torrentindexer - SOURCE CODE

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

# - Based on vesion 0.1.0.3-BETA of TorrentSpy from http://torrentspy.sf.net/
#   Original copyright unknown, SourceForge claims "MIT License"

package TorrentIndexer::BITTORRENT::BDecode;

use Carp;
use strict;


sub bdecode() {
	
	my ($dataref) = shift;
	my $p = 0;

	if ( ref($dataref) ne 'SCALAR') {
		return benc_parse_hash(\$dataref,\$p);
	} elsif ( ref($dataref) eq 'SCALAR') {
		return benc_parse_hash($dataref,\$p);
	};

}; # sub bdecode


sub benc_parse_hash() {
	
	my $data	= shift;
	my $p		= shift;
	
	my $c = substr(${$data},${$p},1);
	my $r = undef;
	
	if($c eq 'd') { # hash
		
		#    print "Found a hash\n";
		%{$r} = ();
		++${$p};
		while((${$p} < length(${$data})) && (substr(${$data}, ${$p}, 1) ne 'e')) {	
			my $k = benc_parse_string($data, $p);
			my $start = ${$p};
			$r->{'_' . $k . '_start'} = ${$p} if($k eq 'info');
			my $v = benc_parse_hash($data, $p);
			$r->{'_' . $k . '_length'} = ($$p - $start)  if($k eq 'info');

... [truncated, 75 more lines] ...

# - Based on vesion 0.1.0.3-BETA of TorrentSpy from http://torrentspy.sf.net/
#   Original copyright unknown, SourceForge claims "MIT License"

package TorrentIndexer::BITTORRENT::BDecode;
use Carp;
use base 'Exporter';
use strict;
our @EXPORT_OK = qw(bdecode);

sub bdecode {
  my ($dataref) = @_;
  unless(ref($dataref) eq 'SCALAR') {
    die('Function bdecode takes a scalar ref!');
  } # unless
  my $p = 0;
  return benc_parse_hash($dataref,\$p);
} # sub bdecode

sub benc_parse_hash {
  my ($data, $p) = @_;
  my $c = substr($$data,$$p,1);
  my $r = undef;
  if($c eq 'd') { # hash
#    print "Found a hash\n";
    %{$r} = ();
    ++$$p;
    while(($$p < length($$data)) && (substr($$data, $$p, 1) ne 'e')) {
      my $k = benc_parse_string($data, $p);
      my $start = $$p;
      $r->{'_' . $k . '_start'} = $$p if($k eq 'info');
      my $v = benc_parse_hash($data, $p);
      $r->{'_' . $k . '_length'} = ($$p - $start)  if($k eq 'info');
#      print "\t{$k} => $v\n";
      $r->{$k} = $v;
    } # while
    ++$$p;
#    print "End of Hash\n";
  } elsif($c eq 'l') { # list
    @{$r} = \();
    ++$$p;
#    print "Found a list\n";
    while(substr($$data, $$p, 1) ne 'e') {
      push(@{$r},benc_parse_hash($data, $p));
#      print "\t[@{$r}] = $$r[-1]\n";
    } # while
    ++$$p;
  } elsif($c eq 'i') { # number
    $r = 0;
    my $c;
    ++$$p;

... [truncated, 38 more lines] ...

# - Based on vesion 0.1.0.3-BETA of TorrentSpy from http://torrentspy.sf.net/
#   Original copyright unknown, SourceForge claims "MIT License"

package BitTorrent::BDecode;
use Carp;
use base 'Exporter';
use strict;
our @EXPORT_OK = qw(bdecode);

sub bdecode {
  my ($dataref) = @_;
  unless(ref($dataref) eq 'SCALAR') {
    die('Function bdecode takes a scalar ref!');
  } # unless
  my $p = 0;
  return benc_parse_hash($dataref,\$p);
} # sub bdecode

sub benc_parse_hash {
  my ($data, $p) = @_;
  my $c = substr($$data,$$p,1);
  my $r = undef;
  if($c eq 'd') { # hash
#    print "Found a hash\n";
    %{$r} = ();
    ++$$p;
    while(($$p < length($$data)) && (substr($$data, $$p, 1) ne 'e')) {
      my $k = benc_parse_string($data, $p);
      my $start = $$p;
      $r->{'_' . $k . '_start'} = $$p if($k eq 'info');
      my $v = benc_parse_hash($data, $p);
      $r->{'_' . $k . '_length'} = ($$p - $start)  if($k eq 'info');
#      print "\t{$k} => $v\n";
      $r->{$k} = $v;
    } # while
    ++$$p;
#    print "End of Hash\n";
  } elsif($c eq 'l') { # list
    @{$r} = \();
    ++$$p;
#    print "Found a list\n";
    while(substr($$data, $$p, 1) ne 'e') {
      push(@{$r},benc_parse_hash($data, $p));
#      print "\t[@{$r}] = $$r[-1]\n";
    } # while
    ++$$p;
  } elsif($c eq 'i') { # number
    $r = 0;
    my $c;
    ++$$p;

... [truncated, 38 more lines] ...

