32 lines
955 B
Plaintext
32 lines
955 B
Plaintext
|
#!/usr/bin/perl -w
|
||
|
|
|
||
|
|
# Shows how to mangle all plain text in an HTML document, using an arbitrary
|
||
|
|
# Perl expression. Plain text is all text not within a tag declaration, i.e.
|
||
|
|
# not in <p ...>, but possibly between <p> and </p>
|
||
|
|
# Example (Reverse 'Debian' in all text) :
|
||
|
|
# lynx -dump -source -raw http://www/debian.org > /tmp/a.txt
|
||
|
|
# ./htextsub '$_ =~ s/Debian/Naibed/gi' /tmp/a.txt
|
||
|
|
|
||
|
|
use strict;
|
||
|
|
my $code = shift || usage();
|
||
|
|
$code = 'sub edit_print { local $_ = shift; ' . $code . '; print }';
|
||
|
|
#print $code;
|
||
|
|
eval $code;
|
||
|
|
die $@ if $@;
|
||
|
|
|
||
|
|
use HTML::Parser 3.05;
|
||
|
|
my $p = HTML::Parser->new(unbroken_text => 1,
|
||
|
|
default_h => [ sub { print @_; }, "text" ],
|
||
|
|
text_h => [ \&edit_print, "text" ],
|
||
|
|
);
|
||
|
|
|
||
|
|
my $file = shift || usage();
|
||
|
|
$p->parse_file($file) || die "Can't open file $file: $!\n";
|
||
|
|
|
||
|
|
sub usage
|
||
|
|
{
|
||
|
|
my $progname = $0;
|
||
|
|
$progname =~ s,^.*/,,;
|
||
|
|
die "Usage: $progname <perlexpr> <filename>\n";
|
||
|
|
}
|