use Encode; use utf8; sub parse_workaround { my $html = shift; my $hs = HTML::Strip->new(); my $octets = encode_utf8($html); utf8::downgrade($octets); my $stripped = $hs->parse($octets); $hs->eof; return decode_utf8($stripped); } #### my $clean_text = parse_workaround( $raw_html ); # my $hs = HTML::Strip->new(); # my $clean_text = $hs->parse( $raw_html ); # $hs->eof;