#!/usr/bin/env python

# Atom feed creator for Liferea/Snownews and user photo pages of fotocommunity.de
#
# Author: Florian Brucker
# E-Mail: torf at torfbold dot com
# Homepage: http://www.torfbold.com
# Version: 0.1
#
# History:
#   0.1 - First release
#
# Simply use the desired user's fotocommunity.de photo page URL as a 
# feed url for Snownews/Liferea. The URLs look like this:
#
#     http://www.fotocommunity.de/pc/pc/mypics/ + NUMBER
#
# Note: Only the newest 8 photos are included in the feed
#   
# This software is provided "as is", without any warrenty. Feel free to
# do with it what you like.

import sys, re, time

def format_date(t=None):
	if t is None: t = time.localtime()
	return time.strftime("%Y-%m-%dT%H:%M:%S-00:00", t)

flags = re.IGNORECASE | re.DOTALL | re.MULTILINE
title_pattern = re.compile('<span class="bildtitel">(.*?)</span>', flags)
src_pattern = re.compile('src="(.*?)"', flags)
link_pattern = re.compile('href="(.*?)"', flags)
date_pattern = re.compile ('(?:(\d\d\.\d\d\.\d\d), )?(\d\d?:\d\d)h', flags)

html = ''.join(sys.stdin.read().splitlines())

# find author name
author = re.search('NAME="author" CONTENT="(.*?)"', html)
if author is None:
	author = 'Unknown'
else:
	author = author.group(1)

# find author's id
id = re.search('/pc/account/myprofile/(\d+)"', html, flags)
if id is not None: 
	id = 'http://www.fotocommunity.de/pc/pc/mypics/' + id.group(1)

# print feed header
print """<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">"""
print "<title>%s</title>" % ("fotocommunity.de Photos By " + author)
if id is not None:
	print '<link href="%s" />' % id
	print '<id>%s</id>' % id
else:
	print '<id>faked</id>'
print "<author><name>%s</name></author>" % author
print '<link rel="self" href="http://does.not.exist.nowhere" />'
print "<updated>%s</updated>" % format_date()

# parse photo information
boxes = re.findall('Anfang NPicture-Box(.*?)Ende NPicture-Box', html, flags)
for box in boxes:
	entries = re.split('<div class="pad">', box)
	for entry in entries:
		title = title_pattern.search(entry)
		src = src_pattern.search(entry)
		link = link_pattern.search(entry)
		pubdate = date_pattern.search(entry)

		if (title is None
				or src is None
				or link is None
				or pubdate is None): continue

		title = title.group(1)
		src = src.group(1)
		link = link.group(1)
		if pubdate.group(1) is not None: 
			pubdate = pubdate.group(1) + " " + pubdate.group(2)
		else:
			pubdate = time.strftime("%d.%m.%y", time.gmtime()) + " " + pubdate.group(2) 
		pubdate = time.strptime(pubdate, "%d.%m.%y %H:%M")
		pubdate = format_date(pubdate)

		print "<entry>"
		print "<title>%s</title>" % title
		print '<link href="%s" />' % link
		print "<updated>%s</updated>" % pubdate
		print "<id>%s</id>" % src
		print '<content type="html">&lt;a href="%s"&gt;&lt;img src="%s" /&gt;&lt;/a&gt;</content>' % (link, src)
		print "</entry>"

print "</feed>"