newPC.upDated())
     
       PCtoget=newPC.newest()
       if PCtoget!=None and len(PCtoget[0])>0: 
         print "New episode:", PCtoget[1] 
         print "url:", len(PCtoget[0])
         try:
           x2=urllib.urlretrieve(PCtoget[0],sDir+"/"+sPodCast+"/"+PCtoget[0].split("/")[-1],myReportHook)
         except urllib.ContentTooShortError:
           print "retrieve fail"
         else:
           os.rename(x[0],sDir+"/"+sPodCast+".xml")

       if os.path.exists(x[0]):
         os.unlink(x[0])

[Desktop Entry]
Encoding=UTF-8
Version=1.0
Name=PPodder
Comment=myPPodder
Exec=/home/user/ppodder.py
Icon=qgn_list_rss
Type=Application