Hi,
I need to parse an HTML file [0] and pull out all the form elements and
put them into a data structure. What I can't seem to do is when I have
found a <select> tag is then parse the associated <option> tags!
So far I have the following...
<perl>
use strict;
use Data::Dumper;
while (<IN>) {
$p->parse($_);
}
$p->eof;
print Dumper($p->htmltree);
package FormParser;
use base "HTML::Parser";
my $HTMLTREE = {};
sub start {
my ($self, $tag, $attr, $attrseq, $origtext) = @_;
if ($tag =~ /^form|input|texarea$/) {
my $name = $attr->{name};
foreach my $i (@$attrseq) {
next if ($i =~ /name/);
$HTMLTREE->{$name}->{$i} = $attr->{$i};
}
} elsif ($tag =~ /^select$/) {
my $name = $attr->{name};
warn "FOUND: $tag : $name\n";
foreach my $i (@$attrseq) {
next if ($i =~ /name/);
$HTMLTREE->{$name}->{$i} = $attr->{$i};
}
# Now need to assign the options to each select....
}
}
sub text {
my ($self, $text) = @_;
#print $text;
}
sub end {
my ($self, $tag, $origtext) = @_;
#print $origtext;
}
sub htmltree {
return $HTMLTREE;
}
</perl>
Andy
[0] - here's the HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html
lang="en">
<head>
<title>Form Test</title>
</head>
<body>
<form action="/cgi-bin/test.pl" method="post">
<input type="text" name="forename"><br>
<input type="text" name="surname"><br>
<input type="hidden" name="cid" value="1234"><br>
<input type="radio" name="rad_1" value="Y">Yes<input
type="radio" name="rad_1" value="N">No<br>
<input type="radio" name="rad_2" value="1">One<input
type="radio" name="rad_2" value="2">Two<br>
<input type="checkbox" name="check_1" value="1">Check 1
<input type="checkbox" name="check_2" value="2">Check 2
<input type="checkbox" name="check_3" value="3">Check 3<br>
Password:<input type="password" name="password"><br>
<textarea name="text_area"></textarea>
<select name="single_select">
<option name="1" value="1">1</option>
<option name="2" value="2">2</option>
</select>
<select name="multiple_select" multiple>
<option name="1" value="1">1</option>
<option name="2" value="2">2</option>
<option name="3" value="3">3</option>
<option name="4" value="4">4</option>
</select>
<br>
<input type="button" name="button">
<input type="submit" name="submit_btn">
<input type="reset" name="reset">
</form>
</body>
</html>
