#!/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 blogger comments from your rss feed.
#
# You must change http://www.bloggers.com/feeds/99999999/posts/default?max-results=500&alt=rss
# Replace the 9999s with your blog id number. Log onto blogger. Go to posts and you'll see
# BlogID= followed by a number in the URL bar of your browser. Just plug in that number and remove
# the 9s
#######################################################
# includes and globals
#######################################################
#includes
use strict;
use LWP::Simple;
# global variables
my $content;
my $file;
# other globals
################################################################################
# Fetch rss stream for comments from all posts
$_ = get ( "http://www.blogger.com/feeds/9999999999999999/comments/default?max-results=300&alt=rss");
#############################################################################################
# pull out all - .*?<\/item>/g;
# for each item in the array pull out the pubDate, description, link and how ever many images there many be
foreach my $item ( @items ){
# pull posting date from entry
$_ = $item;
my @post_date = m/.*?<\/pubDate>/g;
my $date = @post_date[0];
$date =~ s/<\/*pubDate>//g; #remove tags
# pull comment title from entry
my @comment_title_data = m/.*?<\/title>/g;
my $comment = @comment_title_data[0];
$comment =~ s/<\/*title.*?>//g;
# pull actual comment from entry
my @comment_data = m/<description>.*?<\/description>/g;
my $comment = @comment_data[0];
$comment =~ s/<\/*description>//g; # remove tags
$comment =~ s/</</g; # replace < with <
$comment =~ s/>/>/g; # replace > with >
# pull comment author from entry
my @author_data = m/<author>.*?<\/author>/g;
my $author = @author_data[0];
$author =~ s/<\/*author>//g;
# pull the link to this file from item and link is the same as the file name
my @link_data = m/<link>.*?<\/link>/g;
my $link = @link_data[0];
$link =~ s/<\/*link>//g; # remove tags
$link =~ s/http:\/\///; # remove http://
$link =~ s/"//g; # sometimes " are still on end of name
$link =~ s/\.html#/\//; # remove .html# and replace with \
# pull out title of comment
my @title_data = m/<title>.*?<\/title>/g;
my $title = @title_data[0];
$title =~ s/<\/*title>//g;
# create and save a file containing pubDate, description ( post ) name it with the link name
# does directory exist? if not create it
my @directories = split /\//, $link;
$#directories--; # removes file name from end of path list
my $checkDirectory = "";
# put each post in a directory by the month and year it was created
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 $checkDirectory, 0755;
}
}
# create the file on the computer and write to the file
open FILEHANDLE, ">$link";
print FILEHANDLE "\n <html><head><title> $title ";
print FILEHANDLE "\n
$date
";
print FILEHANDLE "\n $comment
";
print FILEHANDLE "\n $author
";
print FILEHANDLE "\n