Please note that this doesn't handle the unescaped closing script tag in document.write. I'd suggest running tidy on the input before passing it to the parser.
#!/usr/bin/perl -w use strict; use HTML::Tree; my $doc = <<EOF; <html> <head> <script language="Javascript"> document.write("Don't forget your </script> tag! It's important! +"); </script> </head> <body> This is just some text. </body> </html> EOF my $root=HTML::TreeBuilder->new(); $root->parse($doc); $root->eof; foreach my $n ($root->descendants) { next unless $n->tag; # skip text nodes $n->delete if $n->tag eq 'script'; } print $root->dump; # prints structure print $root->as_HTML # prints as HTML
-- #!/usr/bin/perl for(ref bless{},just'another'perl'hacker){s-:+-$"-g&&print$_.$/}
In reply to Re: Removing Javascript
by domm
in thread Removing Javascript
by Mur
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |