use strict;
use warnings;
use HTML::TreeBuilder;
my $html;
$html .= $_ while ;
my $Tree = HTML::TreeBuilder->new ();
$Tree->parse ($html);
$Tree->eof ();
my %Words;
++$Words{$_} foreach (split (" ", $Tree->as_text ()));
my @WordPos;
my $Key;
foreach $Key (keys %Words)
{
pos ($html) = 0;
while ($html =~ />[^<]*?(\b$Key\b).*?[<\$]/gis)
{
push @WordPos, [$Key, $-[1]];
}
}
print join "\n", map {ref $_ ? join ' starts at ', @$_ : $_} @WordPos;
__DATA__
This is my text. I hope you like it!
img src, please don't munt me.
|
Would you like to see my Monkey?
|
oh and this too!