in reply to Removing font tags using HTML::TreeBuilder

Don't do that ;) 
#!/usr/bin/perl --

use warnings;
use strict;
use HTML::TreeBuilder;

my $html = <<'__HTML__';
<p>and a <font face="Verdana">one <a href="link.html">two</a> three</f
+ont> four</p>
<p>another |<font name="one">one</font>| and another |<font name="two"
+> one </font>|</p>
__HTML__


{
    my $h = HTML::TreeBuilder->new_from_content($html);

    print $h->as_HTML('<>&',' ',{}), "\n";

    $h->look_down(_tag => q{font},
        sub{
            $_[0]->replace_with_content(
                $_[0]->content_refs_list
            );
            return;
        },
    );

    print $h->as_HTML('<>&',' ',{}), "\n";


}
__END__
<html>
 <head>
 </head>
 <body>
  <p>and a <font face="Verdana">one <a href="link.html">two</a> three<
+/font> four</p>
  <p>another |<font name="one">one</font>| and another |<font name="tw
+o"> one </font>|</p>
 </body>
</html>

<html>
 <head>
 </head>
 <body>
  <p>and a one <a href="link.html">two</a> three four</p>
  <p>another |one| and another | one |</p>
 </body>
</html>

[download]

Replies are listed 'Best First'.
Re^2: Removing font tags using HTML::TreeBuilder
by Anonymous Monk on Oct 27, 2008 at 10:06 UTC
    Bah, that won't handle nested font tags properly, this is better 
    #!/usr/bin/perl --

use warnings;
use strict;
use HTML::TreeBuilder;

my $html = <<'__HTML__';
<p>and a <font face="Verdana">one <a href="link.html">two</a> three</f
+ont> four</p>
<p>another |<font name="one">one</font>| and another |<font name="two"
+> one </font>|</p>
<p>6 nested font tags
<font>1<font>2<font>3<font>4<font>5<font>6</font>5</font>4</font>3</fo
+nt>2</font>1</font>
</p>
__HTML__

{
    my $h = HTML::TreeBuilder->new_from_content($html);

    print $h->as_HTML('<>&',' ',{}), "\n";

    for my $font( $h->look_down(_tag => q{font}) ){
        $font->replace_with_content(
            $font->content_refs_list
        );
    }

    print $h->as_HTML('<>&',' ',{}), "\n";

}

__END__
<html>
 <head>
 </head>
 <body>
  <p>and a <font face="Verdana">one <a href="link.html">two</a> three<
+/font> four</p>
  <p>another |<font name="one">one</font>| and another |<font name="tw
+o"> one </font>|</p>
  <p>6 nested font tags <font>1<font>2<font>3<font>4<font>5<font>6</fo
+nt>5</font>4</font>3</font>2</font>1</font></p>
 </body>
</html>

<html>
 <head>
 </head>
 <body>
  <p>and a one <a href="link.html">two</a> three four</p>
  <p>another |one| and another | one |</p>
  <p>6 nested font tags 12345654321</p>
 </body>
</html>

    [download]
[reply]
[d/l]

In Section Seekers of Perl Wisdom