Server : Apache System : Linux server1.cgrithy.com 3.10.0-1160.95.1.el7.x86_64 #1 SMP Mon Jul 24 13:59:37 UTC 2023 x86_64 User : nobody ( 99) PHP Version : 8.1.23 Disable Function : NONE Directory : /usr/share/doc/perl-HTML-Parser-3.71/eg/ |
#!/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; 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 $text = join("", @{$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); }