podcast downloader (with password)

podcast_downloader.py

#!/usr/bin/env python
# encoding: utf-8

# edit from https://github.com/hrktir/download_podcast_mp3/blob/master/download_podcast_mp3.py
# echo "http://podcasturl/xml podname" >> urls.txt # one podcast rss in each line 
# python podcast_downloader.py urls.txt

import urllib2
from xml.dom.minidom import parse
import time
import os
import sys

user="podcastuser"
password="password"

def getPodcastXmlDom(url):
  response = urllib2.urlopen(url)
  dom1 = parse(response)
  return dom1

def getItemList(dom):
  items = dom.getElementsByTagName('item')
  if len(items) > 0:
    return parseItemsAsRSS(items)
  else:
    raise Exception("no item element found")

def parseItemsAsRSS(items):
  results = []
  for item in items:
    idict = dict()

    enc = item.getElementsByTagName('enclosure')
    if len(enc) == 1:
      idict["url"] = enc[0].getAttribute("url")

    ititle = item.getElementsByTagName('title')
    if len(ititle) == 1:
      idict["title"] = ititle[0].firstChild.wholeText

    results.append(idict)
  return results

def getFilename4mp3(idict):
  ret = idict["title"]
  ret = ret + ".mp3"
  return ret

def downloadFile(url, filename, folder):
  print "download " + url + " as " + filename
  os.system( "mkdir -p "+folder )
  filename = filename.encode("utf-8")
  command = 'wget --http-user='+user+' --http-password='+password+' -c "' + url +'" -O '+ folder +'/'
  command += unicode(filename,"utf-8")
  os.system( command.encode("utf-8") )

def main():
  fileuri = sys.argv[1]
  f1 = open(fileuri, "r")
  urls = f1.readlines()
  for url in urls:
    ul = url.split()

    items = getItemList(getPodcastXmlDom( ul[0] ))
    for item in items:
      downloadFile(item["url"], getFilename4mp3(item), ul[1])


if __name__ == '__main__':
  main()