/
usr
/
share
/
doc
/
perl-HTML-Parser
/
eg
/
/usr/share/doc/perl-HTML-Parser/eg
mkdir
upload
Name
Size
Mode
Actions
hanchors
1138
0644
edit
dl
rm
hdump
541
0644
edit
dl
rm
hform
1846
0644
edit
dl
rm
hlc
547
0644
edit
dl
rm
hrefsub
2782
0644
edit
dl
rm
hstrip
1714
0644
edit
dl
rm
htext
548
0644
edit
dl
rm
htextsub
788
0644
edit
dl
rm
htitle
434
0644
edit
dl
rm
Edit:
/usr/share/doc/perl-HTML-Parser/eg/hform
(1846B)
#!/usr/bin/perl -w # See also HTML::Form module use HTML::PullParser (); use HTML::Entities qw(decode_entities); use Data::Dump qw(dump); my @FORM_TAGS = qw(form input textarea button select option); my $p = HTML::PullParser->new(file => shift || "xxx.html", start => 'tag, attr', end => 'tag', text => '@{text}', report_tags => \@FORM_TAGS, ) || die "$!"; # a little helper function sub get_text { my($p, $stop) = @_; my $text; while (defined(my $t = $p->get_token)) { if (ref $t) { $p->unget_token($t) unless $t->[0] eq $stop; last; } else { $text .= $t; } } return $text; } my @forms; while (defined(my $t = $p->get_token)) { next unless ref $t; # skip text if ($t->[0] eq "form") { shift @$t; push(@forms, $t); while (defined(my $t = $p->get_token)) { next unless ref $t; # skip text last if $t->[0] eq "/form"; if ($t->[0] eq "select") { my $sel = $t; push(@{$forms[-1]}, $t); while (defined(my $t = $p->get_token)) { next unless ref $t; # skip text last if $t->[0] eq "/select"; #print "select ", dump($t), "\n"; if ($t->[0] eq "option") { my $value = $t->[1]->{value}; my $text = get_text($p, "/option"); unless (defined $value) { $value = decode_entities($text); } push(@$sel, $value); } else { warn "$t->[0] inside select"; } } } elsif ($t->[0] =~ /^\/?option$/) { warn "option tag outside select"; } elsif ($t->[0] eq "textarea") { push(@{$forms[-1]}, $t); $t->[1]{value} = get_text($p, "/textarea"); } elsif ($t->[0] =~ m,^/,) { warn "stray $t->[0] tag"; } else { push(@{$forms[-1]}, $t); } } } else { warn "form tag $t->[0] outside form"; } } print dump(\@forms), "\n";
Save
cmd:
run