#!/usr/bin/env python
#
# Copyright (c) 2010 Andrew Barr <andrew.james.barr@gmail.com>
#
#    This program is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; version 3 of the License, or at your 
#    option, any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.



import xml.dom.minidom, urllib2, string, sys

print "Content-Type: application/rss+xml"
print "Status: 200 OK"
print ""

class NotModifiedHandler(urllib2.BaseHandler):
  
    def http_error_304(self, req, fp, code, message, headers):
        addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
        addinfourl.code = code
        return addinfourl
        
def get_feed():
	
	theurl = 'http://feeds.gawker.com/gawker/vip'
	txdata = None
	txheaders = {'User-agent': 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.1) Gecko/20090423 Firefox/3.5.5'}
	
	feed = urllib2.Request(theurl, txdata, txheaders)
	try:
		saved_etag = open('/var/lib/rssfilt/etag/gawker.txt', 'r').read()
	except IOError:
		saved_etag = None
	
	if(saved_etag is not None):
		# put it into if-none-modified header
		feed.add_header('If-None-Match', saved_etag)
			
	
	opener = urllib2.build_opener(NotModifiedHandler())
	feed_stream = opener.open(feed)
	headers = feed_stream.info()
	
	if hasattr(feed_stream, 'code') and feed_stream.code == 304:
		return open('/var/lib/rssfilt/cache/gawker.xml', 'r')
	else:
		# save etag and feed to disk
		etag = feed_stream.headers.get('ETag')
		open('/var/lib/rssfilt/etag/gawker.txt', 'w+', 0600).write(etag)
		open('/var/lib/rssfilt/cache/gawker.xml', 'w+', 0600).write(feed_stream.read())
				
		return open('/var/lib/rssfilt/cache/gawker.xml', 'rU')

feed = get_feed()
dom = xml.dom.minidom.parse(feed)

# only print one author
for author in dom.getElementsByTagName('dc:creator'):
	newell = '<dc:creator><![CDATA[Jim Newell]]></dc:creator>'
	if(author.toxml() != newell):
		item = author.parentNode
		item.parentNode.removeChild(item)

print dom.toxml("utf-8")