| Server IP : 49.231.201.246 / Your IP : 216.73.216.149 Web Server : Apache/2.4.18 (Ubuntu) System : Linux 246 4.4.0-210-generic #242-Ubuntu SMP Fri Apr 16 09:57:56 UTC 2021 x86_64 User : root ( 0) PHP Version : 7.0.33-0ubuntu0.16.04.16 Disable Function : exec,passthru,shell_exec,system,proc_open,popen,pcntl_exec MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : ON | Pkexec : ON Directory : /usr/share/doc/libhtml-parser-perl/examples/ |
Upload File : |
#!/usr/bin/perl -w
# This program will print out all <a href=".."> links in a
# document together with the text that goes with it.
#
# See also HTML::LinkExtor
use HTML::Parser;
use Encode;
my $p = HTML::Parser->new(api_version => 3,
start_h => [\&a_start_handler, "self,tagname,attr"],
report_tags => [qw(a img)],
);
$p->parse_file(shift || die) || die $!;
sub a_start_handler
{
my($self, $tag, $attr) = @_;
return unless $tag eq "a";
return unless exists $attr->{href};
print "A $attr->{href}\n";
$self->handler(text => [], '@{dtext}' );
$self->handler(start => \&img_handler);
$self->handler(end => \&a_end_handler, "self,tagname");
}
sub img_handler
{
my($self, $tag, $attr) = @_;
return unless $tag eq "img";
push(@{$self->handler("text")}, $attr->{alt} || "[IMG]");
}
sub a_end_handler
{
my($self, $tag) = @_;
my $text = encode('utf8',join("", @{$self->handler("text")}));
$text =~ s/^\s+//;
$text =~ s/\s+$//;
$text =~ s/\s+/ /g;
print "T $text\n";
$self->handler("text", undef);
$self->handler("start", \&a_start_handler);
$self->handler("end", undef);
}