HTML-Parser-3.71HEADHTML-Parser-3.71master

1 files changed, 29 insertions, 0 deletions

diff --git a/eg/htext b/eg/htext
new file mode 100755
index 0000000..e4d276d
--- /dev/null
+++ b/eg/htext
@@ -0,0 +1,29 @@
+#!/usr/bin/perl -w
+
+# Extract all plain text from an HTML file
+
+use strict;
+use HTML::Parser 3.00 ();
+
+my %inside;
+
+sub tag
+{
+   my($tag, $num) = @_;
+   $inside{$tag} += $num;
+   print " ";  # not for all tags
+}
+
+sub text
+{
+    return if $inside{script} || $inside{style};
+    print $_[0];
+}
+
+HTML::Parser->new(api_version => 3,
+		  handlers    => [start => [\&tag, "tagname, '+1'"],
+				  end   => [\&tag, "tagname, '-1'"],
+				  text  => [\&text, "dtext"],
+				 ],
+		  marked_sections => 1,
+	)->parse_file(shift) || die "Can't open file: $!\n";;