#!/usr/bin/perl -w
use strict;
use XML::Simple;
use Data::Dumper;

# Date
use POSIX qw(strftime);
my $date = strftime "%d/%m/%Y %H:%M", localtime;

# Functions
sub uniq {
  my %seen;
  grep !$seen{$_}++, @_;
}

print "\033[36m \nDEFACEMENT CHECK [" . $date . "]\n\nSearching for suspects ...\n";
print "FOUND \t\t=> URLs\n";

# # Import config Website (LOAD domain in conf/websites.cfg)
# my @scan;
# my @search;
# my $websites = 'conf/websites.cfg';
# if (open(my $f, '<:encoding(UTF-8)', $websites)) {
#   while (my $row = <$f>) {
#     chomp $row;
#     push @scan, $row;
#   }
# } else {
#   warn "Could not open file '$websites' $!";
# }
#
# # Slurp Websites
# my $site;
# system("rm urls/*.urls");
# foreach $site (@scan)
# {
#   system("/bin/bash slurp_urls.sh $site");
# }

# Import config Website (LOAD domain in ARG : perl defacement_check.pl example.com)
my @whitelist;
my @search;
my $site = $ARGV[0];

# Slurp Site
system("rm urls/*.urls");
system("/bin/bash slurp_urls.sh $site");

# Import config Ignore
my $ignores = 'conf/' . $site . '.ignore';
if (open(my $f, '<:encoding(UTF-8)', $ignores)) {
  while (my $row = <$f>) {
    chomp $row;
    push @whitelist, $row;
  }
} else {
  warn "Could not open file '$ignores' $!";
}

# Import config Keywords
my $keywords = 'conf/keywords.cfg';
if (open(my $f, '<:encoding(UTF-8)', $keywords)) {
  while (my $row = <$f>) {
    chomp $row;
    push @search, $row;
  }
} else {
  warn "Could not open file '$keywords' $!";
}

# Open URLS files
my @files = glob( "urls/*.urls" );
my $file;
my $somme_total_found = 0;
my $grand_total_found = 0;

foreach $file (@files)
{
  my @urls;
  my $url;
  my $somme_total_found = 0;
  open(FH, '<', $file) or die $!;
  while(<FH>){
    my $survey = $_;
    # Create a user agent object
    use LWP::UserAgent;
    my $ua = LWP::UserAgent->new;
    # Create a request
    my $req = HTTP::Request->new(GET => $survey);
    # Pass request to the user agent and get a response back
    my $res = $ua->request($req);
    my $site = $res->content;

    my @found;
    my @clean;
    my $total_found = 0;

    foreach my $s (@search) {
      foreach (grep(/$s/i, split(/\n/, $site))) {
        push @found, $_;
      }
    }

    foreach my $i (@whitelist) {
      foreach (uniq(@found)) {
        foreach (grep(/$i/i, split(/\n/))) {
          print "\033[35mIGNORE ";
          pop @found, $_;
        }
      }
    }

    # Results
    foreach (uniq(@found)) {
      $total_found++;
      print "\033[33m[" . $total_found . "]\t\t" . $_ . "\n"; # VERBOSE
    }
    if ($total_found == 0) {
      print "\033[32m[" . $total_found . "]\t\t=> " . $survey. "\n"; # SAFE
    } else {
      print "\033[31mTREATH [" . $total_found . "]\t=> " . $survey. "\n"; # TREATH
      $somme_total_found = $somme_total_found + $total_found;
    }
  }
  close(FH);
  print "\033[36mTREATH detected on this site \t\t\t\t=> [" . $somme_total_found . "]\n\n";
  $grand_total_found = $somme_total_found + $grand_total_found;
}

print "\033[36mGrand Total TREATH detected on ALL website \t\t=> [" . $grand_total_found . "]\n\n";

# Print results in Output file
open(my $out, '>', 'out.txt');
print $out $grand_total_found;
close $out;