Do not use regular expressions to parse HTML/XML. Assuming your input is indeed HTML, here's a possible solution using Mojo::DOM, based on my code here.
use warnings; use strict; print html_filter(<<'END_HTML', qw/pre strong i/), "\n"; aaa<pre>bbb</pre>ccc<www><i>ddd</i><strong>eee</strong>fff</www>ggg END_HTML use Mojo::DOM; sub html_filter { my $html = shift; my %allowed = map {$_=>1} @_; my $walk; $walk = sub { my ($in, $out) = @_; for my $n ( @{ $in->child_nodes } ) { if ( $n->type eq 'cdata' || $n->type eq 'text' ) { $out->append_content($n->content) } elsif ( $n->type eq 'tag' ) { if ($allowed{$n->tag}) { my $t = $out->new_tag( $n->tag, %{$n->attr} ) ->child_nodes->first; $walk->($n, $t); $out->append_content($t); } else { $walk->($n, $out) } } # ignore other node types for now } return $out; }; return $walk->(Mojo::DOM->new($html), Mojo::DOM->new)->to_string; } __END__ aaa<pre>bbb</pre>ccc<i>ddd</i><strong>eee</strong>fffggg
In reply to Re: perlre inverse check for several patterns
by haukex
in thread perlre inverse check for several patterns
by averlon
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |