#!/usr/bin/env python
#
# $Id: fetch_podcasts.py 583 2007-04-08 15:09:18Z dhellmann $
#
# Copyright 2007 Doug Hellmann.
#
#
#                         All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of Doug
# Hellmann not be used in advertising or publicity pertaining to
# distribution of the software without specific, written prior
# permission.
#
# DOUG HELLMANN DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN
# NO EVENT SHALL DOUG HELLMANN BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#

"""Use several threads to download enclosures from RSS feeds.
"""

from Queue import Queue
from threading import Thread
import time

import feedparser

# Set up some global variables
num_fetch_threads = 2
enclosure_queue = Queue()

# A real app wouldn't use hard-coded data...
feed_urls = [ 'http://www.castsampler.com/cast/feed/rss/guest',
             ]


def downloadEnclosures(i, q):
    """This is the worker thread function.
    It processes items in the queue one after
    another.  These daemon threads go into an
    infinite loop, and only exit when
    the main thread ends.
    """
    while True:
        print '%s: Looking for the next enclosure' % i
        url = q.get()
        print '%s: Downloading:' % i, url
        time.sleep(i + 2) # instead of really downloading the URL, we just pretend
        q.task_done()


# Set up some threads to fetch the enclosures
for i in range(num_fetch_threads):
	worker = Thread(target=downloadEnclosures, args=(i, enclosure_queue,))
	worker.setDaemon(True)
	worker.start()

# Download the feed(s) and put the enclosure URLs into
# the queue.
for url in feed_urls:
    response = feedparser.parse(url, agent='fetch_podcasts.py')
    #print response
    for entry in response['entries']:
		for enclosure in entry.get('enclosures', []):
		    print 'Queuing:', enclosure['url']
		    enclosure_queue.put(enclosure['url'])
        
# Now wait for the queue to be empty, indicating that we have
# processed all of the downloads.
print '*** Main thread waiting'
enclosure_queue.join()
print '*** Done'