#!/usr/bin/perl -w

package Convert::Bencode;
# package BitTorrent::BDecode;

=head1 NAME

Convert::Bencode - Functions for converting to/from bencoded strings

=head1 SYNOPSIS

  use Convert::Bencode qw(bencode bdecode);

  my $string = "d4:ainti12345e3:key5:value4:type4:teste";
  my $hashref = bdecode($string);

  foreach my $key (keys(%{$hashref})) {
      print "Key: $key, Value: ${$hashref}{$key}\n";
  }

  my $encoded_string = bencode($hashref);
  print $encoded_string."\n";

=head1 DESCRIPTION

This module provides two functions, C<bencode> and C<bdecode>, which
encode and decode bencoded strings respectivly.

=head2 Encoding

C<bencode()> expects to be passed a single value, which is either a scalar, 
a arrary ref, or a hash ref, and it returns a scalar containing the bencoded 
representation of the data structure it was passed. If the value passed was 
a scalar, it returns either a bencoded string, or a bencoded integer (floating 
points are not implemented, and would be returned as a string rather than a 
integer). If the value was a array ref, it returns a bencoded list, with all 
the values of that array also bencoded recursivly. If the value was a hash ref,
it returns a bencoded dictionary (which for all intents and purposes can be 
thought of as a synonym for hash) containing the recursivly bencoded key and 
value pairs of the hash.

=head2 Decoding

C<bdecode()> expects to be passed a single scalar containing the bencoded string
to be decoded. Its return value will be either a hash ref, a array ref, or a
scalar, depending on whether the outer most element of the bencoded string
was a dictionary, list, or a string/integer respectivly.

=head1 SEE ALSO


... [truncated, 125 more lines] ...

#!/usr/bin/perl -w

package Convert::Bencode;
# package BitTorrent::BDecode;

=head1 NAME

Convert::Bencode - Functions for converting to/from bencoded strings

=head1 SYNOPSIS

  use Convert::Bencode qw(bencode bdecode);

  my $string = "d4:ainti12345e3:key5:value4:type4:teste";
  my $hashref = bdecode($string);

  foreach my $key (keys(%{$hashref})) {
      print "Key: $key, Value: ${$hashref}{$key}\n";
  }

  my $encoded_string = bencode($hashref);
  print $encoded_string."\n";

=head1 DESCRIPTION

This module provides two functions, C<bencode> and C<bdecode>, which
encode and decode bencoded strings respectivly.

=head2 Encoding

C<bencode()> expects to be passed a single value, which is either a scalar, 
a arrary ref, or a hash ref, and it returns a scalar containing the bencoded 
representation of the data structure it was passed. If the value passed was 
a scalar, it returns either a bencoded string, or a bencoded integer (floating 
points are not implemented, and would be returned as a string rather than a 
integer). If the value was a array ref, it returns a bencoded list, with all 
the values of that array also bencoded recursivly. If the value was a hash ref,
it returns a bencoded dictionary (which for all intents and purposes can be 
thought of as a synonym for hash) containing the recursivly bencoded key and 
value pairs of the hash.

=head2 Decoding

C<bdecode()> expects to be passed a single scalar containing the bencoded string
to be decoded. Its return value will be either a hash ref, a array ref, or a
scalar, depending on whether the outer most element of the bencoded string
was a dictionary, list, or a string/integer respectivly.

=head1 SEE ALSO


... [truncated, 125 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

# perl -MCPAN -e 'force install "String::Approx"'
####

use Blog::PARSER::eMod;
use Blog::PARSER::Gulli;
use Blog::PARSER::BlogJunkie;
use Blog::PARSER::Allmend;
use Blog::PARSER::Golem;
use Blog::PARSER::Netzwelt;
use Blog::PARSER::NullNull;
use Blog::PARSER::FilesharingNews;
use Blog::PARSER::MP3Katalog;
# use Blog::PARSER::Heise;

use Blog::PARSER;
use Blog::SQLIO;
use Blog::HTTP;
use Blog::SQL;
use Data::Dumper;

my $DBH	= Blog::SQL->SQL();



######
###  http://www.emule-mods.cc/
######

my $pagecontent	= Blog::HTTP->GET('http://www.emule-mods.cc/');
my $links		= Blog::PARSER->getLinks($pagecontent,'http://www.emule-mods.cc/','(\d{2})\/(\d{4})','top');

# print Dumper($links); exit;

foreach my $link ( @{$links} ) {
	
	my $status = Blog::SQLIO->DoesLinkExists($DBH, $link);
	if ( $status == 0 ) {
		print "Bearbeite: $link\n";
		my $page = Blog::HTTP->GET($link);
		Blog::PARSER::eMod->GrabContent($DBH, $page, $link, 'K');

... [truncated, 266 more lines] ...

