HTML-Parser-3.71HEADHTML-Parser-3.71master

1 files changed, 28 insertions, 0 deletions

diff --git a/eg/htextsub b/eg/htextsub
new file mode 100755
index 0000000..5091273
--- /dev/null
+++ b/eg/htextsub
@@ -0,0 +1,28 @@
+#!/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>
+
+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";
+}