#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib2
from datetime import date
import re

def get_all_issues():
	today = date.today()
	rawstr = r"""<div class="morepics"><a href="(?P<link>.*)"><img src="http://cache.boston.com/universal/site_graphics/blogs/bigpicture/morepics1.gif" alt="more photos" onmouseout="this.src='http://cache.boston.com/universal/site_graphics/blogs/bigpicture/morepics1.gif'" onmouseover="this.src='http://cache.boston.com/universal/site_graphics/blogs/bigpicture/morepics2.gif'"></a></div>"""
	for year in range(2008, today.year+1):
		for month in range(1, 12+1):			
			target_url = "http://www.boston.com/bigpicture/%s/%s/" % (year, str(month).zfill(2))			
			try:
				f = urllib2.urlopen(target_url)
				for l in f.readlines():						
					match_obj = re.search(rawstr, l,  re.IGNORECASE|re.DOTALL)
					if match_obj:
						link = match_obj.group('link')
						print link
			except urllib2.HTTPError, e:
				pass			
if "__main__" == __name__:
	get_all_issues()
	print "done"