#!/usr/bin/perl

require "functions.pl";

use DBI();
$drh = DBI->install_driver("mysql");

my $timeout		= "300";
my $ua			= "Mozilla/5.0 (Windows; U; Windows NT 5.0; de-DE; rv:1.6) Gecko/20040206 Firefox/1.0.1";

my $DBHOST		= "localhost";
my $DBNAME		= "zoozle";
my $DBUSER		= "zoozle";	
my $DBPASS		= "zoozle23!99";	

my $dbh = DBI->connect("DBI:mysql:database=$DBNAME;host=$DBHOST", "$DBUSER", "$DBPASS", {'RaiseError' => 0});

unlink "emule_news.txt";
open(WH,">emule_news.txt");


&getNewsTV();
sub getNewsTV(){
	
	my $page = &http_get("http://tvunderground.org.ru/index.php", $timeout, $ua, '');
	my @CONTENT = split('"', $page);
	my @CONTENT2 = split('\'', $page);
	
	if ( $#CONTENT < $#CONTENT2 ) {
		@CONTENT = @CONTENT2;
	};
	
	foreach $line (@CONTENT) {	
		$linecount++;
		if ($line =~ /english/i || $line =~ /german/i || $line =~ /french/i || $line =~ /italian/i || $line =~ /polish/i) {
			
			if ($line =~ /english/i ) { $lang = "en"; };
			if ($line =~ /german/i ) { $lang = "en"; }
			if ($line =~ /french/i ) { $lang = "fr"; }
			if ($line =~ /italian/i ) { $lang = "it"; }
			if ($line =~ /polish/i ) { $lang = "pl"; }

			my ( $desc_t ) = split(/<\/a>/i, @CONTENT[$linecount+2] );
			my ( undef, $desc ) = split('>', $desc_t );
			$desc =~ s/<a href=//i;
			chomp($desc);
			next if ( $desc !~ /\w/ ); #	&& (length(@CONTENT[$linecount+1]) < 3) ); 
			next if ( $desc =~ /&nbsp/i );
			$count++;
			print WH "CATE=$lang#DESC=$desc#LINK=http://tvunderground.org.ru/@CONTENT[$linecount+1]\n";

... [truncated, 307 more lines] ...

#!/usr/bin/perl

use LWP::UserAgent;
use HTTP::Cookies;
use HTTP::Request;
use Tie::File;

$PROXYTMP	= "proxy.tmp.txt";
$PROXYGO	= "proxy.working.txt";
$TESTURL	= "http://www.zoozle.net/zoozle/information.html";
$UA			= "Mozilla/5.0 (Windows; U; Windows NT 5.0; de-DE; rv:1.6) / Torrentindexer/1.0 - www.zoozle.net";

############# Subroutine zum erstellen eines HTTP Requestes:Start
# Aufgabe: &http_get - erstelle und sende http request an bergebene url
# Rckgabe: content der angefragten uri/url

sub http_get() {
	
	my ($url, $timeout, $useragent, $proxy) = @_;
	my $UA = LWP::UserAgent->new( keep_alive => 1 );

	$UA->agent($useragent);
	$UA->timeout($timeout);
	$UA->max_size(950_000);
	#$UA->proxy(["http"], "http://$proxy") if ($proxy ne '');
  
	my $jar_jar = HTTP::Cookies->new
		(file => ".Cookies" || ".Cookies.txt",
			autosave => 1,
			max_cookie_size => 40960,
			max_cookies_per_domain => 10000, );
			$UA->cookie_jar($jar_jar );
		
	my $req = HTTP::Request->new(GET => $url);
	
	# Pass request to the user agent and get a response back
  	
	$req->referer($url);
	
	my $res = $UA->request($req);

	if ($res->is_success) {
		return $res->content;
  	} else {
      	#return "<html><body> Spider::Easyspider::http_get(): " . $res->status_line . "</body></html>";
		return 0;
  	};

}; # sub http_get {}
############# Subroutine zum erstellen eines HTTP Requestes:Ende

... [truncated, 253 more lines] ...

use LWP::UserAgent;
  use HTML::LinkExtor;
  use URI::URL;


  $url = "http://www.zoozle.net/links.html";  # for instance
  $ua = LWP::UserAgent->new;

