[Perl] Emails Extractor 0.2

[BigBear]

Un simple script en Perl para buscar direcciones de correo en :

• Un archivo de texto cualquiera
  
• Una pagina
  
• Usando un dork en google para scanear todas las paginas encontradas con el dork
  
• Lo mismo que el anterior pero en bing
  
  El codigo.
  
  
  Código (perl) [Seleccionar] Expandir
  
#!usr/bin/perl
#Email Extractor 0.2
#(C) Doddy Hackman 2013
#Credits : Regex based on
#http://stackoverflow.com/questions/15710275/print-email-addresses-to-a-file-in-perl
#Thanks to motherconfessor & amon

use LWP::UserAgent;
use URI::Escape;

my $nave = LWP::UserAgent->new;
$nave->agent(
"Mozilla/5.0 (Windows; U; Windows NT 5.1; nl; rv:1.8.1.12) Gecko/20080201Firefox/2.0.0.12"
);
$nave->timeout(10);

my $buscador = qr/[A-Z0-9._%+-]+\@[A-Z0-9.-]+\.[A-Z]{2,4}/i
  ;    # Thanks to motherconfessor & amon
my @emails;

head();

if ( $ARGV[0] eq "-file" ) {

    print "\n[+] Opening file ...\n";

    if ( -f $ARGV[1] ) {

        my $code = openfile( $ARGV[1] );

        while ( $code =~ /($buscador)/g ) {
            my $email = $1;
            push( @emails, $email );
        }

        my @emails = repes(@emails);

        print "\n[+] Mails Found : " . int(@emails) . "\n";

        for (@emails) {
            savefile( $ARGV[2], $_ );
        }

    }
    else {
        print "\n[-] File not found\n";
    }

}
elsif ( $ARGV[0] eq "-google" ) {

    print "\n[+] Searching in Google ...\n";

    my @links = google( $ARGV[1], $ARGV[2] );

    print "[+] Scanning [" . int(@links) . "] pages ...\n";

    for my $ink (@links) {
        my $code = toma($ink);

        while ( $code =~ /($buscador)/g ) {
            my $email = $1;
            push( @emails, $email );
        }

    }

    my @emails = repes(@emails);

    print "\n[+] Mails Found : " . int(@emails) . "\n";

    for (@emails) {
        savefile( $ARGV[2], $_ );
    }

}
elsif ( $ARGV[0] eq "-bing" ) {

    print "\n[+] Searching in Bing ...\n";

    my @links = bing( $ARGV[1], $ARGV[2] );

    print "[+] Scanning [" . int(@links) . "] pages ...\n";

    for my $ink (@links) {
        my $code = toma($ink);

        while ( $code =~ /($buscador)/g ) {
            my $email = $1;
            push( @emails, $email );
        }

    }

    my @emails = repes(@emails);

    print "\n[+] Mails Found : " . int(@emails) . "\n";

    for (@emails) {
        savefile( $ARGV[3], $_ );
    }

}
elsif ( $ARGV[0] eq "-page" ) {

    my $code = toma( $ARGV[1] );

    print "\n[+] Loading page ...\n";

    while ( $code =~ /($buscador)/g ) {
        my $email = $1;
        push( @emails, $email );
    }

    my @emails = repes(@emails);

    print "\n[+] Mails Found : " . int(@emails) . "\n";

    for (@emails) {
        savefile( $ARGV[2], $_ );
    }

}
else {
    sintax();
}

copyright();

# Functions

sub bing {

    my ( $a, $b ) = @_;
    for ( $pages = 10 ; $pages <= $b ; $pages = $pages + 10 ) {
        my $code =
          toma( "http://www.bing.com/search?q=" . $a . "&first=" . $pages );

        while ( $code =~ /<h3><a href="(.*?)"/mig ) {
            push( @founds, $1 );
        }
    }
    my @founds = repes( cortar(@founds) );
    return @founds;
}

sub google {
    my ( $a, $b ) = @_;
    my @founds;
    for ( $pages = 10 ; $pages <= $b ; $pages = $pages + 10 ) {
        $code = toma(
            "http://www.google.com.ar/search?hl=&q=" . $a . "&start=$pages" );
        while ( $code =~ /(?<="r"><. href=")(.+?)"/mig ) {
            my $url = $1;
            if ( $url =~ /\/url\?q\=(.*?)\&amp\;/ ) {
                push( @founds, uri_unescape($1) );
            }
        }
    }
    my @founds = repes( cortar(@founds) );
    return @founds;
}

sub cortar {
    my @nuevo;
    for (@_) {
        if ( $_ =~ /=/ ) {
            @tengo = split( "=", $_ );
            push( @nuevo, @tengo[0] . "=" );
        }
        else {
            push( @nuevo, $_ );
        }
    }
    return @nuevo;
}

sub toma {
    return $nave->get( $_[0] )->content;
}

sub savefile {

    if ( $_[0] eq "" ) {
        open( SAVE, ">>logs.txt" );
    }
    else {
        open( SAVE, ">>" . $_[0] );
    }

    print SAVE $_[1] . "\n";
    close SAVE;
}

sub openfile {
    open my $FILE, q[<], $_[0];
    my $word = join q[], <$FILE>;
    close $FILE;
    return $word;
}

sub repes {
    my @limpio;
    foreach $test (@_) {
        push @limpio, $test unless $repe{$test}++;
    }
    return @limpio;
}

sub sintax {
    print "\n[+] Sintax : $0 <options> <logs>\n";
    print "\n[+] Examples : \n\n";
    print "[+] $0 -file test.txt logs.txt\n";
    print "[+] $0 -google 50 mailist logs.txt\n";
    print "[+] $0 -bing 50 mailist logs.txt\n";
    print "[+] $0 -page http://localhost/index.php logs.txt\n";
}

sub head {
    print "\n-- == Email Extractor 0.2 == --\n";
}

sub copyright {
    print "\n-- == (C) Doddy Hackman 2013 == --\n\n";
    exit(1);
}

#The End ?

  
  Mostraria un ejemplo de uso pero puedo tener problemas cuando el script devuelve como 500 mails ajenos claramente para spam xD.