#! /usr/bin/perl
# bookmarks.pl - Script to extract and print the URLs created by the Firefox
#                    Export Bookmarks to HTML feature.
#
# James M. Lynes Jr. - KE4MIQ
# Created:       June 25, 2021
# Last Modified: 06/25/2021 - Initial version
# Environment:   Ubuntu 16.04 LTS
#
# Note: The raw HTML is very messy as it seems to include long strings
#           of encoded images.
#       Working code shamelessly stolen from the perldoc HTML::Element
#           example.
 
use HTML::TreeBuilder;

open(my $outfile, ">", 'bookmarks.txt') or die "Can't open bookmarks.txt: $!";
print $outfile "Firefox Bookmark URLs\n";
print $outfile "=====================\n";

my $tree = HTML::TreeBuilder->new();
$tree->parse_file('bookmarks.html');

for (@{  $tree->extract_links('a')  }) {
          my($link, $element, $attr, $tag) = @$_;
          print "$link\n";
          print $outfile "$link\n";
      }

$tree->delete;