  # Set up a callback that collect image links
  my @imgs = ();
  sub callback {
     my($tag, %attr) = @_;
     return if $tag ne 'a';  # we only look closer at <img ...>
     push(@imgs, values %attr);
  }

  # Make the parser.  Unfortunately, we don't know the base yet
  # (it might be diffent from $url)
  $p = HTML::LinkExtor->new(\&callback);

  # Request document and parse it as it arrives
  $res = $ua->request(HTTP::Request->new(GET => $url),
                      sub {$p->parse($_[0])});



  # Expand all image URLs to absolute ones
  my $base = $res->base;
  @imgs = map { $_ = url($_, $base)->abs; } @imgs;

  # Print them out
  print join("\n", @imgs), "\n";

#!/usr/bin/perl


use Data::Dumper;
use HTML::TokeParser;
use LWP::Simple;
use URI::URL;

my $domain	= "http://www.zoozle.net";

my $doc = get($domain);

# titel
# my @title			= $doc	=~ /<title.*?>(.*?)<\/title>/gis;
# print $title[0];

print _getMetakeys(\$doc, "description" );



sub _getMetakeys(){

	my $PageContentScalarRef	= shift;
	my $GetMetaKeyContent		= shift;

	my @content_lines			= split( "\n", ${$PageContentScalarRef} );  # let's make a gigantic string with all the
	my $single_line				= join( "", @content_lines );				# lines of HTML on one line. Come on, it'll be fun
	
	########
	########
	########

	# <meta name = "name" content = "content" \>
	# $meta{uc($1)} = $2 while $single_line =~ m/<\s*meta\s+name\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*\/>/gi;
	# $meta{uc($1)} = $2 while $single_line =~ m/<\s*meta\s+name\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi;
	# $meta{uc($1)} = $2 while $single_line =~ m/<\s*meta\s+content\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi;

#	if ( $single_line =~ m/<\s*meta\s+content\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi ) {
#		print "META=$1 und CONTENT=$2\n";
#		return $2 if ( $1 =~ /$GetMetaKeyContent/i );	# gib den inhalt von zb description tag zurck
#	} elsif ( $single_line =~ m/<\s*meta\s+name\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi ) {
#		print "META=$1 und CONTENT=$2\n";
#		return $2 if ( $1 =~ /$GetMetaKeyContent/i );
#	} elsif ( $single_line =~ m/<\s*meta\s+content\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi ) {
#		print "META=$1 und CONTENT=$2\n";
#		return $2 if ( $1 =~ /$GetMetaKeyContent/i );
#	};

	if ( $single_line =~ m/<\s*meta\s+content\s*=\s*"([^"]+)"\s*content\s*=\s*"([^"]+)"\s*>/gi ) {
		print "META=$1 und CONTENT=$2\n";

... [truncated, 105 more lines] ...

# my @title = $links	=~ /javascript\:(\w|\d)+\(+(.*?)(\w|\d)+\)/gis; 
			# # javascript:funtion('LINK');
			# my @title = $links	=~ /javascript\:(\w|\d)+\(+(\"|\')+(\w|\d)+(\"|\')+\)/gis;  
			# my @title			= $page	=~ /<title.*?>(.*?)<\/title>/gis;
			
			# if ( $links =~ /\(+(.*?)+\)/g ) {
			# if ( $links =~ m|\(+(.*?)+\)|g ) {
			# if ( $links =~ m|\(+(.*?)+\)|g ) {
			# if ( $links =~ m|\(+(.*?)+\)|g ) {
			# my @title = $links	=~ /([^\(])(.*?)([^\)])/gis;
			my @title = $links	=~ /javascript:(\w)+\(+\"+(.*?)+\"+\)/gis;
			
			print "@title  \n";
				print "JO\n";

#############

#!/usr/bin/perl
# make sure, that the path of perl is right (try: which perl)

###############################################################
#
# Pix2tn by Michael Hahsler 1999
# 
# This script free for use and modification.
# History: 	V1.0 Oct 18 1999
#		V1.1 Mar 08 2004 includes options code by 
#			Juan Carlos Rey Anaya <jcrey@uma.es>
#
# Usage: Copy this script into the directory with your photos or in
#   your directory for executables (e.g. ~/bin). Change to the directory
#   with the photos and run the script. The script will generate the
#   file welcome.html (the index) and the sub-directories tn and med 
#   (for the thumpnails).
#   If you want to have the index and the pictures on the Web, the directory
#   you have to move everything to a directory used by your Web-server 
#   (e.g. ~\www).
#
# Copyright: This script is under GNU GENERAL PUBLIC LICENSE (GPL)
#
# Enjoy,
# Michael Hahsler
# hahsler@ai.wu-wien.ac.at               http://wwwai.wu-wien.ac.at/~hahsler
#

