Funny, here's the script since I modified it perhaps I jacked somehting up
Also I had it checking meta tags ::
my $name = $token->[1]{name} || "-";
my $http = $token->[1]{http-equiv} || "-";
my $cont = $token->[1]{content} || "-";
That would grab content for all of them,
The name if it was a name and if it was an http-equiv it would make come out as -
Not sure what I'm doing wrong but any way here's my script ::
Thanks
#!/usr/bin/perl
use LWP::Simple;
use HTML::TokeParser;
$url = $ARGV[0];
$content = get($url);
$p = HTML::TokeParser->new(\$content);
my %text_links_con;
my %img_con;
my %meta_con;
while(1) {
my $token = $p->get_tag("a","img","title","meta","rel");
last unless($token);
if($token->[0] eq 'img') {
$x++; # I'm doing this so I can get a count of how many it's finding
my $src = $token->[1]{src} || "-";
my $alt = $token->[1]{alt} || "-";
$img_con{$x} = "SRC : $src, ALT :$alt";;
}
elsif($token->[0] eq 'a') {
$i++;
my $url = $token->[1]{href} || "-";
my $text = $p->get_trimmed_text("/a");
$text_links_con{$i} = "Text : $text, URL : $url";
}
elsif($token->[0] eq 'title') {
$title_con = $p->get_trimmed_text;
}
}
print "TITLE : $title_con \n";
foreach $q(keys %text_links_con) { print "LINK : $q - $text_links_con{$q} \n"; }
foreach $x(keys %img_con) { print "IMG : $x - $img_con{$x} \n"; }
>
> what do you mean? the following seems to be working:
>
> #!/usr/bin/perl -w
> use strict;
>
> use HTML::TokeParser;
>
> my $tok = new HTML::TokeParser(*DATA) || die $!;
> while(1){
> my $token = $tok->get_tag("a","img");
> last unless($token);
> if($token->[0] eq 'a'){
> print $token->[1]{href} || "what?","\n";
> }else{
> print $token->[1]{src} || "again?","\n";
> }
> }
>
> __DATA__
> <html>
> <body>
> <a href=link1>link1</a>
> <img src=img1>img1</img>
> <a href=link2><img src=img_inside_a></img></a>
> </body>
> </html>
>
> prints:
>
> link1
> img1
> link2
> img_inside_a
>
> so img_inside_a does show up. am i missing something?
>
> david
>
> --
> To unsubscribe, e-mail: [EMAIL PROTECTED]
> For additional commands, e-mail: [EMAIL PROTECTED]
>
>
--
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
