use LWP::UserAgent;
use URI::Heuristic;

# Parser.pl - Simply put it takes a Dice Web Page that was done in brief mode
#             and saved as dice.html in the same directory. Since it's for my
#             own personal use there isn't really a lot of fault tolerance as
#             I'll already know if there's a problem with Dice or my network.

# Get 2-digit STATE from command-line
$state = lc($ARGV[0]);
if (length($state)!=2) { die "State '$state' MUST be 2-digits\n"; }
# Start MAIN program
&get_acode_line_data();

# Parses out the Area Code lines. It looks like 2 lines
sub get_acode_line_data {
  my (@array,@rarray);
  # The hash below is familiar to those that have used Perl since 4.019
  %codes = (714,1,949,1,909,1,760,1,213,1,323,1,310,1,
            626,1,818,1,562,1,858,1,619,1);
  open(DICE,"dice.html");
  while (<DICE>) { $lines[$count++] = $_; }
  close(DICE);
  foreach $line (0..$count) {
    $lines[$line] =~ /\S+<dt><a.*?"(\S+)"><font.*?;.*?;\s(.+?)<\/d(?:l|t)><d(?:d|t)><font.*?>\w+-(\w+)-(.*?)-(.*?)<\/font>/;
    $link=$1;  $job=$2;  $areacode=$3;  $city=$4;  $detail=$5;
    if ($codes{$3}) { 
      print "$1,$2,$3,$4,$5\n";
      $z = index($link,".com") + 4;
      $webstring = substr($link,$z,length($link)-$z);
      (@F) = split(/\//,$webstring);
      $html = $F[$#F];
      print $html,',';
      open(OUTFILE,">$html") or die "1-Can't open $html: $!\n";
      my $url = URI::Heuristic::uf_urlstr($link);
      $| = 1;
      printf "%s =>\n\t",$url;
      my $ua = new LWP::UserAgent;
      $ua->agent("Netscape/v5.0c Navigator");
      my $req = HTTP::Request->new(GET => $url);
      $req->referer("http:''dde.cia.gov");
      my $response = $ua->request($req);
      if ($response->is_error()) {
        printf " %s\n", $response->status_line;
      } else {
        my $content = $response->content();
        print OUTFILE "$content\n";
      }
      close(OUTFILE);
      makereport($html);
    }
  }
}

sub makereport {
  $outfile = @_[0];
  my $summaryfile = "summaryfile.tab";
  open(OUTFILE,">>$summaryfile");
  open(FILE,$outfile) or die "2-Can't open $outfile: $!\n";
  my (@lines,$incr);
  while (<FILE>) { $lines[$incr++] = $_; }
  close(FILE);
  foreach (0..$incr) {
    if ($lines[$_] =~ /Title:/) {
      my $res = bold($lines[$_],"Title:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Skills:/) {
      my $res = top($lines[$_],"Skills:");
      print OUTFILE $res,"\t";    
    }
    if ($lines[$_] =~ /Date Posted:/) {
      my $res = top($lines[$_],"Date Posted:");
      print OUTFILE $res,"\t";    
    }
    if ($lines[$_] =~ /Location:/) {
      my $res = top($lines[$_],"Location:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Area code:/) {
      my $res = top($lines[$_],"Area code:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Tax Term:/) {
      my $res = left($lines[$_],"Tax Term:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Pay:/) {
      my $res = top($lines[$_],"Pay:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Length:/) {
      my $res = top($lines[$_],"Length:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Email:/) {
      my $res = weblink($lines[$_]);
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Web:/) {
      my $res = weblink($lines[$_]);
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Position ID:/) {
      my $res = top($lines[$_],"Position ID:");
      print OUTFILE $res,"\t";
    }
    if ($lines[$_] =~ /Tel:/) {
      my $res = tel($lines[$_],"Tel:");
      print OUTFILE $res,"\n";
    }
  }
  close(OUTFILE);
}

sub bold {
  my ($line,$string) = @_;
  my $h1 = index($line,"$string");
  my $g1 = substr($line,$h1,length($line)-$h1);
  my $h2 = index($g1,"<b>")+3;
  my $g2 = substr($g1,$h2,length($g1)-$h2);
  my $h3 = index($g2,"<");
  my $g3 = substr($g2,0,$h3);
  return $g3;
}
sub left {
  my ($line,$string) = @_;
  my $h1 = index($line,"$string");
  my $g1 = substr($line,$h1,length($line)-$h1);
  my $h2 = index($g1,"left>")+5;
  my $g2 = substr($g1,$h2,length($g1)-$h2);
  my $h3 = index($g2,"<");
  my $g3 = substr($g2,0,$h3);
  return $g3;
}
sub weblink {
  my ($line) = @_;
  my $h1 = index($line,"?")+1;
  my $g1 = substr($line,$h1,length($line)-$h1);
  my $h2 = index($g1,"&");
  my $g2 = substr($g1,0,$h2);
  return $g2;
}
sub tel {
  my ($line) = @_;
  my $h1 = index($line,"Tel:")+5;
  my $g1 = substr($line,$h1,length($line)-$h1);
  chop $g1;
  return $g1;
}
sub top {
  my ($line,$string) = @_;
  my $h1 = index($line,"$string");
  my $g1 = substr($line,$h1,length($line)-$h1);
  my $h2 = index($g1,"top>")+4;
  my $g2 = substr($g1,$h2,length($g1)-$h2);
  my $h3 = index($g2,"<");
  my $g3 = substr($g2,0,$h3);
  return $g3;
}