use Getopt::Std;

print "pix2tn by Michael Hahsler\n\n";

usage() unless getopts("ht:o:");
usage() if $opt_h;
$filename = $opt_o || "index.html";
$title    = $opt_t || "My Pics";
$dir = shift || ".";
chdir $dir || die "Cannot change to $dir.\n";

my $tnperrow=4;   # thumbnails per row
my $tnsize=80;    # size of thumbnails
my $tnquality=25; # quality of thumbnails [0..100]
# use small thumbnails with poor quality to speed up your index-page

my $medsize=500;    # size of thumbnails
my $medquality=70; # quality of thumbnails [0..100]
# used to create medium sized pictures

# possible image extensions (jpg, gif)
my @pics = (<*.jpg>,<*.gif>);

... [truncated, 77 more lines] ...

#! /usr/bin/perl -w

# This is part of modern Perl distributions.
use FindBin;
use lib "$FindBin::Bin";

# These are part of modern Perl distributions.
use Getopt::Long;

# These modules aren't necessarily "standard" with Perl.  You might need to
# install them seperately.
use Digest::SHA1 qw(sha1);
use LWP::UserAgent;

# This is part of TorrentSniff, and should have been distributed with it.
use BitTorrent::BDecode;

use strict;
use Data::Dumper;
use LWP::Simple;

my $doc = get("http://torrent.to/torrent/upload/moviez/615/150615/555-www.torrent.to...WernerHerzog-Stroszek1977%5Bfreakyflicks%5D.torrent");

my $t = BitTorrent::BDecode::bdecode(\$doc);
	print Dumper($t);

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

#############
###### run from path: /root/zoozle/indexer/GenerellSpider
#############

# perl -MCPAN -e 'force install "XML::TreePP"'
# perl -MCPAN -e 'force install "APR::URI"'

system("clear");


# lade immer alle module -> error checking

use strict;
use IO::Handle;
use Data::Dumper;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;
use TorrentIndexer::CHECKSUM::CheckSum;

use TorrentIndexer::TIME::Time;
use TorrentIndexer::HTML::HtmlParser;
use TorrentIndexer::CRYPTO::CryptoLibrary;
use TorrentIndexer::CRYPTO::SecureHashGenerator;
use TorrentIndexer::HTTP::RobotRules;
use TorrentIndexer::LINK::LinkDept;
use TorrentIndexer::LINK::IsSameLink;
use TorrentIndexer::BITTORRENT::Bittorrent;


# my $MainUrlToScan		= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $MainUrlToScan		= "http://www.zoozle.net/links.html"; 

# my $MainUrlToScan		= "http://eselfilme.com/parents/home.htm";
# my $MainUrlToScan		= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $MainUrlToScan		= "http://www.p2p-blog.de/feed/";
# my $MainUrlToScan		= "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

# my $MainUrlToScan		= "http://www.freesexypics.de.vu"; 
# my $MainUrlToScan		= "http://www.zoozle.net/zoozle/information.html";

... [truncated, 205 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

# perl -MCPAN -e 'force install "XML::TreePP"'

system("clear");

use Data::Dumper;

use BitTorrent::BDecode;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;


# my $domain	= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $domain  = "http://eselfilme.com/parents/home.htm";
# my $domain	= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $domain	= "http://www.p2p-blog.de/feed/";
my $domain = "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

###########
### objekte initialisieren
###########

my $HEAD	= TorrentIndexer::HTTP::Head->new();
my $GET		= TorrentIndexer::HTTP::Get->new();
my $LINK	= TorrentIndexer::LINK::Extractor->new();


########
#### Request senden
########

my $HeadHashResultRef	= $HEAD->Head($domain);
my $HeadStatusCode		= $HeadHashResultRef->{ 'STA' };
my $LinkHashRef;


if ( $HeadStatusCode == 1 ) {

	my $ContentType			= $HeadHashResultRef->{ 'TYP' };
	my $GetHashResultRef	= $GET->Get($domain);

... [truncated, 36 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

#############
###### run from path: /root/zoozle/indexer/GenerellSpider
#############

# perl -MCPAN -e 'force install "XML::TreePP"'
# perl -MCPAN -e 'force install "APR::URI"'

system("clear");


# lade immer alle module -> error checking

use strict;
use IO::Handle;
use Data::Dumper;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;
use TorrentIndexer::CHECKSUM::CheckSum;

use TorrentIndexer::TIME::Time;
use TorrentIndexer::HTML::HtmlParser;
use TorrentIndexer::CRYPTO::CryptoLibrary;
use TorrentIndexer::CRYPTO::SecureHashGenerator;
use TorrentIndexer::HTTP::RobotRules;
use TorrentIndexer::LINK::LinkDept;
use TorrentIndexer::LINK::IsSameLink;
use TorrentIndexer::BITTORRENT::Bittorrent;


