#!/usr/bin/env python2.4

# Simple RSS generation script for unofficial RSS syndication of
# WTF Comics - http://www.wtfcomics.com
#
# Bruce A. Locke (blocke@shivan.org)
# License: Public Domain (Do whatever you want with it)

import re, urllib, string

def check_wtf_comics():

	#page = file("wtftest.html").read()
	page = urllib.urlopen("http://www.wtfcomics.com/").read()

	comic_number = string.split( (re.compile(r"(var.+newest_issues.+=.*\".+\".*;)").split(page, 2)[1]), "\"")[1]

	# Each news posting has the following structure (minus \n, \r, \t, and space):
	# <TD><DIV ALIGN="justify"><FONT FACE="Arial" SIZE="2">
	# <B>01/02/03____</B><BR>
	# <BR>content</FONT>
	rawnews = []
	for x in re.compile(r'<TD><DIV ALIGN="justify"><FONT FACE="Arial" SIZE="2">[\r\n\t]+<B>([0-9/]+)_*</B><BR>[\r\n\t ]+<BR>[\r\n\t ]*', re.I + re.S).split(page)[1:]:
		rawnews.append(string.split(x, "</FONT></DIV></TD>")[0])

	#print rawnews

	# generate RSS 2.0 feed (no, this will not validate, oh well)

	print """<?xml version="1.0"?>
<rss version="2.0">
<channel>
<title>WTF Comics</title>
<link>http://www.wtfcomics.com</link>
<description>A humorous comic based in the world of Everquest by J. Waller</description>
<language>en</language>
<item>
<title>WTF #%s is available!</title>
<link>http://www.wtfcomics.com</link>
<description>
&lt;p&gt;
WTF Comic #%s is now available. ( &lt;a href="http://pub35.ezboard.com/fwtfcomicsfrm2"&gt;Forums&lt;/a&gt; )&lt;/p&gt;
</description>
</item>
""" % ( comic_number, comic_number )

	while len(rawnews):
		print "<item>"
		print "<title>News: " + rawnews.pop(0) + "</title>"
		print "<link>http://www.wtfcomics.com/#news</link>"
		print "<description>"
		print "&lt;p&gt;" + rawnews.pop(0).replace('<', '&lt;').replace('>', '&gt;').replace('\r', '')  + "&lt;p&gt;" 
		print "</description>"
		print "</item>"

	print "</channel></rss>"

if __name__ == '__main__':
	check_wtf_comics()