my $p = HTML::Parser->new(api_version => 3, start_h => [\&div_start_handler, "self,tagname,attr"]); $p->parse_file($file); do_stuff(); sub div_start_handler { my($self, $tag, $attr) = @_; my($blogdate); return unless ($tag eq "div"); return unless exists $attr->{class}; return unless $attr->{class} eq 'post'; #global, so the endhandler knows what the last ID was $blogid = $attr->{id}; $BlogArticles{$blogid}{DateText} = $attr->{unusedattribute}; $self->handler(text => [], "dtext" ); $self->handler(end => \&div_end_handler, "self,tagname"); } sub div_end_handler { my($self, $tag) = @_; return unless $tag eq "div"; my $text = join("", map $_->[0], @{$self->handler("text")}); $BlogArticles{$blogid}{BodyText} = $text; $self->handler("text", undef); $self->handler("start", \&div_start_handler); $self->handler("end", undef); }