# my $MainUrlToScan		= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $MainUrlToScan		= "http://www.zoozle.net/links.html"; 

# my $MainUrlToScan		= "http://eselfilme.com/parents/home.htm";
# my $MainUrlToScan		= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $MainUrlToScan		= "http://www.p2p-blog.de/feed/";
# my $MainUrlToScan		= "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

# my $MainUrlToScan		= "http://www.freesexypics.de.vu"; 
# my $MainUrlToScan		= "http://www.zoozle.net/zoozle/information.html";

... [truncated, 237 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

#############
###### run from path: /root/zoozle/indexer/GenerellSpider
#############

# perl -MCPAN -e 'force install "XML::TreePP"'
# perl -MCPAN -e 'force install "APR::URI"'

system("clear");


# lade immer alle module -> error checking

use strict;
use IO::Handle;
use Data::Dumper;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;
use TorrentIndexer::CHECKSUM::CheckSum;

use TorrentIndexer::TIME::Time;
use TorrentIndexer::HTML::HtmlParser;
use TorrentIndexer::CRYPTO::CryptoLibrary;
use TorrentIndexer::CRYPTO::SecureHashGenerator;
use TorrentIndexer::HTTP::RobotRules;
use TorrentIndexer::LINK::LinkDept;
use TorrentIndexer::LINK::IsSameLink;
use TorrentIndexer::BITTORRENT::Bittorrent;


# my $MainUrlToScan		= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $MainUrlToScan		= "http://www.zoozle.net/links.html"; 

# my $MainUrlToScan		= "http://eselfilme.com/parents/home.htm";
# my $MainUrlToScan		= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $MainUrlToScan		= "http://www.p2p-blog.de/feed/";
# my $MainUrlToScan		= "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

# my $MainUrlToScan		= "http://www.freesexypics.de.vu"; 
# my $MainUrlToScan		= "http://www.zoozle.net/zoozle/information.html";

... [truncated, 230 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

#############
###### run from path: /root/zoozle/indexer/GenerellSpider
#############

# perl -MCPAN -e 'force install "XML::TreePP"'
# perl -MCPAN -e 'force install "APR::URI"'

system("clear");


# lade immer alle module -> error checking

use strict;
use IO::Handle;
use Data::Dumper;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;
use TorrentIndexer::CHECKSUM::CheckSum;

use TorrentIndexer::TIME::Time;
use TorrentIndexer::HTML::HtmlParser;
use TorrentIndexer::CRYPTO::CryptoLibrary;
use TorrentIndexer::CRYPTO::SecureHashGenerator;
use TorrentIndexer::HTTP::RobotRules;
use TorrentIndexer::LINK::LinkDept;
use TorrentIndexer::LINK::IsSameLink;
use TorrentIndexer::BITTORRENT::Bittorrent;


# my $MainUrlToScan		= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $MainUrlToScan		= "http://www.zoozle.net/links.html"; 

# my $MainUrlToScan		= "http://eselfilme.com/parents/home.htm";
# my $MainUrlToScan		= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $MainUrlToScan		= "http://www.p2p-blog.de/feed/";
# my $MainUrlToScan		= "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

# my $MainUrlToScan		= "http://www.freesexypics.de.vu"; 
# my $MainUrlToScan		= "http://www.zoozle.net/zoozle/information.html";

... [truncated, 241 more lines] ...

#!/usr/bin/perl -Imodules

#########################################
##### Author:		Sebastian Enger / B.Sc
##### CopyRight:	Sebastian Enger
##### LastModified	16.07.2006
##### Function:		
##### Todo:			
########################################

#############
###### run from path: /root/zoozle/indexer/GenerellSpider
#############

# perl -MCPAN -e 'force install "XML::TreePP"'
# perl -MCPAN -e 'force install "APR::URI"'

system("clear");


# lade immer alle module -> error checking

use strict;
use IO::Handle;
use Data::Dumper;
use TorrentIndexer::HTTP::Get;
use TorrentIndexer::HTTP::Head;
use TorrentIndexer::LINK::Extractor;
use TorrentIndexer::CHECKSUM::CheckSum;

use TorrentIndexer::TIME::Time;
use TorrentIndexer::HTML::HtmlParser;
use TorrentIndexer::CRYPTO::CryptoLibrary;
use TorrentIndexer::CRYPTO::SecureHashGenerator;
use TorrentIndexer::HTTP::RobotRules;
use TorrentIndexer::LINK::LinkDept;
use TorrentIndexer::LINK::IsSameLink;
use TorrentIndexer::BITTORRENT::Bittorrent;


