#!/usr/bin/perl

# linda macphee-cobb
# http://herselfswebtools.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; either version 2 of the License, or
# (at your option) any later version.
#
#
#  This program backups up websites from your rss feed.  It was written so 
#  I could back up my blogger blogs, but should work just fine with any website.
#  This does not back up comments, just the posts rss feed
#  This program also does not yet back up your images.  I'll add that in later
#
#  This program grabs the rss feed from your blogger blog
#  It then grabs the link to each page and downloads the full html of that page
#  not just the post
#  But it does not yet grab the images.  This is only the first version.
#
#  You can change $content  = get () and put in the rss feed for any website to
#  which you publish an rss feed and it should work just fine.

#########  to do    ###################################
#   download images for webpage
#   download only post not full html for blogger
#   does not yet fetch comments 
##########  end to do  ################################



#######################################################
#  includes and globals
#######################################################

#includes
use strict;
use XML::RSS;
use LWP::Simple;

# global variables
my $content;
my $file;

# other globals
my $rss = new XML::RSS;

################################################################################
# Fetch rss stream for posts
################################################################################

# url to fetch
#  !!!!!
#  You must change 999999999999  to your blog id number !
#  To find your blog id number log onto blogger and go into posts
#  At the top of your browser in the URL bar you will see blogID=
#  The number after blogID= is your blogger id number
#  
#  You can also change max-results=500 to the number of posts you have if you have more
#  than 500 posts
#  !!!!!!
$content = get ( "http://www.blogger.com/feeds/99999999999999/posts/default?max-results=500&alt=rss");

# sort it all out now

$rss->parse($content);



# while more links
foreach my $item (@{$rss->{'items'}}){
	#fetch link
	next unless defined($item->{'title'}) && defined($item->{'link'});
	
	#parse link
	my $path = $item->{'link'};
	$path =~ s/http:\/\///;
	
	my $url = $item->{'link'};
	
	#see if this file exists on our computer?
	if ( -e $path ){
		# file exists do nothing
		
	}else{
		# file does not exist
		# does directory exist?  if not create it
		my @directories = split /\//, $path;
		$#directories--;						# removes file name from end of path list
		my $checkDirectory = "";
		
		foreach my $directory ( @directories ){
			# need to check first and build path as we go or cd into directories as we go
			$checkDirectory .= $directory . "/";
			if ( -e $checkDirectory ){
			}else{
				mkdir $checkDirectory, 0755;
			}
		}
		
		# download the html file
		$content = get( $url );
		
		# create the file on the computer and write to the file
		open FILEHANDLE, ">$path";
		print FILEHANDLE $content;
		close FILEHANDLE;
		
		#download images !!! not yet done
		
		
	}
	
	
} #end while more links