Given the rss feed for a podcast, download it in its entirety.

gistfile1.txt

#!/usr/bin/python3

import os
import sys
import pathlib
import shutil
import tempfile
import urllib.request

import concurrent.futures

from xml.dom import minidom

def textFromNode( node ):
   res = []
   for n in node.childNodes:
      if n.nodeType == node.TEXT_NODE:
         res.append( n.data )
   return ' '.join( res )

def scrape( dest_dir, dom ):
   items = dom.getElementsByTagName( 'item' )

   def scrape_item( item ):
      title = textFromNode( item.getElementsByTagName( 'title' )[ 0 ] )
      dest = os.path.join( dest_dir, title )
      if os.path.exists( dest ):
         return

      tmpDir = tempfile.mkdtemp( suffix=title )
      with open( os.path.join( tmpDir, 'metadata.xml' ), 'w+' ) as metaFile:
         metaFile.write( item.toprettyxml() )

      mp3Url = item.getElementsByTagName( 'enclosure' )[ 0 ].getAttribute( 'url' )
      urllib.request.urlretrieve( mp3Url, os.path.join( tmpDir, title + '.mp3' ) )

      thumbnailUrl = item.getElementsByTagName( 'itunes:image' )[ 0 ].getAttribute( 'href' )
      urllib.request.urlretrieve( thumbnailUrl, os.path.join( tmpDir, 'thumbnail.png' ) )

      shutil.move( tmpDir, dest )

   with concurrent.futures.ThreadPoolExecutor( max_workers=3 ) as pool:
      pool.map( scrape_item, items )

def main( args ):
   if len( sys.argv ) != 3:
      print( 'Usage: {} DEST_DIR FEED.rss'.format( sys.argv[ 0 ] ) )
      os.exit( 2 )
   
   _, dest_dir, rssFile = sys.argv

   dom = minidom.parse( rssFile )
   dest_dir = os.path.abspath( dest_dir )
   pathlib.Path( dest_dir ).mkdir( parents=True, exist_ok=True )

   scrape( dest_dir, dom )

if __name__ == '__main__':
   main( sys.argv )