| Server IP : 74.208.127.88 / Your IP : 216.73.216.156 Web Server : Apache/2.4.41 (Ubuntu) System : Linux ubuntu 5.4.0-163-generic #180-Ubuntu SMP Tue Sep 5 13:21:23 UTC 2023 x86_64 User : www-data ( 33) PHP Version : 7.4.3-4ubuntu2.29 Disable Function : pcntl_alarm,pcntl_fork,pcntl_waitpid,pcntl_wait,pcntl_wifexited,pcntl_wifstopped,pcntl_wifsignaled,pcntl_wifcontinued,pcntl_wexitstatus,pcntl_wtermsig,pcntl_wstopsig,pcntl_signal,pcntl_signal_get_handler,pcntl_signal_dispatch,pcntl_get_last_error,pcntl_strerror,pcntl_sigprocmask,pcntl_sigwaitinfo,pcntl_sigtimedwait,pcntl_exec,pcntl_getpriority,pcntl_setpriority,pcntl_async_signals,pcntl_unshare, MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | 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);
}