# my $MainUrlToScan		= "http://www.zoozle.net/zoozle.php?q=test&s=bittorrent&l=de";
# my $MainUrlToScan		= "http://www.zoozle.net/links.html"; 

# my $MainUrlToScan		= "http://eselfilme.com/parents/home.htm";
# my $MainUrlToScan		= "http://fenopy.com/rss.xml?row=10&cat=5&type=2";
# my $MainUrlToScan		= "http://www.p2p-blog.de/feed/";
 my $MainUrlToScan		= "http://torrent.to/torrent/upload/serien/713/150713/1308-www.torrent.to...CSI.Miami.S04E08.Wunschmoerder.German.Dubbed.DVDRiP.WS.XviD-TvR.torrent";

# my $MainUrlToScan		= "http://www.freesexypics.de.vu"; 
# my $MainUrlToScan		= "http://www.zoozle.net/zoozle/information.html";

... [truncated, 253 more lines] ...

#!/usr/bin/perl

require "functions.pl";

use DBI();
$drh			= DBI->install_driver("mysql");

my $DBHOST		= "localhost";
my $DBNAME		= "zoozle";
my $DBUSER		= "zoozle";	
my $DBPASS		= "zoozle23!99";	

my $dbh			= DBI->connect("DBI:mysql:database=$DBNAME;host=$DBHOST", "$DBUSER", "$DBPASS", {'RaiseError' => 0});

my $AddFile = $ARGV[0];

&add_content_toSQLDB($AddFile);
&add_content_toREALSQLDB($AddFile);

$dbh->disconnect;



sub add_content_toSQLDB() {

	my $filename	= shift;
	my $date		= &getDATE();

	open(RH1,"<$filename") or die "$! - $filename \n";

	foreach (<RH1>) {
		
		my ( $cat, $desc, $link ) = split('#', $_);
		$link =~ s/LINK=//;
		$desc =~ s/DESC=//;
		$cat =~ s/CATE=//;
		
		next if ( $_ !~ /^CATE=/ );
		next if ( $_ =~ /Torrent does not exist/ig );
		next if ( $link =~ /megawerbung/);
		next if ( $desc =~ /<img/ig );
		
		$cat	= &deleteSpecialChars($cat);
		$desc	= &deleteSpecialChars($desc);
		$count++;

		$desc =~ s/&+(\w)+;/ /i;
		$desc =~ s/&#+(\w)+;/ /i;
		$desc =~ s/&+(\d)+;/ /i;
		$desc =~ s/&#+(\d)+;/ /i;

... [truncated, 90 more lines] ...

#!/usr/bin/perl -Imodules

use IO::Handle;

# SELECT * FROM `torrent7` WHERE `LINK` LIKE ('http://fenopy.com%')

my $CatLanguage = "en";
my $StartUrl	= "http://fenopy.com/";

my (undef,undef,$Hostname,undef) = split('/', $StartUrl);

my $CachePath				= "/root/zoozle/indexer/torrentindexer/cache";
my $TorrentStoreFlatFile	= "$CachePath/$Hostname-torrent.txt";
my $LinkScannedFile			= "$CachePath/$Hostname-alreadyscannedlinks.txt"; 
my $LinksToScan				= "$CachePath/$Hostname-linksToScan.txt"; 

my $TorrentPath			= "/root/zoozle/indexer/torrentindexer/torrentgrabber/torrents";		# later check if dir exits if not create, siehe client.pm easyspider
my $FinalTorrentFile	= "$TorrentPath/$Hostname-finaltorrents.txt";
mkdir $TorrentPath;


open(TORRENT,">$FinalTorrentFile") or die;
	TORRENT->autoflush(1);
	TORRENT->blocking(0);
	binmode TORRENT, ":utf8";
	flock(TORRENT, 2);

open(RH,"<$LinksToScan") or die;
	while(<RH>){
		my ( $LinkDesc, $ParentLink, $LinkName ) = split(' ### ', $_);
		
	#	if ( $ParentLink =~ /http:\/\/fenopy.com\/torrent\//i ) {
	#		print "LinkDesc: $LinkDesc\n";
	#		print "Linkname: $ParentLink\n";
	#		print "\n\n";
	#		sleep 1;
	#	};

		# CATE=en#DESC=Read or Die - OVA (GermanDub)#LINK=http://www.mininova.org/tor/471390

		if ( $LinkName =~ /http:\/\/fenopy.com\/torrent\//i ) {
			
			if ( $LinkDesc =~ /\[img\]/i) {
				my (undef,undef,undef,undef, $Raw,undef,undef) = split('/', $LinkName);
				#print "LinkDesc: " . chomp(delteSpecialChars($Raw)) . "\n";
				my $DESC = &delteSpecialChars($Raw);
				chomp($DESC); chomp($LinkName);
				$DESC =~ s/#\s//;
				print TORRENT "CATE=en#DESC=$DESC#LINK=$LinkName\n" if ( $LinkName =~ /index\.html/i );
				$count++ if ( $LinkName =~ /index\.html/i );

... [truncated, 49 more lines] ...

