#! /usr/bin/perl

use strict;
use warnings;

use Data::Dumper;
use HTML::TreeBuilder;
use LWP::Simple;
use URI;

my $url = q{http://csr.wwiionline.com/scripts/services/persona/sorties.jsp};
my $pid = 173384;

my @sids = get_sids($url, $pid);
die qq{no sids found\n} unless @sids;

print Dumper \@sids;

sub get_sids{
  
  my ($url, $pid) = @_;
  my $page = 1;
  my $uri = URI->new($url);
  my ($i, @sids);

  while ($page){
    
    # build the uri
    $uri->query_form(page => $page, pid => $pid);
    my $uri_string = $uri->as_string;

    # get the content, check for success
    my $content = get $uri->as_string;
    die qq{LWP get failed: $!\n} unless $content;
    
    # build the tree
    my $t = HTML::TreeBuilder->new_from_content($content)
      or die qq{new from content failed: $!\n};
    
    # get a list of all anchor tags
    my @anchors = $t->look_down(_tag => q{a})
      or die qq{no tables found in : $!\n};
    
    # look at each anchor
    for my $anchor (@anchors){
      # get the href
      my $href = $anchor->attr(q{href});
      
      if ($href){
        # test for a sid in the query fragment
        my $uri = URI->new($href);
        my %q = $uri->query_form;
        # save it if it is there
        push @sids, $q{sid} if exists $q{sid};
      }
    }
    
    # see if there is another page
    $page = get_next_page($t);
    
    # avoid accidental indefinite loops
    # hammering the server, adjust to suit
    die if $i++ > 5;
    
  }
  
  # send 'em back
  return @sids;
  
}

sub get_next_page{
  
  my ($t) = @_;
  
  # we want table 9
  my @tables = $t->look_down(_tag => q{table});
  my $table = $tables[8];
  
  # first row
  my @trs = $table->look_down(_tag => q{tr});
  my $tr = $trs[0];
  
  # second column
  my @tds = $tr->look_down(_tag => q{td});
  my $td = $tds[1];

  # get any text  
  my $page_number_txt = $td->as_text;
  
  # and test if it is a page number
  # will be undef otherwise
  my ($page) = $page_number_txt =~ /PAGE (\d) >/;
  
  return $page;
  
}