#!/usr/bin/env python
# Convert Advogato's recentlog page to an RSS feed.
# Adam Sampson <ats@offog.org>.
# Needs the timeoutsocket module from:
#   http://www.timo-tasi.org/python/timeoutsocket.py

# People you don't want to see in the feed.
ignore_users = [ "mglazer" ]

import sys, re, timeoutsocket
timeoutsocket.setDefaultSocketTimeout(30)
from urllib import urlopen

def encode(s):
	return s.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")

sys.stdout.write("Content-type: application/rdf+xml\r\n\r\n")

print """<?xml version="1.0" encoding="iso-8859-1"?>
<rss version="0.91">
<channel>
<title>Advogato: Recent diary entries</title>
<link>http://www.advogato.org/recentlog.html</link>
<description>Recent diary entries from Advogato</description>"""

try:
	f = urlopen("http://www.advogato.org/recentlog.html")
	page = f.read().replace("\r\n", "\n")
	f.close()

	articlere = re.compile(r'^<h4.*?> (.*?) <a href=.*?>(.*?)</a>\n.*?<span style="display: none">\((.*?)\).*?\n<blockquote>\n(.*?)</blockquote>\n(<p align=center>\[ <a href="/">Home</a>|<h4 class="level)', re.M | re.S)
	hrefre = re.compile(r'( href=[\'"])/', re.I)
	for (day, user, cert, body, dummy) in articlere.findall(page):
		if user in ignore_users: continue

		print "<item>"
		print "<title>" + user + " (" + cert + ")" + "</title>"
		print "<link>http://www.advogato.org/person/" + user + "/</link>"
		body = re.sub(hrefre, lambda m: m.group(1) + "http://www.advogato.org/", body)
		print "<description>" + encode(body) + "</description>"
		print "</item>"

except timeoutsocket.Timeout:
	pass

print """</channel>
</rss>"""