#!/usr/bin/perl

use LWP::UserAgent;
use HTTP::Cookies;
use HTTP::Request;
use Tie::File;

$PROXYTMP	= "proxy.tmp.txt";
$PROXYGO	= "proxy.working.txt";
$TESTURL	= "http://www.zoozle.net/zoozle/information.html";
$UA			= "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; YPC 3.0.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)";

############# Subroutine zum erstellen eines HTTP Requestes:Start
# Aufgabe: &http_get - erstelle und sende http request an bergebene url
# Rckgabe: content der angefragten uri/url

sub http_get() {
	
	my ($url, $timeout, $useragent, $proxy) = @_;
	my $UA = LWP::UserAgent->new( keep_alive => 1 );

	$UA->agent($useragent);
	$UA->timeout($timeout);
	$UA->max_size(950_000);
	#$UA->proxy(["http"], "http://$proxy") if ($proxy ne '');
  
	my $jar_jar = HTTP::Cookies->new
		(file => ".Cookies" || ".Cookies.txt",
			autosave => 1,
			max_cookie_size => 40960,
			max_cookies_per_domain => 10000, );
			$UA->cookie_jar($jar_jar );
		
	my $req = HTTP::Request->new(GET => $url);
	
	# Pass request to the user agent and get a response back
  	
	$req->referer($url);
	
	my $res = $UA->request($req);

	if ($res->is_success) {
		return $res->content;
  	} else {
      	#return "<html><body> Spider::Easyspider::http_get(): " . $res->status_line . "</body></html>";
		return 0;
  	};

}; # sub http_get {}
############# Subroutine zum erstellen eines HTTP Requestes:Ende

... [truncated, 253 more lines] ...

#!/usr/bin/perl -Imodules

use IO::Handle;

# SELECT * FROM `torrent7` WHERE `LINK` LIKE ('http://fenopy.com%')

my $CatLanguage = "de";
my $StartUrl = "http://torrent.to/";

my (undef,undef,$Hostname,undef) = split('/', $StartUrl);

my $CachePath				= "/root/zoozle/indexer/torrentindexer/cache";
my $TorrentStoreFlatFile	= "$CachePath/$Hostname-torrent.txt";
my $LinkScannedFile			= "$CachePath/$Hostname-alreadyscannedlinks.txt"; 
my $LinksToScan				= "$CachePath/$Hostname-linksToScan.txt"; 

my $TorrentPath			= "/root/zoozle/indexer/torrentindexer/torrentgrabber/torrents";		# later check if dir exits if not create, siehe client.pm easyspider
my $FinalTorrentFile	= "$TorrentPath/$Hostname-finaltorrents.txt";
mkdir $TorrentPath;


open(TORRENT,">$FinalTorrentFile") or die;
	TORRENT->autoflush(1);
	TORRENT->blocking(0);
	binmode TORRENT, ":utf8";
	flock(TORRENT, 2);

open(RH,"<$LinksToScan") or die;
	while(<RH>){
		my ( $LinkDesc, $ParentLink, $LinkName ) = split(' ### ', $_);
		
		# http://torrent.to/torrent/upload/moviez/539/154539/555-www.torrent.to...DasLebendesBrian.torrent
		# if ( $LinkName =~ /http:\/\/torrent\.to\/torrent\/upload\//i && $LinkName =~ /(\w)+\.torrent/i ) {
		# my $Reverse = reverse($LinkName);
		# if ( $Reverse =~ /^tnerrot\./i ) {
		
		if ( $LinkName =~ /http:\/\/torrent\.to\/torrent\/upload\//i && $LinkName =~ /(\w)+\.torrent/i ) {
			
			my $Raw;

			my ( undef, $Raw) = split('\.\.\.', $LinkName);
			$Raw =~ s/\.torrent//gi;
			
			$Raw =~ s/\d+-+\d+-//ig;
			$Raw =~ s/^\.//og; $Raw =~ s/^\.//og; $Raw =~ s/^\.//og; $Raw =~ s/^\.//og; $Raw =~ s/^\.//og;

			my @FileName = split('', $Raw);
			my $FileNameCount = 0;
			my $output;


... [truncated, 96 more lines] ...